1
0
mirror of https://github.com/RSS-Bridge/rss-bridge.git synced 2025-08-15 13:04:01 +02:00

Compare commits

...

245 Commits

Author SHA1 Message Date
Teromene
db25a68072 Revert "[CommonDreamBridge] Promote to secure bridge (fix #777) (#909)"
This reverts commit 8c97953211.
2018-11-05 17:32:28 +01:00
Corentin Garcia
8c97953211 [CommonDreamBridge] Promote to secure bridge (fix #777) (#909) 2018-11-05 17:32:11 +01:00
logmanoriginal
d987ceec73 [CONTRIBUTING.md] Include all policies and link to the Wiki 2018-11-05 14:07:14 +01:00
logmanoriginal
392e3ff6c7 phpcs: Fix violations 2018-11-05 12:55:58 +01:00
logmanoriginal
e295dc5a79 [phpcs] Add check for concatenation operator spacing
The concatenation operator should have one space before and after
2018-11-05 12:52:18 +01:00
logmanoriginal
b9f6bc8197 [XenForoBridge] Fix broken conditions
Restore functionality for https://xenforo.com/community/
2018-11-05 12:19:45 +01:00
logmanoriginal
9c1c0f2974 [XenForoBridge] Fix broken checks 2018-11-05 12:05:14 +01:00
logmanoriginal
65da157fff [XenForoBridge] Add new bridge
Adds a bridge for forums powered by XenForo (see https://xenforo.com).

Support between forums may vary due to ever changing versions with no
clear distinction. Especially timestamps may not work depending on the
supported language (should currently work on en-US and de-DE).

Tested on

- https://xenforo.com/community/
- http://www.ign.com/boards/

Notice: XenForo provides RSS feeds for forums (but not specific topics).
For example: https://xenforo.com/community/forums/-/index.rss
2018-11-05 12:00:12 +01:00
triatic
5fe943562a [FB2Bridge] Prevent shared post duplication (#904)
Prevent shared posts appearing twice in feed.
2018-11-05 11:46:56 +01:00
Thibault Couraud
c58331f74d [BAEBridge] Add bridge for bourse-aux-equipiers.com (#903) 2018-11-05 11:38:22 +01:00
Antoine Turmel
145a46ae1d [ThingiverseBridge] Add new bridge (#869) 2018-11-05 11:27:32 +01:00
mr-flibble
1a7a7bad98 [contents.php] Fix typo (#900)
This fixes "The requested resouce cannot be found!" on line 67
2018-11-05 11:10:32 +01:00
Yardena Cohen
27d6a22675 core: Display optional administrator email (#896) 2018-11-05 10:46:44 +01:00
teromene
b55ec51e0e Fix timestamp decoding 2018-11-04 21:50:18 +01:00
hunhejj
07b4c72d5d [InstagramBridge] Don't add duplicated urls when parsing Instagram stories (#715) 2018-11-03 12:12:37 +01:00
logmanoriginal
2e6cbd1ce7 [GitHubGistBridge] Fix broken bridge
`defaultLinkTo` makes anchors point to the correct path which broke
parsing because it expected href to start with `#gistcomment`.

This commit changes the implementation to make `defaultLinkTo` point
to the correct page (using `getURI` instead of `self::URI`) and search
with `*=` instead of `^=`.
2018-11-03 11:56:51 +01:00
LogMANOriginal
2ac2f3dc66 [README] Add info about feed readers
References #892
2018-11-02 11:45:45 +01:00
logmanoriginal
e2dfea2b77 [index.php] Filter parameter '_error_time' from queries
The parameter is used in error feeds. Since RSS-Bridge returns valid
feeds for error conditions, feed readers may attempt to access the
URI returned for the feed item in order to collect additional data,
thus including the parameter '_error_time' in the query.

This results in another error message, because it is an invalid input
parameter. Filtering the parameter allows RSS-Bridge to return the
original feed.

References #882
2018-11-02 11:05:48 +01:00
Yardena Cohen
c4896c7791 [Configuration] Fix open_basedir warnings (#887)
If .git/HEAD isn't in open_basedir it'd throw ugly warnings.
Suppress errors while checking if file is readable
2018-10-27 10:53:45 +02:00
logmanoriginal
7621784598 bridges: Add favicon to bridges missing it
Adds favicon to bridges that support it. Some sites prevent downloading
favicons, those bridges are left untouched.

Affected bridges:

- AutoJMBridge
- BandcampBridge
- BlaguesDeMerdeBridge
- BloombergBridge
- BundesbankBridge
- ChristianDailyReporterBridge
- ContainerLinuxReleasesBridge
- DailymotionBridge
- DiceBridge
- DribbbleBridge
- EliteDangerousGalnetBridge
- ElsevierBridge
- FacebookBridge
- FB2Bridge
- FDroidBridge
- FierPandaBridge
- GooglePlusPostBridge
- JapanExpoBridge
- KATBridge
- KernelBugTrackerBridge
- LegifranceJOBridge
- NotAlwaysBridge
- NyaaTorrentsBridge
- PinterestBridge
- RadioMelodieBridge
- RainbowSixSiegeBridge
- SupInfoBridge
- TagBoardBridge
- TebeoBridge
- TheTVDBBridge
- WhydBridge
- ZoneTelechargementBridge
2018-10-26 19:10:58 +02:00
logmanoriginal
1cfe939927 [AskfmBridge] Fix broken bridge
References #774
2018-10-24 18:33:07 +02:00
logmanoriginal
c56f7abc2a [FacebookBridge] Reduce occurrence of HTTP error 302
Facebook returns "HTTP/1.1 302 Found" when requesting:
  https://www.facebook.com//pg/username/posts?_fb_noscript=1
Automatically redirecting to:
  https://www.facebook.com/username/posts/

We receive a positive response faster when directly requesting the
correct page:
  https://www.facebook.com/username/posts?_fb_noscript=1

Notice: This is just a minor adjustment to improve performance while
requesting data from the server. The previous version worked fine as
well.
2018-10-24 17:27:46 +02:00
logmanoriginal
e3030cbbfd [InstagramBridge] Reduce occurrence of HTTP error 301
Instagram returns "HTTP/1.1 301 Moved Permanently" on each request
to "https://instagram.com/" because the correct location is
"https://www.instagram.com/".

Instagram will respond with "HTTP/1.1 301 Moved Permanently" if the
URI for the requested user doesn't end with a slash.

Notice: This is only a minor enhancement to prevent error 301 from
happening. The previous version worked fine as is.
2018-10-24 16:42:28 +02:00
logmanoriginal
953c6e1022 [contents] Skip setting options on empty array 2018-10-24 16:28:26 +02:00
logmanoriginal
dbd44f64dd [contents] Add debug messages for 'getContents'
Adds additional messages to the error log when fetching contents. The
data is helpful in finding issues with receiving contents from servers.

References: #879, #882, #884
2018-10-24 16:10:33 +02:00
logmanoriginal
89ca42da54 [index] Always write exceptions to error.log
Exceptions are reported to users, but they do not necessarily appear
in the error log on the server. Using 'error_log' we can explicitly
write exceptions and error messages to the log file, using the
standard PHP message format.

For more information see https://stackoverflow.com/a/26867035
2018-10-24 15:58:12 +02:00
sysadminstory
b4b5340b7e [ZoneTelechargementBridge] Make the bridge more robust to URL change (#881)
Using the classical www.zone-telechargement1.org as base URL, the bridge will
always be redirected to the actual wwX.zone-telechargement1.org final URL. This
makes the bridge more robust to URL changes.
2018-10-22 19:22:02 +02:00
Eugene Molotov
a508dddb36 [core] Fixed broken caching (#880) 2018-10-22 19:14:49 +02:00
logmanoriginal
cb488d9d8c [FacebookBridge] Fix broken feeds
This commit collects the original contents from a different
tag to prevent this issue. The root cause is unknown but closely
related to the regex.

References #877
2018-10-20 15:45:20 +02:00
Antoine Turmel
9820ad5c0f [BridgeCard] Fix checkbox default value (#874)
The current solution just output "1" when checked instead of "checked"
2018-10-20 13:14:46 +02:00
Antoine Turmel
ea2d54523d [EtsyBridge] Fix bridge and correct typos (#873) 2018-10-20 13:08:03 +02:00
Eugene Molotov
87d218296e [YoutubeBridge] Fix playlist mode (#876)
* Corrected duration text selector
* Request YouTube page with English localization
* Filter video items in the beginning of the loop
2018-10-20 12:43:48 +02:00
teromene
afd5ef0f1d [FB2Bridge] Add images support
[FB2Bridge] Add basic "cards" support
2018-10-18 21:10:02 +02:00
teromene
30bc5179c2 Fix number of fetched items.
Strip the username.
2018-10-18 18:44:11 +02:00
teromene
7596be65f2 Use a new URL for the cursor. Should fix #851.
Remove the "...More" item in the output
Remove the information card data
2018-10-18 18:07:07 +02:00
Eugene Molotov
16f0ee7104 [InstagramBridge] added caption existance check in getInstagramStory (#865)
* [InstagramBridge] added caption existance check in getInstagramStory

* [InstagramBridge] Coding policy fixes
2018-10-18 16:45:03 +02:00
fluffy
e0323f06cd update php-urljoin (#867) 2018-10-18 16:43:39 +02:00
logmanoriginal
717b0bdd9c Fix items link to localhost
References #864
2018-10-16 19:16:51 +02:00
logmanoriginal
62d737efe2 Replace emoticon images by their textual representation
References #850
2018-10-16 19:02:55 +02:00
triatic
6fce03daa7 [FB2Bridge] Add updated timestamps to each post (#849)
Additionally, exclude shared posts from output since they already exist inside other posts.
2018-10-16 18:34:39 +02:00
logmanoriginal
7561c0685d [FacebookBridge] Fix 'SpSonSsoSredS' text in title
The function 'defaultLinkTo' applied to the source HTML does break
regex matches later in the bridge. We need to apply the function
right before adding the contents to the item for the bridge to work
properly.

References #856
2018-10-15 19:53:46 +02:00
logmanoriginal
f48eac854f Bump version to 'dev.2018-10-15' 2018-10-15 18:59:03 +02:00
logmanoriginal
a87e7781b1 Bump version to 2018-10-15 2018-10-15 18:54:53 +02:00
logmanoriginal
0dc761d6cf [README] Update authors
Not sure why, but the GitHub API responded with false results the
last time. Cleaning up to reflect current list of contributors.
2018-10-15 18:53:27 +02:00
logmanoriginal
d14f8e3c83 [BundesbankBridge] Add new bridge 2018-10-15 18:38:42 +02:00
logmanoriginal
b4aea21f71 [DesoutterBridge] Add new bridge 2018-10-15 18:35:49 +02:00
logmanoriginal
c06a09fe99 [GlassdoorBridge] Add new bridge 2018-10-15 18:33:02 +02:00
sysadminstory
704ad50607 [DealabsBridge] Follow website changes (#852)
Pepper changed the CSS class of some elements. The bridge was changed to
follow these changes.
2018-10-15 18:25:04 +02:00
sysadminstory
d89c65d219 [ZoneTelechargementBridge] Update the base URL and make URI unique (#853)
- Base URL updated
- Show name has different styles on the Website, use another way to get the show name
- Entry URIs are now unique to make sure RSS readers don't treat episodes as duplicates
- No more new lines in the feed or item title
2018-10-15 18:23:08 +02:00
sysadminstory
9a3c776096 [ExtremeDownloadBridge] Make URI and titles unique (#854)
- Entry URIs are unique to make sure RSS readers don't treat episodes as duplicates
- Titles are unique to make sure RSS readers don't treat streams and downloads as duplicates
2018-10-15 18:19:57 +02:00
triatic
85e8a67568 [MrssFormat.php] Prevent PHP Notice (#858)
Prevent PHP Notice when running in CLI mode
2018-10-15 18:14:06 +02:00
Nicolas Delsaux
ee158468fa Expanded Sexactu to cover the whole GQ magazine (#861)
The bridge has been expanded to better cover the whole GQ magazine.
It should support all countries (provided they all use the same absurdly shitty publication system).
It is guaranteed to be only tested with sexactu articles (that I now obtain by loading Maïa Mazaurette author page).
2018-10-15 18:09:20 +02:00
logmanoriginal
5779f641c0 [FacebookBridge] Add option to limit number of returned items
This commit adds a new optional parameter 'limit' which can be used
to limit the number of items returned by this bridge (i.e. '&limit=10')

As requested in #669
2018-10-15 17:35:10 +02:00
LogMANOriginal
b90bcee1fc Return exceptions in requested feed formats (#841)
* [Exceptions] Don't return header for bridge exceptions
* [Exceptions] Add link to list in exception message

This is an alternative when the button is not rendered
for some reason.

* [index] Don't return bridge exception for formats
* [index] Return feed item for bridge exceptions
* [BridgeAbstract] Rename 'getCacheTime' to 'getModifiedTime'
* [BridgeAbstract] Move caching to index.php to separate concerns

index.php needs more control over caching behavior in order to cache
exceptions. This cannot be done in a bridge, as the bridge might be
broken, thus preventing caching from working.

This also (and more importantly) separates concerns. The bridge should
not even care if caching is involved or not. Its purpose is to collect
and provide data.

Response times should be faster, as more complex bridge functions like
'setDatas' (evaluates all input parameters to predict the current
context) and 'collectData' (collects data from sites) can be skipped
entirely.

Notice: In its current form, index.php takes care of caching. This
could, however, be moved into a separate class (i.e. CacheAbstract)
in order to make implementation details cache specific.

* [index] Add '_error_time' parameter to $item['uri']

This ensures that error messages are recognized by feed readers as
new errors after 24 hours. During that time the same item is returned
no matter how often the cache is cleared.

References https://github.com/RSS-Bridge/rss-bridge/issues/814#issuecomment-420876162

* [index] Include '_error_time' in the title for errors

This prevents feed readers from "updating" feeds based on the title

* [index] Handle "HTTP_IF_MODIFIED_SINCE" client requests

Implementation is based on `BridgeAbstract::dieIfNotModified()`,
introduced in 422c125d8e and
simplified based on https://stackoverflow.com/a/10847262

Basically, before returning cached data we check if the client send
the "HTTP_IF_MODIFIED_SINCE" header. If the modification time is
more recent or equal to the cache time, we reply with "HTTP/1.1 304
 Not Modified" (same as before). Otherwise send the cached data.

* [index] Don't encode exception message with `htmlspecialchars`
* [Exceptions] Include error message in exception
* [index] Show different error message for error code 0
2018-10-15 17:21:43 +02:00
logmanoriginal
996295e82f Add 'dev.' to the release version in master
This helps (roughly) identifying versions when opening issues on
GitHub, using the latest ZIP file for master.

References #773
2018-09-26 20:04:27 +02:00
logmanoriginal
13bd7fe21b [contents] Return error if the server responded with any code other than 200 2018-09-26 19:16:02 +02:00
logmanoriginal
fcc9f9fd61 [FacebookBridge] Use alternative URI to load more posts
The URI "https://facebook.com/username?_fb_noscript=1" returns two
posts per user. Some profiles, however, are very active, causing the
bridge to miss items if more than two posts are send within the cache
duration (5 minutes).

The alternative suggested in #669 is to use a different URI:
"https://facebook.com/pg/username/posts?_fb_noscript=1"

While the contents of this URI essentially look the same when viewed
in a browser, it actually returns more than 10 posts depending on the
profile.

References #669
2018-09-26 18:24:46 +02:00
logmanoriginal
e1c4914b1c [FacebookBridge] Optimize for readability 2018-09-25 18:56:33 +02:00
logmanoriginal
93e7ea9fea [HtmlFormat] Make feeds available via syndication links 2018-09-22 19:51:18 +02:00
logmanoriginal
2d1b446bd1 [DevToBridge] Add new bridge
Returns feeds for tags from https://dev.to

References #840
2018-09-22 18:57:07 +02:00
logmanoriginal
1d451610d6 [ParameterValidator] Move 'getQueriedContext' from BridgeAbstract 2018-09-22 17:04:55 +02:00
logmanoriginal
f853ffc07c [ParameterValidator] Refactor 'validation' into 'ParameterValidator'
Adds a new class 'ParameterValidator' to replace the functions from
'validator.php', separating private functions from 'validateData' to
class private functions in the process.

Instead of echoing error messages, adds messages to a private variable,
accessible via 'getInvalidParameters'.

BridgeAbstract now adds invalid parameter names to the error message.
2018-09-22 16:42:04 +02:00
logmanoriginal
e3a5a6a170 [index] Update and improve parameter handling for bridge and cache
- Use 'array_diff_key' instead of 'unset'
- Remove parameters for caches

By removing certain parameters for caches, the loading times can be
improved considerably:

* action: It doesn't matter which action the user took to generate
feed items.

* format: This has the biggest impact on performance, because cached
items are now shared between different formats (i.e. try switching
between Atom, Html and Mrss and compare previous vs. now). If a
server handles lots of requests, this may even reduce bandwidth if
the same contents are requested for different formats.

* _noproxy: The proxy behavior has no impact on the produced items,
so it can be ignored.

* _cache_timeout: This is another option which might impact performance
for some servers, especially if 'custom_timeout' has been enabled in
the configuration. Requests with different cache timeouts no longer
result in separate cache files.
2018-09-22 15:44:03 +02:00
logmanoriginal
243e324efc [NineGagBridge] Fix missing sections breaking feeds
Posts may supply a list of 'sections' or a single 'postSection'

References #844
2018-09-22 15:19:14 +02:00
logmanoriginal
ae58b1566e [NineGagBridge] Remove type hinting
Type hinting for strings doesn't work prior to PHP 7, see
http://php.net/manual/en/functions.arguments.php#functions.arguments.type-declaration

References #837
2018-09-22 15:19:14 +02:00
sysadminstory
c044694b21 [ZoneTelechargementBridge] Sort episodes from newest to oldest (#835)
References #834
2018-09-21 20:22:49 +02:00
triatic
db24f55c86 [FB2Bridge] Do not strip <h3> and <h4> (#836)
Do not strip <h3> and <h4>. Output looks better when they are retained. See attached.
2018-09-21 20:19:22 +02:00
logmanoriginal
eb30038d6b [README] Update and reorganize 2018-09-16 18:20:35 +02:00
logmanoriginal
712a581ed6 [README] Add badge for Guix release
Unfortunately there is no way to query the current package version,
so this is only a placeholder
2018-09-16 16:01:51 +02:00
logmanoriginal
d3df4b51b8 [README] Add badge for current debian release 2018-09-16 15:13:30 +02:00
logmanoriginal
e6476a600d [KununuBridge] Fix broken bridge and simplify implementation 2018-09-16 09:55:35 +02:00
Grégory T
811e8d8c88 [ETTVBridge] Improvements and bug fixes (#682)
* Fix typo with status field
* Comply with other bridges

Change the uri element of an item to point, not on the magnet link, but on the page, as similar bridges do.

* Improved to return name & uri matching with query

This change makes it possible for the feed reader to discover a title and url consistent with the user's search.
2018-09-15 17:11:36 +02:00
logmanoriginal
adc6f72e97 [style] Fix first letter of labels not capitalized
This error is caused by setting label::before { content: " "; },
which makes the first letter a whitespace on all labels, neccessary
 for browsers that doesn't support the grid layout.

This commit clears the content if the browser supports the grid layout,
properly capitalizing labels again. If a browser doesn't support grid
layout, labels stay as they are provided by the bridge.
2018-09-15 17:04:20 +02:00
logmanoriginal
182153485c [Arte7Bridge] Move parameter examples into tool tip for readability 2018-09-15 16:50:10 +02:00
LogMANOriginal
bf9946d1fc CSS adjustments to improve readability for bridge parameters (#763)
* Group common selectors
* Fix indentation using tabs
* Use same styles for number and text inputs
* Use grid layout for parameters

Introduces the grid layout for bridge parameters. All parameters are
arranged in a grid to improve readability. Read more on grid layouts
at

- https://www.w3schools.com/css/css_grid.asp
- https://developer.mozilla.org/en-US/docs/Web/CSS/CSS_Grid_Layout

Notice:

Grid layouts are not supported in very old browser versions:
https://developer.mozilla.org/en-US/docs/Web/CSS/CSS_Grid_Layout/CSS_Grid_and_Progressive_Enhancement

This is why @supports checks for browser support (not supported in IE)
https://developer.mozilla.org/en-US/docs/Web/CSS/@supports#Browser_compatibility

In case grid layout is not supported, the displayed form is usable
but not very pretty due to <br> being removed by this commit for
cosmetic reasons (breaks grid layout).

Unfortunately it doesn't seem possible to insert line breaks manually
via '::after { content: '\A' }' in cases where grid layout isn't
supported.

* Add padding to card parameters

Adds padding to parameters to improve readability. For bridges without
parameters (count($parameters) === 0), the parameter 'div' is no longer
created.

* Add colon ':' after label via CSS
* Capitalize first letter of label for readability
* Fix checkbox isn't aligned left

Sets the size of the checkbox to 20x20 px for good measure.

* Harmonize formatting
* Add new style to number and select boxes

References #797

* Add fallback solution for browsers without grid support
2018-09-15 16:39:50 +02:00
triatic
ec60752650 [FB2Bridge] Prevent Facebook link href's ending in two quotes (#831)
Additionally prevent Facebook links having two forward slashes after the hostname.
2018-09-15 15:16:15 +02:00
sysadminstory
6688cf0c3b [AutoJMBridge] Fix concatenation bug (#833) 2018-09-15 15:12:34 +02:00
ORelio
ae45a8cfee [contents] Fix open_basedir warning (#832)
References #818
2018-09-15 14:46:11 +02:00
Matthew Seal
e34ef6cb4f [MrssFormat] Escape double quotes in XML attributes (#813)
XML attributes need to have certain characters escaped to be valid. The title attribute can have double quotes in it which need to be properly encoded for attributes.
2018-09-15 14:13:05 +02:00
sysadminstory
5c92a736fa [ZoneTelechargementBridge] Added Bridge for ww2.zone-telechargement1.org (#829)
* [ZoneTelechargementBridge] Added Bridge for ww2.zone-telechargement1.org

Goal for this bridge is to follow the episode publication of a TV show
season while it's broadcasted on the TV.
2018-09-13 19:36:48 +01:00
Eugene Molotov
911bcfb246 [PikabuBridge] Implemented bridge (#830)
* [PikabuBridge] Implemented bridge
2018-09-13 12:52:26 +01:00
ZeNairolf
efa550ef61 Add 9gag.com bridge (#801)
* Add 9gag.com bridge
2018-09-13 10:11:42 +01:00
sysadminstory
d5d7683ed3 [AutoJMBridge] New Bridge (#827)
* [AutoJMBridge] New Bridge

This bridge will show all the car offers AutoJM has for the model you
choosed and using your filter. Very useful to wait for a cheap price for
a new car !
2018-09-13 10:05:07 +01:00
triatic
fe94914eb5 [AtomFormat.php] Eliminate PHP Notice when running in CLI mode (#824) 2018-09-12 14:37:27 +01:00
Quentin Delmas
622802e5d4 Fix multiple warnings.
Fix JSON request string in case of empty location
2018-09-12 13:31:11 +01:00
sysadminstory
6da8daf1a3 [DealabsBridge] Fix for #782 and all categories are now available (#821)
This commit fixes #782 by updating the parameter value of 'Maison &
Jardin', but this means the user has to update his RSS Feed URL (.because
of the bridge structure, it would be a nightmare to fix it in another
way)

This commits add all the categories available on Dealabs Website.
2018-09-11 22:11:00 +01:00
la Bécasse
654e502e84 Arte7 collection support (#819)
* Arte7 collection support
2018-09-11 22:09:47 +01:00
sysadminstory
c8ace9e3bd [ExtremeDownloadBridge] Added Bridge for ww1.extreme-d0wn.com (#820)
* [ExtremeDownloadBridge] Added Bridge for ww1.extreme-d0wn.com

Goal for this bridge is to follow the episode publication of a TV show season
while it's broadcasted on the TV.
2018-09-11 20:10:46 +01:00
Monsieur Poutounours
5722a6c139 Adding a bridge for theyetee.com (#809)
* Adding a bridge for theyetee.com

The bridge fetches daily shirts at theyetee.com.
The Yetee offers two new shirts each day, but you can buy them only for a few hours !
Unfortunately, the site don't provide RSS feed, so the only way to keep up to date on new shirt is their daily mailing ... until now !
2018-09-10 20:56:55 +01:00
Quentin Delmas
458b826871 Remove declaration of extractFromDelimiters, it is now a reusable function. Fixes #815 2018-09-10 09:29:19 +01:00
Quentin Delmas
b397a42876 version: Bump to 2018-09-09 2018-09-09 21:00:10 +01:00
Corentin Garcia
111c45d010 [GithubSearchBridge] Fix content parsing, add tags if present (#803)
* [GithubSearchBridge] Fix content parsing, add tags if present

* [GithubSearchBridge] Add categories (from tags)
2018-09-09 20:30:29 +01:00
Corentin Garcia
55b36b0455 [DauphineLibereBridge] Use https, fix content parsing (fix issue #780) (#811) 2018-09-09 20:23:59 +01:00
ORelio
de8cee6a1c Catching up | [Main] Debug mode, parse utils, MIME | [Bridges] Add/Improve 20 bridges (#802)
* Debug mode improvements

 - Improve debug warning message
 - Restore error reporting in debug mode
 - Fix 'notice' messages for unset fields

* Add parsing utility functions

html.php
 - extractFromDelimiters
 - stripWithDelimiters
 - stripRecursiveHTMLSection
 - markdownToHtml (partial)

bridges
 - remove now-duplicate functions
 - call functions from html.php instead

* [Anidex] New bridge

Anime torrent tracker

* [Anime-Ultime] Restore thumbnail

* [CNET] Recreate bridge

Full rewrite as the previous one was broken

* [Dilbert] Minor URI fix

Use new self::URI property

* [EstCeQuonMetEnProd] Fix content extraction

Bridge was broken

* [Facebook] Fix "SpSonsSoriSsés" label

... which was taking space in item title

* [Futura-Sciences] Use HTTPS, More cleanup

Use HTTPS as FS now offer HTTPS
Clean additional useless HTML elements

* [GBATemp] Multiple fixes

- Fix categories: missing "break" statements
- Restore thumbnail as enclosure
- Fix date extraction
- Fix user blog post extraction
- Use getSimpleHTMLDOMCached

* [JapanExpo] Fix bridge, HTTPS, thumbnails

- Fix getSimpleHTMLDOMCached call
- Upgrade to HTTPS as JE now offers HTTPS
- Restore thumbnails as enclosures

* [LeMondeInformatique] Fix bridge, HTTPS

- Upgrade to HTTPS as LMI now offers HTTPS
- Restore thumbnails using small images
- Fix content extraction
- Fix text encoding issue

* [Nextgov] Fix content extraction

- Restore thumbnail and use small image
- Field extraction fixes

* [NextInpact] Add categories and filtering by type

- Offer all RSS feeds
- Allow filtering by article type
- Implement extraction for brief articles
- Remove article limit, many brief articles are publied all at once

* [NyaaTorrents] New bridge

Anime torrent tracker

* [Releases3DS] Cache content, restore thumbnail

- Use getSimpleHTMLDOMCached
- Restore thumbnail as enclosure

* [TheHackerNews] Fix bridge

 - Fix content extraction including article body
 - Restore thumbnail as enclosure

* [WeLiveSecurity] HTTPS, Fix content extraction

- Upgrade to HTTPS as WLS now offers HTTPS
- Fix content extraction including article body

* [WordPress] Reduce timeout, more content selectors

- Reduce timeout to use default one (1h)
- Add new content selector (articleBody)
- Find thumbnail and set as enclosure
- Fix <script> cleanup

* [YGGTorrent] Increase limit, use cache

- Increase item limit as uploads are very frequent
- Use getSimpleHTMLDOMCached

* [ZDNet] Rewrite with FeedExpander

- Upgrade to HTTPS as ZD now offers HTTPS
- Use FeedExpander for secondary fields
- Fix content extraction for article body

* [Main] Handle MIME type for enclosures

Many feed readers will ignore enclosures (e.g. thumbnails) with no MIME type. This commit adds automatic MIME type detection based on file extension (which may be inaccurate but is the only way without fetching the content).

One can force enclosure type using #.ext anchor (hacky, needs improving)

* [FeedExpander] Improve field extraction

- Add support for passing enclosures
- Improve author and uri extraction
- Fix 'notice' PHP error messages

* [Pull] Coding style fixes for #802

* [Pull] Implementing changes for #802

 - Fix coding style issues with str append
 - Remove useless CACHE_TIMEOUT
 - Use count() instead of $limit
 - Use defaultLinkTo() + handle strings
 - Use http_build_query()
 - Fix missing </em>
 - Remove error_reporting(0)
 - warning CSS (@LogMANOriginal)
 - Fix typo in FeedExpander comment

* [Main] More documentation for markdownToHtml

See #802 for more details
2018-09-09 20:20:13 +01:00
Quentin Delmas
123fce4394 [ForGifsBridge] Fix permissions of ForGifsBridge 2018-09-09 17:34:36 +01:00
Quentin Delmas
a3f99c9c3f [GOGBridge] Added bridge for GOG.com 2018-09-09 17:32:36 +01:00
Eugene Molotov
bf30ad127c [FacebookBridge] Removes query string from post links
* [FacebookBridge] Removes query string from post links
2018-09-09 16:31:15 +01:00
logmanoriginal
37f84196b7 [GooglePlusPostBridge] Fix title is empty if content is too short
The bridge would generate empty titles if the content is longer than
50 characters, but doesn't have further spaces in it. With this commit
the title is correctly generated based on the contents, taking missing
spaces into account.

References #786
2018-09-08 17:07:57 +02:00
Corentin Garcia
44764f7182 [GrandComicsDatabaseBridge] Fix links in content (#804) 2018-09-08 11:12:27 +01:00
Antoine Cadoret
19f294d71d Add fields to leboncoin bridge (#783)
* [LeBonCoinBridge] Add fields to LeBonCoinBridge
2018-08-31 14:34:41 +01:00
Teromene
b0e33e4e01 Update LeBonCoinBridge to use the site's API (#795)
* Update LeBonCoinBridge to use the site's API
2018-08-28 14:20:02 +01:00
Eugene Molotov
558fa50a2a [core] Enabled debug mode before including core files (#790) 2018-08-25 20:02:47 +01:00
Eugene Molotov
ffb8b82c73 [FileCache] reseting cached file stat result to have correct getTime() result (#792)
* [FileCache] reseting cached file stat result to have correct getTime() result
2018-08-25 20:00:51 +01:00
Eugene Molotov
422c125d8e [core] Returning 304 http code when returning cached data (#793) 2018-08-25 20:00:38 +01:00
Quentin Delmas
059656c370 Fix phpcs. 2018-08-22 16:25:08 +01:00
Quentin Delmas
9fc1e97efe Avoid bot exclusion. 2018-08-22 16:21:39 +01:00
Quentin Delmas
be3620acb7 Add extension check for the "json" extension. 2018-08-22 16:21:20 +01:00
LogMANOriginal
16c0a61232 [README] Add a "Deploy to Cloud" button for Docker
Adds a button to deploy RSS-Bridge to the Docker Cloud as described here: https://docs.docker.com/docker-cloud/apps/deploy-to-cloud-btn/
2018-08-21 18:40:39 +02:00
Walter Barrett
704a87ad97 Icons: Allow Bridge-specified icons (#788) 2018-08-21 17:46:47 +02:00
sysadminstory
c4cccfe0f3 [LesJoiesDuCode] Switch to HTTPS and remove author (#787)
Website offers now HTTPS, therefore the bridge was switched to it.
The post author is not displayed anymore on the homepage, so it has been
removed.
2018-08-21 17:41:56 +02:00
Marcin C
d07deb0930 css: Modern look for RSS-Bridge (#781) 2018-08-21 17:22:46 +02:00
Piranhaplant
e7dab5d351 Fixed timestamp on Pixiv bridge (#785) 2018-08-18 16:54:24 -03:00
logmanoriginal
ad82d50bbd [CNETBridge] Remove bridge
CNET now provides public feeds at https://www.cnet.com/rss/

References #775
2018-08-12 11:02:44 +02:00
logmanoriginal
c305c1ded7 [BlaguesDeMerdeBridge] Adjust to layout changes
References #767
2018-08-10 21:08:47 +02:00
logmanoriginal
f14a5bd771 [CADBridge] Remove bridge
https://cad-comic.com/ now provides feeds at

- https://cad-comic.com/feed (rss)
- https://cad-comic.com/feed/atom (atom)

Thus multiple alternatives are available to choose from, making this
bridge obsolete:

- FilterBridge (using one of the feeds above)
- WordPressBridge (on the main site)
- One of the two available feeds

References #752
2018-08-10 19:53:32 +02:00
logmanoriginal
a20d5f9af0 tests: reuse RssBridge.php instead of implementing a custom solution 2018-08-10 15:33:32 +02:00
logmanoriginal
ee28b124e0 [DanbooruBridge] Fix bridge
This commit fixes an issue caused by self closing tags not supported
by simplehtmldom (<source>).

Adds a monkey patch to extend simplehtmldom with the ability to detect
that particular tag. Most of the code added is copied directly from
simplehtmldom (see vendor/simplehtmldom) with adjustments to account
for RSS-Bridge formatting.

Related to: https://sourceforge.net/p/simplehtmldom/bugs/83/

Notice: The tag itself is valid according to Mozilla:

The HTML <picture> element serves as a container for zero or more
<source> elements and one <img> element to provide versions of an
image for different display device scenarios. The browser will
consider each of the child <source> elements and select one
corresponding to the best match found; if no matches are found
among the <source> elements, the file specified by the <img>
element's src attribute is selected. The selected image is then
presented in the space occupied by the <img> element.

-- https://developer.mozilla.org/en-US/docs/Web/HTML/Element/picture

References #753
2018-08-09 21:55:43 +02:00
LogMANOriginal
7dee3a175a [index] Add '?action=list' to list bridges (#493)
Adds a new action '?action=list' to return a list of bridges as JSON formatted text. Each bridge brings following information:

- status (active/inactive)
- uri
- name
- parameters
- maintainer
- description

For inactive bridges only the status is returned.
Bridges that cannot be instantiated are considered inactive.
2018-08-09 19:14:10 +02:00
logmanoriginal
5fea9fc1f5 bridges: Fix bridges failing unit test 2018-08-09 17:04:16 +02:00
logmanoriginal
6bceb2b2db [tests] Add unit test for bridge implementation
Adds unit test for bridge implementations:

- Custom functions must be in protected or private scope
- getName() must return a valid string (non-empty)
- getURI() must return a valid URI
- Each bridge must define constants for NAME, URI, DESCRIPTION and
  MAINTAINER. CACHE_TIMEOUT and PARAMETERS are optional.

The unit test is written for PHPUnit 6.x and will automatically be
tested by Travis-CI for PHP 7.0 (see .travis.yml).

Remarks:

Unit tests for bridge data were scrapped in #378 for complexity
reasons (tests would have to be maintained for each bridge). This
unit test, however, is written for testing all bridges without
taking specific implementation details into account.
2018-08-09 17:04:16 +02:00
Eugene Molotov
df81fa62d1 [VkBridge] Video attachment fixes (#766)
* use defaultLinkTo
* remove duplicate video links
* remove line ending before "Reposted" label
* return newline before reposted string
* remove comments
* use video links that won't require login
* set title if video has no title
2018-08-09 17:02:36 +02:00
Eugene Molotov
f8c6400373 [HtmlFormat] Hide "Categories" label, if array of categories is empty (#765) 2018-08-09 16:46:53 +02:00
logmanoriginal
de7622ebbf version: Bump to 2018-08-07 2018-08-07 18:37:38 +02:00
logmanoriginal
09c9d015b4 [ForGifsBridge] Add new bridge 2018-08-04 23:42:58 +02:00
logmanoriginal
3a496e3b18 [FilterBridge] Add option to build title from content
Adds a new option '&title_from_content=on' to build the title for feed
items from the feeds content. The title is generated from the first
whitespace after 50 characters of the content or the entire content if
the total size is lower than 50 characters.

References #587
2018-08-04 20:46:59 +02:00
Eugene Molotov
df58f5bbdb [core] Add urljoin (#756)
Adds php-urljoin from https://github.com/fluffy-critter/php-urljoin to replace the custom implementation of 'defaultLinkTo'
2018-08-02 06:31:56 +02:00
logmanoriginal
9d0452d11b [.travis] Use composer for HHVM
This fixes the HHVM build failing because pear doesn't exist in HHVM.
2018-08-01 19:37:10 +02:00
sublimz
f92ac49947 [LeBonCoinBridge] Add cities support (#751) 2018-08-01 17:25:18 +02:00
Benasse
a574fa15ac [YGGTorrentBridge] Order search result by publish date (#762) 2018-07-31 21:46:10 +02:00
Nemo
8f9a385b4d [AmazonPriceTrackerBridge] Improve Amazon scraper logic (#761)
- Now works on all websites, and even with products
  with multiple prices
- Closes #750
2018-07-31 21:44:37 +02:00
logmanoriginal
53bdfa3bf0 [GooglePlusPostBridge] Skip posts without message 2018-07-31 19:15:09 +02:00
logmanoriginal
53278b2eed [GooglePlusPostBridge] Add option to include image in content
References #600
2018-07-31 19:09:12 +02:00
logmanoriginal
5f3c55b808 [GooglePlusPostBridge] General cleanup 2018-07-31 18:55:35 +02:00
logmanoriginal
fb79a67370 [GooglePlusPostBridge] Normalize static::URI usage
This commit fixes a few things related to static::URI

1) Remove trailing slash from the URI to simplify using 'defaultLinkTo'
2) Use static::URI instead of self::URI for consistency
3) Remove custom implementation of 'defaultLinkTo'
2018-07-31 18:29:14 +02:00
logmanoriginal
3c4e12ceba [GooglePlusPostBridge] Add images to enclosures
Images are collected for each post and added to enclosures. Images or
animtions from lh3.googleusercontent.com are specifically handled in
order to return the animated version of the gif and the original sized
image (this is normally taken care of by JS in the browser).
2018-07-31 18:18:22 +02:00
logmanoriginal
0d1923c52f [GitHubGistBridge] Add new bridge
Adds a new bridge for https://gist.github.com

The bridge generates feeds for comments on a particular gist based on
the gist ID or full URI. For better readability the general behavior
of code sections is manually restored with the original CSS styles
from GitHub.
2018-07-29 16:31:47 +02:00
logmanoriginal
ce896b4247 [SkimfeedBridge] Add new bridge
New bridge for Skimfeed: https://skimfeed.com

Generates feeds for all features of Skimfeed:

- News (the ones displayed on the front page)
- Hot topics ("What's Hot" section on the front page)
- Tech news (preconfigured feeds in the menu bar)
- Custom feeds (using the configuration system of Skimfeed), see
https://skimfeed.com/custom.php

The number of items returned by the bridge can be limited for all
categories ('&limit=...'). This parameter is optional, all categories
are unlimited by default!

Authors are added with HTML anchors in order to allow quick navigation
to source channels.

The bridge ships with developer tools to auto-generate lists in the
future (especially useful for 'Tech news'!)

References #748
2018-07-27 23:18:32 +02:00
sysadminstory
a4b2d88dbe [DealabsBridge] Follow website change (#758) 2018-07-25 20:02:31 +02:00
logmanoriginal
65ec04ea98 [contents] Remove superfluous debug log from getContents
References #757
2018-07-25 19:56:46 +02:00
logmanoriginal
afb4de318b [FlickrBridge] Fix missing scheme for image URLs
References #754
2018-07-23 20:14:46 +02:00
Eugene Molotov
43bb17f995 [VkBridge] Converting hashtags to categories (#755)
* [VkBridge] Converting hashtags to categories
2018-07-22 16:43:00 +02:00
logmanoriginal
bae7a5879f [FlickrBridge] Fixed broken bridge
Following changes in the JSON data and selecting images for the
content (320x240 or bigger) and enclosure (largest version). All of
the data is now extracted from the JSON data instead of parsing the
DOM.

References #754
2018-07-22 14:06:04 +02:00
LogMANOriginal
bd760cbcee [README] Add docker build status 2018-07-21 21:59:48 +02:00
LogMANOriginal
cd20b4476f [README] Add label for latest release 2018-07-21 21:54:46 +02:00
LogMANOriginal
d83f2f285b Separate index and bridge card generating code into a separate classes (#734)
[html] Generate index and bridge cards using separate clases

Move HTML generating code from 'index.php' to 'Index.php', separating components into static functions.

Move HTML generation code for bridge cards from 'html.php' to 'BridgeCard.php', separating components into static functions.
2018-07-21 18:15:07 +02:00
logmanoriginal
15e6d77569 [FierPandaBridge] Fix bridge
This bridge now returns all articles from the front page, following
layout changes in the past.

References #679
2018-07-21 18:07:03 +02:00
logmanoriginal
f97d2ef254 [Torrent9Bridge] Remove bridge
The site moved from www.torrent9.pe to www.t9.pe and is now protected
by Cloudflare challenges, making it inaccessible to RSS-Bridge.
2018-07-21 17:45:22 +02:00
logmanoriginal
91ae2a23d7 [CpasbienBridge] Remove bridge
Removing this bridge for two reasons:

1) The service moved from www.cpasbien.cm to www.torrents9.blue,
changing the layout in the process (incompatible).

2) The new site is permanently protected by Cloudflare IUAM, making
it inaccessible by RSS-Bridge.

While it would certainly be possible to rewrite the bridge to work
with the new layout, the site is still inaccessible.

References #605
2018-07-21 17:43:29 +02:00
logmanoriginal
066ef1d7db [contents] Add Cloudflare challenge detection
Adds detection for servers responding with Cloudflare challenges,
throwing a server error if detected:

"The server responded with a Cloudflare challenge, which is not
supported by RSS-Bridge! If this error persists longer than a week,
please consider opening an issue on GitHub!"

This is supposed to support maintainers to identify broken bridges
for sites with Cloudflare enabled permanently. It doesn't circumvent
the protection in any form or shape!

The Cloudflare challenge is detected by analyzing the last response
header received from the server. If the HTTP Code is not 200 (OK)
and the server name contains 'cloudflare' ('Server: cloudflare'),
RSS-Bridge assumes the server responded with a challenge.

The header parsing is based on https://stackoverflow.com/a/18682872
2018-07-21 17:43:29 +02:00
LogMANOriginal
4facbf32e3 [InstructableBridge] Add new bridge (#724)
This commit adds a new bridge for http://www.instructables.com. This bridge
currently supports fetching content by category (all categories available 200+),
using available filters (featured, recent, popular, views, contest winners).
2018-07-21 15:25:13 +02:00
logmanoriginal
6bd76af326 [YoutubeBridge] Add duration limits for all modes
Adds duration limits (minimum duration, maximum duration) for all
modes (user/id/playlist/search). Duration limits are optional, so
existing subscriptions don't break.

The limits are specified by two separate parameters, each of which
is optional:

- `&duration_min=` (minimum duration in minutes, default: -1)
- `&duration_max=` (maximum duration in minutes, default: INF)

If duration limits are specified in either user, id or playlist mode,
the bridge defaults to fetching data from HTML intead of XML feeds,
which requires more bandwidth and takes longer, because each video is
loaded individually!

References #670
2018-07-21 14:33:07 +02:00
logmanoriginal
caa622ffec [search] Support searching by URI
Adds matching for URIs to the search bar, using the format
<scheme>://<host>/<path>

Searching by URI scheme is also supported:

"http://"  (returns all bridges with 'http'  scheme)
"https://" (returns all bridges with 'https' scheme)

The following examples are equivalent and will return both of the
Facebook bridges (FacebookBridge and FB2Bridge):

"https://www.facebook.com/facebook"
"https://www.facebook.com/facebook?..."
"https://www.facebook.com"
"http://www.facebook.com"
"https://facebook.com"
"http://facebook.com"
"facebook.com"
"facebook"

Notice: When the URI scheme is omitted, the search algorithm falls back
to regex matching. Searching for "www.facebook.com" doesn't work, as it
is missing the schema and doesn't match via regex!

Omitting the 'www.', however, does work. This was a design decision for
some bridges specify their URI with and others without 'www.'

A search term can still be specified in the browser URL using parameter
'q' => '?q=searchterm'.

References #743
2018-07-20 22:44:13 +02:00
teromene
c4d489f018 Add URI to ElloBridge elements. 2018-07-19 17:07:54 +02:00
logmanoriginal
6a98293fb3 [Configuration] Bump version to 2018-07-17 2018-07-17 20:44:01 +02:00
logmanoriginal
d79630e3b8 [Configuration] Remove check for allow_url_fopen
This commit follows the changes done in commits

fbf874cb29
ead7b2e8de
2018-07-17 20:39:14 +02:00
teromene
1f2fe25471 Fix LeBonCoinBridge, now uses getContents correctly, 2018-07-17 10:50:30 +02:00
Antoine Cadoret
87fc9e9156 fix LeBonCoin bridge (#747) 2018-07-16 20:13:08 +02:00
Nemo
c7b0c9fd31 Amazon Price Tracker Bridge (#741)
* [amazonprice] Adds AmazonPriceTracker bridge
2018-07-16 14:54:52 +02:00
Teromene
fbf874cb29 Update README.md
Remove allow_url_fopen requirement. This should no longer be necessary. Added requirement for curl.
2018-07-16 12:37:09 +02:00
Eugene Molotov
049ee52fb5 Implemented feed item categories (#746) 2018-07-16 12:32:24 +02:00
TheRadialActive
3f41d0593a Added RSS bridge for zenodo.org (#749)
* added RSS bridge for zenodo.org
2018-07-16 12:02:41 +02:00
sysadminstory
7126f5e838 [DealabsBridge] First version of the generic "Pepper" Bridge (#726)
* [DealabsBridge] First version of the generic "Pepper" Bridge
2018-07-13 00:35:13 +01:00
Nemo
ead7b2e8de [fb2] Switches to getContents (#742) 2018-07-10 02:29:47 +01:00
LogMANOriginal
0d80a19e84 [FacebookBridge] Add context for public Facebook groups (#739)
The previous context is now labeled 'User', while the new context is
labeled 'Group'. The existing code was not changed, instead new group*
functions were implemented to handle groups.

The general principle of capturing groups is the same as done for users
with adjustments to account for different HTML structures.

Captcha responses are currently not supported for groups! There doesn't
seem to be a way to trigger them consistently, which makes it hard to
handle them properly.

Features of the group context:

- The feed title is based on the group name
- The group URI used for capturing is returned for the feed URI
- Author names and timestamps are reproduced from the source
- Post titles are reproduced from the source if they exist, otherwise
the title is build manually from the author name and the content
- Original contents are included with the feed
- All images are attached as enclosures as well

Closes #
2018-07-08 17:16:00 +02:00
logmanoriginal
42c699f474 formats: Fix favicon not found if url contains path 2018-06-30 10:27:05 +02:00
logmanoriginal
2bc8daa101 [JustETFBridge] Add new bridge
Supports latest news and profiling a given ETF in Englisch, German
or Italian language. Cover images are attached as enclosures and not
as part of the content.

News:

Optionally loads the full article for each news item. Some articles
may include scripts to provide interactive graphs. These scripts are
removed as they would be rendered as pure text and a message is shown
instead: "[Content removed! Visit site to see full contents!]"

Profile:

Optionally includes the ETF strategy and description.
2018-06-30 10:27:05 +02:00
logmanoriginal
bca79d3f88 [KununuBridge] Fix broken page layout and sort reviews 2018-06-30 10:27:05 +02:00
logmanoriginal
90dc968fd1 Fix PHPCS error 2018-06-30 10:26:48 +02:00
Teromene
da6b98851c Add recuperation of the current version from git if available (#731)
* Add recuperation of the current version from git if available
* Include version when auto-reporting an error
2018-06-30 10:24:22 +02:00
teromene
71c29d4192 Fix phpcs for master. 2018-06-29 23:15:22 +01:00
LogMANOriginal
193ca87afa [phpcs] enforce single quotes (#732)
* [phpcs] Add rule to enforce single quoted strings
2018-06-29 22:55:33 +01:00
Nemo
5ea79ac1fc Add markdown support to Container Linux Feed (#730) 2018-06-28 20:54:42 +02:00
Teromene
937ea49271 Add basic authentication support (#728)
* Move configuration in its own class in order to reduce the verbosity of index.php
* Add authentication mechanism using HTTP auth
* Add a method to get the config parameters
* Remove the installation checks from the index page
* Log all failed authentication attempts
2018-06-27 19:09:41 +02:00
logmanoriginal
95686b803c [IsoHuntBridge] Remove bridge
isoHunt has discontinued services due to legal reasons and is now
accessible via https://isohunts.to

While it is certainly possible to rewrite the bridge to fetch some
information from the new site, it wouldn't be able to provide as
much functionality as before. This is due to isoHunt having removed
all searching and filtering options, only providing static HTML pages
for general categories (anime, movies, etc...). Those pages, however,
are heavily broken.

Unless someone is interested in monitoring the general categories
the effort of upgrading the bridge to the new site is not worth taking
time for.

Users of isoHunt are asked to make use of their client application,
as they don't provide online services anymore (it's now in the darknet)

Here is the statement from isoHunt:

"Due to hard regulations and security issues for bittorrent users, we
have moved into a more secure and even faster district of the internet!

[...]

Torrent Downloads have a high risk of getting legal problems. That is
why we do not offer torrentfiles any more. [...]"

-- source: https://isohunts.to
2018-06-24 18:33:50 +02:00
logmanoriginal
5087f5f79e [FacebookBridge] Support facebook links as user name
Allows users to paste facebook links as user name. The link must contain
the correct host (www.facebook.com) and a valid path (/user-name/...).
The first part of the path is used for the user name. Errors are returned
in case something went wrong.

References #706
2018-06-24 11:14:08 +02:00
logmanoriginal
4a5f190e0e [FacebookBridge] Add option to skip reviews
Reviews are provided the same way as summary posts and therefore returned
as separate feed item for each review. This commit adds a new option
'&skip_reviews=on' to skip reviews entirely.

References #706
2018-06-24 10:52:22 +02:00
logmanoriginal
01a2746715 [YoutubeBridge] Fix sniff violation
This is a fix for a sniff violation not detected by newer versions
of phpcs (not sure why though, it's detected in version 2.7.1).
2018-06-23 21:28:30 +02:00
Nemo
f4a60c1777 Add dockerfile to create an official docker image (#720) 2018-06-23 16:51:48 +02:00
sysadminstory
1b08bce779 [DealabsBridge] Follow site changes (#721)
- Changed some CSS class to follow the website changes (again)
2018-06-21 13:14:59 +01:00
Nemo
9fa74a36c6 Adds Container Linux releases RSS Feed (#718)
* Adds Container Linux releases RSS Feed
2018-06-19 19:39:08 +01:00
Corentin Garcia
7493e2b5b8 [GrandComicsDatabaseBridge] Add bridge (#717)
closes #709
2018-06-15 21:09:09 +02:00
Corentin Garcia
8e468a9ca7 [SuperSmashBlogBridge] Added bridge (#716) 2018-06-15 21:05:31 +02:00
Joe Digilio
50924b9213 Abort on parse error of config.default.ini.php (#714)
If there is an error parsing the default config file, then abort.
2018-06-15 21:02:06 +02:00
logmanoriginal
4c5013bc82 [index] Bump release version to 2018-06-10 2018-06-10 22:14:58 +02:00
Eugene Molotov
7dc09db9ca [VkBridge] More beatifications and fixes (#712)
* Add one more selector for article_author_selector
* Extend video parsing
* Add poll parsing
2018-06-10 22:09:50 +02:00
hunhejj
d92da8f0f7 Add cUrl error message and code to the debugMessage (#711) 2018-06-10 22:08:45 +02:00
logmanoriginal
064ba456e8 [InstagramBridge] Fix broken compatibility for media_type parameter
The media_type parameter was recently replaced by media_type_u (for
user mode) and media_type_h (for hashtag mode). This was necessary
in order to add the media type 'story' only for the user mode.

"The reason for that is that RSS-Bridge supports multiple parameters
with the same name if and only if they contain the exact same value.
Here, hashtags don't have stories, so it would not be possible to
pass "story" as a parameter. This is a design mistake that I made
when I added support for hashtags."

-- 8770c87389 (r28871502)

However as pointed out this change breaks existing feeds as the
parameter name is no longer compatible to previous implementations.

This commit changes the implementation to provide the old media_type
parameter globally and check for invalid options on each request. If
a user uses the 'story' option in history mode the bridge returns a
client error.

references 8770c87
references #694
fixes #696
fixes #699
fixes #701
2018-05-29 12:52:31 +02:00
LogMANOriginal
8ac8e08abf Add user config (#653)
Uses the parse_ini_file function to load default settings from the default configuration file 'config.default.ini.php'. Optionally loads custom settings from 'config.ini.php' to replace the default
values.
2018-05-29 11:52:17 +02:00
rogerdc
c4f32c31a8 Add ChristianDailyReporterBridge (#697) 2018-05-29 11:28:22 +02:00
Eugene Molotov
4369e077c2 [VkBridge] Fixed image src link generating for photo (#700) 2018-05-29 11:01:54 +02:00
sysadminstory
1045850043 [DealabsBridge] Follow site changes, fix unhandled case (#703)
* [DealabsBridge] Follow site changes, fix unhandled case

- Fixed the case where no discount was shown
- Changed some CSS class to follow the website changes
2018-05-29 10:52:13 +02:00
teromene
2d8f4dc3c5 Fix space in URL resulting in API errors. 2018-05-05 18:10:19 +01:00
teromene
779b638fb4 Added ElloBridge. Closes #683 2018-05-05 18:06:27 +01:00
teromene
3ca59392c2 Fix for crashes when accessing FileCache in case it has been purged/not created yet. 2018-05-05 18:05:48 +01:00
teromene
9b34b68180 Do not use an external service in order to fetch the favicon. 2018-05-05 13:55:38 +01:00
teromene
79ebdc4b39 Warn the user when trying to fetch a non-public facebook page. 2018-05-05 13:49:49 +01:00
teromene
8770c87389 Added support for stories in InstagramBridge. Closes #665
Renamed parameters as stories are only available in user mode.
Use a regex instead of HTML parsing to extract the JSON, as it is way faster.
2018-05-05 13:00:59 +01:00
Eugene Molotov
c1e3352218 [VkBridge] Extended article link parsing (#685)
* [VkBridge] Extended article link parsing
2018-05-05 12:03:54 +02:00
Grégory T
00570ce1b4 [ETTVBridge] New bridge, first push (#680)
* [ETTVBridge] New bridge
2018-04-30 23:18:39 +02:00
teromene
df33dcff4e [YGGTorrentBridge] URL encode the first parts of the requests. 2018-04-26 22:57:18 +01:00
Nicolas Delsaux
e60b5ab193 Mise à jour du bridge pour WorldOfTanks (#527)
* Mise à jour de l'un de mes bridges fétiches
2018-04-22 12:58:07 +02:00
teromene
b0c7a62f74 [index] Bumped version to 2018-04-20 2018-04-20 17:15:25 +02:00
teromene
57b15a089e Added DiscogsBridge. Closes #615 2018-04-20 16:57:09 +02:00
teromene
4b7fbe4188 DansTonChatBridge: test before accessing plaintext 2018-04-19 21:00:18 +02:00
Teromene
2390fb58b3 Merge pull request #673 from GregThib/patch-1
DansTonChatBridge: Update to follow DTC website changes
2018-04-19 20:58:01 +02:00
Teromene
1e8d29f6ec Merge pull request #672 from em92/patch-3
[YoutubeBridge] Removed duration in titles on search mode
2018-04-19 20:56:34 +02:00
Eugene Molotov
644d13686c [YoutubeBridge] Removed duration in titles on search mode 2018-04-19 09:03:29 +05:00
teromene
aa0ff1c9b1 Added YGGTorrentBridge. 2018-04-18 21:57:27 +02:00
teromene
539d9f1f06 Add SupInfoBridge, fixes #668 2018-04-18 12:39:45 +02:00
teromene
5ece801ce7 Fix h* display size in HtmlFormat, and fix images being wider than the page. 2018-04-18 12:29:22 +02:00
GregThib
4dcea6d9c9 Update to follow DTC website changes
Now, entry title is optionnal and may be found in h3 HTML element.
Entry content is mandatory and may be found in div[class="item-content"] HTML element.

Moreover, the title may contain simple quotes (here, encoded) so the bridge have to decode first to apply format library function. In case we don't do that, the format function double encode the quote and something like &amp;#039; could appear.
2018-04-18 12:00:00 +02:00
teromene
d69e2521f1 Removed T411 bridge. Website was closed nearly one year ago. 2018-04-18 11:44:54 +02:00
teromene
7927d73719 Rewrote DemonoidBridge. Fixes #626. 2018-04-17 15:25:02 +02:00
teromene
0620f30ae0 Changed the API key used for SoundCloud bridge. Should fix #599 2018-04-17 14:24:00 +02:00
teromene
795494cfce Added enclosures to InstagramBridge. 2018-04-16 19:34:21 +02:00
teromene
ba8542156c Remove usage of function file_get_contents. 2018-04-16 19:27:20 +02:00
Eugene Molotov
55f112e034 [VkBridge] Rewrited bridge code (#667)
* [VkBridge] Convert special HTML entities to characters in pageName

* [VkBridge] Generate feed item title

* [VkBridge] Remove double backslashes in feed item link

* [VkBridge] Unpin post if pinned

* [VkBridge] Mark reposted messages

* [VkBridge] Correct external link parsing

* [VkBridge] Added article parsing

* [VkBridge] Added video parsing

* [VkBridge] Added photo parsing

* [VkBridge] Added album link parsing

* [VkBridge] Added one more external link selector

* [VkBridge] Using array of link selectors to remove

* [VkBridge] Added document parsing

* [VkBridge] Added sign parsing

* [VkBridge] Fixed incorrect sorting with pinned item

* [VkBridge] More methods to parse documents

* [VkBridge] Save fallback if page name element not found

* [VkBridge] Using post signed as feed item author

* [VkBridge] Fixed document link

* [VkBridge] Coding policy fixes
2018-04-16 10:55:31 +01:00
Mitsukarenai
208fff801d [FDroid] minor fixes for Travis CI 2018-04-15 13:21:48 +02:00
Mitsukarenai
3c9860de43 [FDroid] new bridge 2018-04-15 13:13:10 +02:00
Adam Tygart
a16ec196c5 [NotAlways] Add a bridge for the NotAlways family of sites (#537)
NotAlways right found it necessary to remove their RSS feeds recently. This is a *simple* bridge to grab the ones on the front page. It allows you to filter the articles based on their classification (right, working, romantic, related, learning, friendly, hopeless, unfiltered, or all).
2018-04-15 12:02:37 +01:00
teromene
887fc7b037 Fix GoComics, website completely changed. Fixes #663 2018-04-14 18:15:44 +01:00
teromene
1bd4a40f71 Added GNOME Builder configuration to gitignore. 2018-04-14 18:15:13 +01:00
teromene
494169f959 Added bridge for Pixiv.
This bridge is slow, as caching of images is required (REFERER header required to access the full size images)
2018-04-14 16:19:35 +01:00
logmanoriginal
178177e787 [index] Push version to 2018-04-06 2018-04-06 22:45:33 +02:00
logmanoriginal
1cb83ccea3 [IPBBridge] Use limit for the number of items
The limit was used to specify the number of pages to return from a given
topic which resulted in the number of returned items variing between one
and however many entries are listed on one page.

This commit changes the implementation for the limit to keep loading more
pages until the specified limit is reached. Excessive elements are removed
in order to return the exact amount of items specified by the limit.

This behavior is closer to how other bridges are implemented and makes it
more natural to use without being too confusing. Existing queries must be
updated to account for the new limit.

References #657
2018-04-06 22:25:49 +02:00
sysadminstory
c899399569 [DealabsBridge] Follow the website changes (#660) 2018-04-06 21:25:41 +02:00
LogMANOriginal
0f93370e92 Merge pull request #654 from LogMANOriginal/cURL
Use cURL instead of file_get_contents
2018-04-06 20:49:58 +02:00
logmanoriginal
45c3dcb636 [VkBridge] Simplify header specification 2018-04-06 20:42:19 +02:00
logmanoriginal
ecfc220b10 [KernelBugTrackerBridge] Fix too many parameters requesting HTML DOM 2018-04-06 20:42:19 +02:00
logmanoriginal
4b3efed7ec [YoutubeBridge] Fix too many parameters when using HTML mode 2018-04-06 20:42:19 +02:00
logmanoriginal
bc28c5da8e [contents] Set CURLOPT_HTTPHEADER only if the provided array contains data 2018-04-06 20:42:19 +02:00
logmanoriginal
5bd9c1611d [contents] Limit cURL protocols to HTTP and HTTPS 2018-04-06 20:42:19 +02:00
logmanoriginal
6caca4946b bridges: Fix bridges with custom headers and options
This commit fixes bridges which called getContents, getSimpleHTMLDOM
or getSimpleHTMLDOMCached with custom settings.
2018-04-06 20:42:19 +02:00
logmanoriginal
ee78e7613f [contents] Replace file_get_contents by cURL
cURL is a powerful library specifically designed to connect to many
different types of servers with different types of protocols. For
more detailed information refer to the PHP cURL manual:

- http://php.net/manual/en/book.curl.php

Due to this change some parameters for the getContents function were
necessary (also applies to getSimpleHTMLDOM and getSimpleHTMLDOMCached):

> $use_include_path removed

  This parameter has never been used and doesn't even make sense in
  this context; If set to true file_get_contents would also search
  for files in the include_path (specified in php.ini).

> $context replaced by $header and $opts

  The $context parameter allowed for customization of the request in
  order to change how file_get_contents would acquire the data (i.e.
  using POST instead of GET, sending custom header, etc...)

  cURL also provides facilities to specify custom headers and change
  how it communicates to severs. cURL, however, is much more advanced.

  - $header is an optional parameter (empty by default). It receives
    an array of strings to send in the HTTP request header.

    See 'CURLOPT_HTTPHEADER':

    "An array of HTTP header fields to set, in the format
    array('Content-type: text/plain', 'Content-length: 100')"

    - php.net/manual/en/function.curl-setopt.php

  - $opts is an optional parameter (empty by default). It receives
    an array of options, where each option is a key-value-pair of
    a cURL option (CURLOPT_*) and it's associated parameter. This
    parameter accepts any of the CURLOPT_* settings.

    Example (sending POST instead of GET):

    $opts = array(
      CURLOPT_POST => 1,
      CURLOPT_POSTFIELDS => '&action=none'
    );
    $html = getContents($url, array(), $opts);

    Refer to the cURL setopt manual for more information:
    - php.net/manual/en/function.curl-setopt.php

> $offset and $maxlen removed

  These options were supported by file_get_contents, but there doesn't
  seem to be an equivalent in cURL. Since no caller uses them they are
  safe to remove.

Compressed data / Encoding

  By using cURL instead of file_get_contents RSS-Bridge no longer has
  to handle compressed data manually.

  See 'CURLOPT_ENCODING':

  "[...] Supported encodings are "identity", "deflate", and "gzip".
  If an empty string, "", is set, a header containing all supported
  encoding types is sent."

  - http://php.net/manual/en/function.curl-setopt.php

  Notice: By default all encoding types are accepted (""). This can
  be changed by setting a custom option via $opts.

    Example:

    $opts = array(CURLOPT_ENCODING => 'gzip');
    $html = getContents($url, array(), $opts);

Proxy

The proxy implementation should still work, but there doesn't seem
to be an equivalent for 'request_fulluri = true'. To my understanding
this isn't an issue because cURL knows how to handle proxy communication.
2018-04-06 20:42:19 +02:00
logmanoriginal
2df2623430 [index] Add 'curl' extension check 2018-04-06 20:42:19 +02:00
logmanoriginal
de5f850cdb [index] Fix indentation using tabs 2018-04-06 20:34:44 +02:00
teromene
ac6847045c Catch Errors in order to display a message in more cases. We also catch Exceptions to maintain compat with php 5.
Add check for simplexml extension.
2018-04-04 19:02:40 +01:00
logmanoriginal
df6da837dc [FacebookBridge] Return error if username starts with slash
Requesting a username with a leading slash would cause error 500
because the requested URI would contain two slashes in a row.

For example username "/test" would result in:
https://facebook.com//test

References #628
2018-03-23 21:23:30 +01:00
Eugene Molotov
41b7984a4e [YoutubeBridge] Playlist mode: faster feed generating if item count is less or equal to 15 (#648)
* [YoutubeBridge] Playlist mode: faster feed generating if item count is less or equal to 15
2018-03-19 12:41:52 +00:00
teromene
38c7e0272e Add hashtag support to InstagramBridge.
Fixes  #629
2018-03-19 12:29:24 +00:00
teromene
29c690dbcd Fix InstagramBridge, thanks to @pintassilgo comments.
Fixes #646
2018-03-19 12:17:42 +00:00
LogMANOriginal
8ba817478b Implement customizable cache timeout (#641)
* [BridgeAbstract] Implement customizable cache timeout

The customizable cache timeout is used instead of the default cache
timeout (CACHE_TIMEOUT) if specified by the caller.

* [index] Add new global parameter '_cache_timeout'

The _cache_timeout parameter is an optional parameter that can be
used to specify a custom cache timeout. This option is enabled by
default.

It can be disabled using the named constant 'CUSTOM_CACHE_TIMEOUT'
which supports two states:

> true: Enabled (default)
> false: Disabled

* [BridgeAbstract] Change scope of 'getCacheTimeout' to public

* [html] Add cache timeout parameter to all bridges

The timeout parameter only shows if CUSTOM_CACHE_TIMEOUT has been set
to true. The default value is automatically set to the value specified
in the bridge.

* [index] Disable custom cache timeout by default
2018-03-14 18:06:36 +01:00
Eugene Molotov
cacbe90102 [YoutubeBridge] Sort playlist items by publication date (#643) 2018-03-13 11:24:40 +00:00
Antoine Cadoret
cb91cd5d2f Fix SteamBridge (#637) (#639)
Fixes #639
2018-03-12 09:22:34 +00:00
sysadminstory
52dfa3fe76 [RadioMelodieBridge] Add new bridge (#640) 2018-03-11 15:38:07 +01:00
159 changed files with 13873 additions and 3691 deletions

8
.dockerignore Normal file
View File

@@ -0,0 +1,8 @@
.git
cache/*
DEBUG
Dockerfile
whitelist.txt
phpcs.xml
CHANGELOG.md
CONTRIBUTING.md

6
.gitignore vendored
View File

@@ -227,8 +227,12 @@ pip-log.txt
/cache
/whitelist.txt
DEBUG
config.ini.php
######################
## VisualStudioCode ##
######################
.vscode/*
.vscode/*
#Builder
.buildconfig

View File

@@ -3,12 +3,26 @@ sudo: false
language: php
install:
- pear channel-update pear.php.net
- pear install PHP_CodeSniffer
- if [[ $TRAVIS_PHP_VERSION == "hhvm" ]]; then
composer global require squizlabs/PHP_CodeSniffer;
else
pear channel-update pear.php.net;
pear install PHP_CodeSniffer;
fi
- if [[ $TRAVIS_PHP_VERSION == "7.0" ]]; then
composer global require phpunit/phpunit ^6;
fi
script:
- phpenv rehash
- phpcs . --standard=phpcs.xml --warning-severity=0 --extensions=php -p
- if [[ $TRAVIS_PHP_VERSION == "hhvm" ]]; then
/home/travis/.composer/vendor/bin/phpcs . --standard=phpcs.xml --warning-severity=0 --extensions=php -p;
else
phpcs . --standard=phpcs.xml --warning-severity=0 --extensions=php -p;
fi
- if [[ $TRAVIS_PHP_VERSION == "7.0" ]]; then
phpunit --configuration=phpunit.xml --include-path=lib/;
fi
matrix:
fast_finish: true

View File

@@ -1,47 +1,47 @@
### Pull request policy
Fix one issue per pull request.
Squash commits before opening a pull request.
Respect the coding style policy.
Name your PR like the following :
* When correcting a single bridge, use `[BridgeName] Feature`.
* When fixing a problem in a specific file, use `[FileName] Feature`.
* When fixing a general problem, use `category : feature`.
* [Fix one issue per pull request](https://github.com/RSS-Bridge/rss-bridge/wiki/Pull-request-policy#fix-one-issue-per-pull-request)
* [Respect the coding style policy](https://github.com/RSS-Bridge/rss-bridge/wiki/Pull-request-policy#respect-the-coding-style-policy)
* [Properly name your commits](https://github.com/RSS-Bridge/rss-bridge/wiki/Pull-request-policy#properly-name-your-commits)
* When fixing a bridge (located in the `bridges` directory), write `[BridgeName] Feature` <br>(i.e. `[YoutubeBridge] Fix typo in video titles`).
* When fixing other files, use `[FileName] Feature` <br>(i.e. `[index.php] Add multilingual support`).
* When fixing a general problem that applies to multiple files, write `category: feature` <br>(i.e. `bridges: Fix various typos`).
Note that all pull-requests should pass the unit tests before they can be merged.
Note that all pull-requests must pass all tests before they can be merged.
### Coding style
Use `camelCase` for variables and methods.
Use `UPPERCASE` for constants.
Use `PascalCase` for class names. When creating a bridge, your class and PHP file should be named `MyImplementationBridge`.
Use tabs for indentation.
Add an empty line at the end of your file.
Use `''` to encapsulate strings, including in arrays.
Prefer lines shorter than 80 chars, no line longer than 120 chars.
PHP constants should be in lower case (`true, false, null`...)
* Add spaces between the logical operator and your expressions (not needed for the `!` operator).
* Use `||` and `&&` instead of `or` and `and`.
* Add space between your condition and the opening bracket/closing bracket.
* Don't put a space between `if` and your bracket.
* Use `elseif` instead of `else if`.
* Add new lines in your conditions if they are containing more than one line.
* Example :
```PHP
if($a == true && $b) {
print($a);
} else if(!$b) {
$a = !$a;
$b = $b >> $a;
print($b);
} else {
print($b);
}
```
* [Whitespace](https://github.com/RSS-Bridge/rss-bridge/wiki/Whitespace)
* [Add a new line at the end of a file](https://github.com/RSS-Bridge/rss-bridge/wiki/Whitespace#add-a-new-line-at-the-end-of-a-file)
* [Do not add a whitespace before a semicolon](https://github.com/RSS-Bridge/rss-bridge/wiki/Whitespace#add-a-new-line-at-the-end-of-a-file)
* [Do not add whitespace at start or end of a file or end of a line](https://github.com/RSS-Bridge/rss-bridge/wiki/Whitespace#do-not-add-whitespace-at-start-or-end-of-a-file-or-end-of-a-line)
* [Indentation](https://github.com/RSS-Bridge/rss-bridge/wiki/Indentation)
* [Use tabs for indentation](https://github.com/RSS-Bridge/rss-bridge/wiki/Indentation#use-tabs-for-indentation)
* [Maximum line length](https://github.com/RSS-Bridge/rss-bridge/wiki/Maximum-line-length)
* [The maximum line length should not exceed 80 characters](https://github.com/RSS-Bridge/rss-bridge/wiki/Maximum-line-length#the-maximum-line-length-should-not-exceed-80-characters)
* [Strings](https://github.com/RSS-Bridge/rss-bridge/wiki/Strings)
* [Whenever possible use single quoted strings](https://github.com/RSS-Bridge/rss-bridge/wiki/Strings#whenever-possible-use-single-quote-strings)
* [Add spaces around the concatenation operator](https://github.com/RSS-Bridge/rss-bridge/wiki/Strings#add-spaces-around-the-concatenation-operator)
* [Use a single string instead of concatenating](https://github.com/RSS-Bridge/rss-bridge/wiki/Strings#use-a-single-string-instead-of-concatenating)
* [Constants](https://github.com/RSS-Bridge/rss-bridge/wiki/Constants)
* [Use UPPERCASE for constants](https://github.com/RSS-Bridge/rss-bridge/wiki/Constants#use-uppercase-for-constants)
* [Keywords](https://github.com/RSS-Bridge/rss-bridge/wiki/Keywords)
* [Use lowercase for `true`, `false` and `null`](https://github.com/RSS-Bridge/rss-bridge/wiki/Keywords#use-lowercase-for-true-false-and-null)
* [Operators](https://github.com/RSS-Bridge/rss-bridge/wiki/Operators)
* [Operators must have a space around them](https://github.com/RSS-Bridge/rss-bridge/wiki/Operators#operators-must-have-a-space-around-them)
* [Functions](https://github.com/RSS-Bridge/rss-bridge/wiki/Functions)
* [Parameters with default values must appear last in functions](https://github.com/RSS-Bridge/rss-bridge/wiki/Functions#parameters-with-default-values-must-appear-last-in-functions)
* [Calling functions](https://github.com/RSS-Bridge/rss-bridge/wiki/Functions#calling-functions)
* [Do not add spaces after opening or before closing bracket](https://github.com/RSS-Bridge/rss-bridge/wiki/Functions#do-not-add-spaces-after-opening-or-before-closing-bracket)
* [Structures](https://github.com/RSS-Bridge/rss-bridge/wiki/Structures)
* [Structures must always be formatted as multi-line blocks](https://github.com/RSS-Bridge/rss-bridge/wiki/Structures#structures-must-always-be-formatted-as-multi-line-blocks)
* [If-Statement](https://github.com/RSS-Bridge/rss-bridge/wiki/if-Statement)
* [Use `elseif` instead of `else if`](https://github.com/RSS-Bridge/rss-bridge/wiki/if-Statement#use-elseif-instead-of-else-if)
* [Do not write empty statements](https://github.com/RSS-Bridge/rss-bridge/wiki/if-Statement#do-not-write-empty-statements)
* [Do not write unconditional if-statements](https://github.com/RSS-Bridge/rss-bridge/wiki/if-Statement#do-not-write-unconditional-if-statements)
* [Classes](https://github.com/RSS-Bridge/rss-bridge/wiki/Classes)
* [Use PascalCase for class names](https://github.com/RSS-Bridge/rss-bridge/wiki/Classes#use-pascalcase-for-class-names)
* [Do not use final statements inside final classes](https://github.com/RSS-Bridge/rss-bridge/wiki/Classes#do-not-use-final-statements-inside-final-classes)
* [Do not override methods to call their parent](https://github.com/RSS-Bridge/rss-bridge/wiki/Classes#do-not-override-methods-to-call-their-parent)
* [Casting](https://github.com/RSS-Bridge/rss-bridge/wiki/Casting)
* [Do not add spaces when casting](https://github.com/RSS-Bridge/rss-bridge/wiki/Casting#do-not-add-spaces-when-casting)

5
Dockerfile Normal file
View File

@@ -0,0 +1,5 @@
FROM ulsmith/alpine-apache-php7
COPY ./ /app/public/
RUN chown -R apache:root /app/public

226
README.md
View File

@@ -1,10 +1,12 @@
rss-bridge
===
[![LICENSE](https://img.shields.io/badge/license-UNLICENSE-blue.svg)](UNLICENSE) [![Build Status](https://travis-ci.org/RSS-Bridge/rss-bridge.svg?branch=master)](https://travis-ci.org/RSS-Bridge/rss-bridge)
[![LICENSE](https://img.shields.io/badge/license-UNLICENSE-blue.svg)](UNLICENSE) [![GitHub release](https://img.shields.io/github/release/rss-bridge/rss-bridge.svg)](https://github.com/rss-bridge/rss-bridge/releases/latest) [![Debian Release](https://img.shields.io/badge/dynamic/json.svg?label=debian%20release&url=https%3A%2F%2Fsources.debian.org%2Fapi%2Fsrc%2Frss-bridge%2F&query=%24.versions%5B0%5D.version&colorB=blue)](https://tracker.debian.org/pkg/rss-bridge) [![Guix Release](https://img.shields.io/badge/guix%20release-unknown-light--gray.svg)](https://www.gnu.org/software/guix/packages/R/) [![Build Status](https://travis-ci.org/RSS-Bridge/rss-bridge.svg?branch=master)](https://travis-ci.org/RSS-Bridge/rss-bridge) [![Docker Build Status](https://img.shields.io/docker/build/rssbridge/rss-bridge.svg)](https://hub.docker.com/r/rssbridge/rss-bridge/)
rss-bridge is a PHP project capable of generating ATOM feeds for websites which don't have one.
RSS-Bridge is a PHP project capable of generating RSS and Atom feeds for websites which don't have one. It can be used on webservers or as stand alone application in CLI mode.
Supported sites/pages (main)
**Important**: RSS-Bridge is __not__ a feed reader or feed aggregator, but a tool to generate feeds that are consumed by feed readers and feed aggregators. Find a list of feed aggregators on [Wikipedia](https://en.wikipedia.org/wiki/Comparison_of_feed_aggregators).
Supported sites/pages (examples)
===
* `Bandcamp` : Returns last release from [bandcamp](https://bandcamp.com/) for a tag
@@ -25,106 +27,188 @@ Supported sites/pages (main)
* `Wikipedia`: highlighted articles from [Wikipedia](https://wikipedia.org/) in English, German, French or Esperanto
* `YouTube` : YouTube user channel, playlist or search
Plus [many other bridges](bridges/) to enable, thanks to the community
And [many more](bridges/), thanks to the community!
Output format
===
Output format can take several forms:
* `Atom` : ATOM Feed, for use in RSS/Feed readers
* `Html` : Simple html page.
* `Json` : Json, for consumption by other applications.
* `Mrss` : MRSS Feed, for use in RSS/Feed readers
* `Plaintext` : raw text (php object, as returned by print_r)
RSS-Bridge is capable of producing several output formats:
* `Atom` : Atom feed, for use in feed readers
* `Html` : Simple HTML page
* `Json` : JSON, for consumption by other applications
* `Mrss` : MRSS feed, for use in feed readers
* `Plaintext` : Raw text, for consumption by other applications
You can extend RSS-Bridge with your own format, using the [Format API](https://github.com/RSS-Bridge/rss-bridge/wiki/Format-API)!
Screenshot
===
Welcome screen:
![Screenshot](https://github.com/RSS-Bridge/rss-bridge/wiki/images/screenshot_rss-bridge_welcome.png)
RSS-Bridge hashtag (#rss-bridge) search on Twitter, in ATOM format (as displayed by Firefox):
***
RSS-Bridge hashtag (#rss-bridge) search on Twitter, in Atom format (as displayed by Firefox):
![Screenshot](https://github.com/RSS-Bridge/rss-bridge/wiki/images/screenshot_twitterbridge_atom.png)
Requirements
===
* PHP 5.6, e.g. `AddHandler application/x-httpd-php56 .php` in `.htaccess`
* `openssl` extension enabled in PHP config (`php.ini`)
* `allow_url_fopen=1` in `php.ini`
RSS-Bridge requires PHP 5.6 or higher with following extensions enabled:
Enabling/Disabling bridges
- [`openssl`](https://secure.php.net/manual/en/book.openssl.php)
- [`libxml`](https://secure.php.net/manual/en/book.libxml.php)
- [`mbstring`](https://secure.php.net/manual/en/book.mbstring.php)
- [`simplexml`](https://secure.php.net/manual/en/book.simplexml.php)
- [`curl`](https://secure.php.net/manual/en/book.curl.php)
- [`json`](https://secure.php.net/manual/en/book.json.php)
Find more information on our [Wiki](https://github.com/rss-bridge/rss-bridge/wiki)
Enable / Disable bridges
===
By default, the script creates `whitelist.txt` and adds the main bridges (see above). `whitelist.txt` is ignored by git, you can edit it:
* to enable extra bridges (one bridge per line)
* to disable main bridges (remove the line)
* to enable all bridges (just one wildcard `*` as file content)
RSS-Bridge allows you to take full control over which bridges are displayed to the user. That way you can host your own RSS-Bridge service with your favorite collection of bridges!
New bridges are disabled by default, so make sure to check regularly what's new and whitelist what you want!
Find more information on the [Wiki](https://github.com/RSS-Bridge/rss-bridge/wiki/Whitelisting)
**Notice**: By default RSS-Bridge will only show a small subset of bridges. Make sure to read up on [whitelisting](https://github.com/RSS-Bridge/rss-bridge/wiki/Whitelisting) to unlock the full potential of RSS-Bridge!
Deploy
===
Thanks to the community, hosting your own instance of RSS-Bridge is as easy as clicking a button!
[![Deploy on Scalingo](https://cdn.scalingo.com/deploy/button.svg)](https://my.scalingo.com/deploy?source=https://github.com/sebsauvage/rss-bridge)
[![Deploy to Docker Cloud](https://files.cloud.docker.com/images/deploy-to-dockercloud.svg)](https://cloud.docker.com/stack/deploy/?repo=https://github.com/rss-bridge/rss-bridge)
Getting involved
===
There are many ways for you to getting involved with RSS-Bridge. Here are a few things:
- Share RSS-Bridge with your friends (Twitter, Facebook, ..._you name it_...)
- Report broken bridges or bugs by opening [Issues](https://github.com/RSS-Bridge/rss-bridge/issues) on GitHub
- Request new features or suggest ideas (via [Issues](https://github.com/RSS-Bridge/rss-bridge/issues))
- Discuss bugs, features, ideas or [issues](https://github.com/RSS-Bridge/rss-bridge/issues)
- Add new bridges or improve the API
- Improve the [Wiki](https://github.com/RSS-Bridge/rss-bridge/wiki)
- Host an instance of RSS-Bridge for your personal use or make it available to the community :sparkling_heart:
Authors
===
We are RSS Bridge Community, a group of developers continuing the project initiated by sebsauvage, webmaster of [sebsauvage.net](http://sebsauvage.net), author of [Shaarli](http://sebsauvage.net/wiki/doku.php?id=php:shaarli) and [ZeroBin](http://sebsauvage.net/wiki/doku.php?id=php:zerobin).
Patch/contributors :
We are RSS-Bridge community, a group of developers continuing the project initiated by sebsauvage, webmaster of [sebsauvage.net](http://sebsauvage.net), author of [Shaarli](http://sebsauvage.net/wiki/doku.php?id=php:shaarli) and [ZeroBin](http://sebsauvage.net/wiki/doku.php?id=php:zerobin).
* Yves ASTIER ([Draeli](https://github.com/Draeli)) : PHP optimizations, fixes, dynamic brigde/format list with all stuff behind and extend cache system. Mail : contact /at\ yves-astier.com
* [Mitsukarenai](https://github.com/Mitsukarenai) : Initial inspiration, collaborator
* [ArthurHoaro](https://github.com/ArthurHoaro)
* [BoboTiG](https://github.com/BoboTiG)
* [Astalaseven](https://github.com/Astalaseven)
* [qwertygc](https://github.com/qwertygc)
* [Djuuu](https://github.com/Djuuu)
* [Anadrark](https://github.com/Anadrark])
* [Grummfy](https://github.com/Grummfy)
* [Polopollo](https://github.com/Polopollo)
* [16mhz](https://github.com/16mhz)
* [kranack](https://github.com/kranack)
* [logmanoriginal](https://github.com/logmanoriginal)
* [polo2ro](https://github.com/polo2ro)
* [Riduidel](https://github.com/Riduidel)
* [superbaillot.net](http://superbaillot.net/)
* [vinzv](https://github.com/vinzv)
* [teromene](https://github.com/teromene)
* [nel50n](https://github.com/nel50n)
* [nyutag](https://github.com/nyutag)
* [ORelio](https://github.com/ORelio)
* [Pitchoule](https://github.com/Pitchoule)
* [pit-fgfjiudghdf](https://github.com/pit-fgfjiudghdf)
* [aledeg](https://github.com/aledeg)
* [alexAubin](https://github.com/alexAubin)
* [cnlpete](https://github.com/cnlpete)
* [corenting](https://github.com/corenting)
* [Daiyousei](https://github.com/Daiyousei)
* [erwang](https://github.com/erwang)
* [gsurrel](https://github.com/gsurrel)
* [kraoc](https://github.com/kraoc)
* [lagaisse](https://github.com/lagaisse)
* [az5he6ch](https://github.com/az5he6ch)
* [niawag](https://github.com/niawag)
* [JeremyRand](https://github.com/JeremyRand)
* [mro](https://github.com/mro)
**Contributors** (sorted alphabetically):
<!--
Use this script to generate the list automatically (using the GitHub API):
https://gist.github.com/LogMANOriginal/da00cd1e5f0ca31cef8e193509b17fd8
-->
* [16mhz](https://api.github.com/users/16mhz)
* [Ahiles3005](https://api.github.com/users/Ahiles3005)
* [Albirew](https://api.github.com/users/Albirew)
* [AmauryCarrade](https://api.github.com/users/AmauryCarrade)
* [ArthurHoaro](https://api.github.com/users/ArthurHoaro)
* [Astalaseven](https://api.github.com/users/Astalaseven)
* [Astyan-42](https://api.github.com/users/Astyan-42)
* [Daiyousei](https://api.github.com/users/Daiyousei)
* [Djuuu](https://api.github.com/users/Djuuu)
* [Draeli](https://api.github.com/users/Draeli)
* [EtienneM](https://api.github.com/users/EtienneM)
* [Frenzie](https://api.github.com/users/Frenzie)
* [Ginko-Aloe](https://api.github.com/users/Ginko-Aloe)
* [Glandos](https://api.github.com/users/Glandos)
* [GregThib](https://api.github.com/users/GregThib)
* [Grummfy](https://api.github.com/users/Grummfy)
* [JackNUMBER](https://api.github.com/users/JackNUMBER)
* [JeremyRand](https://api.github.com/users/JeremyRand)
* [Jocker666z](https://api.github.com/users/Jocker666z)
* [LogMANOriginal](https://api.github.com/users/LogMANOriginal)
* [MonsieurPoutounours](https://api.github.com/users/MonsieurPoutounours)
* [ORelio](https://api.github.com/users/ORelio)
* [PaulVayssiere](https://api.github.com/users/PaulVayssiere)
* [Piranhaplant](https://api.github.com/users/Piranhaplant)
* [Riduidel](https://api.github.com/users/Riduidel)
* [Strubbl](https://api.github.com/users/Strubbl)
* [TheRadialActive](https://api.github.com/users/TheRadialActive)
* [TwizzyDizzy](https://api.github.com/users/TwizzyDizzy)
* [WalterBarrett](https://api.github.com/users/WalterBarrett)
* [ZeNairolf](https://api.github.com/users/ZeNairolf)
* [adamchainz](https://api.github.com/users/adamchainz)
* [aledeg](https://api.github.com/users/aledeg)
* [alexAubin](https://api.github.com/users/alexAubin)
* [az5he6ch](https://api.github.com/users/az5he6ch)
* [b1nj](https://api.github.com/users/b1nj)
* [benasse](https://api.github.com/users/benasse)
* [captn3m0](https://api.github.com/users/captn3m0)
* [chemel](https://api.github.com/users/chemel)
* [ckiw](https://api.github.com/users/ckiw)
* [cnlpete](https://api.github.com/users/cnlpete)
* [corenting](https://api.github.com/users/corenting)
* [da2x](https://api.github.com/users/da2x)
* [eMerzh](https://api.github.com/users/eMerzh)
* [em92](https://api.github.com/users/em92)
* [griffaurel](https://api.github.com/users/griffaurel)
* [hunhejj](https://api.github.com/users/hunhejj)
* [j0k3r](https://api.github.com/users/j0k3r)
* [jdigilio](https://api.github.com/users/jdigilio)
* [kranack](https://api.github.com/users/kranack)
* [kraoc](https://api.github.com/users/kraoc)
* [laBecasse](https://api.github.com/users/laBecasse)
* [lagaisse](https://api.github.com/users/lagaisse)
* [lalannev](https://api.github.com/users/lalannev)
* [ldidry](https://api.github.com/users/ldidry)
* [m0zes](https://api.github.com/users/m0zes)
* [matthewseal](https://api.github.com/users/matthewseal)
* [mcbyte-it](https://api.github.com/users/mcbyte-it)
* [mdemoss](https://api.github.com/users/mdemoss)
* [melangue](https://api.github.com/users/melangue)
* [metaMMA](https://api.github.com/users/metaMMA)
* [mickael-bertrand](https://api.github.com/users/mickael-bertrand)
* [mitsukarenai](https://api.github.com/users/mitsukarenai)
* [mro](https://api.github.com/users/mro)
* [mxmehl](https://api.github.com/users/mxmehl)
* [nel50n](https://api.github.com/users/nel50n)
* [niawag](https://api.github.com/users/niawag)
* [pellaeon](https://api.github.com/users/pellaeon)
* [pit-fgfjiudghdf](https://api.github.com/users/pit-fgfjiudghdf)
* [pitchoule](https://api.github.com/users/pitchoule)
* [pmaziere](https://api.github.com/users/pmaziere)
* [prysme01](https://api.github.com/users/prysme01)
* [quentinus95](https://api.github.com/users/quentinus95)
* [qwertygc](https://api.github.com/users/qwertygc)
* [regisenguehard](https://api.github.com/users/regisenguehard)
* [rogerdc](https://api.github.com/users/rogerdc)
* [sebsauvage](https://api.github.com/users/sebsauvage)
* [sublimz](https://api.github.com/users/sublimz)
* [sysadminstory](https://api.github.com/users/sysadminstory)
* [tameroski](https://api.github.com/users/tameroski)
* [teromene](https://api.github.com/users/teromene)
* [triatic](https://api.github.com/users/triatic)
* [wtuuju](https://api.github.com/users/wtuuju)
Licenses
===
Code is [Public Domain](UNLICENSE).
Including `PHP Simple HTML DOM Parser` under the [MIT License](http://opensource.org/licenses/MIT)
The source code for RSS-Bridge is [Public Domain](UNLICENSE).
RSS-Bridge uses third party libraries with their own license:
* [`PHP Simple HTML DOM Parser`](http://simplehtmldom.sourceforge.net/) licensed under the [MIT License](http://opensource.org/licenses/MIT)
* [`php-urljoin`](https://github.com/fluffy-critter/php-urljoin) licensed under the [MIT License](http://opensource.org/licenses/MIT)
Technical notes
===
* There is a cache so that source services won't ban you even if you hammer the rss-bridge with requests. Each bridge can have a different duration for the cache. The `cache` subdirectory will be automatically created and cached objects older than 24 hours get purged.
* To implement a new Bridge, [follow the specifications](https://github.com/RSS-Bridge/rss-bridge/wiki/Bridge-API) and take a look at existing Bridges for examples.
* To enable debug mode (disabling cache and enabling error reporting), create an empty file named `DEBUG` in the root directory (next to `index.php`).
* For more information refer to the [Wiki](https://github.com/RSS-Bridge/rss-bridge/wiki)
* RSS-Bridge uses caching to prevent services from banning your server for repeatedly updating feeds. The specific cache duration can be different between bridges. Cached files are deleted automatically after 24 hours.
* You can implement your own bridge, [following these instructions](https://github.com/RSS-Bridge/rss-bridge/wiki/Bridge-API).
* You can enable debug mode to disable caching. Find more information on the [Wiki](https://github.com/RSS-Bridge/rss-bridge/wiki/Debug-mode)
Rant
===
@@ -133,10 +217,10 @@ Rant
Your catchword is "share", but you don't want us to share. You want to keep us within your walled gardens. That's why you've been removing RSS links from webpages, hiding them deep on your website, or removed feeds entirely, replacing it with crippled or demented proprietary API. **FUCK YOU.**
You're not social when you hamper sharing by removing feeds. You're happy to have customers creating content for your ecosystem, but you don't want this content out - a content you do not even own. Google Takeout is just a gimmick. We want our data to flow, we want RSS or ATOM feeds.
You're not social when you hamper sharing by removing feeds. You're happy to have customers creating content for your ecosystem, but you don't want this content out - a content you do not even own. Google Takeout is just a gimmick. We want our data to flow, we want RSS or Atom feeds.
We want to share with friends, using open protocols: RSS, ATOM, XMPP, whatever. Because no one wants to have *your* service with *your* applications using *your* API force-feeding them. Friends must be free to choose whatever software and service they want.
We want to share with friends, using open protocols: RSS, Atom, XMPP, whatever. Because no one wants to have *your* service with *your* applications using *your* API force-feeding them. Friends must be free to choose whatever software and service they want.
We are rebuilding bridges you have wilfully destroyed.
Get your shit together: Put RSS/ATOM back in.
Get your shit together: Put RSS/Atom back in.

View File

@@ -8,7 +8,7 @@ class ABCTabsBridge extends BridgeAbstract {
public function collectData(){
$html = '';
$html = getSimpleHTMLDOM(static::URI.'tablatures/nouveautes.html')
$html = getSimpleHTMLDOM(static::URI . 'tablatures/nouveautes.html')
or returnClientError('No results for this query.');
$table = $html->find('table#myTable', 0)->children(1);

View File

@@ -45,7 +45,7 @@ class AllocineFRBridge extends BridgeAbstract {
public function getName(){
if(!is_null($this->getInput('category'))) {
return self::NAME . ' : '
.array_search(
. array_search(
$this->getInput('category'),
self::PARAMETERS[$this->queriedContext]['category']['values']
);

View File

@@ -52,7 +52,7 @@ class AmazonBridge extends BridgeAbstract {
public function getName(){
if(!is_null($this->getInput('tld')) && !is_null($this->getInput('q'))) {
return 'Amazon.'.$this->getInput('tld').': '.$this->getInput('q');
return 'Amazon.' . $this->getInput('tld') . ': ' . $this->getInput('q');
}
return parent::getName();
@@ -60,8 +60,8 @@ class AmazonBridge extends BridgeAbstract {
public function collectData() {
$uri = 'https://www.amazon.'.$this->getInput('tld').'/';
$uri .= 's/?field-keywords='.urlencode($this->getInput('q')).'&sort='.$this->getInput('sort');
$uri = 'https://www.amazon.' . $this->getInput('tld') . '/';
$uri .= 's/?field-keywords=' . urlencode($this->getInput('q')) . '&sort=' . $this->getInput('sort');
$html = getSimpleHTMLDOM($uri)
or returnServerError('Could not request Amazon.');
@@ -86,7 +86,7 @@ class AmazonBridge extends BridgeAbstract {
$price = $element->find('span.s-price', 0);
$price = ($price) ? $price->innertext : '';
$item['content'] = '<img src="'.$image->getAttribute('src').'" /><br />'.$price;
$item['content'] = '<img src="' . $image->getAttribute('src') . '" /><br />' . $price;
$this->items[] = $item;
}

View File

@@ -0,0 +1,187 @@
<?php
class AmazonPriceTrackerBridge extends BridgeAbstract {
const MAINTAINER = 'captn3m0';
const NAME = 'Amazon Price Tracker';
const URI = 'https://www.amazon.com/';
const CACHE_TIMEOUT = 3600; // 1h
const DESCRIPTION = 'Tracks price for a single product on Amazon';
const PARAMETERS = array(
array(
'asin' => array(
'name' => 'ASIN',
'required' => true,
'exampleValue' => 'B071GB1VMQ',
// https://stackoverflow.com/a/12827734
'pattern' => 'B[\dA-Z]{9}|\d{9}(X|\d)',
),
'tld' => array(
'name' => 'Country',
'type' => 'list',
'required' => true,
'values' => array(
'Australia' => 'com.au',
'Brazil' => 'com.br',
'Canada' => 'ca',
'China' => 'cn',
'France' => 'fr',
'Germany' => 'de',
'India' => 'in',
'Italy' => 'it',
'Japan' => 'co.jp',
'Mexico' => 'com.mx',
'Netherlands' => 'nl',
'Spain' => 'es',
'United Kingdom' => 'co.uk',
'United States' => 'com',
),
'defaultValue' => 'com',
),
));
protected $title;
/**
* Generates domain name given a amazon TLD
*/
private function getDomainName() {
return 'https://www.amazon.' . $this->getInput('tld');
}
/**
* Generates URI for a Amazon product page
*/
public function getURI() {
if (!is_null($this->getInput('asin'))) {
return $this->getDomainName() . '/dp/' . $this->getInput('asin') . '/';
}
return parent::getURI();
}
/**
* Scrapes the product title from the html page
* returns the default title if scraping fails
*/
private function getTitle($html) {
$titleTag = $html->find('#productTitle', 0);
if (!$titleTag) {
return $this->getDefaultTitle();
} else {
return trim(html_entity_decode($titleTag->innertext, ENT_QUOTES));
}
}
/**
* Title used by the feed if none could be found
*/
private function getDefaultTitle() {
return 'Amazon.' . $this->getInput('tld') . ': ' . $this->getInput('asin');
}
/**
* Returns name for the feed
* Uses title (already scraped) if it has one
*/
public function getName() {
if (isset($this->title)) {
return $this->title;
} else {
return parent::getName();
}
}
private function parseDynamicImage($attribute) {
$json = json_decode(html_entity_decode($attribute), true);
if ($json and count($json) > 0) {
return array_keys($json)[0];
}
}
/**
* Returns a generated image tag for the product
*/
private function getImage($html) {
$imageSrc = $html->find('#main-image-container img', 0);
if ($imageSrc) {
$hiresImage = $imageSrc->getAttribute('data-old-hires');
$dynamicImageAttribute = $imageSrc->getAttribute('data-a-dynamic-image');
$image = $hiresImage ?: $this->parseDynamicImage($dynamicImageAttribute);
}
$image = $image ?: 'https://placekitten.com/200/300';
return <<<EOT
<img width="300" style="max-width:300;max-height:300" src="$image" alt="{$this->title}" />
EOT;
}
/**
* Return \simple_html_dom object
* for the entire html of the product page
*/
private function getHtml() {
$uri = $this->getURI();
return getSimpleHTMLDOM($uri) ?: returnServerError('Could not request Amazon.');
}
private function scrapePriceFromMetrics($html) {
$asinData = $html->find('#cerberus-data-metrics', 0);
// <div id="cerberus-data-metrics" style="display: none;"
// data-asin="B00WTHJ5SU" data-asin-price="14.99" data-asin-shipping="0"
// data-asin-currency-code="USD" data-substitute-count="-1" ... />
if ($asinData) {
return [
'price' => $asinData->getAttribute('data-asin-price'),
'currency' => $asinData->getAttribute('data-asin-currency-code'),
'shipping' => $asinData->getAttribute('data-asin-shipping')
];
}
return false;
}
private function scrapePriceGeneric($html) {
$priceDiv = $html->find('span.offer-price', 0) ?: $html->find('.a-color-price', 0);
preg_match('/^\s*([A-Z]{3}|£|\$)\s?([\d.,]+)\s*$/', $priceDiv->plaintext, $matches);
if (count($matches) === 3) {
return [
'price' => $matches[2],
'currency' => $matches[1],
'shipping' => '0'
];
}
return false;
}
/**
* Scrape method for Amazon product page
* @return [type] [description]
*/
public function collectData() {
$html = $this->getHtml();
$this->title = $this->getTitle($html);
$imageTag = $this->getImage($html);
$data = $this->scrapePriceFromMetrics($html) ?: $this->scrapePriceGeneric($html);
$item = array(
'title' => $this->title,
'uri' => $this->getURI(),
'content' => "$imageTag<br/>Price: {$data['price']} {$data['currency']}",
);
if ($data['shipping'] !== '0') {
$item['content'] .= "<br>Shipping: {$data['shipping']} {$data['currency']}</br>";
}
$this->items[] = $item;
}
}

207
bridges/AnidexBridge.php Normal file
View File

@@ -0,0 +1,207 @@
<?php
class AnidexBridge extends BridgeAbstract {
const MAINTAINER = 'ORelio';
const NAME = 'Anidex';
const URI = 'https://anidex.info/';
const DESCRIPTION = 'Returns the newest torrents, with optional search criteria.';
const PARAMETERS = array(
array(
'id' => array(
'name' => 'Category',
'type' => 'list',
'values' => array(
'All categories' => '0',
'Anime' => '1,2,3',
'Anime - Sub' => '1',
'Anime - Raw' => '2',
'Anime - Dub' => '3',
'Live Action' => '4,5',
'Live Action - Sub' => '4',
'Live Action - Raw' => '5',
'Light Novel' => '6',
'Manga' => '7,8',
'Manga - Translated' => '7',
'Manga - Raw' => '8',
'Music' => '9,10,11',
'Music - Lossy' => '9',
'Music - Lossless' => '10',
'Music - Video' => '11',
'Games' => '12',
'Applications' => '13',
'Pictures' => '14',
'Adult Video' => '15',
'Other' => '16'
)
),
'lang_id' => array(
'name' => 'Language',
'type' => 'list',
'values' => array(
'All languages' => '0',
'English' => '1',
'Japanese' => '2',
'Polish' => '3',
'Serbo-Croatian' => '4',
'Dutch' => '5',
'Italian' => '6',
'Russian' => '7',
'German' => '8',
'Hungarian' => '9',
'French' => '10',
'Finnish' => '11',
'Vietnamese' => '12',
'Greek' => '13',
'Bulgarian' => '14',
'Spanish (Spain)' => '15',
'Portuguese (Brazil)' => '16',
'Portuguese (Portugal)' => '17',
'Swedish' => '18',
'Arabic' => '19',
'Danish' => '20',
'Chinese (Simplified)' => '21',
'Bengali' => '22',
'Romanian' => '23',
'Czech' => '24',
'Mongolian' => '25',
'Turkish' => '26',
'Indonesian' => '27',
'Korean' => '28',
'Spanish (LATAM)' => '29',
'Persian' => '30',
'Malaysian' => '31'
)
),
'group_id' => array(
'name' => 'Group ID',
'type' => 'number'
),
'r' => array(
'name' => 'Hide Remakes',
'type' => 'checkbox'
),
'b' => array(
'name' => 'Only Batches',
'type' => 'checkbox'
),
'a' => array(
'name' => 'Only Authorized',
'type' => 'checkbox'
),
'q' => array(
'name' => 'Keyword',
'description' => 'Keyword(s)',
'type' => 'text'
),
'h' => array(
'name' => 'Adult content',
'type' => 'list',
'values' => array(
'No filter' => '0',
'Hide +18' => '1',
'Only +18' => '2'
)
)
)
);
public function collectData() {
// Build Search URL from user-provided parameters
$search_url = self::URI . '?s=upload_timestamp&o=desc';
foreach (array('id', 'lang_id', 'group_id') as $param_name) {
$param = $this->getInput($param_name);
if (!empty($param) && intval($param) != 0 && ctype_digit(str_replace(',', '', $param))) {
$search_url .= '&' . $param_name . '=' . $param;
}
}
foreach (array('r', 'b', 'a') as $param_name) {
$param = $this->getInput($param_name);
if (!empty($param) && boolval($param)) {
$search_url .= '&' . $param_name . '=1';
}
}
$query = $this->getInput('q');
if (!empty($query)) {
$search_url .= '&q=' . urlencode($query);
}
$opt = array();
$h = $this->getInput('h');
if (!empty($h) && intval($h) != 0 && ctype_digit($h)) {
$opt[CURLOPT_COOKIE] = 'anidex_h_toggle=' . $h;
}
// Retrieve torrent listing from search results, which does not contain torrent description
$html = getSimpleHTMLDOM($search_url, array(), $opt)
or returnServerError('Could not request Anidex: ' . $search_url);
$links = $html->find('a');
$results = array();
foreach ($links as $link)
if (strpos($link->href, '/torrent/') === 0 && !in_array($link->href, $results))
$results[] = $link->href;
if (empty($results) && empty($this->getInput('q')))
returnServerError('No results from Anidex: ' . $search_url);
//Process each item individually
foreach ($results as $element) {
//Limit total amount of requests
if(count($this->items) >= 20) {
break;
}
$torrent_id = str_replace('/torrent/', '', $element);
//Ignore entries without valid torrent ID
if ($torrent_id != 0 && ctype_digit($torrent_id)) {
//Retrieve data for this torrent ID
$item_uri = self::URI . 'torrent/' . $torrent_id;
//Retrieve full description from torrent page
if ($item_html = getSimpleHTMLDOMCached($item_uri)) {
//Retrieve data from page contents
$item_title = str_replace(' (Torrent) - AniDex ', '', $item_html->find('title', 0)->plaintext);
$item_desc = $item_html->find('div.panel-body', 0);
$item_author = trim($item_html->find('span.fa-user', 0)->parent()->plaintext);
$item_date = strtotime(trim($item_html->find('span.fa-clock', 0)->parent()->plaintext));
$item_image = $this->getURI() . 'images/user_logos/default.png';
//Check for description-less torrent andn optionally extract image
$desc_title_found = false;
foreach ($item_html->find('h3.panel-title') as $h3) {
if (strpos($h3, 'Description') !== false) {
$desc_title_found = true;
break;
}
}
if ($desc_title_found) {
//Retrieve image for thumbnail or generic logo fallback
foreach ($item_desc->find('img') as $img) {
if (strpos($img->src, 'prez') === false) {
$item_image = $img->src;
break;
}
}
$item_desc = trim($item_desc->innertext);
} else {
$item_desc = '<em>No description.</em>';
}
//Build and add final item
$item = array();
$item['uri'] = $item_uri;
$item['title'] = $item_title;
$item['author'] = $item_author;
$item['timestamp'] = $item_date;
$item['enclosures'] = array($item_image);
$item['content'] = $item_desc;
$this->items[] = $item;
}
}
$element = null;
}
$results = null;
}
}

View File

@@ -5,7 +5,7 @@ class AnimeUltimeBridge extends BridgeAbstract {
const NAME = 'Anime-Ultime';
const URI = 'http://www.anime-ultime.net/';
const CACHE_TIMEOUT = 10800; // 3h
const DESCRIPTION = 'Returns the 10 newest releases posted on Anime-Ultime';
const DESCRIPTION = 'Returns the newest releases posted on Anime-Ultime.';
const PARAMETERS = array( array(
'type' => array(
'name' => 'Type',
@@ -65,6 +65,13 @@ class AnimeUltimeBridge extends BridgeAbstract {
$item_link_element = $release->find('td', 0)->find('a', 0);
$item_uri = self::URI . $item_link_element->href;
$item_name = html_entity_decode($item_link_element->plaintext);
$item_image = self::URI . substr(
$item_link_element->onmouseover,
37,
strpos($item_link_element->onmouseover, ' ', 37) - 37
);
$item_episode = html_entity_decode(
str_pad(
$release->find('td', 1)->plaintext,
@@ -79,8 +86,7 @@ class AnimeUltimeBridge extends BridgeAbstract {
if(!empty($item_uri)) {
// Retrieve description from description page and
// convert relative image src info absolute image src
// Retrieve description from description page
$html_item = getContents($item_uri)
or returnServerError('Could not request Anime-Ultime: ' . $item_uri);
$item_description = substr(
@@ -91,10 +97,9 @@ class AnimeUltimeBridge extends BridgeAbstract {
0,
strpos($item_description, '<div id="table">')
);
$item_description = str_replace(
'src="images', 'src="' . self::URI . 'images',
$item_description
);
// Convert relative image src into absolute image src, remove line breaks
$item_description = defaultLinkTo($item_description, self::URI);
$item_description = str_replace("\r", '', $item_description);
$item_description = str_replace("\n", '', $item_description);
$item_description = utf8_encode($item_description);
@@ -105,6 +110,7 @@ class AnimeUltimeBridge extends BridgeAbstract {
$item['title'] = $item_name . ' ' . $item_type . ' ' . $item_episode;
$item['author'] = $item_fansub;
$item['timestamp'] = $item_date;
$item['enclosures'] = array($item_image);
$item['content'] = $item_description;
$this->items[] = $item;
$processedOK++;

View File

@@ -28,6 +28,13 @@ class Arte7Bridge extends BridgeAbstract {
)
)
),
'Collection (Français)' => array(
'colfr' => array(
'name' => 'Collection id',
'required' => true,
'title' => 'ex. RC-014095 pour https://www.arte.tv/fr/videos/RC-014095/blow-up/'
)
),
'Catégorie (Allemand)' => array(
'catde' => array(
'type' => 'list',
@@ -45,6 +52,13 @@ class Arte7Bridge extends BridgeAbstract {
'Sonstiges' => 'AUT'
)
)
),
'Collection (Allemand)' => array(
'colde' => array(
'name' => 'Collection id',
'required' => true,
'title' => 'ex. RC-014095 pour https://www.arte.tv/de/videos/RC-014095/blow-up/'
)
)
);
@@ -54,23 +68,30 @@ class Arte7Bridge extends BridgeAbstract {
$category = $this->getInput('catfr');
$lang = 'fr';
break;
case 'Collection (Français)':
$lang = 'fr';
$collectionId = $this->getInput('colfr');
break;
case 'Catégorie (Allemand)':
$category = $this->getInput('catde');
$lang = 'de';
break;
case 'Collection (Allemand)':
$lang = 'de';
$collectionId = $this->getInput('colde');
break;
}
$url = 'https://api.arte.tv/api/opa/v3/videos?sort=-lastModified&limit=10&language='
. $lang
. ($category != null ? '&category.code=' . $category : '');
. ($category != null ? '&category.code=' . $category : '')
. ($collectionId != null ? '&collections.collectionId=' . $collectionId : '');
$context = array(
'http' => array(
'header' => 'Authorization: Bearer '. self::API_TOKEN
)
$header = array(
'Authorization: Bearer ' . self::API_TOKEN
);
$input = getContents($url, false, stream_context_create($context)) or die('Could not request ARTE.');
$input = getContents($url, $header) or die('Could not request ARTE.');
$input_json = json_decode($input, true);
foreach($input_json['videos'] as $element) {

View File

@@ -1,7 +1,7 @@
<?php
class AskfmBridge extends BridgeAbstract {
const MAINTAINER = 'az5he6ch';
const MAINTAINER = 'az5he6ch, logmanoriginal';
const NAME = 'Ask.fm Answers';
const URI = 'https://ask.fm/';
const CACHE_TIMEOUT = 300; //5 min
@@ -19,39 +19,39 @@ class AskfmBridge extends BridgeAbstract {
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError('Requested username can\'t be found.');
foreach($html->find('div.streamItem-answer') as $element) {
$html = defaultLinkTo($html, self::URI);
foreach($html->find('article.streamItem-answer') as $element) {
$item = array();
$item['uri'] = self::URI . $element->find('a.streamItemsAge', 0)->href;
$question = trim($element->find('h1.streamItemContent-question', 0)->innertext);
$item['uri'] = $element->find('a.streamItem_meta', 0)->href;
$question = trim($element->find('header.streamItem_header', 0)->innertext);
$item['title'] = trim(
htmlspecialchars_decode($element->find('h1.streamItemContent-question', 0)->plaintext,
htmlspecialchars_decode($element->find('header.streamItem_header', 0)->plaintext,
ENT_QUOTES
)
);
$answer = trim($element->find('p.streamItemContent-answer', 0)->innertext);
$item['timestamp'] = strtotime($element->find('time', 0)->datetime);
// Doesn't work, DOM parser doesn't seem to like data-hint, dunno why
#$item['update'] = $element->find('a.streamitemsage',0)->data-hint;
$answer = trim($element->find('div.streamItem_content', 0)->innertext);
// This probably should be cleaned up, especially for YouTube embeds
$visual = $element->find('div.streamItemContent-visual', 0)->innertext;
//Fix tracking links, also doesn't work
if($visual = $element->find('div.streamItem_visual', 0)) {
$visual = $visual->innertext;
}
// Fix tracking links, also doesn't work
foreach($element->find('a') as $link) {
if(strpos($link->href, 'l.ask.fm') !== false) {
// Too slow
#$link->href = str_replace('#_=_', '', get_headers($link->href, 1)['Location']);
$link->href = $link->plaintext;
}
}
$content = '<p>' . $question . '</p><p>' . $answer . '</p><p>' . $visual . '</p>';
// Fix relative links without breaking // scheme used by YouTube stuff
$content = preg_replace('#href="\/(?!\/)#', 'href="' . self::URI, $content);
$item['content'] = $content;
$item['content'] = '<p>' . $question
. '</p><p>' . $answer
. '</p><p>' . $visual . '</p>';
$this->items[] = $item;
}
}
@@ -66,7 +66,7 @@ class AskfmBridge extends BridgeAbstract {
public function getURI(){
if(!is_null($this->getInput('u'))) {
return self::URI . urlencode($this->getInput('u')) . '/answers/more?page=0';
return self::URI . urlencode($this->getInput('u'));
}
return parent::getURI();

65
bridges/AutoJMBridge.php Normal file
View File

@@ -0,0 +1,65 @@
<?php
class AutoJMBridge extends BridgeAbstract {
const NAME = 'AutoJM';
const URI = 'http://www.autojm.fr/';
const DESCRIPTION = 'Suivre les offres de véhicules proposés par AutoJM en fonction des critères de filtrages';
const MAINTAINER = 'sysadminstory';
const PARAMETERS = array(
'Afficher les offres de véhicules disponible en fonction des critères du site AutoJM' => array(
'url' => array(
'name' => 'URL de la recherche',
'type' => 'text',
'required' => true,
'title' => 'URL d\'une recherche avec filtre de véhicules sans le http://www.autojm.fr/',
'exampleValue' => 'gammes/index/398?order_by=finition_asc&energie[]=3&transmission[]=2&dispo=all'
)
)
);
const CACHE_TIMEOUT = 3600;
public function getIcon() {
return self::URI . 'assets/images/favicon.ico';
}
public function collectData() {
$html = getSimpleHTMLDOM(self::URI . $this->getInput('url'))
or returnServerError('Could not request AutoJM.');
$list = $html->find('div[class*=ligne_modele]');
foreach($list as $element) {
$image = $element->find('img[class=width-100]', 0)->src;
$serie = $element->find('div[class=serie]', 0)->find('span', 0)->plaintext;
$url = $element->find('div[class=serie]', 0)->find('a[class=btn_ligne color-black]', 0)->href;
if($element->find('div[class*=hasStock-info]', 0) != null) {
$dispo = 'Disponible';
} else {
$dispo = 'Sur commande';
}
$carburant = str_replace('dispo |', '', $element->find('div[class=carburant]', 0)->plaintext);
$transmission = $element->find('div[class*=bv]', 0)->plaintext;
$places = $element->find('div[class*=places]', 0)->plaintext;
$portes = $element->find('div[class*=nb_portes]', 0)->plaintext;
$carosserie = $element->find('div[class*=coloris]', 0)->plaintext;
$remise = $element->find('div[class*=remise]', 0)->plaintext;
$prix = $element->find('div[class*=prixjm]', 0)->plaintext;
$item = array();
$item['uri'] = $url;
$item['title'] = $serie;
$item['content'] = '<p><img style="vertical-align:middle ; padding: 10px" src="' . $image . '" />' . $serie . '</p>';
$item['content'] .= '<ul><li>Disponibilité : ' . $dispo . '</li>';
$item['content'] .= '<li>Carburant : ' . $carburant . '</li>';
$item['content'] .= '<li>Transmission : ' . $transmission . '</li>';
$item['content'] .= '<li>Nombre de places : ' . $places . '</li>';
$item['content'] .= '<li>Nombre de portes : ' . $portes . '</li>';
$item['content'] .= '<li>Série : ' . $serie . '</li>';
$item['content'] .= '<li>Carosserie : ' . $carosserie . '</li>';
$item['content'] .= '<li>Remise : ' . $remise . '</li>';
$item['content'] .= '<li>Prix : ' . $prix . '</li></ul>';
$this->items[] = $item;
}
}
}

265
bridges/BAEBridge.php Normal file
View File

@@ -0,0 +1,265 @@
<?php
class BAEBridge extends BridgeAbstract {
const MAINTAINER = 'couraudt';
const NAME = 'Bourse Aux Equipiers Bridge';
const URI = 'https://www.bourse-aux-equipiers.com';
const DESCRIPTION = 'Returns the newest sailing offers.';
const PARAMETERS = array(
array(
'keyword' => array(
'name' => 'Filtrer par mots clés',
'title' => 'Entrez le mot clé à filtrer ici'
),
'type' => array(
'name' => 'Type de recherche',
'title' => 'Afficher seuleument un certain type d\'annonce',
'type' => 'list',
'values' => array(
'Toutes les annonces' => false,
'Les embarquements' => 'boat',
'Les skippers' => 'skipper',
'Les équipiers' => 'crew'
)
)
)
);
public function collectData() {
$url = $this->getURI();
$html = getSimpleHTMLDOM($url) or returnClientError('No results for this query.');
$annonces = $html->find('main article');
foreach ($annonces as $annonce) {
$detail = $annonce->find('footer a', 0);
$htmlDetail = getSimpleHTMLDOMCached(parent::getURI() . $detail->href);
if (!$htmlDetail)
continue;
$item = array();
$item['title'] = $annonce->find('header h2', 0)->plaintext;
$item['uri'] = parent::getURI() . $detail->href;
$content = $htmlDetail->find('article p', 0)->innertext;
if (!empty($this->getInput('keyword'))) {
$keyword = $this->remove_accents(strtolower($this->getInput('keyword')));
$cleanTitle = $this->remove_accents(strtolower($item['title']));
if (strpos($cleanTitle, $keyword) === false) {
$cleanContent = $this->remove_accents(strtolower($content));
if (strpos($cleanContent, $keyword) === false) {
continue;
}
}
}
$content .= '<hr>';
$content .= $htmlDetail->find('section', 0)->innertext;
$content = str_replace('src="/', 'src="' . parent::getURI() . '/', $content);
$content = str_replace('href="/', 'href="' . parent::getURI() . '/', $content);
$item['content'] = $content;
$image = $htmlDetail->find('#zoom', 0);
if ($image) {
$item['enclosures'] = array(parent::getURI() . $image->getAttribute('src'));
}
$this->items[] = $item;
}
}
public function getURI() {
$uri = parent::getURI();
if (!empty($this->getInput('type'))) {
if ($this->getInput('type') == 'boat') {
$uri .= '/embarquements.html';
} elseif ($this->getInput('type') == 'skipper') {
$uri .= '/skippers.html';
} else {
$uri .= '/equipiers.html';
}
}
return $uri;
}
private function remove_accents($string) {
$chars = array(
// Decompositions for Latin-1 Supplement
'ª' => 'a', 'º' => 'o',
'À' => 'A', 'Á' => 'A',
'Â' => 'A', 'Ã' => 'A',
'Ä' => 'A', 'Å' => 'A',
'Æ' => 'AE', 'Ç' => 'C',
'È' => 'E', 'É' => 'E',
'Ê' => 'E', 'Ë' => 'E',
'Ì' => 'I', 'Í' => 'I',
'Î' => 'I', 'Ï' => 'I',
'Ð' => 'D', 'Ñ' => 'N',
'Ò' => 'O', 'Ó' => 'O',
'Ô' => 'O', 'Õ' => 'O',
'Ö' => 'O', 'Ù' => 'U',
'Ú' => 'U', 'Û' => 'U',
'Ü' => 'U', 'Ý' => 'Y',
'Þ' => 'TH', 'ß' => 's',
'à' => 'a', 'á' => 'a',
'â' => 'a', 'ã' => 'a',
'ä' => 'a', 'å' => 'a',
'æ' => 'ae', 'ç' => 'c',
'è' => 'e', 'é' => 'e',
'ê' => 'e', 'ë' => 'e',
'ì' => 'i', 'í' => 'i',
'î' => 'i', 'ï' => 'i',
'ð' => 'd', 'ñ' => 'n',
'ò' => 'o', 'ó' => 'o',
'ô' => 'o', 'õ' => 'o',
'ö' => 'o', 'ø' => 'o',
'ù' => 'u', 'ú' => 'u',
'û' => 'u', 'ü' => 'u',
'ý' => 'y', 'þ' => 'th',
'ÿ' => 'y', 'Ø' => 'O',
// Decompositions for Latin Extended-A
'Ā' => 'A', 'ā' => 'a',
'Ă' => 'A', 'ă' => 'a',
'Ą' => 'A', 'ą' => 'a',
'Ć' => 'C', 'ć' => 'c',
'Ĉ' => 'C', 'ĉ' => 'c',
'Ċ' => 'C', 'ċ' => 'c',
'Č' => 'C', 'č' => 'c',
'Ď' => 'D', 'ď' => 'd',
'Đ' => 'D', 'đ' => 'd',
'Ē' => 'E', 'ē' => 'e',
'Ĕ' => 'E', 'ĕ' => 'e',
'Ė' => 'E', 'ė' => 'e',
'Ę' => 'E', 'ę' => 'e',
'Ě' => 'E', 'ě' => 'e',
'Ĝ' => 'G', 'ĝ' => 'g',
'Ğ' => 'G', 'ğ' => 'g',
'Ġ' => 'G', 'ġ' => 'g',
'Ģ' => 'G', 'ģ' => 'g',
'Ĥ' => 'H', 'ĥ' => 'h',
'Ħ' => 'H', 'ħ' => 'h',
'Ĩ' => 'I', 'ĩ' => 'i',
'Ī' => 'I', 'ī' => 'i',
'Ĭ' => 'I', 'ĭ' => 'i',
'Į' => 'I', 'į' => 'i',
'İ' => 'I', 'ı' => 'i',
'IJ' => 'IJ', 'ij' => 'ij',
'Ĵ' => 'J', 'ĵ' => 'j',
'Ķ' => 'K', 'ķ' => 'k',
'ĸ' => 'k', 'Ĺ' => 'L',
'ĺ' => 'l', 'Ļ' => 'L',
'ļ' => 'l', 'Ľ' => 'L',
'ľ' => 'l', 'Ŀ' => 'L',
'ŀ' => 'l', 'Ł' => 'L',
'ł' => 'l', 'Ń' => 'N',
'ń' => 'n', 'Ņ' => 'N',
'ņ' => 'n', 'Ň' => 'N',
'ň' => 'n', 'ʼn' => 'n',
'Ŋ' => 'N', 'ŋ' => 'n',
'Ō' => 'O', 'ō' => 'o',
'Ŏ' => 'O', 'ŏ' => 'o',
'Ő' => 'O', 'ő' => 'o',
'Œ' => 'OE', 'œ' => 'oe',
'Ŕ' => 'R', 'ŕ' => 'r',
'Ŗ' => 'R', 'ŗ' => 'r',
'Ř' => 'R', 'ř' => 'r',
'Ś' => 'S', 'ś' => 's',
'Ŝ' => 'S', 'ŝ' => 's',
'Ş' => 'S', 'ş' => 's',
'Š' => 'S', 'š' => 's',
'Ţ' => 'T', 'ţ' => 't',
'Ť' => 'T', 'ť' => 't',
'Ŧ' => 'T', 'ŧ' => 't',
'Ũ' => 'U', 'ũ' => 'u',
'Ū' => 'U', 'ū' => 'u',
'Ŭ' => 'U', 'ŭ' => 'u',
'Ů' => 'U', 'ů' => 'u',
'Ű' => 'U', 'ű' => 'u',
'Ų' => 'U', 'ų' => 'u',
'Ŵ' => 'W', 'ŵ' => 'w',
'Ŷ' => 'Y', 'ŷ' => 'y',
'Ÿ' => 'Y', 'Ź' => 'Z',
'ź' => 'z', 'Ż' => 'Z',
'ż' => 'z', 'Ž' => 'Z',
'ž' => 'z', 'ſ' => 's',
// Decompositions for Latin Extended-B
'Ș' => 'S', 'ș' => 's',
'Ț' => 'T', 'ț' => 't',
// Euro Sign
'€' => 'E',
// GBP (Pound) Sign
'£' => '',
// Vowels with diacritic (Vietnamese)
// unmarked
'Ơ' => 'O', 'ơ' => 'o',
'Ư' => 'U', 'ư' => 'u',
// grave accent
'Ầ' => 'A', 'ầ' => 'a',
'Ằ' => 'A', 'ằ' => 'a',
'Ề' => 'E', 'ề' => 'e',
'Ồ' => 'O', 'ồ' => 'o',
'Ờ' => 'O', 'ờ' => 'o',
'Ừ' => 'U', 'ừ' => 'u',
'Ỳ' => 'Y', 'ỳ' => 'y',
// hook
'Ả' => 'A', 'ả' => 'a',
'Ẩ' => 'A', 'ẩ' => 'a',
'Ẳ' => 'A', 'ẳ' => 'a',
'Ẻ' => 'E', 'ẻ' => 'e',
'Ể' => 'E', 'ể' => 'e',
'Ỉ' => 'I', 'ỉ' => 'i',
'Ỏ' => 'O', 'ỏ' => 'o',
'Ổ' => 'O', 'ổ' => 'o',
'Ở' => 'O', 'ở' => 'o',
'Ủ' => 'U', 'ủ' => 'u',
'Ử' => 'U', 'ử' => 'u',
'Ỷ' => 'Y', 'ỷ' => 'y',
// tilde
'Ẫ' => 'A', 'ẫ' => 'a',
'Ẵ' => 'A', 'ẵ' => 'a',
'Ẽ' => 'E', 'ẽ' => 'e',
'Ễ' => 'E', 'ễ' => 'e',
'Ỗ' => 'O', 'ỗ' => 'o',
'Ỡ' => 'O', 'ỡ' => 'o',
'Ữ' => 'U', 'ữ' => 'u',
'Ỹ' => 'Y', 'ỹ' => 'y',
// acute accent
'Ấ' => 'A', 'ấ' => 'a',
'Ắ' => 'A', 'ắ' => 'a',
'Ế' => 'E', 'ế' => 'e',
'Ố' => 'O', 'ố' => 'o',
'Ớ' => 'O', 'ớ' => 'o',
'Ứ' => 'U', 'ứ' => 'u',
// dot below
'Ạ' => 'A', 'ạ' => 'a',
'Ậ' => 'A', 'ậ' => 'a',
'Ặ' => 'A', 'ặ' => 'a',
'Ẹ' => 'E', 'ẹ' => 'e',
'Ệ' => 'E', 'ệ' => 'e',
'Ị' => 'I', 'ị' => 'i',
'Ọ' => 'O', 'ọ' => 'o',
'Ộ' => 'O', 'ộ' => 'o',
'Ợ' => 'O', 'ợ' => 'o',
'Ụ' => 'U', 'ụ' => 'u',
'Ự' => 'U', 'ự' => 'u',
'Ỵ' => 'Y', 'ỵ' => 'y',
// Vowels with diacritic (Chinese, Hanyu Pinyin)
'ɑ' => 'a',
// macron
'Ǖ' => 'U', 'ǖ' => 'u',
// acute accent
'Ǘ' => 'U', 'ǘ' => 'u',
// caron
'Ǎ' => 'A', 'ǎ' => 'a',
'Ǐ' => 'I', 'ǐ' => 'i',
'Ǒ' => 'O', 'ǒ' => 'o',
'Ǔ' => 'U', 'ǔ' => 'u',
'Ǚ' => 'U', 'ǚ' => 'u',
// grave accent
'Ǜ' => 'U', 'ǜ' => 'u',
);
$string = strtr($string, $chars);
return $string;
}
}

View File

@@ -14,6 +14,10 @@ class BandcampBridge extends BridgeAbstract {
)
));
public function getIcon() {
return 'https://s4.bcbits.com/img/bc_favicon.ico';
}
public function collectData(){
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError('No results for this query.');

View File

@@ -1,31 +1,47 @@
<?php
class BlaguesDeMerdeBridge extends BridgeAbstract {
const MAINTAINER = 'superbaillot.net';
const MAINTAINER = 'superbaillot.net, logmanoriginal';
const NAME = 'Blagues De Merde';
const URI = 'http://www.blaguesdemerde.fr/';
const CACHE_TIMEOUT = 7200; // 2h
const DESCRIPTION = 'Blagues De Merde';
public function getIcon() {
return self::URI . 'assets/img/favicon.ico';
}
public function collectData(){
$html = getSimpleHTMLDOM(self::URI)
or returnServerError('Could not request BDM.');
foreach($html->find('article.joke_contener') as $element) {
$item = array();
$temp = $element->find('a');
foreach($html->find('div.blague') as $element) {
$item = array();
$item['uri'] = static::URI . '#' . $element->id;
$item['author'] = $element->find('div[class="blague-footer"] p strong', 0)->plaintext;
// Let the title be everything up to the first <br>
$item['title'] = trim(explode("\n", $element->find('div.text', 0)->plaintext)[0]);
$item['content'] = strip_tags($element->find('div.text', 0));
// timestamp is part of:
// <p>Par <strong>{author}</strong> le {date} dans <strong>{category}</strong></p>
preg_match(
'/.+le(.+)dans.*/',
$element->find('div[class="blague-footer"]', 0)->plaintext,
$matches
);
$item['timestamp'] = strtotime($matches[1]);
$this->items[] = $item;
if(isset($temp[2])) {
$item['content'] = trim($element->find('div.joke_text_contener', 0)->innertext);
$uri = $temp[2]->href;
$item['uri'] = $uri;
$item['title'] = substr($uri, (strrpos($uri, "/") + 1));
$date = $element->find('li.bdm_date', 0)->innertext;
$time = mktime(0, 0, 0, substr($date, 3, 2), substr($date, 0, 2), substr($date, 6, 4));
$item['timestamp'] = $time;
$item['author'] = $element->find('li.bdm_pseudo', 0)->innertext;
$this->items[] = $item;
}
}
}
}

View File

@@ -31,6 +31,10 @@ class BloombergBridge extends BridgeAbstract
return parent::getName();
}
public function getIcon() {
return 'https://assets.bwbx.io/s3/javelin/public/hub/images/favicon-black-63fe5249d3.png';
}
public function collectData()
{
switch($this->queriedContext) {

View File

@@ -0,0 +1,87 @@
<?php
class BundesbankBridge extends BridgeAbstract {
const PARAM_LANG = 'lang';
const LANG_EN = 'en';
const LANG_DE = 'de';
const NAME = 'Bundesbank Bridge';
const URI = 'https://www.bundesbank.de/';
const DESCRIPTION = 'Returns the latest studies of the Bundesbank (Germany)';
const MAINTAINER = 'logmanoriginal';
const CACHE_TIMEOUT = 86400; // 24 hours
const PARAMETERS = array(
array(
self::PARAM_LANG => array(
'name' => 'Language',
'type' => 'list',
'required' => true,
'defaultValue' => self::LANG_DE,
'values' => array(
'English' => self::LANG_EN,
'Deutsch' => self::LANG_DE
)
)
)
);
public function getIcon() {
return self::URI . 'resource/crblob/1890/a7f48ee0ae35348748121770ba3ca009/mL/favicon-ico-data.ico';
}
public function getURI() {
switch($this->getInput(self::PARAM_LANG)) {
case self::LANG_EN: return self::URI . 'en/publications/reports/studies';
case self::LANG_DE: return self::URI . 'de/publikationen/berichte/studien';
}
return parent::getURI();
}
public function collectData() {
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError('No response for ' . $this->getURI());
$html = defaultLinkTo($html, $this->getURI());
foreach($html->find('ul.resultlist li') as $study) {
$item = array();
$item['uri'] = $study->find('.teasable__link', 0)->href;
// Get title without child elements (i.e. subtitle)
$title = $study->find('.teasable__title div.h2', 0);
foreach($title->children as &$child) {
$child->outertext = '';
}
$item['title'] = $title->innertext;
// Add subtitle to the content if it exists
$item['content'] = '';
if($subtitle = $study->find('.teasable__subtitle', 0)) {
$item['content'] .= '<strong>' . $study->find('.teasable__subtitle', 0)->plaintext . '</strong>';
}
$item['content'] .= '<p>' . $study->find('.teasable__text', 0)->plaintext . '</p>';
$item['timestamp'] = strtotime($study->find('.teasable__date', 0)->plaintext);
// Downloads and older studies don't have images
if($study->find('.teasable__image', 0)) {
$item['enclosures'] = array(
$study->find('.teasable__image img', 0)->src
);
}
$this->items[] = $item;
}
}
}

View File

@@ -1,45 +0,0 @@
<?php
class CADBridge extends FeedExpander {
const MAINTAINER = 'nyutag';
const NAME = 'CAD Bridge';
const URI = 'http://www.cad-comic.com/';
const CACHE_TIMEOUT = 7200; //2h
const DESCRIPTION = 'Returns the newest articles.';
public function collectData(){
$this->collectExpandableDatas('http://cdn2.cad-comic.com/rss.xml', 10);
}
protected function parseItem($newsItem){
$item = parent::parseItem($newsItem);
$item['content'] = $this->extractCADContent($item['uri']);
return $item;
}
private function extractCADContent($url) {
$html3 = getSimpleHTMLDOMCached($url);
// The request might fail due to missing https support or wrong URL
if($html3 == false)
return 'Daily comic not released yet';
$htmlpart = explode("/", $url);
switch ($htmlpart[3]) {
case 'cad':
preg_match_all("/http:\/\/cdn2\.cad-comic\.com\/comics\/cad-\S*png/", $html3, $url2);
break;
case 'sillies':
preg_match_all("/http:\/\/cdn2\.cad-comic\.com\/comics\/sillies-\S*gif/", $html3, $url2);
break;
default:
return 'Daily comic not released yet';
}
$img = implode($url2[0]);
$html3->clear();
unset($html3);
if ($img == '')
return 'Daily comic not released yet';
return '<img src="' . $img . '"/>';
}
}

View File

@@ -3,91 +3,107 @@ class CNETBridge extends BridgeAbstract {
const MAINTAINER = 'ORelio';
const NAME = 'CNET News';
const URI = 'http://www.cnet.com/';
const CACHE_TIMEOUT = 1800; // 30min
const DESCRIPTION = 'Returns the newest articles. <br /> You may specify a
topic found in some section URLs, else all topics are selected.';
const PARAMETERS = array( array(
'topic' => array(
'name' => 'Topic name'
const URI = 'https://www.cnet.com/';
const CACHE_TIMEOUT = 3600; // 1h
const DESCRIPTION = 'Returns the newest articles.';
const PARAMETERS = array(
array(
'topic' => array(
'name' => 'Topic',
'type' => 'list',
'values' => array(
'All articles' => '',
'Apple' => 'apple',
'Google' => 'google',
'Microsoft' => 'tags-microsoft',
'Computers' => 'topics-computers',
'Mobile' => 'topics-mobile',
'Sci-Tech' => 'topics-sci-tech',
'Security' => 'topics-security',
'Internet' => 'topics-internet',
'Tech Industry' => 'topics-tech-industry'
)
)
)
));
);
public function collectData(){
private function cleanArticle($article_html) {
$offset_p = strpos($article_html, '<p>');
$offset_figure = strpos($article_html, '<figure');
$offset = ($offset_figure < $offset_p ? $offset_figure : $offset_p);
$article_html = substr($article_html, $offset);
$article_html = str_replace('href="/', 'href="' . self::URI, $article_html);
$article_html = str_replace(' height="0"', '', $article_html);
$article_html = str_replace('<noscript>', '', $article_html);
$article_html = str_replace('</noscript>', '', $article_html);
$article_html = StripWithDelimiters($article_html, '<a class="clickToEnlarge', '</a>');
$article_html = stripWithDelimiters($article_html, '<span class="nowPlaying', '</span>');
$article_html = stripWithDelimiters($article_html, '<span class="duration', '</span>');
$article_html = stripWithDelimiters($article_html, '<script', '</script>');
$article_html = stripWithDelimiters($article_html, '<svg', '</svg>');
return $article_html;
}
function extractFromDelimiters($string, $start, $end){
if(strpos($string, $start) !== false) {
$section_retrieved = substr($string, strpos($string, $start) + strlen($start));
$section_retrieved = substr($section_retrieved, 0, strpos($section_retrieved, $end));
return $section_retrieved;
public function collectData() {
// Retrieve and check user input
$topic = str_replace('-', '/', $this->getInput('topic'));
if (!empty($topic) && (substr_count($topic, '/') > 1 || !ctype_alpha(str_replace('/', '', $topic))))
returnClientError('Invalid topic: ' . $topic);
// Retrieve webpage
$pageUrl = self::URI . (empty($topic) ? 'news/' : $topic . '/');
$html = getSimpleHTMLDOM($pageUrl)
or returnServerError('Could not request CNET: ' . $pageUrl);
// Process articles
foreach($html->find('div.assetBody, div.riverPost') as $element) {
if(count($this->items) >= 10) {
break;
}
return false;
}
$article_title = trim($element->find('h2, h3', 0)->plaintext);
$article_uri = self::URI . substr($element->find('a', 0)->href, 1);
$article_thumbnail = $element->parent()->find('img[src]', 0)->src;
$article_timestamp = strtotime($element->find('time.assetTime, div.timeAgo', 0)->plaintext);
$article_author = trim($element->find('a[rel=author], a.name', 0)->plaintext);
$article_content = '<p><b>' . trim($element->find('p.dek', 0)->plaintext) . '</b></p>';
function stripWithDelimiters($string, $start, $end){
while(strpos($string, $start) !== false) {
$section_to_remove = substr($string, strpos($string, $start));
$section_to_remove = substr($section_to_remove, 0, strpos($section_to_remove, $end) + strlen($end));
$string = str_replace($section_to_remove, '', $string);
}
if (is_null($article_thumbnail))
$article_thumbnail = extractFromDelimiters($element->innertext, '<img src="', '"');
return $string;
}
if (!empty($article_title) && !empty($article_uri) && strpos($article_uri, self::URI . 'news/') !== false) {
function cleanArticle($article_html){
$article_html = '<p>' . substr($article_html, strpos($article_html, '<p>') + 3);
$article_html = stripWithDelimiters($article_html, '<span class="credit">', '</span>');
$article_html = stripWithDelimiters($article_html, '<script', '</script>');
$article_html = stripWithDelimiters($article_html, '<div class="shortcode related-links', '</div>');
$article_html = stripWithDelimiters($article_html, '<a class="clickToEnlarge">', '</a>');
return $article_html;
}
$article_html = getSimpleHTMLDOMCached($article_uri) or $article_html = null;
$pageUrl = self::URI . (empty($this->getInput('topic')) ? '' : 'topics/' . $this->getInput('topic') . '/');
$html = getSimpleHTMLDOM($pageUrl) or returnServerError('Could not request CNET: ' . $pageUrl);
$limit = 0;
if (!is_null($article_html)) {
foreach($html->find('div.assetBody') as $element) {
if($limit < 8) {
$article_title = trim($element->find('h2', 0)->plaintext);
$article_uri = self::URI . ($element->find('a', 0)->href);
$article_timestamp = strtotime($element->find('time.assetTime', 0)->plaintext);
$article_author = trim($element->find('a[rel=author]', 0)->plaintext);
if (empty($article_thumbnail))
$article_thumbnail = $article_html->find('div.originalImage', 0);
if (empty($article_thumbnail))
$article_thumbnail = $article_html->find('span.imageContainer', 0);
if (is_object($article_thumbnail))
$article_thumbnail = $article_thumbnail->find('img', 0)->src;
if(!empty($article_title) && !empty($article_uri) && strpos($article_uri, '/news/') !== false) {
$article_html = getSimpleHTMLDOM($article_uri)
or returnServerError('Could not request CNET: ' . $article_uri);
$article_content = trim(
cleanArticle(
$article_content .= trim(
$this->cleanArticle(
extractFromDelimiters(
$article_html,
'<div class="articleContent',
'<footer>'
$article_html, '<article', '<footer'
)
)
);
$item = array();
$item['uri'] = $article_uri;
$item['title'] = $article_title;
$item['author'] = $article_author;
$item['timestamp'] = $article_timestamp;
$item['content'] = $article_content;
$this->items[] = $item;
$limit++;
}
$item = array();
$item['uri'] = $article_uri;
$item['title'] = $article_title;
$item['author'] = $article_author;
$item['timestamp'] = $article_timestamp;
$item['enclosures'] = array($article_thumbnail);
$item['content'] = $article_content;
$this->items[] = $item;
}
}
}
public function getName(){
if(!is_null($this->getInput('topic'))) {
$topic = $this->getInput('topic');
return 'CNET News Bridge' . (empty($topic) ? '' : ' - ' . $topic);
}
return parent::getName();
}
}

View File

@@ -0,0 +1,28 @@
<?php
class ChristianDailyReporterBridge extends BridgeAbstract {
const MAINTAINER = 'rogerdc';
const NAME = 'Christian Daily Reporter Unofficial RSS';
const URI = 'https://www.christiandailyreporter.com/';
const DESCRIPTION = 'The Unofficial Christian Daily Reporter RSS';
// const CACHE_TIMEOUT = 86400; // 1 day
public function getIcon() {
return self::URI . 'images/cdrfavicon.png';
}
public function collectData() {
$uri = 'https://www.christiandailyreporter.com/';
$html = getSimpleHTMLDOM($uri)
or returnServerError('Could not request Christian Daily Reporter.');
foreach($html->find('div.top p a,div.column p a') as $element) {
$item = array();
// Title
$item['title'] = $element->innertext;
// URL
$item['uri'] = $element->href;
$this->items[] = $item;
}
}
}

View File

@@ -0,0 +1,97 @@
<?php
class ContainerLinuxReleasesBridge extends BridgeAbstract {
const MAINTAINER = 'captn3m0';
const NAME = 'Core OS Container Linux Releases Bridge';
const URI = 'https://coreos.com/releases/';
const DESCRIPTION = 'Returns the releases notes for Container Linux';
const STABLE = 'stable';
const BETA = 'beta';
const ALPHA = 'alpha';
const PARAMETERS = [
[
'channel' => [
'name' => 'Release Channel',
'type' => 'list',
'required' => true,
'defaultValue' => self::STABLE,
'values' => [
'Stable' => self::STABLE,
'Beta' => self::BETA,
'Alpha' => self::ALPHA,
],
]
]
];
private function getReleaseFeed($jsonUrl) {
$json = getContents($jsonUrl)
or returnServerError('Could not request Core OS Website.');
return json_decode($json, true);
}
public function getIcon() {
return 'https://coreos.com/assets/ico/favicon.png';
}
public function collectData() {
$data = $this->getReleaseFeed($this->getJsonUri());
foreach ($data as $releaseVersion => $release) {
$item = [];
$item['uri'] = "https://coreos.com/releases/#$releaseVersion";
$item['title'] = $releaseVersion;
$content = $release['release_notes'];
$content .= <<<EOT
Major Software:
* Kernel: {$release['major_software']['kernel'][0]}
* Docker: {$release['major_software']['docker'][0]}
* etcd: {$release['major_software']['etcd'][0]}
EOT;
$item['timestamp'] = strtotime($release['release_date']);
// Based on https://gist.github.com/jbroadway/2836900
// Links
$regex = '/\[([^\[]+)\]\(([^\)]+)\)/';
$replacement = '<a href=\'\2\'>\1</a>';
$item['content'] = preg_replace($regex, $replacement, $content);
// Headings
$regex = '/^(.*)\:\s?$/m';
$replacement = '<h3>\1</h3>';
$item['content'] = preg_replace($regex, $replacement, $item['content']);
// Lists
$regex = '/\n\s*[\*|\-](.*)/';
$item['content'] = preg_replace_callback ($regex, function($regs) {
$item = $regs[1];
return sprintf ('<ul><li>%s</li></ul>', trim ($item));
}, $item['content']);
$this->items[] = $item;
}
}
private function getJsonUri() {
$channel = $this->getInput('channel');
return "https://coreos.com/releases/releases-$channel.json";
}
public function getURI() {
return self::URI;
}
public function getName(){
if(!is_null($this->getInput('channel'))) {
return 'Container Linux Releases: ' . $this->getInput('channel') . ' Channel';
}
return parent::getName();
}
}

View File

@@ -25,7 +25,7 @@ class CopieDoubleBridge extends BridgeAbstract {
} elseif(strpos($element->innertext, '/images/suivant.gif') === false) {
$a = $element->find('a', 0);
$item['uri'] = self::URI . $a->href;
$content = str_replace('src="/', 'src="/' . self::URI, $element->find("td", 0)->innertext);
$content = str_replace('src="/', 'src="/' . self::URI, $element->find('td', 0)->innertext);
$content = str_replace('href="/', 'href="' . self::URI, $content);
$item['content'] = $content;
$this->items[] = $item;

View File

@@ -11,7 +11,7 @@ class CourrierInternationalBridge extends BridgeAbstract {
$html = getSimpleHTMLDOM(self::URI)
or returnServerError('Error.');
$element = $html->find("article");
$element = $html->find('article');
$article_count = 1;
foreach($element as $article) {

View File

@@ -1,74 +0,0 @@
<?php
class CpasbienBridge extends BridgeAbstract {
const MAINTAINER = 'lagaisse';
const NAME = 'Cpasbien Bridge';
const URI = 'http://www.cpasbien.cm';
const CACHE_TIMEOUT = 86400; // 24h
const DESCRIPTION = 'Returns latest torrents from a request query';
const PARAMETERS = array( array(
'q' => array(
'name' => 'Search',
'required' => true,
'title' => 'Type your search'
)
));
public function collectData(){
$request = str_replace(" ", "-", trim($this->getInput('q')));
$html = getSimpleHTMLDOM(self::URI . '/recherche/' . urlencode($request) . '.html')
or returnServerError('No results for this query.');
foreach($html->find('#gauche', 0)->find('div') as $episode) {
if($episode->getAttribute('class') == 'ligne0'
|| $episode->getAttribute('class') == 'ligne1') {
$urlepisode = $episode->find('a', 0)->getAttribute('href');
$htmlepisode = getSimpleHTMLDOMCached($urlepisode, 86400 * 366 * 30);
$item = array();
$item['author'] = $episode->find('a', 0)->text();
$item['title'] = $episode->find('a', 0)->text();
$item['pubdate'] = $this->getCachedDate($urlepisode);
$textefiche = $htmlepisode->find('#textefiche', 0)->find('p', 1);
if(isset($textefiche)) {
$item['content'] = $textefiche->text();
} else {
$p = $htmlepisode->find('#textefiche', 0)->find('p');
if(!empty($p)) {
$item['content'] = $htmlepisode->find('#textefiche', 0)->find('p', 0)->text();
}
}
$item['id'] = $episode->find('a', 0)->getAttribute('href');
$item['uri'] = self::URI . $htmlepisode->find('#telecharger', 0)->getAttribute('href');
$this->items[] = $item;
}
}
}
public function getName(){
if(!is_null($this->getInput('q'))) {
return $this->getInput('q') . ' : ' . self::NAME;
}
return parent::getName();
}
private function getCachedDate($url){
debugMessage('getting pubdate from url ' . $url . '');
// Initialize cache
$cache = Cache::create('FileCache');
$cache->setPath(CACHE_DIR . '/pages');
$params = [$url];
$cache->setParameters($params);
// Get cachefile timestamp
$time = $cache->getTime();
return ($time !== false ? $time : time());
}
}

View File

@@ -48,6 +48,10 @@ class DailymotionBridge extends BridgeAbstract {
return $metadata;
}
public function getIcon() {
return 'https://static1-ssl.dmcdn.net/images/neon/favicons/android-icon-36x36.png.vf806ca4ed0deed812';
}
public function collectData(){
$html = '';
$limit = 5;

View File

@@ -1,7 +1,7 @@
<?php
class DanbooruBridge extends BridgeAbstract {
const MAINTAINER = 'mitsukarenai';
const MAINTAINER = 'mitsukarenai, logmanoriginal';
const NAME = 'Danbooru';
const URI = 'http://donmai.us/';
const CACHE_TIMEOUT = 1800; // 30min
@@ -41,7 +41,7 @@ class DanbooruBridge extends BridgeAbstract {
$item = array();
$item['uri'] = $element->find('a', 0)->href;
$item['postid'] = (int)preg_replace("/[^0-9]/", '', $element->getAttribute(static::IDATTRIBUTE));
$item['postid'] = (int)preg_replace('/[^0-9]/', '', $element->getAttribute(static::IDATTRIBUTE));
$item['timestamp'] = time();
$thumbnailUri = $element->find('img', 0)->src;
$item['tags'] = $this->getTags($element);
@@ -57,11 +57,80 @@ class DanbooruBridge extends BridgeAbstract {
}
public function collectData(){
$html = getSimpleHTMLDOM($this->getFullURI())
$content = getContents($this->getFullURI())
or returnServerError('Could not request ' . $this->getName());
$html = Fix_Simple_Html_Dom::str_get_html($content);
foreach($html->find(static::PATHTODATA) as $element) {
$this->items[] = $this->getItemFromElement($element);
}
}
}
/**
* This class is a monkey patch to 'extend' simplehtmldom to recognize <source>
* tags (HTML5) as self closing tag. This patch should be removed once
* simplehtmldom was fixed. This seems to be a issue with more tags:
* https://sourceforge.net/p/simplehtmldom/bugs/83/
*
* The tag itself is valid according to Mozilla:
*
* The HTML <picture> element serves as a container for zero or more <source>
* elements and one <img> element to provide versions of an image for different
* display device scenarios. The browser will consider each of the child <source>
* elements and select one corresponding to the best match found; if no matches
* are found among the <source> elements, the file specified by the <img>
* element's src attribute is selected. The selected image is then presented in
* the space occupied by the <img> element.
*
* -- https://developer.mozilla.org/en-US/docs/Web/HTML/Element/picture
*
* Notice: This class uses parts of the original simplehtmldom, adjusted to pass
* the guidelines of RSS-Bridge (formatting)
*/
final class Fix_Simple_Html_Dom extends simple_html_dom {
/* copy from simple_html_dom, added 'source' at the end */
protected $self_closing_tags = array(
'img' => 1,
'br' => 1,
'input' => 1,
'meta' => 1,
'link' => 1,
'hr' => 1,
'base' => 1,
'embed' => 1,
'spacer' => 1,
'source' => 1
);
/* copy from simplehtmldom, changed 'simple_html_dom' to 'Fix_Simple_Html_Dom' */
public static function str_get_html($str,
$lowercase = true,
$forceTagsClosed = true,
$target_charset = DEFAULT_TARGET_CHARSET,
$stripRN = true,
$defaultBRText = DEFAULT_BR_TEXT,
$defaultSpanText = DEFAULT_SPAN_TEXT)
{
$dom = new Fix_Simple_Html_Dom(null,
$lowercase,
$forceTagsClosed,
$target_charset,
$stripRN,
$defaultBRText,
$defaultSpanText);
if (empty($str) || strlen($str) > MAX_FILE_SIZE) {
$dom->clear();
return false;
}
$dom->load($str, $lowercase, $stripRN);
return $dom;
}
}

View File

@@ -15,8 +15,13 @@ class DansTonChatBridge extends BridgeAbstract {
foreach($html->find('div.item') as $element) {
$item = array();
$item['uri'] = $element->find('a', 0)->href;
$item['title'] = 'DansTonChat ' . $element->find('a', 1)->plaintext;
$item['content'] = $element->find('a', 0)->innertext;
$titleContent = $element->find('h3 a', 0);
if($titleContent) {
$item['title'] = 'DansTonChat ' . html_entity_decode($titleContent->plaintext, ENT_QUOTES);
} else {
$item['title'] = 'DansTonChat';
}
$item['content'] = $element->find('div.item-content a', 0)->innertext;
$this->items[] = $item;
}
}

View File

@@ -3,7 +3,7 @@ class DauphineLibereBridge extends FeedExpander {
const MAINTAINER = 'qwertygc';
const NAME = 'Dauphine Bridge';
const URI = 'http://www.ledauphine.com/';
const URI = 'https://www.ledauphine.com/';
const CACHE_TIMEOUT = 7200; // 2h
const DESCRIPTION = 'Returns the newest articles.';
@@ -49,8 +49,9 @@ class DauphineLibereBridge extends FeedExpander {
private function extractContent($url){
$html2 = getSimpleHTMLDOMCached($url);
$text = $html2->find('div.column', 0)->innertext;
$text = preg_replace('@<script[^>]*?>.*?</script>@si', '', $text);
return $text;
foreach ($html2->find('.noprint, link, script, iframe, .shareTool, .contentInfo') as $remove) {
$remove->outertext = '';
}
return $html2->find('div.content', 0)->innertext;
}
}

File diff suppressed because it is too large Load Diff

View File

@@ -35,11 +35,11 @@ class DemoBridge extends BridgeAbstract {
public function collectData(){
$item = array();
$item['author'] = "Me!";
$item['title'] = "Test";
$item['content'] = "Awesome content !";
$item['id'] = "Lalala";
$item['uri'] = "http://example.com/test";
$item['author'] = 'Me!';
$item['title'] = 'Test';
$item['content'] = 'Awesome content !';
$item['id'] = 'Lalala';
$item['uri'] = 'http://example.com/test';
$this->items[] = $item;
}

View File

@@ -4,143 +4,163 @@ class DemonoidBridge extends BridgeAbstract {
const MAINTAINER = 'metaMMA';
const NAME = 'Demonoid';
const URI = 'https://www.demonoid.pw/';
const DESCRIPTION = 'Returns results for the keywords (in all categories or
a specific category). You can put several keywords separated by a semicolon
(e.g. "one show;another show"). Searches can by done in a specific category;
category number must be specified. (All=0, Movies=1, Music=2, TV=3, Games=4,
Applications=5, Pictures=8, Anime=9, Comics=10, Books=11 Music Videos=8,
Audio Books=17). User feed takes the Uploader ID number (not uploader name)
as keyword. Uploader ID is found by clicking on uploader, clicking on
"View this user\'s torrents", and copying the number after "uid=". An entire
category feed is accomplished by leaving "keywords" box blank and using the
corresponding category number.';
const DESCRIPTION = 'Returns results from search';
const PARAMETERS = array( array(
const PARAMETERS = array(array(
'q' => array(
'name' => 'keywords/user ID/category, separated by semicolons',
'exampleValue' => 'first list;second list;…',
'required' => true
),
'crit' => array(
'name' => 'keywords',
'exampleValue' => 'keyword1 keyword2…',
'required' => true,
),
'category' => array(
'name' => 'Category',
'type' => 'list',
'name' => 'Feed type',
'values' => array(
'search' => 'search',
'category' => 'cat',
'user' => 'usr'
'All' => 0,
'Movies' => 1,
'Music' => 2,
'TV' => 3,
'Games' => 4,
'Applications' => 5,
'Pictures' => 8,
'Anime' => 9,
'Comics' => 10,
'Books' => 11,
'Audiobooks' => 17
)
)
),
'catCheck' => array(
'type' => 'checkbox',
'name' => 'Specify category for keyword search ?',
),
'cat' => array(
'name' => 'Category number',
),
));
), array(
'catOnly' => array(
'name' => 'Category',
'type' => 'list',
'values' => array(
'All' => 0,
'Movies' => 1,
'Music' => 2,
'TV' => 3,
'Games' => 4,
'Applications' => 5,
'Pictures' => 8,
'Anime' => 9,
'Comics' => 10,
'Books' => 11,
'Audiobooks' => 17
)
)
), array(
'userid' => array(
'name' => 'user id',
'exampleValue' => '00000',
'required' => true,
'type' => 'number'
),
'category' => array(
'name' => 'Category',
'type' => 'list',
'values' => array(
'All' => 0,
'Movies' => 1,
'Music' => 2,
'TV' => 3,
'Games' => 4,
'Applications' => 5,
'Pictures' => 8,
'Anime' => 9,
'Comics' => 10,
'Books' => 11,
'Audiobooks' => 17
)
)
)
);
public function collectData() {
$catBool = $this->getInput('catCheck');
if($catBool) {
$catNum = $this->getInput('cat');
if(!empty($this->getInput('q'))) {
$html = getSimpleHTMLDOM(
self::URI .
'files/?category=' .
rawurlencode($this->getInput('category')) .
'&subcategory=All&quality=All&seeded=2&external=2&query=' .
urlencode($this->getInput('q')) .
'&uid=0&sort='
) or returnServerError('Could not request Demonoid.');
} elseif(!empty($this->getInput('catOnly'))) {
$html = getSimpleHTMLDOM(
self::URI .
'files/?uid=0&category=' .
rawurlencode($this->getInput('catOnly')) .
'&subcategory=0&language=0&seeded=2&quality=0&query=&sort='
) or returnServerError('Could not request Demonoid.');
} elseif(!empty($this->getInput('userid'))) {
$html = getSimpleHTMLDOM(
self::URI .
'files/?uid=' .
rawurlencode($this->getInput('userid')) .
'&seeded=2'
) or returnServerError('Could not request Demonoid.');
} else {
returnServerError('Invalid parameters !');
}
$critList = $this->getInput('crit');
$keywordsList = explode(';', $this->getInput('q'));
foreach($keywordsList as $keywords) {
switch($critList) {
case 'search':
if($catBool == false) {
$html = file_get_contents(
self::URI .
'files/?category=0&subcategory=All&quality=All&seeded=2&external=2&query=' .
urlencode($keywords) . #not rawurlencode so space -> '+'
'&uid=0&sort='
) or returnServerError('Could not request Demonoid.');
} else {
$html = file_get_contents(
self::URI .
'files/?category=' .
rawurlencode($catNum) .
'&subcategory=All&quality=All&seeded=2&external=2&query=' .
urlencode($keywords) . #not rawurlencode so space -> '+'
'&uid=0&sort='
) or returnServerError('Could not request Demonoid.');
}
break;
case 'usr':
$html = file_get_contents(
self::URI .
'files/?uid=' .
rawurlencode($keywords) .
'&seeded=2'
) or returnServerError('Could not request Demonoid.');
break;
case 'cat':
$html = file_get_contents(
self::URI .
'files/?uid=0&category=' .
rawurlencode($keywords) .
'&subcategory=0&language=0&seeded=2&quality=0&query=&sort='
) or returnServerError('Could not request Demonoid.');
break;
if(preg_match('~No torrents found~', $html)) {
return;
}
$table = $html->find('td[class=ctable_content_no_pad]', 0);
$cursorCount = 4;
$elementCount = 0;
while($elementCount != 40) {
$elementCount++;
$currentElement = $table->find('tr', $cursorCount);
if(preg_match('~items total~', $currentElement)) {
break;
}
if(preg_match('~No torrents found~', $html)) {
returnServerError('No result for query ' . $keywords);
}
$bigTable = explode('<!-- start torrent list -->', $html)[1];
$last50 = explode('<!-- end torrent list -->', $bigTable)[0];
$dateChunk = explode('added_today', $last50);
$item = array ();
for($block = 1;$block < count($dateChunk);$block++) {
preg_match('~(?<=>Add).*?(?=<)~', $dateChunk[$block], $dateStr);
$item = array();
//Do we have a date ?
if(preg_match('~Added.*?(.*)~', $currentElement->plaintext, $dateStr)) {
if(preg_match('~today~', $dateStr[0])) {
date_default_timezone_set('UTC');
$timestamp = mktime(0, 0, 0, gmdate('n'), gmdate('j'), gmdate('Y'));
} else {
preg_match('~(?<=ed on ).*\d+~', $dateStr[0], $fullDateStr);
} else {
preg_match('~(?<=ed on ).*\d+~', $currentElement->plaintext, $fullDateStr);
date_default_timezone_set('UTC');
$dateObj = strptime($fullDateStr[0], '%A, %b %d, %Y');
$timestamp = mktime(0, 0, 0, $dateObj['tm_mon'] + 1, $dateObj['tm_mday'], 1900 + $dateObj['tm_year']);
}
$itemsChunk = explode('<!-- tstart -->', $dateChunk[$block]);
for($items = 1;$items < count($itemsChunk);$items++) {
$item = array();
$cols = explode('<td', $itemsChunk[$items]);
preg_match('~(?<=href=\"/).*?(?=\")~', $cols[1], $matches);
$item['id'] = self::URI . $matches[0];
preg_match('~(?<=href=\").*?(?=\")~', $cols[4], $matches);
$item['uri'] = $matches[0];
$item['timestamp'] = $timestamp;
preg_match('~(?<=href=\"/users/).*?(?=\")~', $cols[3], $matches);
$item['author'] = $matches[0];
preg_match('~(?<=/\">).*?(?=</a>)~', $cols[1], $matches);
$item['title'] = $matches[0];
preg_match('~(?<=green\">)\d+(?=</font>)~', $cols[8], $matches);
$item['seeders'] = $matches[0];
preg_match('~(?<=red\">)\d+(?=</font>)~', $cols[9], $matches);
$item['leechers'] = $matches[0];
preg_match('~(?<=>).*?(?=</td>)~', $cols[5], $matches);
$item['size'] = $matches[0];
$item['content'] = 'Uploaded by ' . $item['author']
. ' , Size ' . $item['size']
. '<br>seeders: '
. $item['seeders']
. ' | leechers: '
. $item['leechers']
. '<br><a href="'
. $item['id']
. '">info page</a>';
if(isset($item['title']))
$this->items[] = $item;
}
$cursorCount++;
}
$content = $table->find('tr', $cursorCount)->find('a', 1);
$cursorCount++;
$torrentInfo = $table->find('tr', $cursorCount);
$item['timestamp'] = $timestamp;
$item['title'] = $content->plaintext;
$item['id'] = self::URI . $content->href;
$item['uri'] = self::URI . $content->href;
$item['author'] = $torrentInfo->find('a[class=user]', 0)->plaintext;
$item['seeders'] = $torrentInfo->find('font[class=green]', 0)->plaintext;
$item['leechers'] = $torrentInfo->find('font[class=red]', 0)->plaintext;
$item['size'] = $torrentInfo->find('td', 3)->plaintext;
$item['content'] = 'Uploaded by ' . $item['author']
. ' , Size ' . $item['size']
. '<br>seeders: '
. $item['seeders']
. ' | leechers: '
. $item['leechers']
. '<br><a href="'
. $item['id']
. '">info page</a>';
$this->items[] = $item;
$cursorCount++;
}
}
}

240
bridges/DesoutterBridge.php Normal file
View File

@@ -0,0 +1,240 @@
<?php
class DesoutterBridge extends BridgeAbstract {
const CATEGORY_NEWS = 'News & Events';
const CATEGORY_INDUSTRY = 'Industry 4.0 News';
const NAME = 'Desoutter Bridge';
const URI = 'https://www.desouttertools.com';
const DESCRIPTION = 'Returns feeds for news from Desoutter';
const MAINTAINER = 'logmanoriginal';
const CACHE_TIMEOUT = 86400; // 24 hours
const PARAMETERS = array(
self::CATEGORY_NEWS => array(
'news_lang' => array(
'name' => 'Language',
'type' => 'list',
'required' => true,
'title' => 'Select your language',
'defaultValue' => 'Corporate',
'values' => array(
'Corporate'
=> 'https://www.desouttertools.com/about-desoutter/news-events',
'Česko'
=> 'https://www.desouttertools.cz/o-desoutter/aktuality-udalsoti',
'Deutschland'
=> 'https://www.desoutter.de/ueber-desoutter/news-events',
'España'
=> 'https://www.desouttertools.es/sobre-desoutter/noticias-eventos',
'México'
=> 'https://www.desouttertools.mx/acerca-desoutter/noticias-eventos',
'France'
=> 'https://www.desouttertools.fr/a-propos-de-desoutter/actualites-evenements',
'Magyarország'
=> 'https://www.desouttertools.hu/a-desoutter-vallalatrol/hirek-esemenyek',
'Italia'
=> 'https://www.desouttertools.it/su-desoutter/news-eventi',
'日本'
=> 'https://www.desouttertools.jp/desotanituite/niyusu-ibento',
'대한민국'
=> 'https://www.desouttertools.co.kr/desoteoe-daehaeseo/nyuseu-mic-ibenteu',
'Polska'
=> 'https://www.desouttertools.pl/o-desoutter/aktualnosci-wydarzenia',
'Brasil'
=> 'https://www.desouttertools.com.br/sobre-desoutter/noti%C2%ADcias-eventos',
'Portugal'
=> 'https://www.desouttertools.pt/sobre-desoutter/notIcias-eventos',
'România'
=> 'https://www.desouttertools.ro/despre-desoutter/noutati-evenimente',
'Российская Федерация'
=> 'https://www.desouttertools.com.ru/o-desoutter/novosti-mieropriiatiia',
'Slovensko'
=> 'https://www.desouttertools.sk/o-spolocnosti-desoutter/novinky-udalosti',
'Slovenija'
=> 'https://www.desouttertools.si/o-druzbi-desoutter/novice-dogodki',
'Sverige'
=> 'https://www.desouttertools.se/om-desoutter/nyheter-evenemang',
'Türkiye'
=> 'https://www.desoutter.com.tr/desoutter-hakkinda/haberler-etkinlikler',
'中国'
=> 'https://www.desouttertools.com.cn/guan-yu-ma-tou/xin-wen-he-huo-dong',
)
),
),
self::CATEGORY_INDUSTRY => array(
'industry_lang' => array(
'name' => 'Language',
'type' => 'list',
'required' => true,
'title' => 'Select your language',
'defaultValue' => 'Corporate',
'values' => array(
'Corporate'
=> 'https://www.desouttertools.com/industry-4-0/news',
'Česko'
=> 'https://www.desouttertools.cz/prumysl-4-0/novinky',
'Deutschland'
=> 'https://www.desoutter.de/industrie-4-0/news',
'España'
=> 'https://www.desouttertools.es/industria-4-0/noticias',
'México'
=> 'https://www.desouttertools.mx/industria-4-0/noticias',
'France'
=> 'https://www.desouttertools.fr/industrie-4-0/actualites',
'Magyarország'
=> 'https://www.desouttertools.hu/industry-4-0/hirek',
'Italia'
=> 'https://www.desouttertools.it/industry-4-0/news',
'日本'
=> 'https://www.desouttertools.jp/industry-4-0/news',
'대한민국'
=> 'https://www.desouttertools.co.kr/industry-4-0/news',
'Polska'
=> 'https://www.desouttertools.pl/przemysl-4-0/wiadomosci',
'Brasil'
=> 'https://www.desouttertools.com.br/industria-4-0/noticias',
'Portugal'
=> 'https://www.desouttertools.pt/industria-4-0/noticias',
'România'
=> 'https://www.desouttertools.ro/industry-4-0/noutati',
'Российская Федерация'
=> 'https://www.desouttertools.com.ru/industry-4-0/news',
'Slovensko'
=> 'https://www.desouttertools.sk/priemysel-4-0/novinky',
'Slovenija'
=> 'https://www.desouttertools.si/industrija-4-0/novice',
'Sverige'
=> 'https://www.desouttertools.se/industri-4-0/nyheter',
'Türkiye'
=> 'https://www.desoutter.com.tr/endustri-4-0/haberler',
'中国'
=> 'https://www.desouttertools.com.cn/industry-4-0/news',
)
),
),
'global' => array(
'full' => array(
'name' => 'Load full articles',
'type' => 'checkbox',
'required' => false,
'title' => 'Enable to load the full article for each item'
)
)
);
private $title;
public function getURI() {
switch($this->queriedContext) {
case self::CATEGORY_NEWS:
return $this->getInput('news_lang') ?: parent::getURI();
case self::CATEGORY_INDUSTRY:
return $this->getInput('industry_lang') ?: parent::getURI();
}
return parent::getURI();
}
public function getName() {
return isset($this->title) ? $this->title . ' - ' . parent::getName() : parent::getName();
}
public function collectData() {
// Uncomment to generate list of languages automtically (dev mode)
/*
switch($this->queriedContext) {
case self::CATEGORY_NEWS:
$this->extractNewsLanguages(); die;
case self::CATEGORY_INDUSTRY:
$this->extractIndustryLanguages(); die;
}
*/
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError('Could not request ' . $this->getURI());
$html = defaultLinkTo($html, $this->getURI());
$this->title = html_entity_decode($html->find('title', 0)->plaintext, ENT_QUOTES);
foreach($html->find('article') as $article) {
$item = array();
$item['uri'] = $article->find('[itemprop="name"]', 0)->href;
$item['title'] = $article->find('[itemprop="name"]', 0)->title;
if($this->getInput('full')) {
$item['content'] = $this->getFullNewsArticle($item['uri']);
} else {
$item['content'] = $article->find('[itemprop="description"]', 0)->plaintext;
}
$this->items[] = $item;
}
}
private function getFullNewsArticle($uri) {
$html = getSimpleHTMLDOMCached($uri)
or returnServerError('Unable to load full article!');
$html = defaultLinkTo($html, $this->getURI());
return $html->find('section.article', 0);
}
/**
* Generates a HTML page with a PHP formatted array of languages,
* pointing to the corresponding news pages. Implementation is based
* on the 'Corporate' site.
* @return void
*/
private function extractNewsLanguages() {
$html = getSimpleHTMLDOMCached('https://www.desouttertools.com/about-desoutter/news-events')
or returnServerError('Error loading news!');
$html = defaultLinkTo($html, static::URI);
$items = $html->find('ul[class="dropdown-menu"] li');
$list = "\t'Corporate'\n\t=> 'https://www.desouttertools.com/about-desoutter/news-events',\n";
foreach($items as $item) {
$lang = trim($item->plaintext);
$uri = $item->find('a', 0)->href;
$list .= "\t'{$lang}'\n\t=> '{$uri}',\n";
}
echo $list;
}
/**
* Generates a HTML page with a PHP formatted array of languages,
* pointing to the corresponding news pages. Implementation is based
* on the 'Corporate' site.
* @return void
*/
private function extractIndustryLanguages() {
$html = getSimpleHTMLDOMCached('https://www.desouttertools.com/industry-4-0/news')
or returnServerError('Error loading news!');
$html = defaultLinkTo($html, static::URI);
$items = $html->find('ul[class="dropdown-menu"] li');
$list = "\t'Corporate'\n\t=> 'https://www.desouttertools.com/industry-4-0/news',\n";
foreach($items as $item) {
$lang = trim($item->plaintext);
$uri = $item->find('a', 0)->href;
$list .= "\t'{$lang}'\n\t=> '{$uri}',\n";
}
echo $list;
}
}

105
bridges/DevToBridge.php Normal file
View File

@@ -0,0 +1,105 @@
<?php
class DevToBridge extends BridgeAbstract {
const CONTEXT_BY_TAG = 'By tag';
const NAME = 'dev.to Bridge';
const URI = 'https://dev.to';
const DESCRIPTION = 'Returns feeds for tags';
const MAINTAINER = 'logmanoriginal';
const CACHE_TIMEOUT = 10800; // 15 min.
const PARAMETERS = array(
self::CONTEXT_BY_TAG => array(
'tag' => array(
'name' => 'Tag',
'type' => 'text',
'required' => true,
'title' => 'Insert your tag',
'exampleValue' => 'python'
),
'full' => array(
'name' => 'Full article',
'type' => 'checkbox',
'required' => false,
'title' => 'Enable to receive the full article for each item',
'defaultValue' => false
)
)
);
public function getURI() {
switch($this->queriedContext) {
case self::CONTEXT_BY_TAG:
if($tag = $this->getInput('tag')) {
return static::URI . '/t/' . urlencode($tag);
}
break;
}
return parent::getURI();
}
public function getIcon() {
return 'https://practicaldev-herokuapp-com.freetls.fastly.net/assets/
apple-icon-5c6fa9f2bce280428589c6195b7f1924206a53b782b371cfe2d02da932c8c173.png';
}
public function collectData() {
$html = getSimpleHTMLDOMCached($this->getURI())
or returnServerError('Could not request ' . $this->getURI());
$html = defaultLinkTo($html, static::URI);
$articles = $html->find('div[class="single-article"]')
or returnServerError('Could not find articles!');
foreach($articles as $article) {
if($article->find('[class*="cta"]', 0)) { // Skip ads
continue;
}
$item = array();
$item['uri'] = $article->find('a[id*=article-link]', 0)->href;
$item['title'] = $article->find('h3', 0)->plaintext;
// i.e. "Charlie Harrington・Sep 21"
$item['timestamp'] = strtotime(explode('・', $article->find('h4 a', 0)->plaintext, 2)[1]);
$item['author'] = explode('・', $article->find('h4 a', 0)->plaintext, 2)[0];
// Profile image
$item['enclosures'] = array($article->find('img', 0)->src);
if($this->getInput('full')) {
$fullArticle = $this->getFullArticle($item['uri']);
$item['content'] = <<<EOD
<img src="{$item['enclosures'][0]}" alt="{$item['author']}">
<p>{$fullArticle}</p>
EOD;
} else {
$item['content'] = <<<EOD
<img src="{$item['enclosures'][0]}" alt="{$item['author']}">
<p>{$item['title']}</p>
EOD;
}
$item['categories'] = array_map(function($e){ return $e->plaintext; }, $article->find('div.tags span.tag'));
$this->items[] = $item;
}
}
private function getFullArticle($url) {
$html = getSimpleHTMLDOMCached($url)
or returnServerError('Unable to load article from "' . $url . '"!');
$html = defaultLinkTo($html, static::URI);
return $html->find('[id="article-body"]', 0);
}
}

View File

@@ -75,6 +75,10 @@ class DiceBridge extends BridgeAbstract {
),
));
public function getIcon() {
return 'https://assets.dice.com/techpro/img/favicons/favicon.ico';
}
public function collectData() {
$uri = 'https://www.dice.com/jobs/advancedResult.html';
$uri .= '?for_one=' . urlencode($this->getInput('for_one'));

View File

@@ -9,8 +9,8 @@ class DilbertBridge extends BridgeAbstract {
public function collectData(){
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError('Could not request Dilbert: ' . $this->getURI());
$html = getSimpleHTMLDOM(self::URI)
or returnServerError('Could not request Dilbert: ' . self::URI);
foreach($html->find('section.comic-item') as $element) {

112
bridges/DiscogsBridge.php Normal file
View File

@@ -0,0 +1,112 @@
<?php
class DiscogsBridge extends BridgeAbstract {
const MAINTAINER = 'teromene';
const NAME = 'DiscogsBridge';
const URI = 'https://www.discogs.com/';
const DESCRIPTION = 'Returns releases from discogs';
const PARAMETERS = array(
'Artist Releases' => array(
'artistid' => array(
'name' => 'Artist ID',
'type' => 'number',
)
),
'Label Releases' => array(
'labelid' => array(
'name' => 'Label ID',
'type' => 'number',
)
),
'User Wantlist' => array(
'username_wantlist' => array(
'name' => 'Username',
'type' => 'text',
)
),
'User Folder' => array(
'username_folder' => array(
'name' => 'Username',
'type' => 'text',
),
'folderid' => array(
'name' => 'Folder ID',
'type' => 'number',
)
)
);
public function collectData() {
if(!empty($this->getInput('artistid')) || !empty($this->getInput('labelid'))) {
if(!empty($this->getInput('artistid'))) {
$data = getContents('https://api.discogs.com/artists/'
. $this->getInput('artistid')
. '/releases?sort=year&sort_order=desc')
or returnServerError('Unable to query discogs !');
} elseif(!empty($this->getInput('labelid'))) {
$data = getContents('https://api.discogs.com/labels/'
. $this->getInput('labelid')
. '/releases?sort=year&sort_order=desc')
or returnServerError('Unable to query discogs !');
}
$jsonData = json_decode($data, true);
foreach($jsonData['releases'] as $release) {
$item = array();
$item['author'] = $release['artist'];
$item['title'] = $release['title'];
$item['id'] = $release['id'];
$resId = array_key_exists('main_release', $release) ? $release['main_release'] : $release['id'];
$item['uri'] = self::URI . $this->getInput('artistid') . '/release/' . $resId;
$item['timestamp'] = DateTime::createFromFormat('Y', $release['year'])->getTimestamp();
$item['content'] = $item['author'] . ' - ' . $item['title'];
$this->items[] = $item;
}
} elseif(!empty($this->getInput('username_wantlist')) || !empty($this->getInput('username_folder'))) {
if(!empty($this->getInput('username_wantlist'))) {
$data = getContents('https://api.discogs.com/users/'
. $this->getInput('username_wantlist')
. '/wants?sort=added&sort_order=desc')
or returnServerError('Unable to query discogs !');
$jsonData = json_decode($data, true)['wants'];
} elseif(!empty($this->getInput('username_folder'))) {
$data = getContents('https://api.discogs.com/users/'
. $this->getInput('username_folder')
. '/collection/folders/'
. $this->getInput('folderid')
. '/releases?sort=added&sort_order=desc')
or returnServerError('Unable to query discogs !');
$jsonData = json_decode($data, true)['releases'];
}
foreach($jsonData as $element) {
$infos = $element['basic_information'];
$item = array();
$item['title'] = $infos['title'];
$item['author'] = $infos['artists'][0]['name'];
$item['id'] = $infos['artists'][0]['id'];
$item['uri'] = self::URI . $infos['artists'][0]['id'] . '/release/' . $infos['id'];
$item['timestamp'] = strtotime($element['date_added']);
$item['content'] = $item['author'] . ' - ' . $item['title'];
$this->items[] = $item;
}
}
}
public function getURI() {
return self::URI;
}
public function getName() {
return static::NAME;
}
}

View File

@@ -7,6 +7,11 @@ class DribbbleBridge extends BridgeAbstract {
const CACHE_TIMEOUT = 1800;
const DESCRIPTION = 'Returns the newest popular shots from Dribbble.';
public function getIcon() {
return 'https://cdn.dribbble.com/assets/
favicon-63b2904a073c89b52b19aa08cebc16a154bcf83fee8ecc6439968b1e6db569c7.ico';
}
public function collectData(){
$html = getSimpleHTMLDOM(self::URI . '/shots')
or returnServerError('Error while downloading the website content');

161
bridges/ETTVBridge.php Normal file
View File

@@ -0,0 +1,161 @@
<?php
class ETTVBridge extends BridgeAbstract {
const MAINTAINER = 'GregThib';
const NAME = 'ETTV';
const URI = 'https://www.ettv.tv/';
const DESCRIPTION = 'Returns list of 20 latest torrents for a specific search.';
const CACHE_TIMEOUT = 14400; // 4 hours
const PARAMETERS = array( array(
'query' => array(
'name' => 'Keywords',
'required' => true
),
'cat' => array(
'type' => 'list',
'name' => 'Category',
'values' => array(
'(ALL TYPES)' => '0',
'Anime: Movies' => '73',
'Anime: Dubbed/Subbed' => '74',
'Anime: Others' => '75',
'Books: Ebooks' => '53',
'Books: Magazines' => '54',
'Books: Comics' => '55',
'Books: Audio' => '56',
'Books: Others' => '68',
'Games: Windows' => '57',
'Games: Android' => '58',
'Games: Others' => '71',
'Movies: HD 1080p' => '1',
'Movies: HD 720p' => '2',
'Movies: UltraHD/4K' => '3',
'Movies: XviD' => '42',
'Movies: X264/H264' => '47',
'Movies: 3D' => '49',
'Movies: Dubs/Dual Audio' => '51',
'Movies: CAM/TS' => '65',
'Movies: BluRay Disc/Remux' => '66',
'Movies: DVDR' => '67',
'Movies: HEVC/x265' => '76',
'Music: MP3' => '59',
'Music: FLAC' => '60',
'Music: Music Videos' => '61',
'Music: Others' => '69',
'Software: Windows' => '62',
'Software: Android' => '63',
'Software: Mac' => '64',
'Software: Others' => '70',
'TV: HD/X264/H264' => '41',
'TV: SD/X264/H264' => '5',
'TV: TV Packs' => '7',
'TV: SD/XVID' => '50',
'TV: Sport' => '72',
'TV: HEVC/x265' => '77',
'Unsorted: Unsorted' => '78'
),
'defaultValue' => '(ALL TYPES)'
),
'status' => array(
'type' => 'list',
'name' => 'Status',
'values' => array(
'Active Transfers' => '0',
'Included Dead' => '1',
'Only Dead' => '2'
),
'defaultValue' => 'Included Dead'
),
'lang' => array(
'type' => 'list',
'name' => 'Lang',
'values' => array(
'(ALL)' => '0',
'Arabic' => '17',
'Chinese ' => '10',
'Danish' => '13',
'Dutch' => '11',
'English' => '1',
'Finnish' => '18',
'French' => '2',
'German' => '3',
'Greek' => '15',
'Hindi' => '8',
'Italian' => '4',
'Japanese' => '5',
'Korean' => '9',
'Polish' => '14',
'Russian' => '7',
'Spanish' => '6',
'Turkish' => '16'
),
'defaultValue' => '(ALL)'
)
));
protected $results_link;
public function collectData(){
// No control on inputs, because all defaultValue are set
$query_str = 'torrents-search.php';
$query_str .= '?search=' . urlencode('+' . str_replace(' ', ' +', $this->getInput('query')));
$query_str .= '&cat=' . $this->getInput('cat');
$query_str .= '&incldead=' . $this->getInput('status');
$query_str .= '&lang=' . $this->getInput('lang');
$query_str .= '&sort=id&order=desc';
// Get results page
$this->results_link = self::URI . $query_str;
$html = getSimpleHTMLDOM($this->results_link)
or returnServerError('Could not request ' . $this->getName());
// Loop on each entry
foreach($html->find('table.table tr') as $element) {
if($element->parent->tag == 'thead') continue;
$entry = $element->find('td', 1)->find('a', 0);
// retrieve result page to get more details
$link = rtrim(self::URI, '/') . $entry->href;
$page = getSimpleHTMLDOM($link)
or returnServerError('Could not request page ' . $link);
// get details & download links
$details = $page->find('fieldset.download table', 0); // WHAT?? It should be the second one…
$dllinks = $page->find('div#downloadbox table', 0);
// fill item
$item = array();
$item['author'] = $details->children(6)->children(1)->plaintext;
$item['title'] = $entry->title;
$item['uri'] = $link;
$item['timestamp'] = strtotime($details->children(7)->children(1)->plaintext);
$item['content'] = '';
$item['content'] .= '<br/><b>Name: </b>' . $details->children(0)->children(1)->innertext;
$item['content'] .= '<br/><b>Lang: </b>' . $details->children(3)->children(1)->innertext;
$item['content'] .= '<br/><b>Size: </b>' . $details->children(4)->children(1)->innertext;
$item['content'] .= '<br/><b>Hash: </b>' . $details->children(5)->children(1)->innertext;
foreach($dllinks->children(0)->children(1)->find('a') as $dl) {
$item['content'] .= '<br/>' . $dl->outertext;
}
$item['content'] .= '<br/><br/>' . $details->children(1)->children(0)->innertext;
$this->items[] = $item;
}
}
public function getName(){
if($this->getInput('query')) {
return '[' . self::NAME . '] ' . $this->getInput('query');
}
return self::NAME;
}
public function getURI(){
if(isset($this->results_link) && !empty($this->results_link)) {
return $this->results_link;
}
return self::URI;
}
}

View File

@@ -1,7 +1,7 @@
<?php
class EZTVBridge extends BridgeAbstract {
const MAINTAINER = "alexAubin";
const MAINTAINER = 'alexAubin';
const NAME = 'EZTV';
const URI = 'https://eztv.ch/';
const DESCRIPTION = 'Returns list of *recent* torrents for a specific show
@@ -23,15 +23,15 @@ on EZTV. Get showID from URLs in https://eztv.ch/shows/showID/show-full-name.';
$relativeDays = 0;
$relativeHours = 0;
foreach(explode(" ", $relativeReleaseTime) as $relativeTimeElement) {
if(substr($relativeTimeElement, -1) == "d") $relativeDays = substr($relativeTimeElement, 0, -1);
if(substr($relativeTimeElement, -1) == "h") $relativeHours = substr($relativeTimeElement, 0, -1);
foreach(explode(' ', $relativeReleaseTime) as $relativeTimeElement) {
if(substr($relativeTimeElement, -1) == 'd') $relativeDays = substr($relativeTimeElement, 0, -1);
if(substr($relativeTimeElement, -1) == 'h') $relativeHours = substr($relativeTimeElement, 0, -1);
}
return mktime(date('h') - $relativeHours, 0, 0, date('m'), date('d') - $relativeDays, date('Y'));
}
// Loop on show ids
$showList = explode(",", $this->getInput('i'));
$showList = explode(',', $this->getInput('i'));
foreach($showList as $showID) {
// Get show page

View File

@@ -7,6 +7,11 @@ class EliteDangerousGalnetBridge extends BridgeAbstract {
const CACHE_TIMEOUT = 7200; // 2h
const DESCRIPTION = 'Returns the latest page of news from Galnet';
public function getIcon() {
return 'https://community.elitedangerous.com/sites/
EDSITE_COMM/themes/bootstrap/bootstrap_community/favicon.ico';
}
public function collectData(){
$html = getSimpleHTMLDOM(self::URI)
or returnServerError('Error while downloading the website content');

147
bridges/ElloBridge.php Normal file
View File

@@ -0,0 +1,147 @@
<?php
class ElloBridge extends BridgeAbstract {
const MAINTAINER = 'teromene';
const NAME = 'Ello Bridge';
const URI = 'https://ello.co/';
const CACHE_TIMEOUT = 4800; //2hours
const DESCRIPTION = 'Returns the newest posts for Ello';
const PARAMETERS = array(
'By User' => array(
'u' => array(
'name' => 'Username',
'required' => true,
'title' => 'Username'
)
),
'Search' => array(
's' => array(
'name' => 'Search',
'required' => true,
'title' => 'Search'
)
)
);
public function collectData() {
$header = array(
'Authorization: Bearer ' . $this->getAPIKey()
);
if(!empty($this->getInput('u'))) {
$postData = getContents(self::URI . 'api/v2/users/~' . urlencode($this->getInput('u')) . '/posts', $header) or
returnServerError('Unable to query Ello API.');
} else {
$postData = getContents(self::URI . 'api/v2/posts?terms=' . urlencode($this->getInput('s')), $header) or
returnServerError('Unable to query Ello API.');
}
$postData = json_decode($postData);
$count = 0;
foreach($postData->posts as $post) {
$item = array();
$item['author'] = $this->getUsername($post, $postData);
$item['timestamp'] = strtotime($post->created_at);
$item['title'] = strip_tags($this->findText($post->summary));
$item['content'] = $this->getPostContent($post->body);
$item['enclosures'] = $this->getEnclosures($post, $postData);
$item['uri'] = self::URI . $item['author'] . '/post/' . $post->token;
$content = $post->body;
$this->items[] = $item;
$count += 1;
}
}
private function findText($path) {
foreach($path as $summaryElement) {
if($summaryElement->kind == 'text') {
return $summaryElement->data;
}
}
return '';
}
private function getPostContent($path) {
$content = '';
foreach($path as $summaryElement) {
if($summaryElement->kind == 'text') {
$content .= $summaryElement->data;
} elseif ($summaryElement->kind == 'image') {
$alt = '';
if(property_exists($summaryElement->data, 'alt')) {
$alt = $summaryElement->data->alt;
}
$content .= '<img src="' . $summaryElement->data->url . '" alt="' . $alt . '" />';
}
}
return $content;
}
private function getEnclosures($post, $postData) {
$assets = [];
foreach($post->links->assets as $asset) {
foreach($postData->linked->assets as $assetLink) {
if($asset == $assetLink->id) {
$assets[] = $assetLink->attachment->original->url;
break;
}
}
}
return $assets;
}
private function getUsername($post, $postData) {
foreach($postData->linked->users as $user) {
if($user->id == $post->links->author->id) {
return $user->username;
}
}
}
private function getAPIKey() {
$cache = Cache::create('FileCache');
$cache->setPath(CACHE_DIR);
$cache->setParameters(['key']);
$key = $cache->loadData();
if($key == null) {
$keyInfo = getContents(self::URI . 'api/webapp-token') or
returnServerError('Unable to get token.');
$key = json_decode($keyInfo)->token->access_token;
$cache->saveData($key);
}
return $key;
}
public function getName(){
if(!is_null($this->getInput('u'))) {
return $this->getInput('u') . ' - Ello Bridge';
}
return parent::getName();
}
}

View File

@@ -57,6 +57,10 @@ class ElsevierBridge extends BridgeAbstract {
return '';
}
public function getIcon() {
return 'https://cdn.elsevier.io/verona/includes/favicons/favicon-32x32.png';
}
public function collectData(){
$uri = self::URI . $this->getInput('j') . '/recent-articles/';
$html = getSimpleHTMLDOM($uri)

View File

@@ -7,19 +7,9 @@ class EstCeQuonMetEnProdBridge extends BridgeAbstract {
const CACHE_TIMEOUT = 21600; // 6h
const DESCRIPTION = 'Should we put a website in production today? (French)';
public function collectData(){
function extractFromDelimiters($string, $start, $end){
if(strpos($string, $start) !== false) {
$section_retrieved = substr($string, strpos($string, $start) + strlen($start));
$section_retrieved = substr($section_retrieved, 0, strpos($section_retrieved, $end));
return $section_retrieved;
}
return false;
}
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError('Could not request EstCeQuonMetEnProd: ' . $this->getURI());
public function collectData() {
$html = getSimpleHTMLDOM(self::URI)
or returnServerError('Could not request EstCeQuonMetEnProd: ' . self::URI);
$item = array();
$item['uri'] = $this->getURI() . '#' . date('Y-m-d');
@@ -28,8 +18,8 @@ class EstCeQuonMetEnProdBridge extends BridgeAbstract {
$item['timestamp'] = strtotime('today midnight');
$item['content'] = str_replace(
'src="/',
'src="' . $this->getURI(),
trim(extractFromDelimiters($html->outertext, '<body role="document">', '<br /><br />'))
'src="' . self::URI,
trim(extractFromDelimiters($html->outertext, '<body role="document">', '<div id="share'))
);
$this->items[] = $item;

View File

@@ -17,7 +17,7 @@ class EtsyBridge extends BridgeAbstract {
'queryextension' => array(
'name' => 'Query extension',
'type' => 'text',
'requied' => false,
'required' => false,
'title' => 'Insert additional query parts here
(anything after ?search=<your search query>)',
'exampleValue' => '&explicit=1&locationQuery=2921044'
@@ -25,9 +25,9 @@ class EtsyBridge extends BridgeAbstract {
'showimage' => array(
'name' => 'Show image in content',
'type' => 'checkbox',
'requrired' => false,
'required' => false,
'title' => 'Activate to show the image in the content',
'defaultValue' => false
'defaultValue' => 'checked'
)
)
);
@@ -36,26 +36,27 @@ class EtsyBridge extends BridgeAbstract {
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError('Failed to receive ' . $this->getURI());
$results = $html->find('div.block-grid-item');
$results = $html->find('li.block-grid-item');
foreach($results as $result) {
// Skip banner cards (ads for categories)
if($result->find('a.banner-card'))
if($result->find('span.ad-indicator'))
continue;
$item = array();
$item['title'] = $result->find('a', 0)->title;
$item['uri'] = $result->find('a', 0)->href;
$item['author'] = $result->find('div.card-shop-name', 0)->plaintext;
$item['author'] = $result->find('p.text-gray-lighter', 0)->plaintext;
$item['content'] = '<p>'
. $result->find('div.card-price', 0)->plaintext
. $result->find('span.currency-value', 0)->plaintext . ' '
. $result->find('span.currency-symbol', 0)->plaintext
. '</p><p>'
. $result->find('div.card-title', 0)->plaintext
. $result->find('a', 0)->title
. '</p>';
$image = $result->find('img.placeholder', 0)->src;
$image = $result->find('img.display-block', 0)->src;
if($this->getInput('showimage')) {
$item['content'] .= '<img src="' . $image . '">';

View File

@@ -0,0 +1,104 @@
<?php
class ExtremeDownloadBridge extends BridgeAbstract {
const NAME = 'Extreme Download';
const URI = 'https://ww1.extreme-d0wn.com/';
const DESCRIPTION = 'Suivi de série sur Extreme Download';
const MAINTAINER = 'sysadminstory';
const PARAMETERS = array(
'Suivre la publication des épisodes d\'une série en cours de diffusion' => array(
'url' => array(
'name' => 'URL de la série',
'type' => 'text',
'required' => true,
'title' => 'URL d\'une série sans le https://ww1.extreme-d0wn.com/',
'exampleValue' => 'series-hd/hd-series-vostfr/46631-halt-and-catch-fire-saison-04-vostfr-hdtv-720p.html'),
'filter' => array(
'name' => 'Type de contenu',
'type' => 'list',
'required' => 'true',
'title' => 'Type de contenu à suivre : Téléchargement, Streaming ou les deux',
'values' => array(
'Streaming et Téléchargement' => 'both',
'Téléchargement' => 'download',
'Streaming' => 'streaming'
)
)
)
);
public function collectData(){
$html = getSimpleHTMLDOM(self::URI . $this->getInput('url'))
or returnServerError('Could not request Extreme Download.');
$filter = $this->getInput('filter');
$typesText = array(
'download' => 'Téléchargement',
'streaming' => 'Streaming'
);
// Get the TV show title
$this->showTitle = trim($html->find('span[id=news-title]', 0)->plaintext);
$list = $html->find('div[class=prez_7]');
foreach($list as $element) {
$add = false;
// Link type is needed is needed to generate an unique link
$type = $this->findLinkType($element);
if($filter == 'both') {
$add = true;
} else {
if($type == $filter) {
$add = true;
}
}
if($add == true) {
$item = array();
// Get the element name
$title = $element->plaintext;
// Get thee element links
$links = $element->next_sibling()->innertext;
$item['content'] = $links;
$item['title'] = $this->showTitle . ' ' . $title . ' - ' . $typesText[$type];
// As RSS Bridge use the URI as GUID they need to be unique : adding a md5 hash of the title element
// should geneerate unique URI to prevent confusion for RSS readers
$item['uri'] = self::URI . $this->getInput('url') . '#' . hash('md5', $item['title']);
$this->items[] = $item;
}
}
}
public function getName(){
switch($this->queriedContext) {
case 'Suivre la publication des épisodes d\'une série en cours de diffusion':
return $this->showTitle . ' - ' . self::NAME;
break;
default:
return self::NAME;
}
}
private function findLinkType($element)
{
$return = '';
// Walk through all elements in the reverse order until finding one with class 'presz_2'
while($element->class != 'prez_2') {
$element = $element->prev_sibling();
}
$text = html_entity_decode($element->plaintext);
// Regarding the text of the element, return the according link type
if(stristr($text, 'téléchargement') != false) {
$return = 'download';
} else if(stristr($text, 'streaming') != false) {
$return = 'streaming';
}
return $return;
}
}

View File

@@ -15,24 +15,18 @@ class FB2Bridge extends BridgeAbstract {
)
));
public function getIcon() {
return 'https://static.xx.fbcdn.net/rsrc.php/yo/r/iRmz9lCMBD2.ico';
}
public function collectData(){
function extractFromDelimiters($string, $start, $end){
if(strpos($string, $start) !== false) {
$section_retrieved = substr($string, strpos($string, $start) + strlen($start));
$section_retrieved = substr($section_retrieved, 0, strpos($section_retrieved, $end));
return $section_retrieved;
}
return false;
}
//Utility function for cleaning a Facebook link
$unescape_fb_link = function($matches){
if(is_array($matches) && count($matches) > 1) {
$link = $matches[1];
if(strpos($link, '/') === 0)
$link = self::URI . $link . '"';
$link = self::URI . substr($link, 1);
if(strpos($link, 'facebook.com/l.php?u=') !== false)
$link = urldecode(extractFromDelimiters($link, 'facebook.com/l.php?u=', '&'));
return ' href="' . $link . '"';
@@ -75,14 +69,14 @@ class FB2Bridge extends BridgeAbstract {
if($this->getInput('u') !== null) {
$page = 'https://touch.facebook.com/' . $this->getInput('u');
$cookies = $this->getCookies($page);
$pageID = $this->getPageID($page, $cookies);
$pageInfo = $this->getPageInfos($page, $cookies);
if($pageID === null) {
if($pageInfo['userId'] === null) {
echo <<<EOD
Unable to get the page id. You should consider getting the ID by hand, then importing it into FB2Bridge
EOD;
die();
} elseif($pageID == -1) {
} elseif($pageInfo['userId'] == -1) {
echo <<<EOD
This page is not accessible without being logged in.
EOD;
@@ -91,35 +85,47 @@ EOD;
}
//Build the string for the first request
$requestString = 'https://touch.facebook.com/pages_reaction_units/more/?page_id='
. $pageID
. '&cursor={"card_id"%3A"videos"%2C"has_next_page"%3Atrue}&surface=mobile_page_home&unit_count=8';
$fileContent = file_get_contents($requestString);
$articleIndex = 0;
$maxArticle = 3;
$requestString = 'https://touch.facebook.com/page_content_list_view/more/?page_id='
. $pageInfo['userId']
. '&start_cursor=1&num_to_fetch=105&surface_type=timeline';
$fileContent = getContents($requestString);
$html = $this->buildContent($fileContent);
$author = $this->getInput('u');
$author = $pageInfo['username'];
foreach($html->find("article") as $content) {
foreach($html->find('article') as $content) {
$item = array();
//echo $content; die();
preg_match('/publish_time\\\":([0-9]+),/', $content->getAttribute('data-store', 0), $match);
if(isset($match[1]))
$timestamp = $match[1];
else
$timestamp = 0;
$item['uri'] = "http://touch.facebook.com"
. $content->find("div[class='_52jc _5qc4 _24u0 _36xo']", 0)->find("a", 0)->getAttribute("href");
$item['uri'] = html_entity_decode('http://touch.facebook.com'
. $content->find("div[class='_52jc _5qc4 _24u0 _36xo']", 0)->find('a', 0)->getAttribute('href'), ENT_QUOTES);
if($content->find("header", 0) !== null) {
$content->find("header", 0)->innertext = "";
//Decode images
$imagecleaned = preg_replace_callback('/<i [^>]* style="[^"]*url\(\'(.*?)\'\).*?><\/i>/m', function ($matches) {
return "<img src='" . str_replace(['\\3a ', '\\3d ', '\\26 '], [':', '=', '&'], $matches[1]) . "' />";
}, $content);
$content = str_get_html($imagecleaned);
if($content->find('header', 0) !== null) {
$content->find('header', 0)->innertext = '';
}
if($content->find("footer", 0) !== null) {
$content->find("footer", 0)->innertext = "";
if($content->find('footer', 0) !== null) {
$content->find('footer', 0)->innertext = '';
}
// Replace emoticon images by their textual representation (part of the span)
foreach($content->find('span[title*="emoticon"]') as $emoticon) {
$emoticon->innertext = $emoticon->find('span[aria-hidden="true"]', 0)->innertext;
}
//Remove html nodes, keep only img, links, basic formatting
$content = strip_tags($content, '<a><img><i><u><br><p>');
$content = strip_tags($content, '<a><img><i><u><br><p><h3><h4><section>');
//Adapt link hrefs: convert relative links into absolute links and bypass external link redirection
$content = preg_replace_callback('/ href=\"([^"]+)\"/i', $unescape_fb_link, $content);
@@ -132,7 +138,6 @@ EOD;
'ajaxify',
'tabindex',
'class',
'style',
'data-[^=]*',
'aria-[^=]*',
'role',
@@ -145,7 +150,36 @@ EOD;
// "<i><u>smile emoticon</u></i>" back to ASCII emoticons eg ":)"
$content = preg_replace_callback('/<i><u>([^ <>]+) ([^<>]+)<\/u><\/i>/i', $unescape_fb_emote, $content);
$item['content'] = $content;
//Remove the "...Plus" tag
$content = preg_replace(
'/… (<span>|)<a href="https:\/\/www\.facebook\.com\/story\.php\?story_fbid=.*?<\/a>/m',
'', $content, 1);
//Remove tracking images
$content = preg_replace('/<img src=\'.*?safe_image\.php.*?\' \/>/m', '', $content);
//Remove the double section tags
$content = str_replace(['<section><section>', '</section></section>'], ['<section>', '</section>'], $content);
//Move the section tag link upper, if it is down
$content = str_get_html($content);
$sectionContent = $content->find('section', 0);
if($sectionContent != null) {
$sectionLink = $sectionContent->nextSibling();
if($sectionLink != null) {
$fullLink = '<a href="' . $sectionLink->getAttribute('href') . '">' . $sectionContent->innertext . '</a>';
$sectionContent->innertext = $fullLink;
}
}
//Move the href tag upper if it is inside the section
foreach($content->find('section > a') as $sectionToFix) {
$sectionLink = $sectionToFix->getAttribute('href');
$section = $sectionToFix->parent();
$section->outertext = '<a href="' . $sectionLink . '">' . $section . '</a>';
}
$item['content'] = html_entity_decode($content, ENT_QUOTES);
$title = $author;
if (strlen($title) > 24)
@@ -154,57 +188,29 @@ EOD;
if (strlen($title) > 64)
$title = substr($title, 0, strpos(wordwrap($title, 64), "\n")) . '...';
$item['title'] = $title;
$item['author'] = $author;
$item['title'] = html_entity_decode($title, ENT_QUOTES);
$item['author'] = html_entity_decode($author, ENT_QUOTES);
$item['timestamp'] = html_entity_decode($timestamp, ENT_QUOTES);
array_push($this->items, $item);
if($item['timestamp'] != 0)
array_push($this->items, $item);
}
}
// Currently not used. Is used to get more than only 3 elements, as they appear on another page.
private function computeNextLink($string, $pageID){
$regex = implode(
'',
array(
"/timeline_unit",
"\\\\\\\\u00253A1",
"\\\\\\\\u00253A([0-9]*)",
"\\\\\\\\u00253A([0-9]*)",
"\\\\\\\\u00253A([0-9]*)",
"\\\\\\\\u00253A([0-9]*)/"
)
);
preg_match($regex, $string, $result);
return implode(
'',
array(
"https://touch.facebook.com/pages_reaction_units/more/?page_id=",
$pageID,
"&cursor=%7B%22timeline_cursor%22%3A%22timeline_unit%3A1%3A",
$result[1],
"%3A",
$result[2],
"%3A",
$result[3],
"%3A",
$result[4],
"%22%2C%22timeline_section_cursor%22%3A%7B%7D%2C%22",
"has_next_page%22%3Atrue%7D&surface=mobile_page_home&unit_count=3"
)
);
}
//Builds the HTML from the encoded JS that Facebook provides.
private function buildContent($pageContent){
$regex = "/\\\"html\\\":\\\"(.*?)\\\",\\\"replace/";
// The html ends with:
// /div>","replaceifexists
$regex = '/\\"html\\":(\".+\/div>"),"replace/';
preg_match($regex, $pageContent, $result);
return str_get_html(html_entity_decode(json_decode('"' . $result[1] . '"')));
$htmlContent = json_decode($result[1]);
$htmlContent = preg_replace('/(?<!style)="(.*?)"/', '=\'$1\'', $htmlContent);
$htmlContent = html_entity_decode($htmlContent, ENT_QUOTES, 'UTF-8');
return str_get_html($htmlContent);
}
@@ -214,7 +220,7 @@ EOD;
$ctx = stream_context_create(array(
'http' => array(
'user_agent' => "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:46.0) Gecko/20100101 Firefox/46.0",
'user_agent' => 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:46.0) Gecko/20100101 Firefox/46.0',
'Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'
)
)
@@ -222,24 +228,24 @@ EOD;
$a = file_get_contents($pageURL, 0, $ctx);
//First request to get the cookie
$cookies = "";
$cookies = '';
foreach($http_response_header as $hdr) {
if(strpos($hdr, "Set-Cookie") !== false) {
$cLine = explode(":", $hdr)[1];
$cLine = explode(";", $cLine)[0];
$cookies .= ";" . $cLine;
if(strpos($hdr, 'Set-Cookie') !== false) {
$cLine = explode(':', $hdr)[1];
$cLine = explode(';', $cLine)[0];
$cookies .= ';' . $cLine;
}
}
return substr($cookies, 1);
}
//Get the page ID from the Facebook page.
private function getPageID($page, $cookies){
//Get the page ID and username from the Facebook page.
private function getPageInfos($page, $cookies){
$context = stream_context_create(array(
'http' => array(
'user_agent' => "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:46.0) Gecko/20100101 Firefox/46.0",
'user_agent' => 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:46.0) Gecko/20100101 Firefox/46.0',
'header' => 'Cookie: ' . $cookies
)
)
@@ -247,23 +253,32 @@ EOD;
$pageContent = file_get_contents($page, 0, $context);
if(strpos($pageContent, "signup-button") != false) {
if(strpos($pageContent, 'signup-button') != false) {
return -1;
}
//Get the username
$usernameRegex = '/data-nt=\"FB:TEXT4\">(.*?)<\/div>/m';
preg_match($usernameRegex, $pageContent, $usernameMatches);
if(count($usernameMatches) > 0) {
$username = strip_tags($usernameMatches[1]);
} else {
$username = $this->getInput('u');
}
//Get the page ID if we don't have a captcha
$regex = "/page_id=([0-9]*)&/";
$regex = '/page_id=([0-9]*)&/';
preg_match($regex, $pageContent, $matches);
if(count($matches) > 0) {
return $matches[1];
return array('userId' => $matches[1], 'username' => $username);
}
//Get the page ID if we do have a captcha
$regex = "/\"pageID\":\"([0-9]*)\"/";
$regex = '/"pageID":"([0-9]*)"/';
preg_match($regex, $pageContent, $matches);
return $matches[1];
return array('userId' => $matches[1], 'username' => $username);
}
@@ -275,7 +290,4 @@ EOD;
return 'http://facebook.com';
}
public function getCacheDuration(){
return 60 * 60 * 3; // 5 minutes
}
}

58
bridges/FDroidBridge.php Normal file
View File

@@ -0,0 +1,58 @@
<?php
class FDroidBridge extends BridgeAbstract {
const MAINTAINER = 'Mitsukarenai';
const NAME = 'F-Droid Bridge';
const URI = 'https://f-droid.org/';
const CACHE_TIMEOUT = 60 * 60 * 2; // 2 hours
const DESCRIPTION = 'Returns latest added/updated apps on the open-source Android apps repository F-Droid';
const PARAMETERS = array( array(
'u' => array(
'name' => 'Widget selection',
'type' => 'list',
'required' => true,
'values' => array(
'Latest added apps' => 'added',
'Latest updated apps' => 'updated'
)
)
));
public function getIcon() {
return self::URI . 'assets/favicon.ico?v=8j6PKzW9Mk';
}
public function collectData(){
$url = self::URI;
$html = getSimpleHTMLDOM($url)
or returnServerError('Could not request F-Droid.');
// targetting the corresponding widget based on user selection
// "updated" is the 4th widget on the page, "added" is the 5th
switch($this->getInput('u')) {
case 'updated':
$html_widget = $html->find('div.sidebar-widget', 4);
break;
default:
$html_widget = $html->find('div.sidebar-widget', 5);
break;
}
// and now extracting app info from the selected widget (and yeah turns out icons are of heterogeneous sizes)
foreach($html_widget->find('a') as $element) {
$item = array();
$item['uri'] = self::URI . $element->href;
$item['title'] = $element->find('h4', 0)->plaintext;
$item['icon'] = $element->find('img', 0)->src;
$item['summary'] = $element->find('span.package-summary', 0)->plaintext;
$item['content'] = '
<a href="' . $item['uri'] . '">
<img alt="" style="max-height:128px" src="' . $item['icon'] . '">
</a><br>' . $item['summary'];
$this->items[] = $item;
}
}
}

View File

@@ -1,190 +1,527 @@
<?php
class FacebookBridge extends BridgeAbstract {
const MAINTAINER = 'teromene';
const NAME = 'Facebook';
const MAINTAINER = 'teromene, logmanoriginal';
const NAME = 'Facebook Bridge';
const URI = 'https://www.facebook.com/';
const CACHE_TIMEOUT = 300; // 5min
const DESCRIPTION = 'Input a page title or a profile log. For a profile log,
please insert the parameter as follow : myExamplePage/132621766841117';
const PARAMETERS = array( array(
'u' => array(
'name' => 'Username',
'required' => true
),
'media_type' => array(
'name' => 'Media type',
'type' => 'list',
'required' => false,
'values' => array(
'All' => 'all',
'Video' => 'video',
'No Video' => 'novideo'
const PARAMETERS = array(
'User' => array(
'u' => array(
'name' => 'Username',
'required' => true
),
'defaultValue' => 'all'
'media_type' => array(
'name' => 'Media type',
'type' => 'list',
'required' => false,
'values' => array(
'All' => 'all',
'Video' => 'video',
'No Video' => 'novideo'
),
'defaultValue' => 'all'
),
'skip_reviews' => array(
'name' => 'Skip reviews',
'type' => 'checkbox',
'required' => false,
'defaultValue' => false,
'title' => 'Feed includes reviews when checked'
)
),
'Group' => array(
'g' => array(
'name' => 'Group',
'type' => 'text',
'required' => true,
'exampleValue' => 'https://www.facebook.com/groups/743149642484225',
'title' => 'Insert group name or facebook group URL'
)
),
'global' => array(
'limit' => array(
'name' => 'Limit',
'type' => 'number',
'required' => false,
'title' => 'Specify the number of items to return (default: -1)',
'defaultValue' => -1
)
)
));
);
private $authorName = '';
private $groupName = '';
public function collectData(){
public function getIcon() {
return 'https://static.xx.fbcdn.net/rsrc.php/yo/r/iRmz9lCMBD2.ico';
}
//Extract a string using start and end delimiters
function extractFromDelimiters($string, $start, $end){
if(strpos($string, $start) !== false) {
$section_retrieved = substr($string, strpos($string, $start) + strlen($start));
$section_retrieved = substr($section_retrieved, 0, strpos($section_retrieved, $end));
return $section_retrieved;
}
public function getName(){
switch($this->queriedContext) {
case 'User':
if(!empty($this->authorName)) {
return isset($this->extraInfos['name']) ? $this->extraInfos['name'] : $this->authorName
. ' - ' . static::NAME;
}
break;
case 'Group':
if(!empty($this->groupName)) {
return $this->groupName . ' - ' . static::NAME;
}
break;
return false;
}
//Utility function for cleaning a Facebook link
$unescape_fb_link = function($matches){
return parent::getName();
}
public function getURI() {
$uri = self::URI;
switch($this->queriedContext) {
case 'Group':
// Discover groups via https://www.facebook.com/groups/
// Example group: https://www.facebook.com/groups/sailors.worldwide
$uri .= 'groups/' . $this->sanitizeGroup(filter_var($this->getInput('g'), FILTER_SANITIZE_URL));
break;
case 'User':
// Example user 1: https://www.facebook.com/artetv/
// Example user 2: artetv
$user = $this->sanitizeUser($this->getInput('u'));
if(!strpos($user, '/')) {
$uri .= urlencode($user) . '/posts';
} else {
$uri .= 'pages/' . $user;
}
break;
}
// Request the mobile version to reduce page size (no javascript)
// More information: https://stackoverflow.com/a/11103592
return $uri .= '?_fb_noscript=1';
}
public function collectData() {
switch($this->queriedContext) {
case 'Group':
$this->collectGroupData();
break;
case 'User':
$this->collectUserData();
break;
default:
returnClientError('Unknown context: "' . $this->queriedContext . '"!');
}
$limit = $this->getInput('limit') ?: -1;
if($limit > 0 && count($this->items) > $limit) {
$this->items = array_slice($this->items, 0, $limit);
}
}
#region Group
private function collectGroupData() {
$header = array('Accept-Language: ' . getEnv('HTTP_ACCEPT_LANGUAGE') . "\r\n");
$html = getSimpleHTMLDOM($this->getURI(), $header)
or returnServerError('Failed loading facebook page: ' . $this->getURI());
if(!$this->isPublicGroup($html)) {
returnClientError('This group is not public! RSS-Bridge only supports public groups!');
}
defaultLinkTo($html, substr(self::URI, 0, strlen(self::URI) - 1));
$this->groupName = $this->extractGroupName($html);
$posts = $html->find('div.userContentWrapper')
or returnServerError('Failed finding posts!');
foreach($posts as $post) {
$item = array();
$item['uri'] = $this->extractGroupURI($post);
$item['title'] = $this->extractGroupTitle($post);
$item['author'] = $this->extractGroupAuthor($post);
$item['content'] = $this->extractGroupContent($post);
$item['timestamp'] = $this->extractGroupTimestamp($post);
$item['enclosures'] = $this->extractGroupEnclosures($post);
$this->items[] = $item;
}
}
private function sanitizeGroup($group) {
if(filter_var(
$group,
FILTER_VALIDATE_URL,
FILTER_FLAG_HOST_REQUIRED | FILTER_FLAG_PATH_REQUIRED)) {
// User provided a URL
$urlparts = parse_url($group);
if($urlparts['host'] !== parse_url(self::URI)['host']
&& 'www.' . $urlparts['host'] !== parse_url(self::URI)['host']) {
returnClientError('The host you provided is invalid! Received "'
. $urlparts['host']
. '", expected "'
. parse_url(self::URI)['host']
. '"!');
}
return explode('/', $urlparts['path'])[2];
} elseif(strpos($group, '/') !== false) {
returnClientError('The group you provided is invalid: ' . $group);
} else {
return $group;
}
}
private function isPublicGroup($html) {
// Facebook redirects to the groups about page for non-public groups
$about = $html->find('#pagelet_group_about', 0);
return !($about);
}
private function extractGroupName($html) {
$ogtitle = $html->find('meta[property="og:title"]', 0)
or returnServerError('Unable to find group title!');
return htmlspecialchars_decode($ogtitle->content, ENT_QUOTES);
}
private function extractGroupURI($post) {
$elements = $post->find('a')
or returnServerError('Unable to find URI!');
foreach($elements as $anchor) {
// Find the one that is a permalink
if(strpos($anchor->href, 'permalink') !== false) {
return $anchor->href;
}
}
return null;
}
private function extractGroupContent($post) {
$content = $post->find('div.userContent', 0)
or returnServerError('Unable to find user content!');
return $content->innertext . $content->next_sibling()->innertext;
}
private function extractGroupTimestamp($post) {
$element = $post->find('abbr[data-utime]', 0)
or returnServerError('Unable to find timestamp!');
return $element->getAttribute('data-utime');
}
private function extractGroupAuthor($post) {
$element = $post->find('img', 0)
or returnServerError('Unable to find author information!');
return $element->{'aria-label'};
}
private function extractGroupEnclosures($post) {
$elements = $post->find('div.userContent', 0)->next_sibling()->find('img');
$enclosures = array();
foreach($elements as $enclosure) {
$enclosures[] = $enclosure->src;
}
return empty($enclosures) ? null : $enclosures;
}
private function extractGroupTitle($post) {
$element = $post->find('h5', 0)
or returnServerError('Unable to find title!');
if(strpos($element->plaintext, 'shared') === false) {
$content = strip_tags($this->extractGroupContent($post));
return $this->extractGroupAuthor($post)
. ' posted: '
. substr(
$content,
0,
strpos(wordwrap($content, 64), "\n")
)
. '...';
}
return $element->plaintext;
}
#endregion (Group)
#region User
/**
* Checks if $user is a valid username or URI and returns the username
*/
private function sanitizeUser($user) {
if (filter_var($user, FILTER_VALIDATE_URL)) {
$urlparts = parse_url($user);
if($urlparts['host'] !== parse_url(self::URI)['host']) {
returnClientError('The host you provided is invalid! Received "'
. $urlparts['host']
. '", expected "'
. parse_url(self::URI)['host']
. '"!');
}
if(!array_key_exists('path', $urlparts)
|| $urlparts['path'] === '/') {
returnClientError('The URL you provided doesn\'t contain the user name!');
}
return explode('/', $urlparts['path'])[1];
} else {
// First character cannot be a forward slash
if(strpos($user, '/') === 0) {
returnClientError('Remove leading slash "/" from the username!');
}
return $user;
}
}
/**
* Bypass external link redirection
*/
private function unescape_fb_link($content){
return preg_replace_callback('/ href=\"([^"]+)\"/i', function($matches){
if(is_array($matches) && count($matches) > 1) {
$link = $matches[1];
if(strpos($link, '/') === 0)
$link = self::URI . $link;
if(strpos($link, 'facebook.com/l.php?u=') !== false)
$link = urldecode(extractFromDelimiters($link, 'facebook.com/l.php?u=', '&'));
return ' href="' . $link . '"';
}
};
}, $content);
}
//Utility function for converting facebook emoticons
$unescape_fb_emote = function($matches){
static $facebook_emoticons = array(
'smile' => ':)',
'frown' => ':(',
'tongue' => ':P',
'grin' => ':D',
'gasp' => ':O',
'wink' => ';)',
'pacman' => ':<',
'grumpy' => '>_<',
'unsure' => ':/',
'cry' => ':\'(',
'kiki' => '^_^',
'glasses' => '8-)',
'sunglasses' => 'B-)',
'heart' => '<3',
'devil' => ']:D',
'angel' => '0:)',
'squint' => '-_-',
'confused' => 'o_O',
'upset' => 'xD',
'colonthree' => ':3',
'like' => '&#x1F44D;');
$len = count($matches);
if ($len > 1)
for ($i = 1; $i < $len; $i++)
foreach ($facebook_emoticons as $name => $emote)
if ($matches[$i] === $name)
return $emote;
return $matches[0];
};
/**
* Convert textual representation of emoticons back to ASCII emoticons.
* i.e. "<i><u>smile emoticon</u></i>" => ":)"
*/
private function unescape_fb_emote($content){
return preg_replace_callback('/<i><u>([^ <>]+) ([^<>]+)<\/u><\/i>/i', function($matches){
static $facebook_emoticons = array(
'smile' => ':)',
'frown' => ':(',
'tongue' => ':P',
'grin' => ':D',
'gasp' => ':O',
'wink' => ';)',
'pacman' => ':<',
'grumpy' => '>_<',
'unsure' => ':/',
'cry' => ':\'(',
'kiki' => '^_^',
'glasses' => '8-)',
'sunglasses' => 'B-)',
'heart' => '<3',
'devil' => ']:D',
'angel' => '0:)',
'squint' => '-_-',
'confused' => 'o_O',
'upset' => 'xD',
'colonthree' => ':3',
'like' => '&#x1F44D;');
$html = null;
$len = count($matches);
//Handle captcha response sent by the viewer
if ($len > 1)
for ($i = 1; $i < $len; $i++)
foreach ($facebook_emoticons as $name => $emote)
if ($matches[$i] === $name)
return $emote;
return $matches[0];
}, $content);
}
/**
* Returns the captcha message for the given captcha
*/
private function returnCaptchaMessage($captcha) {
// Save form for submitting after getting captcha response
if (session_status() == PHP_SESSION_NONE) {
session_start();
}
$captcha_fields = array();
foreach ($captcha->find('input, button') as $input) {
$captcha_fields[$input->name] = $input->value;
}
$_SESSION['captcha_fields'] = $captcha_fields;
$_SESSION['captcha_action'] = $captcha->find('form', 0)->action;
// Show captcha filling form to the viewer, proxying the captcha image
$img = base64_encode(getContents($captcha->find('img', 0)->src));
http_response_code(500);
header('Content-Type: text/html');
$message = <<<EOD
<form method="post" action="?{$_SERVER['QUERY_STRING']}">
<h2>Facebook captcha challenge</h2>
<p>Unfortunately, rss-bridge cannot fetch the requested page.<br />
Facebook wants rss-bridge to resolve the following captcha:</p>
<p><img src="data:image/png;base64,{$img}" /></p>
<p><b>Response:</b> <input name="captcha_response" placeholder="please fill in" />
<input type="submit" value="Submit!" /></p>
</form>
EOD;
die($message);
}
/**
* Checks if a capture response was received and tries to load the contents
* @return mixed null if no capture response was received, simplhtmldom document otherwise
*/
private function handleCaptchaResponse() {
if (isset($_POST['captcha_response'])) {
if (session_status() == PHP_SESSION_NONE)
session_start();
if (isset($_SESSION['captcha_fields'], $_SESSION['captcha_action'])) {
$captcha_action = $_SESSION['captcha_action'];
$captcha_fields = $_SESSION['captcha_fields'];
$captcha_fields['captcha_response'] = preg_replace("/[^a-zA-Z0-9]+/", "", $_POST['captcha_response']);
$http_options = array(
'http' => array(
'method' => 'POST',
'user_agent' => ini_get('user_agent'),
'header' => array("Content-type:
application/x-www-form-urlencoded\r\nReferer: $captcha_action\r\nCookie: noscript=1\r\n"),
'content' => http_build_query($captcha_fields)
),
);
$context = stream_context_create($http_options);
$html = getContents($captcha_action, false, $context);
$captcha_fields['captcha_response'] = preg_replace('/[^a-zA-Z0-9]+/', '', $_POST['captcha_response']);
if($html === false) {
returnServerError('Failed to submit captcha response back to Facebook');
}
unset($_SESSION['captcha_fields']);
$html = str_get_html($html);
$header = array(
'Content-type: application/x-www-form-urlencoded',
'Referer: ' . $captcha_action,
'Cookie: noscript=1'
);
$opts = array(
CURLOPT_POST => 1,
CURLOPT_POSTFIELDS => http_build_query($captcha_fields)
);
$html = getSimpleHTMLDOM($captcha_action, $header, $opts)
or returnServerError('Failed to submit captcha response back to Facebook');
return $html;
}
unset($_SESSION['captcha_fields']);
unset($_SESSION['captcha_action']);
}
//Retrieve page contents
return null;
}
private function collectUserData(){
$html = $this->handleCaptchaResponse();
// Retrieve page contents
if(is_null($html)) {
$http_options = array(
'http' => array(
'method' => 'GET',
'user_agent' => ini_get('user_agent'),
'header' => 'Accept-Language: ' . getEnv('HTTP_ACCEPT_LANGUAGE') . "\r\n"
)
);
$context = stream_context_create($http_options);
if(!strpos($this->getInput('u'), "/")) {
$html = getSimpleHTMLDOM(self::URI . urlencode($this->getInput('u')) . '?_fb_noscript=1',
false,
$context)
or returnServerError('No results for this query.');
} else {
$html = getSimpleHTMLDOM(self::URI . 'pages/' . $this->getInput('u') . '?_fb_noscript=1',
false,
$context)
or returnServerError('No results for this query.');
}
$header = array('Accept-Language: ' . getEnv('HTTP_ACCEPT_LANGUAGE'));
$html = getSimpleHTMLDOM($this->getURI(), $header)
or returnServerError('No results for this query.');
}
//Handle captcha form?
// Handle captcha form?
$captcha = $html->find('div.captcha_interstitial', 0);
if (!is_null($captcha)) {
//Save form for submitting after getting captcha response
if (session_status() == PHP_SESSION_NONE)
session_start();
$captcha_fields = array();
foreach ($captcha->find('input, button') as $input)
$captcha_fields[$input->name] = $input->value;
$_SESSION['captcha_fields'] = $captcha_fields;
$_SESSION['captcha_action'] = $captcha->find('form', 0)->action;
//Show captcha filling form to the viewer, proxying the captcha image
$img = base64_encode(getContents($captcha->find('img', 0)->src));
http_response_code(500);
header('Content-Type: text/html');
$message = <<<EOD
<form method="post" action="?{$_SERVER['QUERY_STRING']}">
<h2>Facebook captcha challenge</h2>
<p>Unfortunately, rss-bridge cannot fetch the requested page.<br />
Facebook wants rss-bridge to resolve the following captcha:</p>
<p><img src="data:image/png;base64,{$img}" /></p>
<p><b>Response:</b> <input name="captcha_response" placeholder="please fill in" />
<input type="submit" value="Submit!" /></p>
</form>
EOD;
die($message);
if (!is_null($captcha)) {
$this->returnCaptchaMessage($captcha);
}
// No captcha? We can carry on retrieving page contents :)
// First, we check wether the page is public or not
$loginForm = $html->find('._585r', 0);
if($loginForm != null) {
returnServerError('You must be logged in to view this page. This is not supported by RSS-Bridge.');
}
//No captcha? We can carry on retrieving page contents :)
$element = $html
->find('#pagelet_timeline_main_column')[0]
->children(0)
->children(0)
->children(0)
->next_sibling()
->children(0);
if(isset($element)) {
$author = str_replace(' | Facebook', '', $html->find('title#pageTitle', 0)->innertext);
$profilePic = 'https://graph.facebook.com/'
. $this->getInput('u')
. '/picture?width=200&amp;height=200';
$profilePic = $html->find('meta[property="og:image"]', 0)->content;
$this->authorName = $author;
@@ -196,6 +533,12 @@ EOD;
$posts = array($cell);
}
// Optionally skip reviews
if($this->getInput('skip_reviews')
&& !is_null($cell->find('#review_composer_container', 0))) {
continue;
}
foreach($posts as $post) {
// Check media type
switch($this->getInput('media_type')) {
@@ -213,11 +556,7 @@ EOD;
if(count($post->find('abbr')) > 0) {
//Retrieve post contents
$content = preg_replace(
'/(?i)><div class=\"clearfix([^>]+)>(.+?)div\ class=\"userContent\"/i',
'',
$post);
$content = $post->find('.userContentWrapper', 0);
$content = preg_replace(
'/(?i)><div class=\"_59tj([^>]+)>(.+?)<\/div><\/div><a/i',
@@ -234,13 +573,18 @@ EOD;
'',
$content);
//Remove html nodes, keep only img, links, basic formatting
// Remove "SpSonsSoriSsés"
$content = preg_replace(
'/(?iU)<a [^>]+ href="#" role="link" [^>}]+>.+<\/a>/iU',
'',
$content);
// Remove html nodes, keep only img, links, basic formatting
$content = strip_tags($content, '<a><img><i><u><br><p>');
//Adapt link hrefs: convert relative links into absolute links and bypass external link redirection
$content = preg_replace_callback('/ href=\"([^"]+)\"/i', $unescape_fb_link, $content);
$content = $this->unescape_fb_link($content);
//Clean useless html tag properties and fix link closing tags
// Clean useless html tag properties and fix link closing tags
foreach (array(
'onmouseover',
'onclick',
@@ -253,35 +597,45 @@ EOD;
'aria-[^=]*',
'role',
'rel',
'id') as $property_name)
$content = preg_replace('/ ' . $property_name . '=\"[^"]*\"/i', '', $content);
'id') as $property_name) {
$content = preg_replace('/ ' . $property_name . '=\"[^"]*\"/i', '', $content);
}
$content = preg_replace('/<\/a [^>]+>/i', '</a>', $content);
//Convert textual representation of emoticons eg
//"<i><u>smile emoticon</u></i>" back to ASCII emoticons eg ":)"
$content = preg_replace_callback(
'/<i><u>([^ <>]+) ([^<>]+)<\/u><\/i>/i',
$unescape_fb_emote,
$content
);
$this->unescape_fb_emote($content);
// Restore links in the post before further parsing
$post = defaultLinkTo($post, self::URI);
// Restore links in the content before adding to the item
$content = defaultLinkTo($content, self::URI);
// Retrieve date of the post
$date = $post->find('abbr')[0];
//Retrieve date of the post
$date = $post->find("abbr")[0];
if(isset($date) && $date->hasAttribute('data-utime')) {
$date = $date->getAttribute('data-utime');
} else {
$date = 0;
}
//Build title from username and content
// Build title from username and content
$title = $author;
if(strlen($title) > 24)
$title = substr($title, 0, strpos(wordwrap($title, 24), "\n")) . '...';
$title = $title . ' | ' . strip_tags($content);
if(strlen($title) > 64)
$title = substr($title, 0, strpos(wordwrap($title, 64), "\n")) . '...';
$uri = self::URI . $post->find('abbr')[0]->parent()->getAttribute('href');
$uri = $post->find('abbr')[0]->parent()->getAttribute('href');
if (false !== strpos($uri, '?')) {
$uri = substr($uri, 0, strpos($uri, '?'));
}
//Build and add final item
$item['uri'] = htmlspecialchars_decode($uri);
@@ -289,6 +643,11 @@ EOD;
$item['title'] = $title;
$item['author'] = $author;
$item['timestamp'] = $date;
if(strpos($item['content'], '<img') === false) {
$item['enclosures'] = array($profilePic);
}
$this->items[] = $item;
}
}
@@ -296,12 +655,6 @@ EOD;
}
}
public function getName(){
if(!empty($this->authorName)) {
return isset($this->extraInfos['name']) ? $this->extraInfos['name'] : $this->authorName
. ' - Facebook Bridge';
}
#endregion (User)
return parent::getName();
}
}

View File

@@ -7,18 +7,27 @@ class FierPandaBridge extends BridgeAbstract {
const CACHE_TIMEOUT = 21600; // 6h
const DESCRIPTION = 'Returns latest articles from Fier Panda.';
public function getIcon() {
return self::URI . 'wp-content/themes/fier-panda/img/favicon.png';
}
public function collectData(){
$html = getSimpleHTMLDOM(self::URI)
or returnServerError('Could not request Fier Panda.');
foreach($html->find('div.container-content article') as $element) {
defaultLinkTo($html, static::URI);
foreach($html->find('article') as $article) {
$item = array();
$item['uri'] = $this->getURI() . $element->find('a', 0)->href;
$item['title'] = trim($element->find('h1 a', 0)->innertext);
// Remove the link at the end of the article
$element->find('p a', 0)->outertext = '';
$item['content'] = $element->find('p', 0)->innertext;
$item['uri'] = $article->find('a', 0)->href;
$item['title'] = $article->find('a', 0)->title;
$this->items[] = $item;
}
}
}

View File

@@ -6,6 +6,7 @@ class FilterBridge extends FeedExpander {
const NAME = 'Filter';
const CACHE_TIMEOUT = 3600; // 1h
const DESCRIPTION = 'Filters a feed of your choice';
const URI = 'https://github.com/rss-bridge/rss-bridge';
const PARAMETERS = array(array(
'url' => array(
@@ -26,11 +27,34 @@ class FilterBridge extends FeedExpander {
),
'defaultValue' => 'permit',
),
'title_from_content' => array(
'name' => 'Generate title from content',
'type' => 'checkbox',
'required' => false,
)
));
protected function parseItem($newItem){
$item = parent::parseItem($newItem);
if($this->getInput('title_from_content') && array_key_exists('content', $item)) {
$content = str_get_html($item['content']);
$pos = strpos($item['content'], ' ', 50);
$item['title'] = substr(
$content->plaintext,
0,
$pos
);
if(strlen($content->plaintext) >= $pos) {
$item['title'] .= '...';
}
}
switch(true) {
case $this->getFilterType() === 'permit':
if (preg_match($this->getFilter(), $item['title'])) {

View File

@@ -30,30 +30,76 @@ class FlickrBridge extends BridgeAbstract {
'title' => 'Insert username (as shown in the address bar)',
'exampleValue' => 'flickr'
)
),
)
);
public function collectData(){
switch($this->queriedContext) {
case 'Explore':
$key = 'photos';
$filter = 'photo-lite-models';
$html = getSimpleHTMLDOM(self::URI . 'explore')
or returnServerError('Could not request Flickr.');
break;
case 'By keyword':
$key = 'photos';
$filter = 'photo-lite-models';
$html = getSimpleHTMLDOM(self::URI . 'search/?q=' . urlencode($this->getInput('q')) . '&s=rec')
or returnServerError('No results for this query.');
break;
case 'By username':
$key = 'photoPageList';
$filter = 'photo-models';
$html = getSimpleHTMLDOM(self::URI . 'photos/' . urlencode($this->getInput('u')))
or returnServerError('Requested username can\'t be found.');
break;
default:
returnClientError('Invalid context: ' . $this->queriedContext);
}
$model_json = $this->extractJsonModel($html);
$photo_models = $this->getPhotoModels($model_json, $filter);
foreach($photo_models as $model) {
$item = array();
/* Author name depends on scope. On a keyword search the
* author is part of the picture data. On a username search
* the author is part of the owner data.
*/
if(array_key_exists('username', $model)) {
$item['author'] = $model['username'];
} elseif (array_key_exists('owner', reset($model_json)[0])) {
$item['author'] = reset($model_json)[0]['owner']['username'];
}
$item['title'] = (array_key_exists('title', $model) ? $model['title'] : 'Untitled');
$item['uri'] = self::URI . 'photo.gne?id=' . $model['id'];
$description = (array_key_exists('description', $model) ? $model['description'] : '');
$item['content'] = '<a href="'
. $item['uri']
. '"><img src="'
. $this->extractContentImage($model)
. '" style="max-width: 640px; max-height: 480px;"/></a><br><p>'
. $description
. '</p>';
$item['enclosures'] = $this->extractEnclosures($model);
$this->items[] = $item;
}
}
private function extractJsonModel($html) {
// Find SCRIPT containing JSON data
$model = $html->find('.modelExport', 0);
$model_text = $model->innertext;
@@ -62,59 +108,79 @@ class FlickrBridge extends BridgeAbstract {
$start = strpos($model_text, 'modelExport:') + strlen('modelExport:');
$end = strpos($model_text, 'auth:') - strlen('auth:');
// Dissect JSON data and remove trailing comma
// Extract JSON data, remove trailing comma
$model_text = trim(substr($model_text, $start, $end - $start));
$model_text = substr($model_text, 0, strlen($model_text) - 1);
$model_json = json_decode($model_text, true);
return json_decode($model_text, true);
foreach($html->find('.photo-list-photo-view') as $element) {
// Get the styles
$style = explode(';', $element->style);
// Get the background-image style
$backgroundImage = explode(':', end($style));
// URI type : url(//cX.staticflickr.com/X/XXXXX/XXXXXXXXX.jpg)
$imageURI = trim(str_replace(['url(', ')'], '', end($backgroundImage)));
// Get the image ID
$imageURIs = explode('_', basename($imageURI));
$imageID = reset($imageURIs);
// Use JSON data to build items
foreach(reset($model_json)[0][$key]['_data'] as $element) {
if($element['id'] === $imageID) {
$item = array();
/* Author name depends on scope. On a keyword search the
* author is part of the picture data. On a username search
* the author is part of the owner data.
*/
if(array_key_exists('username', $element)) {
$item['author'] = $element['username'];
} elseif (array_key_exists('owner', reset($model_json)[0])) {
$item['author'] = reset($model_json)[0]['owner']['username'];
}
$item['title'] = (array_key_exists('title', $element) ? $element['title'] : 'Untitled');
$item['uri'] = self::URI . 'photo.gne?id=' . $imageID;
$description = (array_key_exists('description', $element) ? $element['description'] : '');
$item['content'] = '<a href="'
. $item['uri']
. '"><img src="'
. $imageURI
. '" /></a><br><p>'
. $description
. '</p>';
$this->items[] = $item;
break;
}
}
}
}
private function getPhotoModels($json, $filter) {
// The JSON model contains a "legend" array, where each element contains
// the path to an element in the "main" object
$photo_models = array();
foreach($json['legend'] as $legend) {
$photo_model = $json['main'];
foreach($legend as $element) { // Traverse tree
$photo_model = $photo_model[$element];
}
// We are only interested in content
if($photo_model['_flickrModelRegistry'] === $filter) {
$photo_models[] = $photo_model;
}
}
return $photo_models;
}
private function extractEnclosures($model) {
$areas = array();
foreach($model['sizes'] as $size) {
$areas[$size['width'] * $size['height']] = $size['url'];
}
return array($this->fixURL(max($areas)));
}
private function extractContentImage($model) {
$areas = array();
$limit = 320 * 240;
foreach($model['sizes'] as $size) {
$image_area = $size['width'] * $size['height'];
if($image_area >= $limit) {
$areas[$image_area] = $size['url'];
}
}
return $this->fixURL(min($areas));
}
private function fixURL($url) {
// For some reason the image URLs don't include the protocol (https)
if(strpos($url, '//') === 0) {
$url = 'https:' . $url;
}
return $url;
}
}

View File

@@ -15,47 +15,47 @@ class FootitoBridge extends BridgeAbstract {
$content = trim($element->innertext);
$content = str_replace(
"<img",
'<img',
"<img style='float : left;'",
$content );
$content = str_replace(
"class=\"logo\"",
'class="logo"',
"style='float : left;'",
$content );
$content = str_replace(
"class=\"contenu\"",
'class="contenu"',
"style='margin-left : 60px;'",
$content );
$content = str_replace(
"class=\"responsive-comment\"",
'class="responsive-comment"',
"style='border-top : 1px #DDD solid; background-color : white; padding : 10px;'",
$content );
$content = str_replace(
"class=\"jaime\"",
'class="jaime"',
"style='display : none;'",
$content );
$content = str_replace(
"class=\"auteur-event responsive\"",
'class="auteur-event responsive"',
"style='display : none;'",
$content );
$content = str_replace(
"class=\"report-abuse-button\"",
'class="report-abuse-button"',
"style='display : none;'",
$content );
$content = str_replace(
"class=\"reaction clearfix\"",
'class="reaction clearfix"',
"style='margin : 10px 0px; padding : 5px; border-bottom : 1px #DDD solid;'",
$content );
$content = str_replace(
"class=\"infos\"",
'class="infos"',
"style='font-size : 0.7em;'",
$content );

41
bridges/ForGifsBridge.php Normal file
View File

@@ -0,0 +1,41 @@
<?php
class ForGifsBridge extends FeedExpander {
const MAINTAINER = 'logmanoriginal';
const NAME = 'forgifs Bridge';
const URI = 'https://forgifs.com';
const DESCRIPTION = 'Returns the forgifs feed with actual gifs instead of images';
public function collectData() {
$this->collectExpandableDatas('https://forgifs.com/gallery/srss/7');
}
protected function parseItem($feedItem) {
$item = parent::parseItem($feedItem);
$content = str_get_html($item['content']);
$img = $content->find('img', 0);
$poster = $img->src;
// The actual gif is the same path but its id must be decremented by one.
// Example:
// http://forgifs.com/gallery/d/279419-2/Reporter-videobombed-shoulder-checks.gif
// http://forgifs.com/gallery/d/279418-2/Reporter-videobombed-shoulder-checks.gif
// Notice how this changes ----------^
// Now let's extract that number and do some math
// Notice: Technically we could also load the content page but that would
// require unnecessary traffic. As long as it works...
$num = substr($img->src, 29, 6);
$num -= 1;
$img->src = substr_replace($img->src, $num, 29, strlen($num));
$img->width = 'auto';
$img->height = 'auto';
$item['content'] = $content;
return $item;
}
}

View File

@@ -30,7 +30,7 @@ class FourchanBridge extends BridgeAbstract {
public function collectData(){
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError("Could not request 4chan, thread not found");
or returnServerError('Could not request 4chan, thread not found');
foreach($html->find('div.postContainer') as $element) {
$item = array();
@@ -69,7 +69,7 @@ class FourchanBridge extends BridgeAbstract {
. '" src="'
. $item['imageThumb']
. '" /></a><br>'
.$item['content'];
. $item['content'];
}
$this->items[] = $item;
}

View File

@@ -3,7 +3,7 @@ class FuturaSciencesBridge extends FeedExpander {
const MAINTAINER = 'ORelio';
const NAME = 'Futura-Sciences Bridge';
const URI = 'http://www.futura-sciences.com/';
const URI = 'https://www.futura-sciences.com/';
const DESCRIPTION = 'Returns the newest articles.';
const PARAMETERS = array( array(
@@ -90,42 +90,11 @@ class FuturaSciencesBridge extends FeedExpander {
or returnServerError('Could not request Futura-Sciences: ' . $item['uri']);
$item['content'] = $this->extractArticleContent($article);
$author = $this->extractAuthor($article);
$item['author'] = empty($author) ? $item['author'] : $author;
if (!empty($author))
$item['author'] = $author;
return $item;
}
private function stripWithDelimiters($string, $start, $end){
while(strpos($string, $start) !== false) {
$section_to_remove = substr($string, strpos($string, $start));
$section_to_remove = substr($section_to_remove, 0, strpos($section_to_remove, $end) + strlen($end));
$string = str_replace($section_to_remove, '', $string);
} return $string;
}
private function stripRecursiveHTMLSection($string, $tag_name, $tag_start){
$open_tag = '<' . $tag_name;
$close_tag = '</' . $tag_name . '>';
$close_tag_length = strlen($close_tag);
if(strpos($tag_start, $open_tag) === 0) {
while(strpos($string, $tag_start) !== false) {
$max_recursion = 100;
$section_to_remove = null;
$section_start = strpos($string, $tag_start);
$search_offset = $section_start;
do {
$max_recursion--;
$section_end = strpos($string, $close_tag, $search_offset);
$search_offset = $section_end + $close_tag_length;
$section_to_remove = substr($string, $section_start, $section_end - $section_start + $close_tag_length);
$open_tag_count = substr_count($section_to_remove, $open_tag);
$close_tag_count = substr_count($section_to_remove, $close_tag);
} while ($open_tag_count > $close_tag_count && $max_recursion > 0);
$string = str_replace($section_to_remove, '', $string);
}
}
return $string;
}
private function extractArticleContent($article){
$contents = $article->find('section.article-text-classic', 0)->innertext;
$headline = trim($article->find('p.description', 0)->plaintext);
@@ -137,6 +106,7 @@ class FuturaSciencesBridge extends FeedExpander {
'<div class="sharebar2',
'<div class="diaporamafullscreen"',
'<div class="module social-button',
'<div class="module social-share',
'<div style="margin-bottom:10px;" class="noprint"',
'<div class="ficheprevnext',
'<div class="bar noprint',
@@ -148,16 +118,17 @@ class FuturaSciencesBridge extends FeedExpander {
'<div id="forumcomments',
'<div ng-if="active"'
) as $div_start) {
$contents = $this->stripRecursiveHTMLSection($contents, 'div', $div_start);
$contents = stripRecursiveHTMLSection($contents, 'div', $div_start);
}
$contents = $this->stripWithDelimiters($contents, '<hr ', '/>');
$contents = $this->stripWithDelimiters($contents, '<p class="content-date', '</p>');
$contents = $this->stripWithDelimiters($contents, '<h1 class="content-title', '</h1>');
$contents = $this->stripWithDelimiters($contents, 'fs:definition="', '"');
$contents = $this->stripWithDelimiters($contents, 'fs:xt:clicktype="', '"');
$contents = $this->stripWithDelimiters($contents, 'fs:xt:clickname="', '"');
$contents = $this->stripWithDelimiters($contents, '<script ', '</script>');
$contents = stripWithDelimiters($contents, '<hr ', '/>');
$contents = stripWithDelimiters($contents, '<p class="content-date', '</p>');
$contents = stripWithDelimiters($contents, '<h1 class="content-title', '</h1>');
$contents = stripWithDelimiters($contents, 'fs:definition="', '"');
$contents = stripWithDelimiters($contents, 'fs:xt:clicktype="', '"');
$contents = stripWithDelimiters($contents, 'fs:xt:clickname="', '"');
$contents = StripWithDelimiters($contents, '<section class="module-toretain module-propal-nl', '</section>');
$contents = stripWithDelimiters($contents, '<script ', '</script>');
return $headline . trim($contents);
}

View File

@@ -20,50 +20,58 @@ class GBAtempBridge extends BridgeAbstract {
)
));
private function extractFromDelimiters($string, $start, $end){
if(strpos($string, $start) !== false) {
$section_retrieved = substr($string, strpos($string, $start) + strlen($start));
$section_retrieved = substr($section_retrieved, 0, strpos($section_retrieved, $end));
return $section_retrieved;
}
return false;
}
private function stripWithDelimiters($string, $start, $end){
while(strpos($string, $start) !== false) {
$section_to_remove = substr($string, strpos($string, $start));
$section_to_remove = substr($section_to_remove, 0, strpos($section_to_remove, $end) + strlen($end));
$string = str_replace($section_to_remove, '', $string);
}
return $string;
}
private function buildItem($uri, $title, $author, $timestamp, $content){
private function buildItem($uri, $title, $author, $timestamp, $thumbnail, $content){
$item = array();
$item['uri'] = $uri;
$item['title'] = $title;
$item['author'] = $author;
$item['timestamp'] = $timestamp;
$item['content'] = $content;
if (!empty($thumbnail)) {
$item['enclosures'] = array($thumbnail);
}
return $item;
}
private function cleanupPostContent($content, $site_url){
$content = str_replace(':arrow:', '&#x27a4;', $content);
$content = str_replace('href="attachments/', 'href="'.$site_url.'attachments/', $content);
$content = $this->stripWithDelimiters($content, '<script', '</script>');
$content = str_replace('href="attachments/', 'href="' . $site_url . 'attachments/', $content);
$content = stripWithDelimiters($content, '<script', '</script>');
return $content;
}
private function findItemDate($item){
$time = 0;
$dateField = $item->find('abbr.DateTime', 0);
if (is_object($dateField)) {
$time = intval(
extractFromDelimiters(
$dateField->outertext,
'data-time="',
'"'
)
);
} else {
$dateField = $item->find('span.DateTime', 0);
$time = DateTime::createFromFormat(
'M j, Y \a\t g:i A',
extractFromDelimiters(
$dateField->outertext,
'title="',
'"'
)
)->getTimestamp();
}
return $time;
}
private function fetchPostContent($uri, $site_url){
$html = getSimpleHTMLDOM($uri);
$html = getSimpleHTMLDOMCached($uri);
if(!$html) {
return 'Could not request GBAtemp ' . $uri;
return 'Could not request GBAtemp: ' . $uri;
}
$content = $html->find('div.messageContent', 0)->innertext;
$content = $html->find('div.messageContent, blockquote.baseHtml', 0)->innertext;
return $this->cleanupPostContent($content, $site_url);
}
@@ -76,70 +84,56 @@ class GBAtempBridge extends BridgeAbstract {
case 'N':
foreach($html->find('li[class=news_item full]') as $newsItem) {
$url = self::URI . $newsItem->find('a', 0)->href;
$time = intval(
$this->extractFromDelimiters(
$newsItem->find('abbr.DateTime', 0)->outertext,
'data-time="',
'"'
)
);
$img = $this->getURI() . $newsItem->find('img', 0)->src . '#.image';
$time = $this->findItemDate($newsItem);
$author = $newsItem->find('a.username', 0)->plaintext;
$title = $newsItem->find('a', 1)->plaintext;
$content = $this->fetchPostContent($url, self::URI);
$this->items[] = $this->buildItem($url, $title, $author, $time, $content);
$this->items[] = $this->buildItem($url, $title, $author, $time, $img, $content);
unset($newsItem); // Some items are heavy, freeing the item proactively helps saving memory
}
break;
case 'R':
foreach($html->find('li.portal_review') as $reviewItem) {
$url = self::URI . $reviewItem->find('a', 0)->href;
$img = $this->getURI() . extractFromDelimiters($reviewItem->find('a', 0)->style, 'image:url(', ')');
$title = $reviewItem->find('span.review_title', 0)->plaintext;
$content = getSimpleHTMLDOM($url)
or returnServerError('Could not request GBAtemp: ' . $uri);
$author = $content->find('a.username', 0)->plaintext;
$time = intval(
$this->extractFromDelimiters(
$content->find('abbr.DateTime', 0)->outertext,
'data-time="',
'"'
)
);
$time = $this->findItemDate($content);
$intro = '<p><b>' . ($content->find('div#review_intro', 0)->plaintext) . '</b></p>';
$review = $content->find('div#review_main', 0)->innertext;
$subheader = '<p><b>' . $content->find('div.review_subheader', 0)->plaintext . '</b></p>';
$procons = $content->find('table.review_procons', 0)->outertext;
$scores = $content->find('table.reviewscores', 0)->outertext;
$content = $this->cleanupPostContent($intro . $review . $subheader . $procons . $scores, self::URI);
$this->items[] = $this->buildItem($url, $title, $author, $time, $content);
$this->items[] = $this->buildItem($url, $title, $author, $time, $img, $content);
unset($reviewItem); // Free up memory
}
break;
case 'T':
foreach($html->find('li.portal-tutorial') as $tutorialItem) {
$url = self::URI . $tutorialItem->find('a', 0)->href;
$title = $tutorialItem->find('a', 0)->plaintext;
$time = intval(
$this->extractFromDelimiters(
$tutorialItem->find('abbr.DateTime', 0)->outertext,
'data-time="',
'"'
)
);
$time = $this->findItemDate($tutorialItem);
$author = $tutorialItem->find('a.username', 0)->plaintext;
$content = $this->fetchPostContent($url, self::URI);
$this->items[] = $this->buildItem($url, $title, $author, $time, $content);
$this->items[] = $this->buildItem($url, $title, $author, $time, null, $content);
unset($tutorialItem); // Free up memory
}
break;
case 'F':
foreach($html->find('li.rc_item') as $postItem) {
$url = self::URI . $postItem->find('a', 1)->href;
$title = $postItem->find('a', 1)->plaintext;
$time = intval(
$this->extractFromDelimiters(
$postItem->find('abbr.DateTime', 0)->outertext,
'data-time="',
'"'
)
);
$time = $this->findItemDate($postItem);
$author = $postItem->find('a.username', 0)->plaintext;
$content = $this->fetchPostContent($url, self::URI);
$this->items[] = $this->buildItem($url, $title, $author, $time, $content);
$this->items[] = $this->buildItem($url, $title, $author, $time, null, $content);
unset($postItem); // Free up memory
}
break;
}
}

66
bridges/GOGBridge.php Normal file
View File

@@ -0,0 +1,66 @@
<?php
class GOGBridge extends BridgeAbstract {
const NAME = 'GOGBridge';
const MAINTAINER = 'teromene';
const URI = 'https://gog.com';
const DESCRIPTION = 'Returns the latest releases from GOG.com';
public function collectData() {
$values = getContents('https://www.gog.com/games/ajax/filtered?limit=25&sort=new') or
die('Unable to get the news pages from GOG !');
$decodedValues = json_decode($values);
$limit = 0;
foreach($decodedValues->products as $game) {
$item = array();
$item['author'] = $game->developer . ' / ' . $game->publisher;
$item['title'] = $game->title;
$item['id'] = $game->id;
$item['uri'] = self::URI . $game->url;
$item['content'] = $this->buildGameContentPage($game);
$item['timestamp'] = $game->globalReleaseDate;
foreach($game->gallery as $image) {
$item['enclosures'][] = $image . '.jpg';
}
$this->items[] = $item;
$limit += 1;
if($limit == 10) break;
}
}
private function buildGameContentPage($game) {
$gameDescriptionText = getContents('https://api.gog.com/products/' . $game->id . '?expand=description') or
die('Unable to get game description from GOG !');
$gameDescriptionValue = json_decode($gameDescriptionText);
$content = 'Genres: ';
$content .= implode(', ', $game->genres);
$content .= '<br />Supported Platforms: ';
if($game->worksOn->Windows) {
$content .= 'Windows ';
}
if($game->worksOn->Mac) {
$content .= 'Mac ';
}
if($game->worksOn->Linux) {
$content .= 'Linux ';
}
$content .= '<br />' . $gameDescriptionValue->description->full;
return $content;
}
}

View File

@@ -0,0 +1,119 @@
<?php
/**
* An extension of the previous SexactuBridge to cover the whole GQMagazine.
* This one taks a page (as an example sexe/news or journaliste/maia-mazaurette) which is to be configured,
* reads all the articles visible on that page, and make a stream out of it.
* @author nicolas-delsaux
*
*/
class GQMagazineBridge extends BridgeAbstract
{
const MAINTAINER = 'Riduidel';
const NAME = 'GQMagazine';
// URI is no more valid, since we can address the whole gq galaxy
const URI = 'https://www.gqmagazine.fr';
const CACHE_TIMEOUT = 7200; // 2h
const DESCRIPTION = 'GQMagazine section extractor bridge. This bridge allows you get only a specific section.';
const PARAMETERS = array( array(
'domain' => array(
'name' => 'Domain to use',
'required' => true,
'values' => array(
'www.gqmagazine.fr' => 'www.gqmagazine.fr'
),
'defaultValue' => 'www.gqmagazine.fr'
),
'page' => array(
'name' => 'Initial page to load',
'required' => true
),
));
const REPLACED_ATTRIBUTES = array(
'href' => 'href',
'src' => 'src',
'data-original' => 'src'
);
private function getDomain() {
return $this->getInput('domain');
}
public function getURI()
{
return $this->getDomain() . '/' . $this->getInput('page');
}
public function collectData()
{
$html = getSimpleHTMLDOM($this->getURI()) or returnServerError('Could not request ' . $this->getURI());
// Since GQ don't want simple class scrapping, let's do it the hard way and ... discover content !
$main = $html->find('main', 0);
foreach ($main->find('a') as $link) {
$uri = $link->href;
$title = $link->find('h2', 0);
$date = $link->find('time', 0);
$item = array();
$author = $link->find('span[itemprop=name]', 0);
$item['author'] = $author->plaintext;
$item['title'] = $title->plaintext;
if(substr($uri, 0, 1) === 'h') { // absolute uri
$item['uri'] = $uri;
} else if(substr($uri, 0, 1) === '/') { // domain relative url
$item['uri'] = $this->getDomain() . $uri;
} else {
$item['uri'] = $this->getDomain() . '/' . $uri;
}
$article = $this->loadFullArticle($item['uri']);
if($article) {
$item['content'] = $this->replaceUriInHtmlElement($article);
} else {
$item['content'] = "<strong>Article body couldn't be loaded</strong>. It must be a bug!";
}
$short_date = $date->datetime;
$item['timestamp'] = strtotime($short_date);
$this->items[] = $item;
}
}
/**
* Loads the full article and returns the contents
* @param $uri The article URI
* @return The article content
*/
private function loadFullArticle($uri){
$html = getSimpleHTMLDOMCached($uri);
// Once again, that generated css classes madness is an obstacle ... which i can go over easily
foreach($html->find('div') as $div) {
// List the CSS classes of that div
$classes = $div->class;
// I can't directly lookup that class since GQ since to generate random names like "ArticleBodySection-fkggUW"
if(strpos($classes, 'ArticleBodySection') !== false) {
return $div;
}
}
return null;
}
/**
* Replaces all relative URIs with absolute ones
* @param $element A simplehtmldom element
* @return The $element->innertext with all URIs replaced
*/
private function replaceUriInHtmlElement($element){
$returned = $element->innertext;
foreach (self::REPLACED_ATTRIBUTES as $initial => $final) {
$returned = str_replace($initial . '="/', $final . '="' . self::URI . '/', $returned);
}
return $returned;
}
}

View File

@@ -0,0 +1,164 @@
<?php
class GitHubGistBridge extends BridgeAbstract {
const NAME = 'GitHubGist comment bridge';
const URI = 'https://gist.github.com';
const DESCRIPTION = 'Generates feeds for Gist comments';
const MAINTAINER = 'logmanoriginal';
const CACHE_TIMEOUT = 3600;
const PARAMETERS = array(array(
'id' => array(
'name' => 'Gist',
'type' => 'text',
'required' => true,
'title' => 'Insert Gist ID or URI',
'exampleValue' => '2646763, https://gist.github.com/2646763'
)
));
private $filename;
public function getURI() {
$id = $this->getInput('id') ?: '';
$urlpath = parse_url($id, PHP_URL_PATH);
if($urlpath) {
$components = explode('/', $urlpath);
$id = end($components);
}
return static::URI . '/' . $id;
}
public function getName() {
return $this->filename ? $this->filename . ' - ' . static::NAME : static::NAME;
}
public function collectData() {
$html = getSimpleHTMLDOM($this->getURI(),
null,
null,
true,
true,
DEFAULT_TARGET_CHARSET,
false, // Do NOT remove line breaks
DEFAULT_BR_TEXT,
DEFAULT_SPAN_TEXT)
or returnServerError('Could not request ' . $this->getURI());
$html = defaultLinkTo($html, $this->getURI());
$fileinfo = $html->find('[class="file-info"]', 0)
or returnServerError('Could not find file info!');
$this->filename = $fileinfo->plaintext;
$comments = $html->find('div[class="timeline-comment-wrapper"]');
if(is_null($comments)) { // no comments yet
return;
}
foreach($comments as $comment) {
$uri = $comment->find('a[href*=#gistcomment]', 0)
or returnServerError('Could not find comment anchor!');
$title = $comment->find('div[class="unminimized-comment"] h3[class="timeline-comment-header-text"]', 0)
or returnServerError('Could not find comment header text!');
$datetime = $comment->find('[datetime]', 0)
or returnServerError('Could not find comment datetime!');
$author = $comment->find('a.author', 0)
or returnServerError('Could not find author name!');
$message = $comment->find('[class="comment-body"]', 0)
or returnServerError('Could not find comment body!');
$item = array();
$item['uri'] = $uri->href;
$item['title'] = str_replace('commented', 'commented on', $title->plaintext);
$item['timestamp'] = strtotime($datetime->datetime);
$item['author'] = '<a href="' . $author->href . '">' . $author->plaintext . '</a>';
$item['content'] = $this->fixContent($message);
// $item['enclosures'] = array();
// $item['categories'] = array();
$this->items[] = $item;
}
}
/** Removes all unnecessary tags and adds formatting */
private function fixContent($content){
// Restore code (inside <pre />) highlighting
foreach($content->find('pre') as $pre) {
$pre->style = <<<EOD
padding: 16px;
overflow: auto;
font-size: 85%;
line-height: 1.45;
background-color: #f6f8fa;
border-radius: 3px;
word-wrap: normal;
box-sizing: border-box;
margin-bottom: 16px;
EOD;
$code = $pre->find('code', 0);
if($code) {
$code->style = <<<EOD
white-space: pre;
word-break: normal;
EOD;
}
}
// find <code /> not inside <pre /> (`inline-code`)
foreach($content->find('code') as $code) {
if($code->parent()->tag === 'pre') {
continue;
}
$code->style = <<<EOD
background-color: rgba(27,31,35,0.05);
padding: 0.2em 0.4em;
border-radius: 3px;
EOD;
}
// restore text spacing
foreach($content->find('p') as $p) {
$p->style = 'margin-bottom: 16px;';
}
// Remove unnecessary tags
$content = strip_tags(
$content->innertext,
'<p><a><img><ol><ul><li><table><tr><th><td><string><pre><code><br><hr><h>'
);
return $content;
}
}

View File

@@ -106,7 +106,7 @@ class GithubIssueBridge extends BridgeAbstract {
$content = $comment->parent()->innertext;
} else {
$title .= ' / ' . trim($comment->firstChild()->plaintext);
$content = "<pre>" . $comment->find('.comment-body', 0)->innertext . "</pre>";
$content = '<pre>' . $comment->find('.comment-body', 0)->innertext . '</pre>';
}
$item = array();

View File

@@ -34,13 +34,29 @@ class GithubSearchBridge extends BridgeAbstract {
$title = $element->find('h3', 0)->plaintext;
$item['title'] = $title;
if (count($element->find('p')) == 2) {
$content = $element->find('p', 0)->innertext;
// Description
if (count($element->find('p.d-inline-block')) != 0) {
$content = $element->find('p.d-inline-block', 0)->innertext;
} else{
$content = '';
$content = 'No description';
}
$item['content'] = $content;
// Tags
$content = $content . '<br />';
$tags = $element->find('a.topic-tag');
$tags_array = array();
if (count($tags) != 0) {
$content = $content . 'Tags : ';
foreach($tags as $tag_element) {
$tag_link = 'https://github.com' . $tag_element->href;
$tag_name = trim($tag_element->innertext);
$content = $content . '<a href="' . $tag_link . '">' . $tag_name . '</a> ';
array_push($tags_array, $tag_element->innertext);
}
}
$item['categories'] = $tags_array;
$item['content'] = $content;
$date = $element->find('relative-time', 0)->datetime;
$item['timestamp'] = strtotime($date);

222
bridges/GlassdoorBridge.php Executable file
View File

@@ -0,0 +1,222 @@
<?php
class GlassdoorBridge extends BridgeAbstract {
// Contexts
const CONTEXT_BLOG = 'Blogs';
const CONTEXT_REVIEW = 'Company Reviews';
const CONTEXT_GLOBAL = 'global';
// Global context parameters
const PARAM_LIMIT = 'limit';
// Blog context parameters
const PARAM_BLOG_TYPE = 'blog_type';
const PARAM_BLOG_FULL = 'full_article';
const BLOG_TYPE_HOME = 'Home';
const BLOG_TYPE_COMPANIES_HIRING = 'Companies Hiring';
const BLOG_TYPE_CAREER_ADVICE = 'Career Advice';
const BLOG_TYPE_INTERVIEWS = 'Interviews';
const BLOG_TYPE_GUIDE = 'Guides';
// Review context parameters
const PARAM_REVIEW_COMPANY = 'company';
const MAINTAINER = 'logmanoriginal';
const NAME = 'Glassdoor Bridge';
const URI = 'https://www.glassdoor.com/';
const DESCRIPTION = 'Returns feeds for blog posts and company reviews';
const CACHE_TIMEOUT = 86400; // 24 hours
const PARAMETERS = array(
self::CONTEXT_BLOG => array(
self::PARAM_BLOG_TYPE => array(
'name' => 'Blog type',
'type' => 'list',
'title' => 'Select the blog you want to follow',
'values' => array(
self::BLOG_TYPE_HOME => 'blog/',
self::BLOG_TYPE_COMPANIES_HIRING => 'blog/companies-hiring/',
self::BLOG_TYPE_CAREER_ADVICE => 'blog/career-advice/',
self::BLOG_TYPE_INTERVIEWS => 'blog/interviews/',
self::BLOG_TYPE_GUIDE => 'blog/guide/'
)
),
self::PARAM_BLOG_FULL => array(
'name' => 'Full article',
'type' => 'checkbox',
'title' => 'Enable to return the full article for each post'
),
),
self::CONTEXT_REVIEW => array(
self::PARAM_REVIEW_COMPANY => array(
'name' => 'Company URL',
'type' => 'text',
'required' => true,
'title' => 'Paste the company review page URL here!',
'exampleValue' => 'https://www.glassdoor.com/Reviews/GitHub-Reviews-E671945.htm'
)
),
self::CONTEXT_GLOBAL => array(
self::PARAM_LIMIT => array(
'name' => 'Limit',
'type' => 'number',
'defaultValue' => -1,
'title' => 'Specifies the maximum number of items to return (default: All)'
)
)
);
private $host = self::URI; // They redirect without notice :/
private $title = '';
public function getURI() {
switch($this->queriedContext) {
case self::CONTEXT_BLOG:
return self::URI . $this->getInput(self::PARAM_BLOG_TYPE);
case self::CONTEXT_REVIEW:
return $this->filterCompanyURI($this->getInput(self::PARAM_REVIEW_COMPANY));
}
return parent::getURI();
}
public function getName() {
return $this->title ? $this->title . ' - ' . self::NAME : parent::getName();
}
public function collectData() {
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError('Failed loading contents!');
$this->host = $html->find('link[rel="canonical"]', 0)->href;
$html = defaultLinkTo($html, $this->host);
$this->title = $html->find('meta[property="og:title"]', 0)->content;
$limit = $this->getInput(self::PARAM_LIMIT);
switch($this->queriedContext) {
case self::CONTEXT_BLOG:
$this->collectBlogData($html, $limit);
break;
case self::CONTEXT_REVIEW:
$this->collectReviewData($html, $limit);
break;
}
}
private function collectBlogData($html, $limit) {
$posts = $html->find('section')
or returnServerError('Unable to find blog posts!');
foreach($posts as $post) {
$item = array();
$item['uri'] = $post->find('header a', 0)->href;
$item['title'] = $post->find('header', 0)->plaintext;
$item['content'] = $post->find('div[class="excerpt-content"]', 0)->plaintext;
$item['enclosures'] = array(
$this->getFullSizeImageURI($post->find('div[class="post-thumb"]', 0)->{'data-original'})
);
// optionally load full articles
if($this->getInput(self::PARAM_BLOG_FULL)) {
$full_html = getSimpleHTMLDOMCached($item['uri'])
or returnServerError('Unable to load full article!');
$full_html = defaultLinkTo($full_html, $this->host);
$item['author'] = $full_html->find('a[rel="author"]', 0);
$item['content'] = $full_html->find('article', 0);
$item['timestamp'] = strtotime($full_html->find('time.updated', 0)->datetime);
$item['categories'] = $full_html->find('span[class="post_tag"]');
}
$this->items[] = $item;
if($limit > 0 && count($this->items) >= $limit)
return;
}
}
private function collectReviewData($html, $limit) {
$reviews = $html->find('#EmployerReviews li[id^="empReview]')
or returnServerError('Unable to find reviews!');
foreach($reviews as $review) {
$item = array();
$item['uri'] = $review->find('a.reviewLink', 0)->href;
$item['title'] = $review->find('[class="summary"]', 0)->plaintext;
$item['author'] = $review->find('div.author span', 0)->plaintext;
$item['timestamp'] = strtotime($review->find('time', 0)->datetime);
$mainText = $review->find('p.mainText', 0)->plaintext;
$description = $review->find('div.prosConsAdvice', 0)->innertext;
$item['content'] = "<p>{$mainText}</p><p>{$description}</p>";
$this->items[] = $item;
if($limit > 0 && count($this->items) >= $limit)
return;
}
}
private function getFullSizeImageURI($uri) {
/* Images are scaled for display on the website. The scaling takes place
* on the host, who provides images in different sizes.
*
* For example:
* https://www.glassdoor.com/blog/app/uploads/sites/2/GettyImages-982402074-e1538092065712-390x193.jpg
*
* By removing the size information we receive the full sized image.
*
* For example:
* https://www.glassdoor.com/blog/app/uploads/sites/2/GettyImages-982402074-e1538092065712.jpg
*/
$uri = filter_var($uri, FILTER_SANITIZE_URL);
return preg_replace('/(.*)(\-\d+x\d+)(\.jpg)/', '$1$3', $uri);
}
private function filterCompanyURI($uri) {
/* Make sure the URI is a valid review page. Unfortunately there is no
* simple way to determine if the URI is valid, because of automagic
* redirection and strange naming conventions.
*/
if(!filter_var($uri,
FILTER_VALIDATE_URL,
FILTER_FLAG_SCHEME_REQUIRED | FILTER_FLAG_HOST_REQUIRED | FILTER_FLAG_PATH_REQUIRED)) {
returnClientError('The specified URL is invalid!');
}
$uri = filter_var($uri, FILTER_SANITIZE_URL);
$path = parse_url($uri, PHP_URL_PATH);
$parts = explode('/', $path);
$allowed_strings = array(
'de-DE' => 'Bewertungen',
'en-AU' => 'Reviews',
'nl-BE' => 'Reviews',
'fr-BE' => 'Avis',
'en-CA' => 'Reviews',
'fr-CA' => 'Avis',
'fr-FR' => 'Avis',
'en-IN' => 'Reviews',
'en-IE' => 'Reviews',
'nl-NL' => 'Reviews',
'de-AT' => 'Bewertungen',
'de-CH' => 'Bewertungen',
'fr-CH' => 'Avis',
'en-GB' => 'Reviews',
'en' => 'Reviews'
);
if(!in_array($parts[1], $allowed_strings)) {
returnClientError('Please specify a URL pointing to the companies review page!');
}
return $uri;
}
}

View File

@@ -3,7 +3,7 @@ class GoComicsBridge extends BridgeAbstract {
const MAINTAINER = 'sky';
const NAME = 'GoComics Unofficial RSS';
const URI = 'http://www.gocomics.com/';
const URI = 'https://www.gocomics.com/';
const CACHE_TIMEOUT = 21600; // 6h
const DESCRIPTION = 'The Unofficial GoComics RSS';
const PARAMETERS = array( array(
@@ -18,25 +18,27 @@ class GoComicsBridge extends BridgeAbstract {
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError('Could not request GoComics: ' . $this->getURI());
foreach($html->find('div.comic__container') as $element) {
//Get info from first page
$author = preg_replace('/By /', '', $html->find('.media-subheading', 0)->plaintext);
$img = $element->find('.item-comic-image img', 0);
$link = $element->find('a.js-item-comic-link', 0);
$comic = $img->src;
$title = $link->title;
$url = $html->find('input.js-copy-link', 0)->value;
$date = substr($title, -10);
if (empty($title))
$title = 'GoComics ' . $this->getInput('comicname') . ' on ' . $date;
$date = strtotime($date);
$link = self::URI . $html->find('.gc-deck--cta-0', 0)->find('a', 0)->href;
for($i = 0; $i < 5; $i++) {
$item = array();
$item['id'] = $url;
$item['uri'] = $url;
$item['title'] = $title;
$item['author'] = preg_replace('/by /', '', $element->find('a.link-blended small', 0)->plaintext);
$item['timestamp'] = $date;
$item['content'] = '<img src="' . $comic . '" alt="' . $title . '" />';
$page = getSimpleHTMLDOM($link)
or returnServerError('Could not request GoComics: ' . $link);
$imagelink = $page->find('.img-fluid', 1)->src;
$date = explode('/', $link);
$item['id'] = $imagelink;
$item['uri'] = $link;
$item['author'] = $author;
$item['title'] = 'GoComics ' . $this->getInput('comicname');
$item['timestamp'] = DateTime::createFromFormat('Ymd', $date[5] . $date[6] . $date[7])->getTimestamp();
$item['content'] = '<img src="' . $imagelink . '" />';
$link = self::URI . $page->find('.js-previous-comic', 0)->href;
$this->items[] = $item;
}
}

View File

@@ -1,12 +1,12 @@
<?php
class GooglePlusPostBridge extends BridgeAbstract{
protected $_title;
protected $_url;
private $title;
private $url;
const MAINTAINER = 'Grummfy';
const MAINTAINER = 'Grummfy, logmanoriginal';
const NAME = 'Google Plus Post Bridge';
const URI = 'https://plus.google.com/';
const URI = 'https://plus.google.com';
const CACHE_TIMEOUT = 600; //10min
const DESCRIPTION = 'Returns user public post (without API).';
@@ -14,10 +14,20 @@ class GooglePlusPostBridge extends BridgeAbstract{
'username' => array(
'name' => 'username or Id',
'required' => true
),
'include_media' => array(
'name' => 'Include media',
'type' => 'checkbox',
'title' => 'Enable to include media in the feed content'
)
));
public function getIcon() {
return 'https://ssl.gstatic.com/images/branding/product/ico/google_plus_alldp.ico';
}
public function collectData(){
$username = $this->getInput('username');
// Usernames start with a + if it's not an ID
@@ -25,22 +35,20 @@ class GooglePlusPostBridge extends BridgeAbstract{
$username = '+' . $username;
}
// get content parsed
$html = getSimpleHTMLDOMCached(self::URI . urlencode($username) . '/posts')
$html = getSimpleHTMLDOM(static::URI . '/' . urlencode($username) . '/posts')
or returnServerError('No results for this query.');
// get title, url, ... there is a lot of intresting stuff in meta
$this->_title = $html->find('meta[property=og:title]', 0)->getAttribute('content');
$this->_url = $html->find('meta[property=og:url]', 0)->getAttribute('content');
$html = defaultLinkTo($html, static::URI);
$this->title = $html->find('meta[property=og:title]', 0)->getAttribute('content');
$this->url = $html->find('meta[property=og:url]', 0)->getAttribute('content');
// I don't even know where to start with this discusting html...
foreach($html->find('div[jsname=WsjYwc]') as $post) {
$item = array();
$item['author'] = $item['fullname'] = $post->find('div div div div a', 0)->innertext;
$item['id'] = $post->find('div div div', 0)->getAttribute('id');
$item['avatar'] = $post->find('div img', 0)->src;
$item['uri'] = self::URI . $post->find('div div div a', 1)->href;
$item['author'] = $post->find('div div div div a', 0)->innertext;
$item['uri'] = $post->find('div div div a', 1)->href;
$timestamp = $post->find('a.qXj2He span', 0);
@@ -51,61 +59,151 @@ class GooglePlusPostBridge extends BridgeAbstract{
$timestamp->getAttribute('aria-label')));
}
// hashtag to treat : https://plus.google.com/explore/tag
// $hashtags = array();
// foreach($post->find('a.d-s') as $hashtag){
// $hashtags[trim($hashtag->plaintext)] = self::URI . $hashtag->href;
// }
$message = $post->find('div[jsname=EjRJtf]', 0);
$item['content'] = '';
// Empty messages are not supported right now
if(!$message) {
continue;
}
// avatar display
$item['content'] .= '<div style="float:left; margin: 0 0.5em 0.5em 0;"><a href="'
. self::URI
. urlencode($this->getInput('username'));
$item['content'] .= '"><img align="top" alt="'
$item['content'] = '<div style="float: left; padding: 0 10px 10px 0;"><a href="'
. $this->url
. '"><img align="top" alt="'
. $item['author']
. '" src="'
. $item['avatar']
. '" /></a></div>';
. $post->find('div img', 0)->src
. '" /></a></div><div>'
. trim(strip_tags($message, '<a><p><div><img>'))
. '</div>';
$content = $post->find('div[jsname=EjRJtf]', 0);
// extract plaintext
$item['content_simple'] = $content->plaintext;
$item['title'] = substr($item['content_simple'], 0, 72) . '...';
// XXX ugly but I don't have any idea how to do a better stuff,
// str_replace on link doesn't work as expected and ask too many checks
foreach($content->find('a') as $link) {
$hasHttp = strpos($link->href, 'http');
$hasDoubleSlash = strpos($link->href, '//');
if((!$hasHttp && !$hasDoubleSlash)
|| (false !== $hasHttp && strpos($link->href, 'http') != 0)
|| (false === $hasHttp && false !== $hasDoubleSlash && $hasDoubleSlash != 0)) {
// skipp bad link, for some hashtag or other stuff
if(strpos($link->href, '/') == 0) {
$link->href = substr($link->href, 1);
}
$link->href = self::URI . $link->href;
}
// Make title at least 50 characters long, but don't add '...' if it is shorter!
if(strlen($message->plaintext) > 50) {
$end = strpos($message->plaintext, ' ', 50) ?: strlen($message->plaintext);
} else {
$end = strlen($message->plaintext);
}
$content = $content->innertext;
$item['content'] .= '<div style="margin-top: -1.5em">' . $content . '</div>';
$item['content'] = trim(strip_tags($item['content'], '<a><p><div><img>'));
if(strlen(substr($message->plaintext, 0, $end)) === strlen($message->plaintext)) {
$item['title'] = $message->plaintext;
} else {
$item['title'] = substr($message->plaintext, 0, $end) . '...';
}
$media = $post->find('[jsname="MTOxpb"]', 0);
if($media) {
$item['enclosures'] = array();
foreach($media->find('img') as $img) {
$item['enclosures'][] = $this->fixImage($img)->src;
}
if($this->getInput('include_media') === true && count($item['enclosures'] > 0)) {
$item['content'] .= '<div style="clear: both;"><a href="'
. $item['enclosures'][0]
. '"><img src="'
. $item['enclosures'][0]
. '" /></a></div>';
}
}
// Add custom parameters (only useful for JSON or Plaintext)
$item['fullname'] = $item['author'];
$item['avatar'] = $post->find('div img', 0)->src;
$item['id'] = $post->find('div div div', 0)->getAttribute('id');
$item['content_simple'] = $message->plaintext;
$this->items[] = $item;
}
}
public function getName(){
return $this->_title ?: 'Google Plus Post Bridge';
return $this->title ?: 'Google Plus Post Bridge';
}
public function getURI(){
return $this->_url ?: parent::getURI();
return $this->url ?: parent::getURI();
}
private function fixImage($img) {
// There are certain images like .gif which link to a static picture and
// get replaced dynamically via JS in the browser. If we want the "real"
// image we need to account for that.
$urlparts = parse_url($img->src);
if(array_key_exists('host', $urlparts)) {
// For some reason some URIs don't contain the scheme, assume https
if(!array_key_exists('scheme', $urlparts)) {
$urlparts['scheme'] = 'https';
}
$pathelements = explode('/', $urlparts['path']);
switch($urlparts['host']) {
case 'lh3.googleusercontent.com':
if(pathinfo(end($pathelements), PATHINFO_EXTENSION)) {
// The second to last element of the path specifies the
// image format. The URL is still valid if we remove it.
unset($pathelements[count($pathelements) - 2]);
} elseif(strrpos(end($pathelements), '=') !== false) {
// Some images go throug a proxy. For those images they
// add size information after an equal sign.
// Example: '=w530-h298-n'. Again this can safely be
// removed to get the original image.
$pathelements[count($pathelements) - 1] = substr(
end($pathelements),
0,
strrpos(end($pathelements), '=')
);
}
break;
}
$urlparts['path'] = implode('/', $pathelements);
}
$img->src = $this->build_url($urlparts);
return $img;
}
/**
* From: https://gist.github.com/Ellrion/f51ba0d40ae1d62eeae44fd1adf7b704
* slightly adjusted to work with PHP < 7.0
* @param array $parts
* @return string
*/
private function build_url(array $parts)
{
$scheme = isset($parts['scheme']) ? ($parts['scheme'] . '://') : '';
$host = isset($parts['host']) ? $parts['host'] : '';
$port = isset($parts['port']) ? (':' . $parts['port']) : '';
$user = isset($parts['user']) ? $parts['user'] : '';
$pass = isset($parts['pass']) ? (':' . $parts['pass']) : '';
$pass = ($user || $pass) ? ($pass . '@') : '';
$path = isset($parts['path']) ? $parts['path'] : '';
$query = isset($parts['query']) ? ('?' . $parts['query']) : '';
$fragment = isset($parts['fragment']) ? ('#' . $parts['fragment']) : '';
return implode('', [$scheme, $user, $pass, $host, $port, $path, $query, $fragment]);
}
}

View File

@@ -17,7 +17,7 @@ class GoogleSearchBridge extends BridgeAbstract {
const PARAMETERS = array(array(
'q' => array(
'name' => "keyword",
'name' => 'keyword',
'required' => true
)
));
@@ -28,7 +28,7 @@ class GoogleSearchBridge extends BridgeAbstract {
$html = getSimpleHTMLDOM(self::URI
. 'search?q='
. urlencode($this->getInput('q'))
.'&num=100&complete=0&tbs=qdr:y,sbd:1')
. '&num=100&complete=0&tbs=qdr:y,sbd:1')
or returnServerError('No results for this query.');
$emIsRes = $html->find('div[id=ires]', 0);

View File

@@ -0,0 +1,62 @@
<?php
class GrandComicsDatabaseBridge extends BridgeAbstract {
const MAINTAINER = 'corenting';
const NAME = 'Grand Comics Database Bridge';
const URI = 'https://www.comics.org/';
const CACHE_TIMEOUT = 7200; // 2h
const DESCRIPTION = 'Returns the latest comics added to a series timeline';
const PARAMETERS = array( array(
'series' => array(
'name' => 'Series id (from the timeline URL)',
'required' => true,
'exampleValue' => '63051',
),
));
public function collectData(){
$url = self::URI . 'series/' . $this->getInput('series') . '/details/timeline/';
$html = getSimpleHTMLDOM($url)
or returnServerError('Error while downloading the website content');
$table = $html->find('table', 0);
$list = array_reverse($table->find('[class^=row_even]'));
$seriesName = $html->find('span[id=series_name]', 0)->innertext;
// Get row headers
$rowHeaders = $table->find('th');
foreach($list as $article) {
// Skip empty rows
$emptyRow = $article->find('td.empty_month');
if (count($emptyRow) != 0) {
continue;
}
$rows = $article->find('td');
$key_date = $rows[0]->innertext;
// Get URL too
$uri = 'https://www.comics.org' . $article->find('a')[0]->href;
// Build content
$content = '';
for($i = 0; $i < count($rowHeaders); $i++) {
$headerItem = $rowHeaders[$i]->innertext;
$rowItem = $rows[$i]->innertext;
$content = $content . $headerItem . ': ' . $rowItem . '<br/>';
}
// Build final item
$content = str_replace('href="/', 'href="' . static::URI, $content);
$item = array();
$item['title'] = $seriesName . ' - ' . $key_date;
$item['timestamp'] = strtotime($key_date);
$item['content'] = str_get_html($content);
$item['uri'] = $uri;
$this->items[] = $item;
}
}
}

1397
bridges/HotUKDealsBridge.php Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -18,8 +18,8 @@ class IPBBridge extends FeedExpander {
'name' => 'Limit',
'type' => 'number',
'required' => false,
'title' => 'Specify how many pages should be fetched (-1: all)',
'defaultValue' => 1
'title' => 'Specifies the number of items to return on each request (-1: all)',
'defaultValue' => 10
)
)
);
@@ -161,15 +161,18 @@ class IPBBridge extends FeedExpander {
$next = null; // Holds the URI of the next page
do {
// Skip loading HTML on first iteration
if(!is_null($next)) {
$html = getSimpleHTMLDOMCached($next);
while(true) {
$next = $this->$callback($html, is_null($next));
if(is_null($next) || ($limit > 0 && count($this->items) >= $limit)) {
break;
}
$next = $this->$callback($html, is_null($next));
$limit--;
} while(!is_null($next) && $limit <> 0);
$html = getSimpleHTMLDOMCached($next);
}
// We might have more items than specified, remove excess
$this->items = array_slice($this->items, 0, $limit);
}
private function collectTopicArticle($html, $firstrun = true){

View File

@@ -3,78 +3,137 @@ class InstagramBridge extends BridgeAbstract {
const MAINTAINER = 'pauder';
const NAME = 'Instagram Bridge';
const URI = 'https://instagram.com/';
const URI = 'https://www.instagram.com/';
const DESCRIPTION = 'Returns the newest images';
const PARAMETERS = array( array(
'u' => array(
'name' => 'username',
'required' => true
const PARAMETERS = array(
array(
'u' => array(
'name' => 'username',
'required' => true
)
),
'media_type' => array(
'name' => 'Media type',
'type' => 'list',
'required' => false,
'values' => array(
'Both' => 'all',
'Video' => 'video',
'Picture' => 'picture'
),
'defaultValue' => 'all'
array(
'h' => array(
'name' => 'hashtag',
'required' => true
)
),
'global' => array(
'media_type' => array(
'name' => 'Media type',
'type' => 'list',
'required' => false,
'values' => array(
'All' => 'all',
'Story' => 'story',
'Video' => 'video',
'Picture' => 'picture',
),
'defaultValue' => 'all'
)
)
));
);
public function collectData(){
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError('Could not request Instagram.');
$innertext = null;
foreach($html->find('script') as $script) {
if('' === $script->innertext) {
continue;
}
$pos = strpos(trim($script->innertext), 'window._sharedData');
if(0 !== $pos) {
continue;
}
$innertext = $script->innertext;
break;
if(!is_null($this->getInput('h')) && $this->getInput('media_type') == 'story') {
returnClientError('Stories are not supported for hashtags!');
}
$json = trim(substr($innertext, $pos + 18), ' =;');
$data = json_decode($json);
$data = $this->getInstagramJSON($this->getURI());
$userMedia = $data->entry_data->ProfilePage[0]->user->media->nodes;
if(!is_null($this->getInput('u'))) {
$userMedia = $data->entry_data->ProfilePage[0]->graphql->user->edge_owner_to_timeline_media->edges;
} else {
$userMedia = $data->entry_data->TagPage[0]->graphql->hashtag->edge_hashtag_to_media->edges;
}
foreach($userMedia as $media) {
// Check media type
switch($this->getInput('media_type')) {
case 'all': break;
case 'video':
if($media->is_video === false) continue 2;
break;
case 'picture':
if($media->is_video === true) continue 2;
break;
default: break;
$media = $media->node;
if(!is_null($this->getInput('u'))) {
switch($this->getInput('media_type')) {
case 'all': break;
case 'video':
if($media->__typename != 'GraphVideo') continue 2;
break;
case 'picture':
if($media->__typename != 'GraphImage') continue 2;
break;
case 'story':
if($media->__typename != 'GraphSidecar') continue 2;
break;
default: break;
}
} else {
if($this->getInput('media_type') == 'video' && !$media->is_video) continue;
}
$item = array();
$item['uri'] = self::URI . 'p/' . $media->code . '/';
$item['content'] = '<img src="' . htmlentities($media->display_src) . '" />';
if (isset($media->caption)) {
$item['title'] = $media->caption;
$item['uri'] = self::URI . 'p/' . $media->shortcode . '/';
if (isset($media->edge_media_to_caption->edges[0]->node->text)) {
$item['title'] = $media->edge_media_to_caption->edges[0]->node->text;
} else {
$item['title'] = basename($media->display_src);
$item['title'] = basename($media->display_url);
}
$item['timestamp'] = $media->date;
if(!is_null($this->getInput('u')) && $media->__typename == 'GraphSidecar') {
$data = $this->getInstagramStory($item['uri']);
$item['content'] = $data[0];
$item['enclosures'] = $data[1];
} else {
$item['content'] = '<img src="' . htmlentities($media->display_url) . '" alt="' . $item['title'] . '" />';
$item['enclosures'] = array($media->display_url);
}
$item['timestamp'] = $media->taken_at_timestamp;
$this->items[] = $item;
}
}
protected function getInstagramStory($uri) {
$data = $this->getInstagramJSON($uri);
$mediaInfo = $data->entry_data->PostPage[0]->graphql->shortcode_media;
//Process the first element, that isn't in the node graph
if (count($mediaInfo->edge_media_to_caption->edges) > 0) {
$caption = $mediaInfo->edge_media_to_caption->edges[0]->node->text;
} else {
$caption = '';
}
$enclosures = [$mediaInfo->display_url];
$content = '<img src="' . htmlentities($mediaInfo->display_url) . '" alt="' . $caption . '" />';
foreach($mediaInfo->edge_sidecar_to_children->edges as $media) {
$display_url = $media->node->display_url;
if(!in_array($display_url, $enclosures)) { // add only if not added yet
$content .= '<img src="' . htmlentities($display_url) . '" alt="' . $caption . '" />';
$enclosures[] = $display_url;
}
}
return [$content, $enclosures];
}
protected function getInstagramJSON($uri) {
$html = getContents($uri)
or returnServerError('Could not request Instagram.');
$scriptRegex = '/window\._sharedData = (.*);<\/script>/';
preg_match($scriptRegex, $html, $matches, PREG_OFFSET_CAPTURE, 0);
return json_decode($matches[1][0]);
}
public function getName(){
if(!is_null($this->getInput('u'))) {
return $this->getInput('u') . ' - Instagram Bridge';
@@ -85,7 +144,9 @@ class InstagramBridge extends BridgeAbstract {
public function getURI(){
if(!is_null($this->getInput('u'))) {
return self::URI . urlencode($this->getInput('u'));
return self::URI . urlencode($this->getInput('u')) . '/';
} elseif(!is_null($this->getInput('h'))) {
return self::URI . 'explore/tags/' . urlencode($this->getInput('h'));
}
return parent::getURI();

View File

@@ -0,0 +1,370 @@
<?php
/**
* This class implements a bridge for http://www.instructables.com, supporting
* general feeds and feeds by category. Instructables doesn't support HTTPS as
* of now (23.06.2018), so all connections are insecure!
*
* Remarks:
* - For some reason it is very important to have the category URI end with a
* slash, otherwise the site defaults to the main category (i.e. Technology)!
* If you need to update the categories list, enable the 'listCategories'
* function (see comments below) and run the bridge with format=Html (see page
* source)
*/
class InstructablesBridge extends BridgeAbstract {
const NAME = 'Instructables Bridge';
const URI = 'http://www.instructables.com';
const DESCRIPTION = 'Returns general feeds and feeds by category';
const MAINTAINER = 'logmanoriginal';
const PARAMETERS = array(
'Category' => array(
'category' => array(
'name' => 'Category',
'type' => 'list',
'required' => true,
'values' => array(
'Play' => array(
'All' => '/play/',
'KNEX' => '/play/knex/',
'Offbeat' => '/play/offbeat/',
'Lego' => '/play/lego/',
'Airsoft' => '/play/airsoft/',
'Card Games' => '/play/card-games/',
'Guitars' => '/play/guitars/',
'Instruments' => '/play/instruments/',
'Magic Tricks' => '/play/magic-tricks/',
'Minecraft' => '/play/minecraft/',
'Music' => '/play/music/',
'Nerf' => '/play/nerf/',
'Nintendo' => '/play/nintendo/',
'Office Supplies' => '/play/office-supplies/',
'Paintball' => '/play/paintball/',
'Paper Airplanes' => '/play/paper-airplanes/',
'Party Tricks' => '/play/party-tricks/',
'PlayStation' => '/play/playstation/',
'Pranks and Humor' => '/play/pranks-and-humor/',
'Puzzles' => '/play/puzzles/',
'Siege Engines' => '/play/siege-engines/',
'Sports' => '/play/sports/',
'Table Top' => '/play/table-top/',
'Toys' => '/play/toys/',
'Video Games' => '/play/video-games/',
'Wii' => '/play/wii/',
'Xbox' => '/play/xbox/',
'Yo-Yo' => '/play/yo-yo/',
),
'Craft' => array(
'All' => '/craft/',
'Art' => '/craft/art/',
'Sewing' => '/craft/sewing/',
'Paper' => '/craft/paper/',
'Jewelry' => '/craft/jewelry/',
'Fashion' => '/craft/fashion/',
'Books & Journals' => '/craft/books-and-journals/',
'Cards' => '/craft/cards/',
'Clay' => '/craft/clay/',
'Duct Tape' => '/craft/duct-tape/',
'Embroidery' => '/craft/embroidery/',
'Felt' => '/craft/felt/',
'Fiber Arts' => '/craft/fiber-arts/',
'Gifts & Wrapping' => '/craft/gifts-and-wrapping/',
'Knitting & Crocheting' => '/craft/knitting-and-crocheting/',
'Leather' => '/craft/leather/',
'Mason Jars' => '/craft/mason-jars/',
'No-Sew' => '/craft/no-sew/',
'Parties & Weddings' => '/craft/parties-and-weddings/',
'Print Making' => '/craft/print-making/',
'Soap' => '/craft/soap/',
'Wallets' => '/craft/wallets/',
),
'Technology' => array(
'All' => '/technology/',
'Electronics' => '/technology/electronics/',
'Arduino' => '/technology/arduino/',
'Photography' => '/technology/photography/',
'Leds' => '/technology/leds/',
'Science' => '/technology/science/',
'Reuse' => '/technology/reuse/',
'Apple' => '/technology/apple/',
'Computers' => '/technology/computers/',
'3D Printing' => '/technology/3D-Printing/',
'Robots' => '/technology/robots/',
'Art' => '/technology/art/',
'Assistive Tech' => '/technology/assistive-technology/',
'Audio' => '/technology/audio/',
'Clocks' => '/technology/clocks/',
'CNC' => '/technology/cnc/',
'Digital Graphics' => '/technology/digital-graphics/',
'Gadgets' => '/technology/gadgets/',
'Kits' => '/technology/kits/',
'Laptops' => '/technology/laptops/',
'Lasers' => '/technology/lasers/',
'Linux' => '/technology/linux/',
'Microcontrollers' => '/technology/microcontrollers/',
'Microsoft' => '/technology/microsoft/',
'Mobile' => '/technology/mobile/',
'Raspberry Pi' => '/technology/raspberry-pi/',
'Remote Control' => '/technology/remote-control/',
'Sensors' => '/technology/sensors/',
'Software' => '/technology/software/',
'Soldering' => '/technology/soldering/',
'Speakers' => '/technology/speakers/',
'Steampunk' => '/technology/steampunk/',
'Tools' => '/technology/tools/',
'USB' => '/technology/usb/',
'Wearables' => '/technology/wearables/',
'Websites' => '/technology/websites/',
'Wireless' => '/technology/wireless/',
),
'Workshop' => array(
'All' => '/workshop/',
'Woodworking' => '/workshop/woodworking/',
'Tools' => '/workshop/tools/',
'Gardening' => '/workshop/gardening/',
'Cars' => '/workshop/cars/',
'Metalworking' => '/workshop/metalworking/',
'Cardboard' => '/workshop/cardboard/',
'Electric Vehicles' => '/workshop/electric-vehicles/',
'Energy' => '/workshop/energy/',
'Furniture' => '/workshop/furniture/',
'Home Improvement' => '/workshop/home-improvement/',
'Home Theater' => '/workshop/home-theater/',
'Hydroponics' => '/workshop/hydroponics/',
'Laser Cutting' => '/workshop/laser-cutting/',
'Lighting' => '/workshop/lighting/',
'Molds & Casting' => '/workshop/molds-and-casting/',
'Motorcycles' => '/workshop/motorcycles/',
'Organizing' => '/workshop/organizing/',
'Pallets' => '/workshop/pallets/',
'Repair' => '/workshop/repair/',
'Shelves' => '/workshop/shelves/',
'Solar' => '/workshop/solar/',
'Workbenches' => '/workshop/workbenches/',
),
'Home' => array(
'All' => '/home/',
'Halloween' => '/home/halloween/',
'Decorating' => '/home/decorating/',
'Organizing' => '/home/organizing/',
'Pets' => '/home/pets/',
'Life Hacks' => '/home/life-hacks/',
'Beauty' => '/home/beauty/',
'Christmas' => '/home/christmas/',
'Cleaning' => '/home/cleaning/',
'Education' => '/home/education/',
'Finances' => '/home/finances/',
'Gardening' => '/home/gardening/',
'Green' => '/home/green/',
'Health' => '/home/health/',
'Hiding Places' => '/home/hiding-places/',
'Holidays' => '/home/holidays/',
'Homesteading' => '/home/homesteading/',
'Kids' => '/home/kids/',
'Kitchen' => '/home/kitchen/',
'Life Skills' => '/home/life-skills/',
'Parenting' => '/home/parenting/',
'Pest Control' => '/home/pest-control/',
'Relationships' => '/home/relationships/',
'Reuse' => '/home/reuse/',
'Travel' => '/home/travel/',
),
'Outside' => array(
'All' => '/outside/',
'Bikes' => '/outside/bikes/',
'Survival' => '/outside/survival/',
'Backyard' => '/outside/backyard/',
'Beach' => '/outside/beach/',
'Birding' => '/outside/birding/',
'Boats' => '/outside/boats/',
'Camping' => '/outside/camping/',
'Climbing' => '/outside/climbing/',
'Fire' => '/outside/fire/',
'Fishing' => '/outside/fishing/',
'Hunting' => '/outside/hunting/',
'Kites' => '/outside/kites/',
'Knives' => '/outside/knives/',
'Knots' => '/outside/knots/',
'Paracord' => '/outside/paracord/',
'Rockets' => '/outside/rockets/',
'Skateboarding' => '/outside/skateboarding/',
'Snow' => '/outside/snow/',
'Water' => '/outside/water/',
),
'Food' => array(
'All' => '/food/',
'Dessert' => '/food/dessert/',
'Snacks & Appetizers' => '/food/snacks-and-appetizers/',
'Bacon' => '/food/bacon/',
'BBQ & Grilling' => '/food/bbq-and-grilling/',
'Beverages' => '/food/beverages/',
'Bread' => '/food/bread/',
'Breakfast' => '/food/breakfast/',
'Cake' => '/food/cake/',
'Candy' => '/food/candy/',
'Canning & Preserves' => '/food/canning-and-preserves/',
'Cocktails & Mocktails' => '/food/cocktails-and-mocktails/',
'Coffee' => '/food/coffee/',
'Cookies' => '/food/cookies/',
'Cupcakes' => '/food/cupcakes/',
'Homebrew' => '/food/homebrew/',
'Main Course' => '/food/main-course/',
'Pasta' => '/food/pasta/',
'Pie' => '/food/pie/',
'Pizza' => '/food/pizza/',
'Salad' => '/food/salad/',
'Sandwiches' => '/food/sandwiches/',
'Soups & Stews' => '/food/soups-and-stews/',
'Vegetarian & Vegan' => '/food/vegetarian-and-vegan/',
),
'Costumes' => array(
'All' => '/costumes/',
'Props' => '/costumes/props-and-accessories/',
'Animals' => '/costumes/animals/',
'Comics' => '/costumes/comics/',
'Fantasy' => '/costumes/fantasy/',
'For Kids' => '/costumes/for-kids/',
'For Pets' => '/costumes/for-pets/',
'Funny' => '/costumes/funny/',
'Games' => '/costumes/games/',
'Historic & Futuristic' => '/costumes/historic-and-futuristic/',
'Makeup' => '/costumes/makeup/',
'Masks' => '/costumes/masks/',
'Scary' => '/costumes/scary/',
'TV & Movies' => '/costumes/tv-and-movies/',
'Weapons & Armor' => '/costumes/weapons-and-armor/',
)
),
'title' => 'Select your category (required)',
'defaultValue' => 'Technology'
),
'filter' => array(
'name' => 'Filter',
'type' => 'list',
'required' => true,
'values' => array(
'Featured' => ' ',
'Recent' => 'recent/',
'Popular' => 'popular/',
'Views' => 'views/',
'Contest Winners' => 'winners/'
),
'title' => 'Select a filter',
'defaultValue' => 'Featured'
)
)
);
private $uri;
public function collectData() {
// Enable the following line to get the category list (dev mode)
// $this->listCategories();
$this->uri = static::URI;
switch($this->queriedContext) {
case 'Category': $this->uri .= $this->getInput('category') . $this->getInput('filter');
}
$html = getSimpleHTMLDOM($this->uri)
or returnServerError('Error loading category ' . $this->uri);
foreach($html->find('ul.explore-covers-list li') as $cover) {
$item = array();
$item['uri'] = static::URI . $cover->find('a.cover-image', 0)->href;
$item['title'] = $cover->find('.title', 0)->innertext;
$item['author'] = $this->getCategoryAuthor($cover);
$item['content'] = '<a href='
. $item['uri']
. '><img src='
. $cover->find('a.cover-image img', 0)->src
. '></a>';
$image = str_replace('.RECTANGLE1', '.LARGE', $cover->find('a.cover-image img', 0)->src);
$item['enclosures'] = [$image];
$this->items[] = $item;
}
}
public function getName() {
if(!is_null($this->getInput('category'))
&& !is_null($this->getInput('filter'))) {
foreach(self::PARAMETERS[$this->queriedContext]['category']['values'] as $key => $value) {
$subcategory = array_search($this->getInput('category'), $value);
if($subcategory !== false)
break;
}
$filter = array_search(
$this->getInput('filter'),
self::PARAMETERS[$this->queriedContext]['filter']['values']
);
return $subcategory . ' (' . $filter . ') - ' . static::NAME;
}
return parent::getName();
}
public function getURI() {
if(!is_null($this->getInput('category'))
&& !is_null($this->getInput('filter'))) {
return $this->uri;
}
return parent::getURI();
}
/**
* Returns a list of categories for development purposes (used to build the
* parameters list)
*/
private function listCategories(){
// Use arbitrary category to receive full list
$html = getSimpleHTMLDOM(self::URI . '/technology/');
foreach($html->find('.channel a') as $channel) {
$name = html_entity_decode(trim($channel->innertext));
// Remove unwanted entities
$name = str_replace("'", '', $name);
$name = str_replace('&#39;', '', $name);
$uri = $channel->href;
$category = explode('/', $uri)[1];
if(!isset($categories)
|| !array_key_exists($category, $categories)
|| !in_array($uri, $categories[$category]))
$categories[$category][$name] = $uri;
}
// Build PHP array manually
foreach($categories as $key => $value) {
$name = ucfirst($key);
echo "'{$name}' => array(\n";
echo "\t'All' => '/{$key}/',\n";
foreach($value as $name => $uri) {
echo "\t'{$name}' => '{$uri}',\n";
}
echo "),\n";
}
die;
}
/**
* Returns the author as anchor for a given cover.
*/
private function getCategoryAuthor($cover) {
return '<a href='
. static::URI . $cover->find('span.author a', 0)->href
. '>'
. $cover->find('span.author a', 0)->innertext
. '</a>';
}
}

View File

@@ -1,465 +0,0 @@
<?php
class IsoHuntBridge extends BridgeAbstract {
const MAINTAINER = 'logmanoriginal';
const NAME = 'isoHunt Bridge';
const URI = 'https://isohunt.to/';
const CACHE_TIMEOUT = 300; //5min
const DESCRIPTION = 'Returns the latest results by category or search result';
const PARAMETERS = array(
/*
* Get feeds for one of the "latest" categories
* Notice: The categories "News" and "Top Searches" are received from the main page
* Elements are sorted by name ascending!
*/
'By "Latest" category' => array(
'latest_category' => array(
'name' => 'Latest category',
'type' => 'list',
'required' => true,
'title' => 'Select your category',
'defaultValue' => 'news',
'values' => array(
'Hot Torrents' => 'hot_torrents',
'News' => 'news',
'Releases' => 'releases',
'Torrents' => 'torrents'
)
)
),
/*
* Get feeds for one of the "torrent" categories
* Make sure to add new categories also to get_torrent_category_index($)!
* Elements are sorted by name ascending!
*/
'By "Torrent" category' => array(
'torrent_category' => array(
'name' => 'Torrent category',
'type' => 'list',
'required' => true,
'title' => 'Select your category',
'defaultValue' => 'anime',
'values' => array(
'Adult' => 'adult',
'Anime' => 'anime',
'Books' => 'books',
'Games' => 'games',
'Movies' => 'movies',
'Music' => 'music',
'Other' => 'other',
'Series & TV' => 'series_tv',
'Software' => 'software'
)
),
'torrent_popularity' => array(
'name' => 'Sort by popularity',
'type' => 'checkbox',
'title' => 'Activate to receive results by popularity'
)
),
/*
* Get feeds for a specific search request
*/
'Search torrent by name' => array(
'search_name' => array(
'name' => 'Name',
'required' => true,
'title' => 'Insert your search query',
'exampleValue' => 'Bridge'
),
'search_category' => array(
'name' => 'Category',
'type' => 'list',
'title' => 'Select your category',
'defaultValue' => 'all',
'values' => array(
'Adult' => 'adult',
'All' => 'all',
'Anime' => 'anime',
'Books' => 'books',
'Games' => 'games',
'Movies' => 'movies',
'Music' => 'music',
'Other' => 'other',
'Series & TV' => 'series_tv',
'Software' => 'software'
)
)
)
);
public function getURI(){
$uri = self::URI;
switch($this->queriedContext) {
case 'By "Latest" category':
switch($this->getInput('latest_category')) {
case 'hot_torrents':
$uri .= 'statistic/hot/torrents';
break;
case 'news':
break;
case 'releases':
$uri .= 'releases.php';
break;
case 'torrents':
$uri .= 'latest.php';
break;
}
break;
case 'By "Torrent" category':
$uri .= $this->buildCategoryUri(
$this->getInput('torrent_category'),
$this->getInput('torrent_popularity')
);
break;
case 'Search torrent by name':
$category = $this->getInput('search_category');
$uri .= $this->buildCategoryUri($category);
if($category !== 'movies')
$uri .= '&ihq=' . urlencode($this->getInput('search_name'));
break;
default: parent::getURI();
}
return $uri;
}
public function getName(){
switch($this->queriedContext) {
case 'By "Latest" category':
$categoryName = array_search(
$this->getInput('latest_category'),
self::PARAMETERS['By "Latest" category']['latest_category']['values']
);
$name = 'Latest ' . $categoryName . ' - ' . self::NAME;
break;
case 'By "Torrent" category':
$categoryName = array_search(
$this->getInput('torrent_category'),
self::PARAMETERS['By "Torrent" category']['torrent_category']['values']
);
$name = 'Category: ' . $categoryName . ' - ' . self::NAME;
break;
case 'Search torrent by name':
$categoryName = array_search(
$this->getInput('search_category'),
self::PARAMETERS['Search torrent by name']['search_category']['values']
);
$name = 'Search: "'
. $this->getInput('search_name')
. '" in category: '
. $categoryName . ' - '
. self::NAME;
break;
default: return parent::getName();
}
return $name;
}
public function collectData(){
$html = $this->loadHtml($this->getURI());
switch($this->queriedContext) {
case 'By "Latest" category':
switch($this->getInput('latest_category')) {
case 'hot_torrents':
$this->getLatestHotTorrents($html);
break;
case 'news':
$this->getLatestNews($html);
break;
case 'releases':
case 'torrents':
$this->getLatestTorrents($html);
break;
}
break;
case 'By "Torrent" category':
if($this->getInput('torrent_category') === 'movies') {
// This one is special (content wise)
$this->getMovieTorrents($html);
} else {
$this->getLatestTorrents($html);
}
break;
case 'Search torrent by name':
if($this->getInput('search_category') === 'movies') {
// This one is special (content wise)
$this->getMovieTorrents($html);
} else {
$this->getLatestTorrents($html);
}
break;
}
}
#region Helper functions for "Movie Torrents"
private function getMovieTorrents($html){
$container = $html->find('div#w0', 0);
if(!$container)
returnServerError('Unable to find torrent container!');
$torrents = $container->find('article');
if(!$torrents)
returnServerError('Unable to find torrents!');
foreach($torrents as $torrent) {
$anchor = $torrent->find('a', 0);
if(!$anchor)
returnServerError('Unable to find anchor!');
$date = $torrent->find('small', 0);
if(!$date)
returnServerError('Unable to find date!');
$item = array();
$item['uri'] = $this->fixRelativeUri($anchor->href);
$item['title'] = $anchor->title;
// $item['author'] =
$item['timestamp'] = strtotime($date->plaintext);
$item['content'] = $this->fixRelativeUri($torrent->innertext);
$this->items[] = $item;
}
}
#endregion
#region Helper functions for "Latest Hot Torrents"
private function getLatestHotTorrents($html){
$container = $html->find('div#serps', 0);
if(!$container)
returnServerError('Unable to find torrent container!');
$torrents = $container->find('tr');
if(!$torrents)
returnServerError('Unable to find torrents!');
// Remove first element (header row)
$torrents = array_slice($torrents, 1);
foreach($torrents as $torrent) {
$cell = $torrent->find('td', 0);
if(!$cell)
returnServerError('Unable to find cell!');
$element = $cell->find('a', 0);
if(!$element)
returnServerError('Unable to find element!');
$item = array();
$item['uri'] = $element->href;
$item['title'] = $element->plaintext;
// $item['author'] =
// $item['timestamp'] =
// $item['content'] =
$this->items[] = $item;
}
}
#endregion
#region Helper functions for "Latest News"
private function getLatestNews($html){
$container = $html->find('div#postcontainer', 0);
if(!$container)
returnServerError('Unable to find post container!');
$posts = $container->find('div.index-post');
if(!$posts)
returnServerError('Unable to find posts!');
foreach($posts as $post) {
$item = array();
$item['uri'] = $this->latestNewsExtractUri($post);
$item['title'] = $this->latestNewsExtractTitle($post);
$item['author'] = $this->latestNewsExtractAuthor($post);
$item['timestamp'] = $this->latestNewsExtractTimestamp($post);
$item['content'] = $this->latestNewsExtractContent($post);
$this->items[] = $item;
}
}
private function latestNewsExtractAuthor($post){
$author = $post->find('small', 0);
if(!$author)
returnServerError('Unable to find author!');
// The author is hidden within a string like: 'Posted by {author} on {date}'
preg_match('/Posted\sby\s(.*)\son/i', $author->innertext, $matches);
return $matches[1];
}
private function latestNewsExtractTimestamp($post){
$date = $post->find('small', 0);
if(!$date)
returnServerError('Unable to find date!');
// The date is hidden within a string like: 'Posted by {author} on {date}'
preg_match('/Posted\sby\s.*\son\s(.*)/i', $date->innertext, $matches);
$timestamp = strtotime($matches[1]);
// Make sure date is not in the future (dates are given like 'Nov. 20' without year)
if($timestamp > time()) {
$timestamp = strtotime('-1 year', $timestamp);
}
return $timestamp;
}
private function latestNewsExtractTitle($post){
$title = $post->find('a', 0);
if(!$title)
returnServerError('Unable to find title!');
return $title->plaintext;
}
private function latestNewsExtractUri($post){
$uri = $post->find('a', 0);
if(!$uri)
returnServerError('Unable to find uri!');
return $uri->href;
}
private function latestNewsExtractContent($post){
$content = $post->find('div', 0);
if(!$content)
returnServerError('Unable to find content!');
// Remove <h2>...</h2> (title)
foreach($content->find('h2') as $element) {
$element->outertext = '';
}
// Remove <small>...</small> (author)
foreach($content->find('small') as $element) {
$element->outertext = '';
}
return $content->innertext;
}
#endregion
#region Helper functions for "Latest Torrents", "Latest Releases" and "Torrent Category"
private function getLatestTorrents($html){
$container = $html->find('div#serps', 0);
if(!$container)
returnServerError('Unable to find torrent container!');
$torrents = $container->find('tr[data-key]');
if(!$torrents)
returnServerError('Unable to find torrents!');
foreach($torrents as $torrent) {
$item = array();
$item['uri'] = $this->latestTorrentsExtractUri($torrent);
$item['title'] = $this->latestTorrentsExtractTitle($torrent);
$item['author'] = $this->latestTorrentsExtractAuthor($torrent);
$item['timestamp'] = $this->latestTorrentsExtractTimestamp($torrent);
$item['content'] = ''; // There is no valuable content
$this->items[] = $item;
}
}
private function latestTorrentsExtractTitle($torrent){
$cell = $torrent->find('td.title-row', 0);
if(!$cell)
returnServerError('Unable to find title cell!');
$title = $cell->find('span', 0);
if(!$title)
returnServerError('Unable to find title!');
return $title->plaintext;
}
private function latestTorrentsExtractUri($torrent){
$cell = $torrent->find('td.title-row', 0);
if(!$cell)
returnServerError('Unable to find title cell!');
$uri = $cell->find('a', 0);
if(!$uri)
returnServerError('Unable to find uri!');
return $this->fixRelativeUri($uri->href);
}
private function latestTorrentsExtractAuthor($torrent){
$cell = $torrent->find('td.user-row', 0);
if(!$cell)
return; // No author
$user = $cell->find('a', 0);
if(!$user)
returnServerError('Unable to find user!');
return $user->plaintext;
}
private function latestTorrentsExtractTimestamp($torrent){
$cell = $torrent->find('td.date-row', 0);
if(!$cell)
returnServerError('Unable to find date cell!');
return strtotime('-' . $cell->plaintext, time());
}
#endregion
#region Generic helper functions
private function loadHtml($uri){
$html = getSimpleHTMLDOM($uri);
if(!$html)
returnServerError('Unable to load ' . $uri . '!');
return $html;
}
private function fixRelativeUri($uri){
return preg_replace('/\//i', self::URI, $uri, 1);
}
private function buildCategoryUri($category, $order_popularity = false){
switch($category) {
case 'anime': $index = 1; break;
case 'software' : $index = 2; break;
case 'games' : $index = 3; break;
case 'adult' : $index = 4; break;
case 'movies' : $index = 5; break;
case 'music' : $index = 6; break;
case 'other' : $index = 7; break;
case 'series_tv' : $index = 8; break;
case 'books': $index = 9; break;
case 'all':
default: $index = 0; break;
}
return 'torrents/?iht=' . $index . '&ihs=' . ($order_popularity ? 1 : 0) . '&age=0';
}
#endregion
}

View File

@@ -3,7 +3,7 @@ class JapanExpoBridge extends BridgeAbstract {
const MAINTAINER = 'Ginko';
const NAME = 'Japan Expo Actualités';
const URI = 'http://www.japan-expo-paris.com/fr/actualites';
const URI = 'https://www.japan-expo-paris.com/fr/actualites';
const CACHE_TIMEOUT = 14400; // 4h
const DESCRIPTION = 'Returns most recent entries from Japan Expo actualités.';
const PARAMETERS = array( array(
@@ -13,6 +13,10 @@ class JapanExpoBridge extends BridgeAbstract {
)
));
public function getIcon() {
return 'https://s.japan-expo.com/katana/images/JES073/favicons/paris.png';
}
public function collectData(){
function frenchPubDateToTimestamp($date_to_parse) {
@@ -51,7 +55,7 @@ class JapanExpoBridge extends BridgeAbstract {
foreach($html->find('a._tile2') as $element) {
$url = $element->href;
$thumbnail = 'http://s.japan-expo.com/katana/images/JES049/paris.png';
$thumbnail = 'https://s.japan-expo.com/katana/images/JES049/paris.png';
preg_match('/url\(([^)]+)\)/', $element->find('img.rspvimgset', 0)->style, $img_search_result);
if(count($img_search_result) >= 2)
@@ -62,7 +66,8 @@ class JapanExpoBridge extends BridgeAbstract {
break;
}
$article_html = getSimpleHTMLDOMCached('Could not request JapanExpo: ' . $url);
$article_html = getSimpleHTMLDOMCached($url)
or returnServerError('Could not request JapanExpo: ' . $url);
$header = $article_html->find('header.pageHeadBox', 0);
$timestamp = strtotime($header->find('time', 0)->datetime);
$title_html = $header->find('div.section', 0)->next_sibling();
@@ -92,6 +97,7 @@ class JapanExpoBridge extends BridgeAbstract {
$item['uri'] = $url;
$item['title'] = $title;
$item['timestamp'] = $timestamp;
$item['enclosures'] = array($thumbnail);
$item['content'] = $content;
$this->items[] = $item;
$count++;

353
bridges/JustETFBridge.php Normal file
View File

@@ -0,0 +1,353 @@
<?php
class JustETFBridge extends BridgeAbstract {
const NAME = 'justETF Bridge';
const URI = 'https://www.justetf.com';
const DESCRIPTION = 'Currently only supports the news feed';
const MAINTAINER = 'logmanoriginal';
const PARAMETERS = array(
'News' => array(
'full' => array(
'name' => 'Full Article',
'type' => 'checkbox',
'title' => 'Enable to load full articles'
)
),
'Profile' => array(
'isin' => array(
'name' => 'ISIN',
'type' => 'text',
'required' => true,
'pattern' => '[a-zA-Z]{2}[a-zA-Z0-9]{10}',
'title' => 'ISIN, consisting of 2-letter country code, 9-character identifier, check character'
),
'strategy' => array(
'name' => 'Include Strategy',
'type' => 'checkbox',
'defaultValue' => 'checked'
),
'description' => array(
'name' => 'Include Description',
'type' => 'checkbox',
'defaultValue' => 'checked'
)
),
'global' => array(
'lang' => array(
'name' => 'Language',
'required' => true,
'type' => 'list',
'values' => array(
'Englisch' => 'en',
'Deutsch' => 'de',
'Italiano' => 'it'
),
'defaultValue' => 'Englisch'
)
)
);
public function collectData() {
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError('Failed loading contents from ' . $this->getURI());
defaultLinkTo($html, static::URI);
switch($this->queriedContext) {
case 'News':
$this->collectNews($html);
break;
case 'Profile':
$this->collectProfile($html);
break;
}
}
public function getURI() {
$uri = static::URI;
if($this->getInput('lang')) {
$uri .= '/' . $this->getInput('lang');
}
switch($this->queriedContext) {
case 'News':
$uri .= '/news';
break;
case 'Profile':
$uri .= '/etf-profile.html?' . http_build_query(array(
'isin' => strtoupper($this->getInput('isin'))
));
break;
}
return $uri;
}
public function getName() {
$name = static::NAME;
$name .= ($this->queriedContext) ? ' - ' . $this->queriedContext : '';
switch($this->queriedContext) {
case 'News': break;
case 'Profile':
if($this->getInput('isin')) {
$name .= ' ISIN ' . strtoupper($this->getInput('isin'));
}
}
if($this->getInput('lang')) {
$name .= ' (' . strtoupper($this->getInput('lang')) . ')';
}
return $name;
}
#region Common
/**
* Fixes dates depending on the choosen language:
*
* de : dd.mm.yy
* en : dd.mm.yy
* it : dd/mm/yy
*
* Basically strtotime doesn't convert dates correctly due to formats
* being hard to interpret. So we use the DateTime object, manually
* fixing dates and times (set to 00:00:00.000).
*
* We don't know the timezone, so just assume +00:00 (or whatever
* DateTime chooses)
*/
private function fixDate($date) {
switch($this->getInput('lang')) {
case 'en':
case 'de':
$df = date_create_from_format('d.m.y', $date);
break;
case 'it':
$df = date_create_from_format('d/m/y', $date);
break;
}
date_time_set($df, 0, 0);
// debugMessage(date_format($df, 'U'));
return date_format($df, 'U');
}
private function extractImages($article) {
// Notice: We can have zero or more images (though it should mostly be 1)
$elements = $article->find('img');
$images = array();
foreach($elements as $img) {
// Skip the logo (mostly provided part of a hidden div)
if(substr($img->src, strrpos($img->src, '/') + 1) === 'logo.png')
continue;
$images[] = $img->src;
}
return $images;
}
#endregion
#region News
private function collectNews($html) {
$articles = $html->find('div.newsTopArticle')
or returnServerError('No articles found! Layout might have changed!');
foreach($articles as $article) {
$item = array();
// Common data
$item['uri'] = $this->extractNewsUri($article);
$item['timestamp'] = $this->extractNewsDate($article);
$item['title'] = $this->extractNewsTitle($article);
if($this->getInput('full')) {
$uri = $this->extractNewsUri($article);
$html = getSimpleHTMLDOMCached($uri)
or returnServerError('Failed loading full article from ' . $uri);
$fullArticle = $html->find('div.article', 0)
or returnServerError('No content found! Layout might have changed!');
defaultLinkTo($fullArticle, static::URI);
$item['author'] = $this->extractFullArticleAuthor($fullArticle);
$item['content'] = $this->extractFullArticleContent($fullArticle);
$item['enclosures'] = $this->extractImages($fullArticle);
} else {
$item['content'] = $this->extractNewsDescription($article);
$item['enclosures'] = $this->extractImages($article);
}
$this->items[] = $item;
}
}
private function extractNewsUri($article) {
$element = $article->find('a', 0)
or returnServerError('Anchor not found!');
return $element->href;
}
private function extractNewsDate($article) {
$element = $article->find('div.subheadline', 0)
or returnServerError('Date not found!');
// debugMessage($element->plaintext);
$date = trim(explode('|', $element->plaintext)[0]);
return $this->fixDate($date);
}
private function extractNewsDescription($article) {
$element = $article->find('span.newsText', 0)
or returnServerError('Description not found!');
$element->find('a', 0)->onclick = '';
// debugMessage($element->innertext);
return $element->innertext;
}
private function extractNewsTitle($article) {
$element = $article->find('h3', 0)
or returnServerError('Title not found!');
return $element->plaintext;
}
private function extractFullArticleContent($article) {
$element = $article->find('div.article_body', 0)
or returnServerError('Article body not found!');
// Remove teaser image
$element->find('img.teaser-img', 0)->outertext = '';
// Remove self advertisements
foreach($element->find('.call-action') as $adv) {
$adv->outertext = '';
}
// Remove tips
foreach($element->find('.panel-edu') as $tip) {
$tip->outertext = '';
}
// Remove inline scripts (used for i.e. interactive graphs) as they are
// rendered as a long series of strings
foreach($element->find('script') as $script) {
$script->outertext = '[Content removed! Visit site to see full contents!]';
}
return $element->innertext;
}
private function extractFullArticleAuthor($article) {
$element = $article->find('span[itemprop=name]', 0)
or returnServerError('Author not found!');
return $element->plaintext;
}
#endregion
#region Profile
private function collectProfile($html) {
$item = array();
$item['uri'] = $this->getURI();
$item['timestamp'] = $this->extractProfileDate($html);
$item['title'] = $this->extractProfiletitle($html);
$item['author'] = $this->extractProfileAuthor($html);
$item['content'] = $this->extractProfileContent($html);
$this->items[] = $item;
}
private function extractProfileDate($html) {
$element = $html->find('div.infobox div.vallabel', 0)
or returnServerError('Date not found!');
// debugMessage($element->plaintext);
$date = trim(explode("\r\n", $element->plaintext)[1]);
return $this->fixDate($date);
}
private function extractProfileTitle($html) {
$element = $html->find('span.h1', 0)
or returnServerError('Title not found!');
return $element->plaintext;
}
private function extractProfileContent($html) {
// There are a few thins we are interested:
// - Investment Strategy
// - Description
// - Quote
$strategy = $html->find('div.tab-container div.col-sm-6 p', 0)
or returnServerError('Investment Strategy not found!');
// Description requires a bit of cleanup due to lack of propper identification
$description = $html->find('div.headline', 5)
or returnServerError('Description container not found!');
$description = $description->parent();
foreach($description->find('div') as $div) {
$div->outertext = '';
}
$quote = $html->find('div.infobox div.val', 0)
or returnServerError('Quote not found!');
$quote_html = '<strong>Quote</strong><br><p>' . $quote . '</p>';
$strategy_html = '';
$description_html = '';
if($this->getInput('strategy') === true) {
$strategy_html = '<strong>Strategy</strong><br><p>' . $strategy . '</p><br>';
}
if($this->getInput('description') === true) {
$description_html = '<strong>Description</strong><br><p>' . $description . '</p><br>';
}
return $strategy_html . $description_html . $quote_html;
}
private function extractProfileAuthor($html) {
// Use ISIN + WKN as author
// Notice: "identfier" is not a typo [sic]!
$element = $html->find('span.identfier', 0)
or returnServerError('Author not found!');
return $element->plaintext;
}
#endregion
}

View File

@@ -36,6 +36,11 @@ class KATBridge extends BridgeAbstract {
'name' => 'Only get results from Elite or Verified uploaders ?',
),
));
public function getIcon() {
return 'https://statuskatcrco-631f.kxcdn.com/assets/images/favicon.ico';
}
public function collectData(){
function parseDateTimestamp($element){
$guessedDate = strptime($element, '%d-%m-%Y %H:%M:%S');

View File

@@ -38,6 +38,10 @@ class KernelBugTrackerBridge extends BridgeAbstract {
private $bugid = '';
private $bugdesc = '';
public function getIcon() {
return self::URI . '/images/favicon.ico';
}
public function collectData(){
$limit = $this->getInput('limit');
$sorting = $this->getInput('sorting');
@@ -45,9 +49,7 @@ class KernelBugTrackerBridge extends BridgeAbstract {
// We use the print preview page for simplicity
$html = getSimpleHTMLDOMCached($this->getURI() . '&format=multiple',
86400,
false,
null,
0,
null,
true,
true,

View File

@@ -58,13 +58,13 @@ class KununuBridge extends BridgeAbstract {
break;
}
return self::URI . $site . '/' . $company . '/' . $section;
return self::URI . $site . '/' . $company . '/' . $section . '?sort=update_time_desc';
}
return parent::getURI();
}
function getName(){
public function getName(){
if(!is_null($this->getInput('company'))) {
$company = $this->fixCompanyName($this->getInput('company'));
return ($this->companyName ?: $company) . ' - ' . self::NAME;
@@ -73,52 +73,67 @@ class KununuBridge extends BridgeAbstract {
return parent::getName();
}
public function getIcon() {
return 'https://www.kununu.com/favicon-196x196.png';
}
public function collectData(){
$full = $this->getInput('full');
// Load page
$html = getSimpleHTMLDOMCached($this->getURI());
if(!$html)
returnServerError('Unable to receive data from ' . $this->getURI() . '!');
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError('Unable to receive data from ' . $this->getURI() . '!');
$html = defaultLinkTo($html, static::URI);
// Update name for this request
$this->companyName = $this->extractCompanyName($html);
$company = $html->find('span[class="company-name"]', 0)
or returnServerError('Cannot find company name!');
$this->companyName = $company->innertext;
// Find the section with all the panels (reviews)
$section = $html->find('section.kununu-scroll-element', 0);
if($section === false)
returnServerError('Unable to find panel section!');
$section = $html->find('section.kununu-scroll-element', 0)
or returnServerError('Unable to find panel section!');
// Find all articles (within the panels)
$articles = $section->find('article');
if($articles === false || empty($articles))
returnServerError('Unable to find articles!');
$articles = $section->find('article')
or returnServerError('Unable to find articles!');
// Go through all articles
foreach($articles as $article) {
$anchor = $article->find('h1.review-title a', 0)
or returnServerError('Cannot find article URI!');
$date = $article->find('meta[itemprop=dateCreated]', 0)
or returnServerError('Cannot find article date!');
$rating = $article->find('span.rating', 0)
or returnServerError('Cannot find article rating!');
$summary = $article->find('[itemprop=name]', 0)
or returnServerError('Cannot find article summary!');
$item = array();
$item['author'] = $this->extractArticleAuthorPosition($article);
$item['timestamp'] = $this->extractArticleDate($article);
$item['title'] = $this->extractArticleRating($article)
$item['timestamp'] = strtotime($date);
$item['title'] = $rating->getAttribute('aria-label')
. ' : '
. $this->extractArticleSummary($article);
. strip_tags($summary->innertext);
$item['uri'] = $this->extractArticleUri($article);
$item['uri'] = $anchor->href;
if($full)
if($full) {
$item['content'] = $this->extractFullDescription($item['uri']);
else
} else {
$item['content'] = $this->extractArticleDescription($article);
}
$this->items[] = $item;
}
}
/**
* Fixes relative URLs in the given text
*/
private function fixUrl($text){
return preg_replace('/href=(\'|\")\//i', 'href="'.self::URI, $text);
}
}
/*
@@ -128,73 +143,11 @@ class KununuBridge extends BridgeAbstract {
$company = trim($company);
$company = str_replace(' ', '-', $company);
$company = strtolower($company);
return $this->encodeUmlauts($company);
}
/**
* Encodes unmlauts in the given text
*/
private function encodeUmlauts($text){
$umlauts = Array("/ä/","/ö/","/ü/","/Ä/","/Ö/","/Ü/","/ß/");
$replace = Array("ae","oe","ue","Ae","Oe","Ue","ss");
$umlauts = Array('/ä/','/ö/','/ü/','/Ä/','/Ö/','/Ü/','/ß/');
$replace = Array('ae','oe','ue','Ae','Oe','Ue','ss');
return preg_replace($umlauts, $replace, $text);
}
/**
* Returns the company name from the review html
*/
private function extractCompanyName($html){
$company_name = $html->find('h1[itemprop=name]', 0);
if(is_null($company_name))
returnServerError('Cannot find company name!');
return $company_name->plaintext;
}
/**
* Returns the date from a given article
*/
private function extractArticleDate($article){
// They conviniently provide a time attribute for us :)
$date = $article->find('meta[itemprop=dateCreated]', 0);
if(is_null($date))
returnServerError('Cannot find article date!');
return strtotime($date->content);
}
/**
* Returns the rating from a given article
*/
private function extractArticleRating($article){
$rating = $article->find('span.rating', 0);
if(is_null($rating))
returnServerError('Cannot find article rating!');
return $rating->getAttribute('aria-label');
}
/**
* Returns the summary from a given article
*/
private function extractArticleSummary($article){
$summary = $article->find('[itemprop=name]', 0);
if(is_null($summary))
returnServerError('Cannot find article summary!');
return strip_tags($summary->innertext);
}
/**
* Returns the URI from a given article
*/
private function extractArticleUri($article){
$anchor = $article->find('ku-company-review-more', 0);
if(is_null($anchor))
returnServerError('Cannot find article URI!');
return self::URI . $anchor->{'review-url'};
return preg_replace($umlauts, $replace, $company);
}
/**
@@ -202,9 +155,8 @@ class KununuBridge extends BridgeAbstract {
*/
private function extractArticleAuthorPosition($article){
// We need to parse the user-content manually
$user_content = $article->find('div.user-content', 0);
if(is_null($user_content))
returnServerError('Cannot find user content!');
$user_content = $article->find('div.user-content', 0)
or returnServerError('Cannot find user content!');
// Go through all h2 elements to find index of required span (I know... it's stupid)
$author_position = 'Unknown';
@@ -222,11 +174,10 @@ class KununuBridge extends BridgeAbstract {
* Returns the description from a given article
*/
private function extractArticleDescription($article){
$description = $article->find('[itemprop=reviewBody]', 0);
if(is_null($description))
returnServerError('Cannot find article description!');
$description = $article->find('[itemprop=reviewBody]', 0)
or returnServerError('Cannot find article description!');
return $this->fixUrl($description->innertext);
return $description->innertext;
}
/**
@@ -234,14 +185,14 @@ class KununuBridge extends BridgeAbstract {
*/
private function extractFullDescription($uri){
// Load full article
$html = getSimpleHTMLDOMCached($uri);
if($html === false)
returnServerError('Could not load full description!');
$html = getSimpleHTMLDOMCached($uri)
or returnServerError('Could not load full description!');
$html = defaultLinkTo($html, static::URI);
// Find the article
$article = $html->find('article', 0);
if(is_null($article))
returnServerError('Cannot find article!');
$article = $html->find('article', 0)
or returnServerError('Cannot find article!');
// Luckily they use the same layout for the review overview and full article pages :)
return $this->extractArticleDescription($article);

View File

@@ -9,7 +9,7 @@ class LWNprevBridge extends BridgeAbstract{
private $editionTimeStamp;
function getURI(){
return self::URI.'free/bigpage';
return self::URI . 'free/bigpage';
}
private function jumpToNextTag(&$node){
@@ -47,7 +47,7 @@ class LWNprevBridge extends BridgeAbstract{
<html><head><title>LWN</title></head><body>{$content}</body></html>
EOD;
} else {
$content = $content.'</body></html>';
$content = $content . '</body></html>';
}
libxml_use_internal_errors(true);
@@ -172,7 +172,7 @@ EOD;
$prefix = '';
if(!empty($cats[0])) {
$prefix .= '['.$cats[0].($cats[1] ? '/'.$cats[1] : '').'] ';
$prefix .= '[' . $cats[0] . ($cats[1] ? '/' . $cats[1] : '') . '] ';
}
return $prefix;
}
@@ -188,7 +188,7 @@ EOD;
$item = array();
$item['uri'] = self::URI.'#'.count($items);
$item['uri'] = self::URI . '#' . count($items);
$item['timestamp'] = $this->editionTimeStamp;
@@ -197,7 +197,7 @@ EOD;
$cat = $newsletters->previousSibling;
$this->jumpToPreviousTag($cat);
$prefix = $this->getItemPrefix($cat, $cats);
$item['title'] = $prefix.' '.$newsletters->textContent;
$item['title'] = $prefix . ' ' . $newsletters->textContent;
$node = $newsletters;
$content = '';
@@ -233,7 +233,7 @@ EOD;
$cat = $cat->previousSibling;
$this->jumpToPreviousTag($cat);
$prefix = $this->getItemPrefix($cat, $cats);
$item['title'] = $prefix.' '.$title->textContent;
$item['title'] = $prefix . ' ' . $title->textContent;
$items[] = array_merge($item, $this->getArticleContent($title));
}
@@ -255,7 +255,7 @@ EOD;
$cat = $cat->previousSibling;
$this->jumpToPreviousTag($cat);
$prefix = $this->getItemPrefix($cat, $cats);
$item['title'] = $prefix.' '.$title->textContent;
$item['title'] = $prefix . ' ' . $title->textContent;
$items[] = array_merge($item, $this->getArticleContent($title));
}

View File

@@ -1,190 +1,538 @@
<?php
class LeBonCoinBridge extends BridgeAbstract {
const MAINTAINER = '16mhz';
const MAINTAINER = 'jacknumber';
const NAME = 'LeBonCoin';
const URI = 'https://www.leboncoin.fr/';
const DESCRIPTION = 'Returns most recent results from LeBonCoin for a
region, and optionally a category and a keyword .';
const DESCRIPTION = 'Returns most recent results from LeBonCoin';
const PARAMETERS = array(
array(
'k' => array('name' => 'Mot Clé'),
'r' => array(
'keywords' => array('name' => 'Mots-Clés'),
'region' => array(
'name' => 'Région',
'type' => 'list',
'values' => array(
'Toute la France' => 'ile_de_france/occasions',
'Alsace' => 'alsace',
'Aquitaine' => 'aquitaine',
'Auvergne' => 'auvergne',
'Basse Normandie' => 'basse_normandie',
'Bourgogne' => 'bourgogne',
'Bretagne' => 'bretagne',
'Centre' => 'centre',
'Champagne Ardenne' => 'champagne_ardenne',
'Corse' => 'corse',
'Franche Comté' => 'franche_comte',
'Haute Normandie' => 'haute_normandie',
'Ile de France' => 'ile_de_france',
'Languedoc Roussillon' => 'languedoc_roussillon',
'Limousin' => 'limousin',
'Lorraine' => 'lorraine',
'Midi Pyrénées' => 'midi_pyrenees',
'Nord Pas De Calais' => 'nord_pas_de_calais',
'Pays de la Loire' => 'pays_de_la_loire',
'Picardie' => 'picardie',
'Poitou Charentes' => 'poitou_charentes',
'Provence Alpes Côte d\'Azur' => 'provence_alpes_cote_d_azur',
'Rhône-Alpes' => 'rhone_alpes',
'Guadeloupe' => 'guadeloupe',
'Martinique' => 'martinique',
'Guyane' => 'guyane',
'Réunion' => 'reunion'
'Toute la France' => '',
'Alsace' => '1',
'Aquitaine' => '2',
'Auvergne' => '3',
'Basse Normandie' => '4',
'Bourgogne' => '5',
'Bretagne' => '6',
'Centre' => '7',
'Champagne Ardenne' => '8',
'Corse' => '9',
'Franche Comté' => '10',
'Haute Normandie' => '11',
'Ile de France' => '12',
'Languedoc Roussillon' => '13',
'Limousin' => '14',
'Lorraine' => '15',
'Midi Pyrénées' => '16',
'Nord Pas De Calais' => '17',
'Pays de la Loire' => '18',
'Picardie' => '19',
'Poitou Charentes' => '20',
'Provence Alpes Côte d\'Azur' => '21',
'Rhône-Alpes' => '22',
'Guadeloupe' => '23',
'Martinique' => '24',
'Guyane' => '25',
'Réunion' => '26'
)
),
'c' => array(
'department' => array(
'name' => 'Département',
'type' => 'list',
'values' => array(
'' => '',
'Ain' => '1',
'Aisne' => '2',
'Allier' => '3',
'Alpes-de-Haute-Provence' => '4',
'Hautes-Alpes' => '5',
'Alpes-Maritimes' => '6',
'Ardèche' => '7',
'Ardennes' => '8',
'Ariège' => '9',
'Aube' => '10',
'Aude' => '11',
'Aveyron' => '12',
'Bouches-du-Rhône' => '13',
'Calvados' => '14',
'Cantal' => '15',
'Charente' => '16',
'Charente-Maritime' => '17',
'Cher' => '18',
'Corrèze' => '19',
'Corse-du-Sud' => '2A',
'Haute-Corse' => '2B',
'Côte-d\'Or' => '21',
'Côtes-d\'Armor' => '22',
'Creuse' => '23',
'Dordogne' => '24',
'Doubs' => '25',
'Drôme' => '26',
'Eure' => '27',
'Eure-et-Loir' => '28',
'Finistère' => '29',
'Gard' => '30',
'Haute-Garonne' => '31',
'Gers' => '32',
'Gironde' => '33',
'Hérault' => '34',
'Ille-et-Vilaine' => '35',
'Indre' => '36',
'Indre-et-Loire' => '37',
'Isère' => '38',
'Jura' => '39',
'Landes' => '40',
'Loir-et-Cher' => '41',
'Loire' => '42',
'Haute-Loire' => '43',
'Loire-Atlantique' => '44',
'Loiret' => '45',
'Lot' => '46',
'Lot-et-Garonne' => '47',
'Lozère' => '48',
'Maine-et-Loire' => '49',
'Manche' => '50',
'Marne' => '51',
'Haute-Marne' => '52',
'Mayenne' => '53',
'Meurthe-et-Moselle' => '54',
'Meuse' => '55',
'Morbihan' => '56',
'Moselle' => '57',
'Nièvre' => '58',
'Nord' => '59',
'Oise' => '60',
'Orne' => '61',
'Pas-de-Calais' => '62',
'Puy-de-Dôme' => '63',
'Pyrénées-Atlantiques' => '64',
'Hautes-Pyrénées' => '65',
'Pyrénées-Orientales' => '66',
'Bas-Rhin' => '67',
'Haut-Rhin' => '68',
'Rhône' => '69',
'Haute-Saône' => '70',
'Saône-et-Loire' => '71',
'Sarthe' => '72',
'Savoie' => '73',
'Haute-Savoie' => '74',
'Paris' => '75',
'Seine-Maritime' => '76',
'Seine-et-Marne' => '77',
'Yvelines' => '78',
'Deux-Sèvres' => '79',
'Somme' => '80',
'Tarn' => '81',
'Tarn-et-Garonne' => '82',
'Var' => '83',
'Vaucluse' => '84',
'Vendée' => '85',
'Vienne' => '86',
'Haute-Vienne' => '87',
'Vosges' => '88',
'Yonne' => '89',
'Territoire de Belfort' => '90',
'Essonne' => '91',
'Hauts-de-Seine' => '92',
'Seine-Saint-Denis' => '93',
'Val-de-Marne' => '94',
'Val-d\'Oise' => '95'
)
),
'cities' => array(
'name' => 'Villes',
'title' => 'Codes postaux séparés par des virgules'
),
'category' => array(
'name' => 'Catégorie',
'type' => 'list',
'values' => array(
'TOUS' => '',
'EMPLOI' => '_emploi_',
'VEHICULES' => array(
'Tous' => '_vehicules_',
'Voitures' => 'voitures',
'Motos' => 'motos',
'Caravaning' => 'caravaning',
'Utilitaires' => 'utilitaires',
'Équipement Auto' => 'equipement_auto',
'Équipement Moto' => 'equipement_moto',
'Équipement Caravaning' => 'equipement_caravaning',
'Nautisme' => 'nautisme',
'Équipement Nautisme' => 'equipement_nautisme'
'Toutes catégories' => '',
'EMPLOI' => array(
'Emploi et recrutement' => '71',
'Offres d\'emploi et jobs' => '33'
),
'VÉHICULES' => array(
'Tous' => '1',
'Voitures' => '2',
'Motos' => '3',
'Caravaning' => '4',
'Utilitaires' => '5',
'Equipement Auto' => '6',
'Equipement Moto' => '44',
'Equipement Caravaning' => '50',
'Nautisme' => '7',
'Equipement Nautisme' => '51'
),
'IMMOBILIER' => array(
'Tous' => '_immobilier_',
'Ventes immobilières' => 'ventes_immobilieres',
'Locations' => 'locations',
'Colocations' => 'colocations',
'Bureaux & Commerces' => 'bureaux_commerces'
'Tous' => '8',
'Ventes immobilières' => '9',
'Locations' => '10',
'Colocations' => '11',
'Bureaux & Commerces' => '13'
),
'VACANCES' => array(
'Tous' => '_vacances_',
'Location gîtes' => 'locations_gites',
'Chambres d\'hôtes' => 'chambres_d_hotes',
'Campings' => 'campings',
'Hôtels' => 'hotels',
'Hébergements insolites' => 'hebergements_insolites'
'Tous' => '66',
'Locations & Gîtes' => '12',
'Chambres d\'hôtes' => '67',
'Campings' => '68',
'Hôtels' => '69',
'Hébergements insolites' => '70'
),
'MULTIMEDIA' => array(
'Tous' => '_multimedia_',
'Informatique' => 'informatique',
'Consoles & Jeux vidéo' => 'consoles_jeux_video',
'Image & Son' => 'image_son',
'Téléphonie' => 'telephonie'
'MULTIMÉDIA' => array(
'Tous' => '14',
'Informatique' => '15',
'Consoles & Jeux vidéo' => '43',
'Image & Son' => '16',
'Téléphonie' => '17'
),
'LOISIRS' => array(
'Tous' => '_loisirs_',
'DVD / Films' => 'dvd_films',
'CD / Musique' => 'cd_musique',
'Livres' => 'livres',
'Animaux' => 'animaux',
'Vélos' => 'velos',
'Sports & Hobbies' => 'sports_hobbies',
'Instruments de musique' => 'instruments_de_musique',
'Collection' => 'collection',
'Jeux & Jouets' => 'jeux_jouets',
'Vins & Gastronomie' => 'vins_gastronomie'
'Tous' => '24',
'DVD / Films' => '25',
'CD / Musique' => '26',
'Livres' => '27',
'Animaux' => '28',
'Vélos' => '55',
'Sports & Hobbies' => '29',
'Instruments de musique' => '30',
'Collection' => '40',
'Jeux & Jouets' => '41',
'Vins & Gastronomie' => '48'
),
'MATÉRIEL PROFESSIONNEL' => array(
'Tous' => '_materiel_professionnel_',
'Matériel Agricole' => 'mateiel_agricole',
'Transport - Manutention' => 'transport_manutention',
'BTP - Chantier - Gros-œuvre' => 'btp_chantier_gros_oeuvre',
'Outillage - Matériaux 2nd-œuvre' => 'outillage_materiaux_2nd_oeuvre',
'Équipements Industriels' => 'equipement_industriels',
'Restauration - Hôtellerie' => 'restauration_hotellerie',
'Fournitures de Bureau' => 'fournitures_de_bureau',
'Commerces & Marchés' => 'commerces_marches',
'Matériel médical' => 'materiel_medical'
'Tous' => '56',
'Matériel Agricole' => '57',
'Transport - Manutention' => '58',
'BTP - Chantier Gros-oeuvre' => '59',
'Outillage - Matériaux 2nd-oeuvre' => '60',
'Équipements Industriels' => '32',
'Restauration - Hôtellerie' => '61',
'Fournitures de Bureau' => '62',
'Commerces & Marchés' => '63',
'Matériel Médical' => '64'
),
'SERVICES' => array(
'Tous' => '_services_',
'Prestations de services' => 'prestations_de_services',
'Billetterie' => 'billetterie',
'Évènements' => 'evenements',
'Cours particuliers' => 'cours_particuliers',
'Covoiturage' => 'covoiturage'
'Tous' => '31',
'Prestations de services' => '34',
'Billetterie' => '35',
'Événements' => '49',
'Cours particuliers' => '36',
'Covoiturage' => '65'
),
'MAISON' => array(
'Tous' => '_maison_',
'Ameublement' => 'ameublement',
'Électroménager' => 'electromenager',
'Arts de la table' => 'arts_de_la_table',
'Décoration' => 'decoration',
'Linge de maison' => 'linge_de_maison',
'Bricolage' => 'bricolage',
'Jardinage' => 'jardinage',
'Vêtements' => 'vetements',
'Chaussures' => 'chaussures',
'Accessoires & Bagagerie' => 'accessoires_bagagerie',
'Montres & Bijoux' => 'montres_bijoux',
'Équipement bébé' => 'equipement_bebe',
'Vêtements bébé' => 'vetements_bebe'
'Tous' => '18',
'Ameublement' => '19',
'Électroménager' => '20',
'Arts de la table' => '45',
'Décoration' => '39',
'Linge de maison' => '46',
'Bricolage' => '21',
'Jardinage' => '52',
'Vêtements' => '22',
'Chaussures' => '53',
'Accessoires & Bagagerie' => '47',
'Montres & Bijoux' => '42',
'Équipement bébé' => '23',
'Vêtements bébé' => '54',
),
'AUTRES' => 'autres'
'AUTRES' => '37'
)
),
'pricemin' => array(
'name' => 'Prix min',
'type' => 'number'
),
'pricemax' => array(
'name' => 'Prix max',
'type' => 'number'
),
'estate' => array(
'name' => 'Type de bien',
'type' => 'list',
'values' => array(
'' => '',
'Maison' => '1',
'Appartement' => '2',
'Terrain' => '3',
'Parking' => '4',
'Autre' => '5'
)
),
'roomsmin' => array(
'name' => 'Pièces min',
'type' => 'number'
),
'roomsmax' => array(
'name' => 'Pièces max',
'type' => 'number'
),
'squaremin' => array(
'name' => 'Surface min',
'type' => 'number'
),
'squaremax' => array(
'name' => 'Surface max',
'type' => 'number'
),
'mileagemin' => array(
'name' => 'Kilométrage min',
'type' => 'number'
),
'mileagemax' => array(
'name' => 'Kilométrage max',
'type' => 'number'
),
'yearmin' => array(
'name' => 'Année min',
'type' => 'number'
),
'yearmax' => array(
'name' => 'Année max',
'type' => 'number'
),
'cubiccapacitymin' => array(
'name' => 'Cylindrée min',
'type' => 'number'
),
'cubiccapacitymax' => array(
'name' => 'Cylindrée max',
'type' => 'number'
),
'fuel' => array(
'name' => 'Énergie',
'type' => 'list',
'values' => array(
'' => '',
'Essence' => '1',
'Diesel' => '2',
'GPL' => '3',
'Électrique' => '4',
'Hybride' => '6',
'Autre' => '5'
)
),
'owner' => array(
'name' => 'Vendeur',
'type' => 'list',
'values' => array(
'Tous' => '',
'Particuliers' => 'private',
'Professionnels' => 'pro'
)
)
)
);
public function collectData(){
public static $LBC_API_KEY = 'ba0c2dad52b3ec';
$category = $this->getInput('c');
if(empty($category)) {
$category = 'annonces';
private function getRange($field, $range_min, $range_max){
if(!is_null($range_min)
&& !is_null($range_max)
&& $range_min > $range_max) {
returnClientError('Min-' . $field . ' must be lower than max-' . $field . '.');
}
$html = getSimpleHTMLDOM(self::URI
. $category
. '/offres/'
. $this->getInput('r')
. '/?f=a&th=1&q='
. urlencode($this->getInput('k')))
or returnServerError('Could not request LeBonCoin.');
if(!is_null($range_min)
&& is_null($range_max)) {
returnClientError('Max-' . $field . ' is needed when min-' . $field . ' is setted (range).');
}
$list = $html->find('.tabsContent', 0);
if($list === null) {
return array(
'min' => $range_min,
'max' => $range_max
);
}
public function collectData(){
$url = 'https://api.leboncoin.fr/finder/search/';
$data = $this->buildRequestJson();
$header = array(
'Content-Type: application/json',
'Content-Length: ' . strlen($data),
'api_key: ' . self::$LBC_API_KEY
);
$opts = array(
CURLOPT_CUSTOMREQUEST => 'POST',
CURLOPT_POSTFIELDS => $data
);
$content = getContents($url, $header, $opts)
or returnServerError('Could not request LeBonCoin. Tried: ' . $url);
$json = json_decode($content);
if($json->total === 0) {
return;
}
$tags = $list->find('li');
foreach($json->ads as $element) {
foreach($tags as $element) {
$item['title'] = $element->subject;
$item['content'] = $element->body;
$item['date'] = $element->index_date;
$item['timestamp'] = strtotime($element->index_date);
$item['uri'] = $element->url;
$item['ad_type'] = $element->ad_type;
$item['author'] = $element->owner->name;
$element = $element->find('a', 0);
if(isset($element->location->city)) {
$item = array();
$item['uri'] = $element->href;
$title = html_entity_decode($element->getAttribute('title'));
$content_image = $element->find('div.item_image', 0)->find('.lazyload', 0);
$item['city'] = $element->location->city;
$item['content'] .= ' -- ' . $element->location->city;
if($content_image !== null) {
$content = '<img src="' . $content_image->getAttribute('data-imgsrc') . '" alt="thumbnail">';
} else {
$content = "";
}
$date = $element->find('aside.item_absolute', 0)->find('p.item_sup', 0);
$detailsList = $element->find('section.item_infos', 0);
if(isset($element->location->zipcode)) {
$item['zipcode'] = $element->location->zipcode;
}
for($i = 0; $i <= 1; $i++) $content .= $detailsList->find('p.item_supp', $i)->plaintext;
$price = $detailsList->find('h3.item_price', 0);
$content .= $price === null ? '' : $price->plaintext;
if(isset($element->price)) {
$item['price'] = $element->price[0];
$item['content'] .= ' -- ' . current($element->price) . '€';
}
if(isset($element->images->urls)) {
$item['thumbnail'] = $element->images->thumb_url;
$item['enclosures'] = array();
foreach($element->images->urls as $image) {
$item['enclosures'][] = $image;
}
}
$item['title'] = $title;
$item['content'] = $content . $date;
$this->items[] = $item;
}
}
private function buildRequestJson() {
$requestJson = new StdClass();
$requestJson->owner_type = $this->getInput('owner');
$requestJson->filters = new StdClass();
$requestJson->filters->keywords = array(
'text' => $this->getInput('keywords')
);
if($this->getInput('region') != '') {
$requestJson->filters->location['regions'] = [$this->getInput('region')];
}
if($this->getInput('department') != '') {
$requestJson->filters->location['departments'] = [$this->getInput('department')];
}
if($this->getInput('cities') != '') {
$requestJson->filters->location['city_zipcodes'] = array();
foreach (explode(',', $this->getInput('cities')) as $zipcode) {
$requestJson->filters->location['city_zipcodes'][] = array(
'zipcode' => trim($zipcode)
);
}
}
$requestJson->filters->category = array(
'id' => $this->getInput('category')
);
if($this->getInput('pricemin') != ''
|| $this->getInput('pricemax') != '') {
$requestJson->filters->ranges->price = $this->getRange(
'price',
$this->getInput('pricemin'),
$this->getInput('pricemax')
);
}
if($this->getInput('estate') != '') {
$requestJson->filters->enums['real_estate_type'] = [$this->getInput('estate')];
}
if($this->getInput('roomsmin') != ''
|| $this->getInput('roomsmax') != '') {
$requestJson->filters->ranges->rooms = $this->getRange(
'rooms',
$this->getInput('roomsmin'),
$this->getInput('roomsmax')
);
}
if($this->getInput('squaremin') != ''
|| $this->getInput('squaremax') != '') {
$requestJson->filters->ranges->square = $this->getRange(
'square',
$this->getInput('squaremin'),
$this->getInput('squaremax')
);
}
if($this->getInput('mileagemin') != ''
|| $this->getInput('mileagemax') != '') {
$requestJson->filters->ranges->mileage = $this->getRange(
'mileage',
$this->getInput('mileagemin'),
$this->getInput('mileagemax')
);
}
if($this->getInput('yearmin') != ''
|| $this->getInput('yearmax') != '') {
$requestJson->filters->ranges->regdate = $this->getRange(
'year',
$this->getInput('yearmin'),
$this->getInput('yearmax')
);
}
if($this->getInput('cubiccapacitymin') != ''
|| $this->getInput('cubiccapacitymax') != '') {
$requestJson->filters->ranges->cubic_capacity = $this->getRange(
'cubic_capacity',
$this->getInput('cubiccapacitymin'),
$this->getInput('cubiccapacitymax')
);
}
if($this->getInput('fuel') != '') {
$requestJson->filters->enums['fuel'] = [$this->getInput('fuel')];
}
$requestJson->limit = 30;
return json_encode($requestJson);
}
}

View File

@@ -3,8 +3,7 @@ class LeMondeInformatiqueBridge extends FeedExpander {
const MAINTAINER = 'ORelio';
const NAME = 'Le Monde Informatique';
const URI = 'http://www.lemondeinformatique.fr/';
const CACHE_TIMEOUT = 1800; // 30min
const URI = 'https://www.lemondeinformatique.fr/';
const DESCRIPTION = 'Returns the newest articles.';
public function collectData(){
@@ -15,30 +14,26 @@ class LeMondeInformatiqueBridge extends FeedExpander {
$item = parent::parseItem($newsItem);
$article_html = getSimpleHTMLDOMCached($item['uri'])
or returnServerError('Could not request LeMondeInformatique: ' . $item['uri']);
$item['content'] = $this->cleanArticle($article_html->find('div#article', 0)->innertext);
$item['title'] = $article_html->find('h1.cleanprint-title', 0)->plaintext;
//Deduce thumbnail URL from article image URL
$item['enclosures'] = array(
str_replace(
'/grande/',
'/petite/',
$article_html->find('.article-image', 0)->find('img', 0)->src
)
);
//No response header sets the encoding, explicit conversion is needed or subsequent xml_encode() will fail
$item['content'] = utf8_encode($this->cleanArticle($article_html->find('div.col-primary', 0)->innertext));
$item['author'] = utf8_encode($article_html->find('div.author-infos', 0)->find('b', 0)->plaintext);
return $item;
}
private function stripCDATA($string){
$string = str_replace('<![CDATA[', '', $string);
$string = str_replace(']]>', '', $string);
return $string;
}
private function stripWithDelimiters($string, $start, $end){
while(strpos($string, $start) !== false) {
$section_to_remove = substr($string, strpos($string, $start));
$section_to_remove = substr($section_to_remove, 0, strpos($section_to_remove, $end) + strlen($end));
$string = str_replace($section_to_remove, '', $string);
}
return $string;
}
private function cleanArticle($article_html){
$article_html = $this->stripWithDelimiters($article_html, '<script', '</script>');
$article_html = $this->stripWithDelimiters($article_html, '<h1 class="cleanprint-title"', '</h1>');
$article_html = stripWithDelimiters($article_html, '<script', '</script>');
$article_html = explode('<p class="contact-error', $article_html)[0] . '</div>';
return $article_html;
}
}

View File

@@ -38,6 +38,10 @@ class LegifranceJOBridge extends BridgeAbstract {
return $item;
}
public function getIcon() {
return 'https://www.legifrance.gouv.fr/img/favicon.ico';
}
public function collectData(){
$html = getSimpleHTMLDOM(self::URI)
or $this->returnServer('Unable to download ' . self::URI);

View File

@@ -3,7 +3,7 @@ class LesJoiesDuCodeBridge extends BridgeAbstract {
const MAINTAINER = 'superbaillot.net';
const NAME = 'Les Joies Du Code';
const URI = 'http://lesjoiesducode.fr/';
const URI = 'https://lesjoiesducode.fr/';
const CACHE_TIMEOUT = 7200; // 2h
const DESCRIPTION = 'LesJoiesDuCode';
@@ -22,20 +22,12 @@ class LesJoiesDuCodeBridge extends BridgeAbstract {
// retrieve .gif instead of static .jpg
$images = $temp->find('p img');
foreach($images as $image) {
$img_src = str_replace(".jpg", ".gif", $image->src);
$img_src = str_replace('.jpg', '.gif', $image->src);
$image->src = $img_src;
}
$content = $temp->innertext;
$auteur = $temp->find('i', 0);
$pos = strpos($auteur->innertext, "by");
if($pos > 0) {
$auteur = trim(str_replace("*/", "", substr($auteur->innertext, ($pos + 2))));
$item['author'] = $auteur;
}
$item['content'] .= trim($content);
$item['content'] = trim($content);
$item['uri'] = $url;
$item['title'] = trim($titre);

View File

@@ -100,7 +100,7 @@ class MangareaderBridge extends BridgeAbstract {
case 'Get popular mangas':
// Find manga name within "Popular mangas for ..."
$pagetitle = $xpath->query(".//*[@id='bodyalt']/h1")->item(0)->nodeValue;
$this->request = substr($pagetitle, 0, strrpos($pagetitle, " -"));
$this->request = substr($pagetitle, 0, strrpos($pagetitle, ' -'));
$this->getPopularMangas($xpath);
break;
case 'Get manga updates':
@@ -120,7 +120,7 @@ class MangareaderBridge extends BridgeAbstract {
// Return some dummy-data if no content available
if(empty($this->items)) {
$item = array();
$item['content'] = "<p>No updates available</p>";
$item['content'] = '<p>No updates available</p>';
$this->items[] = $item;
}
@@ -143,18 +143,18 @@ class MangareaderBridge extends BridgeAbstract {
$item['title'] = htmlspecialchars($manga->nodeValue);
// Add each chapter to the feed
$item['content'] = "";
$item['content'] = '';
foreach ($chapters as $chapter) {
if($item['content'] <> "") {
$item['content'] .= "<br>";
if($item['content'] <> '') {
$item['content'] .= '<br>';
}
$item['content'] .= "<a href='"
. self::URI
. htmlspecialchars($chapter->getAttribute('href'))
. "'>"
. htmlspecialchars($chapter->nodeValue)
. "</a>";
. '</a>';
}
$this->items[] = $item;
@@ -211,13 +211,13 @@ EOD;
foreach ($chapters as $chapter) {
$item = array();
$item['title'] = htmlspecialchars($xpath->query("td[1]", $chapter)
$item['title'] = htmlspecialchars($xpath->query('td[1]', $chapter)
->item(0)
->nodeValue);
$item['uri'] = self::URI . $xpath->query("td[1]/a", $chapter)
$item['uri'] = self::URI . $xpath->query('td[1]/a', $chapter)
->item(0)
->getAttribute('href');
$item['timestamp'] = strtotime($xpath->query("td[2]", $chapter)
$item['timestamp'] = strtotime($xpath->query('td[2]', $chapter)
->item(0)
->nodeValue);
array_unshift($this->items, $item);
@@ -227,12 +227,12 @@ EOD;
public function getURI(){
switch($this->queriedContext) {
case 'Get latest updates':
$path = "latest";
$path = 'latest';
break;
case 'Get popular mangas':
$path = "popular";
if($this->getInput('category') !== "all") {
$path .= "/" . $this->getInput('category');
$path = 'popular';
if($this->getInput('category') !== 'all') {
$path .= '/' . $this->getInput('category');
}
break;
case 'Get manga updates':

144
bridges/MydealsBridge.php Normal file
View File

@@ -0,0 +1,144 @@
<?php
require_once(__DIR__ . '/DealabsBridge.php');
class MydealsBridge extends PepperBridgeAbstract {
const NAME = 'Mydeals bridge';
const URI = 'https://www.mydealz.de/';
const DESCRIPTION = 'Zeigt die Deals von mydeals.de';
const MAINTAINER = 'sysadminstory';
const PARAMETERS = array(
'Suche nach Stichworten' => array (
'q' => array(
'name' => 'Stichworten',
'type' => 'text',
'required' => true
),
'hide_expired' => array(
'name' => 'Abgelaufenes ausblenden',
'type' => 'checkbox',
'required' => 'true'
),
'hide_local' => array(
'name' => 'Lokales ausblenden',
'type' => 'checkbox',
'title' => 'Deals im physischen Geschäft ausblenden',
'required' => 'true'
),
'priceFrom' => array(
'name' => 'Minimaler Preis',
'type' => 'text',
'title' => 'Minmaler Preis in Euros',
'required' => 'false',
'defaultValue' => ''
),
'priceTo' => array(
'name' => 'Maximaler Preis',
'type' => 'text',
'title' => 'maximaler Preis in Euro',
'required' => 'false',
'defaultValue' => ''
),
),
'Deals pro Gruppen' => array(
'group' => array(
'name' => 'Gruppen',
'type' => 'list',
'required' => 'true',
'title' => 'Gruppe, deren Deals angezeigt werden müssen',
'values' => array(
'Elektronik' => 'elektronik',
'Handy & Smartphone' => 'smartphone',
'Gaming' => 'gaming',
'Software' => 'apps-software',
'Fashion Frauen' => 'fashion-frauen',
'Fashion Männer' => 'fashion-accessoires',
'Beauty & Gesundheit' => 'beauty',
'Family & Kids' => 'family-kids',
'Essen & Trinken' => 'food',
'Freizeit & Reisen' => 'reisen',
'Haushalt & Garten' => 'home-living',
'Entertainment' => 'entertainment',
'Verträge & Finanzen' => 'vertraege-finanzen',
'Coupons' => 'coupons',
)
),
'order' => array(
'name' => 'sortieren nach',
'type' => 'list',
'required' => 'true',
'title' => 'Sortierung der deals',
'values' => array(
'Vom heißesten zum kältesten Deal' => '',
'Vom jüngsten Deal zum ältesten' => '-new',
'Vom am meisten kommentierten Deal zum am wenigsten kommentierten Deal' => '-discussed'
)
)
)
);
public $lang = array(
'bridge-uri' => SELF::URI,
'bridge-name' => SELF::NAME,
'context-keyword' => 'Suche nach Stichworten',
'context-group' => 'Deals pro Gruppen',
'uri-group' => '/gruppe/',
'request-error' => 'Could not request mydeals',
'no-results' => 'Ups, wir konnten keine Deals zu',
'relative-date-indicator' => array(
'vor',
'seit'
),
'price' => 'Preis',
'shipping' => 'Versand',
'origin' => 'Ursprung',
'discount' => 'Rabatte',
'title-keyword' => 'Suche',
'title-group' => 'Gruppe',
'local-months' => array(
'Jan',
'Feb',
'Mär',
'Apr',
'Mai',
'Jun',
'Jul',
'Aug',
'Sep',
'Okt',
'Nov',
'Dez',
'.'
),
'local-time-relative' => array(
'eingestellt vor ',
'm',
'h,',
'day',
'days',
'month',
'year',
'and '
),
'date-prefixes' => array(
'eingestellt am ',
'lokal ',
'aktualisiert ',
),
'relative-date-alt-prefixes' => array(
'aktualisiert vor ',
'kommentiert vor ',
'heiß seit '
),
'relative-date-ignore-suffix' => array(
'/von.*$/'
),
'localdeal' => array(
'Lokal ',
'Läuft bis '
)
);
}

View File

@@ -12,7 +12,7 @@ class NasaApodBridge extends BridgeAbstract {
$html = getSimpleHTMLDOM(self::URI . 'archivepix.html')
or returnServerError('Error while downloading the website content');
$list = explode("<br>", $html->find('b', 0)->innertext);
$list = explode('<br>', $html->find('b', 0)->innertext);
for($i = 0; $i < 3; $i++) {
$line = $list[$i];
@@ -32,7 +32,7 @@ class NasaApodBridge extends BridgeAbstract {
$explanation = $picture_html->find('p', 2)->innertext;
//Extract date from the picture page
$date = explode(" ", $picture_html->find('p', 1)->innertext);
$date = explode(' ', $picture_html->find('p', 1)->innertext);
$item['timestamp'] = strtotime($date[4] . $date[3] . $date[2]);
//Other informations

View File

@@ -6,16 +6,6 @@ class NeuviemeArtBridge extends FeedExpander {
const URI = 'http://www.9emeart.fr/';
const DESCRIPTION = 'Returns the newest articles.';
private function stripWithDelimiters($string, $start, $end){
while(strpos($string, $start) !== false) {
$section_to_remove = substr($string, strpos($string, $start));
$section_to_remove = substr($section_to_remove, 0, strpos($section_to_remove, $end) + strlen($end));
$string = str_replace($section_to_remove, '', $string);
}
return $string;
}
protected function parseItem($item){
$item = parent::parseItem($item);
@@ -34,16 +24,16 @@ class NeuviemeArtBridge extends FeedExpander {
}
$article_content = '';
if($article_image) {
if ($article_image) {
$article_content = '<p><img src="' . $article_image . '" /></p>';
}
$article_content .= str_replace(
'src="/', 'src="' . self::URI,
$article_html->find('div.newsGenerique_con', 0)->innertext
);
$article_content = $this->stripWithDelimiters($article_content, '<script', '</script>');
$article_content = $this->stripWithDelimiters($article_content, '<style', '</style>');
$article_content = $this->stripWithDelimiters($article_content, '<link', '>');
$article_content = stripWithDelimiters($article_content, '<script', '</script>');
$article_content = stripWithDelimiters($article_content, '<style', '</style>');
$article_content = stripWithDelimiters($article_content, '<link', '>');
$item['content'] = $article_content;

View File

@@ -6,29 +6,105 @@ class NextInpactBridge extends FeedExpander {
const URI = 'https://www.nextinpact.com/';
const DESCRIPTION = 'Returns the newest articles.';
const PARAMETERS = array( array(
'feed' => array(
'name' => 'Feed',
'type' => 'list',
'values' => array(
'Tous nos articles' => 'news',
'Nos contenus en accès libre' => 'acces-libre',
'Blog' => 'blog',
'Bons plans' => 'bonsplans'
)
),
'filter_premium' => array(
'name' => 'Premium',
'type' => 'list',
'values' => array(
'No filter' => '0',
'Hide Premium' => '1',
'Only Premium' => '2'
)
),
'filter_brief' => array(
'name' => 'Brief',
'type' => 'list',
'values' => array(
'No filter' => '0',
'Hide Brief' => '1',
'Only Brief' => '2'
)
)
));
public function collectData(){
$this->collectExpandableDatas(self::URI . 'rss/news.xml', 10);
$feed = $this->getInput('feed');
if (empty($feed))
$feed = 'news';
$this->collectExpandableDatas(self::URI . 'rss/' . $feed . '.xml');
}
protected function parseItem($newsItem){
$item = parent::parseItem($newsItem);
$item['content'] = $this->extractContent($item['uri']);
$item['content'] = $this->extractContent($item, $item['uri']);
if (is_null($item['content']))
return null; //Filtered article
return $item;
}
private function extractContent($url){
$html2 = getSimpleHTMLDOMCached($url);
$text = '<p><em>'
. $html2->find('span.sub_title', 0)->innertext
. '</em></p><p><img src="'
. $html2->find('div.container_main_image_article', 0)->find('img.dedicated', 0)->src
. '" alt="-" /></p><div>'
. $html2->find('div[itemprop=articleBody]', 0)->innertext
. '</div>';
private function extractContent($item, $url){
$html = getSimpleHTMLDOMCached($url);
if (!is_object($html))
return 'Failed to request NextInpact: ' . $url;
foreach(array(
'filter_premium' => 'h2.title_reserve_article',
'filter_brief' => 'div.brief-inner-content'
) as $param_name => $selector) {
$param_val = intval($this->getInput($param_name));
if ($param_val != 0) {
$element_present = is_object($html->find($selector, 0));
$element_wanted = ($param_val == 2);
if ($element_present != $element_wanted) {
return null; //Filter article
}
}
}
if (is_object($html->find('div[itemprop=articleBody], div.brief-inner-content', 0))) {
$subtitle = trim($html->find('span.sub_title, div.brief-head', 0));
if(is_object($subtitle) && $subtitle->plaintext !== $item['title']) {
$subtitle = '<p><em>' . $subtitle->plaintext . '</em></p>';
} else {
$subtitle = '';
}
$postimg = $html->find(
'div.container_main_image_article, div.image-brief-container, div.image-brief-side-container', 0
);
if(is_object($postimg)) {
$postimg = '<p><img src="'
. $postimg->find('img.dedicated', 0)->src
. '" alt="-" /></p>';
} else {
$postimg = '';
}
$text = $subtitle
. $postimg
. $html->find('div[itemprop=articleBody], div.brief-inner-content', 0)->outertext;
} else {
$text = $item['content']
. '<p><em>Failed retrieve full article content</em></p>';
}
$premium_article = $html->find('h2.title_reserve_article', 0);
if (is_object($premium_article)) {
$text .= '<p><em>' . $premium_article->innertext . '</em></p>';
}
$premium_article = $html2->find('h2.title_reserve_article', 0);
if (is_object($premium_article))
$text = $text . '<p><em>' . $premium_article->innertext . '</em></p>';
return $text;
}
}

View File

@@ -32,43 +32,39 @@ class NextgovBridge extends FeedExpander {
protected function parseItem($newsItem){
$item = parent::parseItem($newsItem);
$item['content'] = '';
$article_thumbnail = 'https://cdn.nextgov.com/nextgov/images/logo.png';
$item['content'] = '<p><b>' . $item['content'] . '</b></p>';
$namespaces = $newsItem->getNamespaces(true);
if(isset($namespaces['media'])) {
$media = $newsItem->children($namespaces['media']);
if(isset($media->content)) {
$attributes = $media->content->attributes();
$item['content'] = '<img src="' . $attributes['url'] . '">';
$item['content'] = '<p><img src="' . $attributes['url'] . '"></p>' . $item['content'];
$article_thumbnail = str_replace(
'large.jpg',
'small.jpg',
strval($attributes['url'])
);
}
}
$item['enclosures'] = array($article_thumbnail);
$item['content'] .= $this->extractContent($item['uri']);
return $item;
}
private function stripWithDelimiters($string, $start, $end){
while (strpos($string, $start) !== false) {
$section_to_remove = substr($string, strpos($string, $start));
$section_to_remove = substr($section_to_remove, 0, strpos($section_to_remove, $end) + strlen($end));
$string = str_replace($section_to_remove, '', $string);
}
return $string;
}
private function extractContent($url){
$article = getSimpleHTMLDOMCached($url)
or returnServerError('Could not request Nextgov: ' . $url);
$article = getSimpleHTMLDOMCached($url);
$contents = $article->find('div.wysiwyg', 0)->innertext;
$contents = $this->stripWithDelimiters($contents, '<div class="ad-container">', '</div>');
$contents = $this->stripWithDelimiters($contents, '<div', '</div>'); //ad outer div
return $this->stripWithDelimiters($contents, '<script', '</script>');
$contents = ($article_thumbnail == '' ? '' : '<p><img src="' . $article_thumbnail . '" /></p>')
. '<p><b>'
. $article_subtitle
. '</b></p>'
. trim($contents);
if (!is_object($article))
return 'Could not request Nextgov: ' . $url;
$contents = $article->find('div.wysiwyg', 0);
$contents->find('svg.content-tombstone', 0)->outertext = '';
$contents = $contents->innertext;
$contents = stripWithDelimiters($contents, '<div class="ad-container">', '</div>');
$contents = stripWithDelimiters($contents, '<div', '</div>'); //ad outer div
return trim(stripWithDelimiters($contents, '<script', '</script>'));
}
}

331
bridges/NineGagBridge.php Normal file
View File

@@ -0,0 +1,331 @@
<?php
class NineGagBridge extends BridgeAbstract {
const NAME = '9gag Bridge';
const URI = 'https://9gag.com/';
const DESCRIPTION = 'Returns latest quotes from 9gag.';
const MAINTAINER = 'ZeNairolf';
const CACHE_TIMEOUT = 3600;
const PARAMETERS = array(
'Popular' => array(
'd' => array(
'name' => 'Section',
'type' => 'list',
'required' => true,
'values' => array(
'Hot' => 'hot',
'Trending' => 'trending',
'Fresh' => 'fresh',
),
),
'p' => array(
'name' => 'Pages',
'type' => 'number',
'defaultValue' => 3,
),
),
'Sections' => array(
'g' => array(
'name' => 'Section',
'type' => 'list',
'required' => true,
'values' => array(
'Animals' => 'cute',
'Anime & Manga' => 'anime-manga',
'Ask 9GAG' => 'ask9gag',
'Awesome' => 'awesome',
'Basketball' => 'basketball',
'Car' => 'car',
'Classical Art Memes' => 'classicalartmemes',
'Comic' => 'comic',
'Cosplay' => 'cosplay',
'Countryballs' => 'country',
'DIY & Crafts' => 'imadedis',
'Drawing & Illustration' => 'drawing',
'Fan Art' => 'animefanart',
'Food & Drinks' => 'food',
'Football' => 'football',
'Fortnite' => 'fortnite',
'Funny' => 'funny',
'GIF' => 'gif',
'Gaming' => 'gaming',
'Girl' => 'girl',
'Girly Things' => 'girly',
'Guy' => 'guy',
'History' => 'history',
'Home Design' => 'home',
'Horror' => 'horror',
'K-Pop' => 'kpop',
'LEGO' => 'lego',
'League of Legends' => 'leagueoflegends',
'Movie & TV' => 'movie-tv',
'Music' => 'music',
'NFK - Not For Kids' => 'nsfw',
'Overwatch' => 'overwatch',
'PC Master Race' => 'pcmr',
'PUBG' => 'pubg',
'Pic Of The Day' => 'photography',
'Pokémon' => 'pokemon',
'Politics' => 'politics',
'Relationship' => 'relationship',
'Roast Me' => 'roastme',
'Satisfying' => 'satisfying',
'Savage' => 'savage',
'School' => 'school',
'Sci-Tech' => 'science',
'Sport' => 'sport',
'Star Wars' => 'starwars',
'Superhero' => 'superhero',
'Surreal Memes' => 'surrealmemes',
'Timely' => 'timely',
'Travel' => 'travel',
'Video' => 'video',
'WTF' => 'wtf',
'Wallpaper' => 'wallpaper',
'Warhammer' => 'warhammer',
),
),
't' => array(
'name' => 'Type',
'type' => 'list',
'required' => true,
'values' => array(
'Hot' => 'hot',
'Fresh' => 'fresh',
),
),
'p' => array(
'name' => 'Pages',
'type' => 'number',
'defaultValue' => 3,
),
),
);
const MIN_NBR_PAGE = 1;
const MAX_NBR_PAGE = 6;
protected $p = null;
public function collectData() {
$url = sprintf(
'%sv1/group-posts/group/%s/type/%s?',
self::URI,
$this->getGroup(),
$this->getType()
);
$cursor = 'c=10';
$posts = array();
for ($i = 0; $i < $this->getPages(); ++$i) {
$content = getContents($url . $cursor);
$json = json_decode($content, true);
$posts = array_merge($posts, $json['data']['posts']);
$cursor = $json['data']['nextCursor'];
}
foreach ($posts as $post) {
$item['uri'] = $post['url'];
$item['title'] = $post['title'];
$item['content'] = self::getContent($post);
$item['categories'] = self::getCategories($post);
$item['timestamp'] = self::getTimestamp($post);
$this->items[] = $item;
}
}
public function getName() {
if ($this->getInput('d')) {
$name = sprintf('%s - %s', '9GAG', $this->getParameterKey('d'));
} elseif ($this->getInput('g')) {
$name = sprintf('%s - %s', '9GAG', $this->getParameterKey('g'));
if ($this->getInput('t')) {
$name = sprintf('%s [%s]', $name, $this->getParameterKey('t'));
}
}
if (!empty($name)) {
return $name;
}
return self::NAME;
}
public function getURI() {
$uri = $this->getInput('g');
if ($uri === 'default') {
$uri = $this->getInput('t');
}
return self::URI . $uri;
}
protected function getGroup() {
if ($this->getInput('d')) {
return 'default';
}
return $this->getInput('g');
}
protected function getType() {
if ($this->getInput('d')) {
return $this->getInput('d');
}
return $this->getInput('t');
}
protected function getPages() {
if ($this->p === null) {
$value = (int) $this->getInput('p');
$value = ($value < self::MIN_NBR_PAGE) ? self::MIN_NBR_PAGE : $value;
$value = ($value > self::MAX_NBR_PAGE) ? self::MAX_NBR_PAGE : $value;
$this->p = $value;
}
return $this->p;
}
protected function getParameterKey($input = '') {
$params = $this->getParameters();
$tab = 'Sections';
if ($input === 'd') {
$tab = 'Popular';
}
if (!isset($params[$tab][$input])) {
return '';
}
return array_search(
$this->getInput($input),
$params[$tab][$input]['values']
);
}
protected static function getContent($post) {
if ($post['type'] === 'Animated') {
$content = self::getAnimated($post);
} elseif ($post['type'] === 'Article') {
$content = self::getArticle($post);
} else {
$content = self::getPhoto($post);
}
return $content;
}
protected static function getPhoto($post) {
$image = $post['images']['image460'];
$photo = '<picture>';
$photo .= sprintf(
'<source srcset="%s" type="image/webp">',
$image['webpUrl']
);
$photo .= sprintf(
'<img src="%s" alt="%s" %s>',
$image['url'],
$post['title'],
'width="500"'
);
$photo .= '</picture>';
return $photo;
}
protected static function getAnimated($post) {
$poster = $post['images']['image460']['url'];
$sources = $post['images'];
$video = sprintf(
'<video poster="%s" %s>',
$poster,
'preload="auto" loop controls style="min-height: 300px" width="500"'
);
$video .= sprintf(
'<source src="%s" type="video/webm">',
$sources['image460sv']['vp9Url']
);
$video .= sprintf(
'<source src="%s" type="video/mp4">',
$sources['image460sv']['h265Url']
);
$video .= sprintf(
'<source src="%s" type="video/mp4">',
$sources['image460svwm']['url']
);
$video .= '</video>';
return $video;
}
protected static function getArticle($post) {
$blocks = $post['article']['blocks'];
$medias = $post['article']['medias'];
$contents = array();
foreach ($blocks as $block) {
if ('Media' === $block['type']) {
$mediaId = $block['mediaId'];
$contents[] = self::getContent($medias[$mediaId]);
} elseif ('RichText' === $block['type']) {
$contents[] = self::getRichText($block['content']);
}
}
$content = join('</div><div>', $contents);
$content = sprintf(
'<%1$s>%2$s</%1$s>',
'div',
$content
);
return $content;
}
protected static function getRichText($text = '') {
$text = trim($text);
if (preg_match('/^>\s(?<text>.*)/', $text, $matches)) {
$text = sprintf(
'<%1$s>%2$s</%1$s>',
'blockquote',
$matches['text']
);
} else {
$text = sprintf(
'<%1$s>%2$s</%1$s>',
'p',
$text
);
}
return $text;
}
protected static function getCategories($post) {
$params = self::PARAMETERS;
$sections = $params['Sections']['g']['values'];
if(isset($post['sections'])) {
$postSections = $post['sections'];
} elseif (isset($post['postSection'])) {
$postSections = array($post['postSection']);
} else {
$postSections = array();
}
foreach ($postSections as $key => $section) {
$postSections[$key] = array_search($section, $sections);
}
return $postSections;
}
protected static function getTimestamp($post) {
$url = $post['images']['image460']['url'];
$headers = get_headers($url, true);
$date = $headers['Date'];
$time = strtotime($date);
return $time;
}
}

View File

@@ -0,0 +1,61 @@
<?php
class NotAlwaysBridge extends BridgeAbstract {
const MAINTAINER = 'mozes';
const NAME = 'Not Always family Bridge';
const URI = 'https://notalwaysright.com/';
const DESCRIPTION = 'Returns the latest stories';
const CACHE_TIMEOUT = 1800; // 30 minutes
const PARAMETERS = array( array(
'filter' => array(
'type' => 'list',
'name' => 'Filter',
'values' => array(
'All' => 'all',
'Right' => 'right',
'Working' => 'working',
'Romantic' => 'romantic',
'Related' => 'related',
'Learning' => 'learning',
'Friendly' => 'friendly',
'Hopeless' => 'hopeless',
'Unfiltered' => 'unfiltered'
),
'required' => true
)
));
public function getIcon() {
return self::URI . 'favicon_nar.png';
}
public function collectData(){
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError('Could not request NotAlways.');
foreach($html->find('.post') as $post) {
#print_r($post);
$item = array();
$item['uri'] = $post->find('h1', 0)->find('a', 0)->href;
$item['content'] = $post;
$item['title'] = $post->find('h1', 0)->find('a', 0)->innertext;
$this->items[] = $item;
}
}
public function getName(){
if(!is_null($this->getInput('filter'))) {
return $this->getInput('filter') . ' - NotAlways Bridge';
}
return parent::getName();
}
public function getURI(){
if(!is_null($this->getInput('filter'))) {
return self::URI . $this->getInput('filter') . '/';
}
return parent::getURI();
}
}

View File

@@ -0,0 +1,131 @@
<?php
class NyaaTorrentsBridge extends BridgeAbstract {
const MAINTAINER = 'ORelio';
const NAME = 'NyaaTorrents';
const URI = 'https://nyaa.si/';
const DESCRIPTION = 'Returns the newest torrents, with optional search criteria.';
const PARAMETERS = array(
array(
'f' => array(
'name' => 'Filter',
'type' => 'list',
'values' => array(
'No filter' => '0',
'No remakes' => '1',
'Trusted only' => '2'
)
),
'c' => array(
'name' => 'Category',
'type' => 'list',
'values' => array(
'All categories' => '0_0',
'Anime' => '1_0',
'Anime - AMV' => '1_1',
'Anime - English' => '1_2',
'Anime - Non-English' => '1_3',
'Anime - Raw' => '1_4',
'Audio' => '2_0',
'Audio - Lossless' => '2_1',
'Audio - Lossy' => '2_2',
'Literature' => '3_0',
'Literature - English' => '3_1',
'Literature - Non-English' => '3_2',
'Literature - Raw' => '3_3',
'Live Action' => '4_0',
'Live Action - English' => '4_1',
'Live Action - Idol/PV' => '4_2',
'Live Action - Non-English' => '4_3',
'Live Action - Raw' => '4_4',
'Pictures' => '5_0',
'Pictures - Graphics' => '5_1',
'Pictures - Photos' => '5_2',
'Software' => '6_0',
'Software - Apps' => '6_1',
'Software - Games' => '6_2',
)
),
'q' => array(
'name' => 'Keyword',
'description' => 'Keyword(s)',
'type' => 'text'
)
)
);
public function getIcon() {
return self::URI . 'static/favicon.png';
}
public function collectData() {
// Build Search URL from user-provided parameters
$search_url = self::URI . '?s=id&o=desc&'
. http_build_query(array(
'f' => $this->getInput('f'),
'c' => $this->getInput('c'),
'q' => $this->getInput('q')
));
// Retrieve torrent listing from search results, which does not contain torrent description
$html = getSimpleHTMLDOM($search_url)
or returnServerError('Could not request Nyaa: ' . $search_url);
$links = $html->find('a');
$results = array();
foreach ($links as $link)
if (strpos($link->href, '/view/') === 0 && !in_array($link->href, $results))
$results[] = $link->href;
if (empty($results) && empty($this->getInput('q')))
returnServerError('No results from Nyaa: ' . $url, 500);
//Process each item individually
foreach ($results as $element) {
//Limit total amount of requests
if(count($this->items) >= 20) {
break;
}
$torrent_id = str_replace('/view/', '', $element);
//Ignore entries without valid torrent ID
if ($torrent_id != 0 && ctype_digit($torrent_id)) {
//Retrieve data for this torrent ID
$item_uri = self::URI . 'view/' . $torrent_id;
//Retrieve full description from torrent page
if ($item_html = getSimpleHTMLDOMCached($item_uri)) {
//Retrieve data from page contents
$item_title = str_replace(' :: Nyaa', '', $item_html->find('title', 0)->plaintext);
$item_desc = str_get_html(markdownToHtml($item_html->find('#torrent-description', 0)->innertext));
$item_author = extractFromDelimiters($item_html->outertext, 'href="/user/', '"');
$item_date = intval(extractFromDelimiters($item_html->outertext, 'data-timestamp="', '"'));
//Retrieve image for thumbnail or generic logo fallback
$item_image = $this->getURI() . 'static/img/avatar/default.png';
foreach ($item_desc->find('img') as $img) {
if (strpos($img->src, 'prez') === false) {
$item_image = $img->src;
break;
}
}
//Build and add final item
$item = array();
$item['uri'] = $item_uri;
$item['title'] = $item_title;
$item['author'] = $item_author;
$item['timestamp'] = $item_date;
$item['enclosures'] = array($item_image);
$item['content'] = $item_desc;
$this->items[] = $item;
}
}
$element = null;
}
$results = null;
}
}

100
bridges/PikabuBridge.php Normal file
View File

@@ -0,0 +1,100 @@
<?php
class PikabuBridge extends BridgeAbstract {
const NAME = 'Пикабу';
const URI = 'https://pikabu.ru';
const DESCRIPTION = 'Выводит посты по тегу';
const MAINTAINER = 'em92';
const PARAMETERS = array(
'По тегу' => array(
'tag' => array(
'name' => 'Тег',
'exampleValue' => 'it',
'required' => true
),
'filter' => array(
'name' => 'Фильтр',
'type' => 'list',
'values' => array(
'Горячее' => 'hot',
'Свежее' => 'new',
),
'defaultValue' => 'hot'
)
)
);
public function getURI() {
if ($this->getInput('tag')) {
return self::URI . '/tag/' . rawurlencode($this->getInput('tag')) . '/' . rawurlencode($this->getInput('filter'));
} else {
return parent::getURI();
}
}
public function getIcon() {
return 'https://cs.pikabu.ru/assets/favicon.ico';
}
public function getName() {
if (is_string($this->getInput('tag'))) {
return $this->getInput('tag') . ' - ' . parent::getName();
} else {
return parent::getName();
}
}
public function collectData(){
$link = $this->getURI();
$text_html = getContents($link) or returnServerError('Could not fetch ' . $link);
$text_html = iconv('windows-1251', 'utf-8', $text_html);
$html = str_get_html($text_html);
foreach($html->find('article.story') as $post) {
$time = $post->find('time.story__datetime', 0);
if (is_null($time)) continue;
$el_to_remove_selectors = array(
'.story__read-more',
'svg.story-image__stretch',
);
foreach($el_to_remove_selectors as $el_to_remove_selector) {
foreach($post->find($el_to_remove_selector) as $el) {
$el->outertext = '';
}
}
foreach($post->find('img') as $img) {
$src = $img->getAttribute('src');
if (!$src) {
$src = $img->getAttribute('data-src');
if (!$src) {
continue;
}
}
$img->outertext = '<img src="' . $src . '">';
}
$categories = array();
foreach($post->find('.tags__tag') as $tag) {
if ($tag->getAttribute('data-tag')) {
$categories[] = $tag->innertext;
}
}
$title = $post->find('.story__title-link', 0);
$item = array();
$item['categories'] = $categories;
$item['author'] = $post->find('.user__nick', 0)->innertext;
$item['title'] = $title->plaintext;
$item['content'] = strip_tags(backgroundToImg($post->find('.story__content-inner', 0)->innertext), '<br><p><img>');
$item['uri'] = $title->href;
$item['timestamp'] = strtotime($time->getAttribute('datetime'));
$this->items[] = $item;
}
}
}

View File

@@ -25,6 +25,10 @@ class PinterestBridge extends FeedExpander {
)
);
public function getIcon() {
return 'https://s.pinimg.com/webapp/style/images/favicon-9f8f9adf.png';
}
public function collectData(){
switch($this->queriedContext) {
case 'By username and board':
@@ -44,7 +48,7 @@ class PinterestBridge extends FeedExpander {
$pattern = '/https\:\/\/i\.pinimg\.com\/[a-zA-Z0-9]*x\//';
foreach($this->items as $item) {
$item["content"] = preg_replace($pattern, 'https://i.pinimg.com/originals/', $item["content"]);
$item['content'] = preg_replace($pattern, 'https://i.pinimg.com/originals/', $item['content']);
$newitems[] = $item;
}
$this->items = $newitems;
@@ -64,10 +68,10 @@ class PinterestBridge extends FeedExpander {
// provide even less info. Thus we attempt multiple options.
$item['title'] = trim($result['title']);
if($item['title'] === "")
if($item['title'] === '')
$item['title'] = trim($result['rich_summary']['display_name']);
if($item['title'] === "")
if($item['title'] === '')
$item['title'] = trim($result['grid_description']);
$item['timestamp'] = strtotime($result['created_at']);

74
bridges/PixivBridge.php Normal file
View File

@@ -0,0 +1,74 @@
<?php
class PixivBridge extends BridgeAbstract {
const MAINTAINER = 'teromene';
const NAME = 'Pixiv Bridge';
const URI = 'https://www.pixiv.net/';
const DESCRIPTION = 'Returns the tag search from pixiv.net';
const PARAMETERS = array( array(
'tag' => array(
'name' => 'Tag to search',
'exampleValue' => 'example',
'required' => true
),
));
public function collectData(){
$html = getContents(static::URI . 'search.php?word=' . urlencode($this->getInput('tag')))
or returnClientError('Unable to query pixiv.net');
$regex = '/<input type="hidden"id="js-mount-point-search-result-list"data-items="([^"]*)/';
$timeRegex = '/img\/([0-9]{4})\/([0-9]{2})\/([0-9]{2})\/([0-9]{2})\/([0-9]{2})\/([0-9]{2})\//';
preg_match_all($regex, $html, $matches, PREG_SET_ORDER, 0);
if(!$matches) return;
$content = json_decode(html_entity_decode($matches[0][1]), true);
$count = 0;
foreach($content as $result) {
if($count == 10) break;
$count++;
$item = array();
$item['id'] = $result['illustId'];
$item['uri'] = 'https://www.pixiv.net/member_illust.php?mode=medium&illust_id=' . $result['illustId'];
$item['title'] = $result['illustTitle'];
$item['author'] = $result['userName'];
preg_match_all($timeRegex, $result['url'], $dt, PREG_SET_ORDER, 0);
$elementDate = DateTime::createFromFormat('YmdHis',
$dt[0][1] . $dt[0][2] . $dt[0][3] . $dt[0][4] . $dt[0][5] . $dt[0][6],
new DateTimeZone('Asia/Tokyo'));
$item['timestamp'] = $elementDate->getTimestamp();
$item['content'] = "<img src='" . $this->cacheImage($result['url'], $item['id']) . "' />";
$this->items[] = $item;
}
}
private function cacheImage($url, $illustId) {
$url = str_replace('_master1200', '', $url);
$url = str_replace('c/240x240/img-master/', 'img-original/', $url);
$path = CACHE_DIR . '/pixiv_img';
if(!is_dir($path))
mkdir($path, 0755, true);
if(!is_file($path . '/' . $illustId . '.jpeg')) {
$headers = array('Referer: https://www.pixiv.net/member_illust.php?mode=medium&illust_id=' . $illustId);
$illust = getContents($url, $headers);
if(strpos($illust, '404 Not Found') !== false) {
$illust = getContents(str_replace('jpg', 'png', $url), $headers);
}
file_put_contents($path . '/' . $illustId . '.jpeg', $illust);
}
return 'cache/pixiv_img/' . $illustId . '.jpeg';
}
}

View File

@@ -58,7 +58,7 @@ class RTBFBridge extends BridgeAbstract {
public function getName(){
if(!is_null($this->getInput('c'))) {
return $this->getInput('c') .' - RTBF Bridge';
return $this->getInput('c') . ' - RTBF Bridge';
}
return parent::getName();

View File

@@ -0,0 +1,34 @@
<?php
class RadioMelodieBridge extends BridgeAbstract {
const NAME = 'Radio Melodie Actu';
const URI = 'https://www.radiomelodie.com/';
const DESCRIPTION = 'Retourne les actualités publiées par Radio Melodie';
const MAINTAINER = 'sysadminstory';
public function getIcon() {
return self::URI . 'img/favicon.png';
}
public function collectData(){
$html = getSimpleHTMLDOM(self::URI . 'actu')
or returnServerError('Could not request Radio Melodie.');
$list = $html->find('div[class=actuitem]');
foreach($list as $element) {
$item = array();
// Get picture URL
$pictureHTML = $element->find('div[class=picture]');
preg_match(
'/background-image:url\((.*)\);/',
$pictureHTML[0]->getAttribute('style'),
$pictures);
$pictureURL = $pictures[1];
$item['enclosures'] = array($pictureURL);
$item['uri'] = self::URI . $element->parent()->href;
$item['title'] = $element->find('h3', 0)->plaintext;
$item['content'] = $element->find('p', 0)->plaintext . '<br/><img src="' . $pictureURL . '"/>';
$this->items[] = $item;
}
}
}

View File

@@ -7,10 +7,14 @@ class RainbowSixSiegeBridge extends BridgeAbstract {
const CACHE_TIMEOUT = 7200; // 2h
const DESCRIPTION = 'Latest articles from the Rainbow Six Siege blog';
public function getIcon() {
return 'https://ubistatic19-a.akamaihd.net/resource/en-us/game/rainbow6/siege-v3/r6s-favicon_316592.ico';
}
public function collectData(){
$dlUrl = "https://prod-tridionservice.ubisoft.com/live/v1/News/Latest?templateId=tcm%3A152-7677";
$dlUrl .= "8-32&pageIndex=0&pageSize=10&language=en-US&detailPageId=tcm%3A152-194572-64";
$dlUrl .= "&keywordList=175426&siteId=undefined&useSeoFriendlyUrl=true";
$dlUrl = 'https://prod-tridionservice.ubisoft.com/live/v1/News/Latest?templateId=tcm%3A152-7677';
$dlUrl .= '8-32&pageIndex=0&pageSize=10&language=en-US&detailPageId=tcm%3A152-194572-64';
$dlUrl .= '&keywordList=175426&siteId=undefined&useSeoFriendlyUrl=true';
$jsonString = getContents($dlUrl) or returnServerError('Error while downloading the website content');
$json = json_decode($jsonString, true);

View File

@@ -25,7 +25,7 @@ class ReadComicsBridge extends BridgeAbstract {
return $timestamp;
}
$keywordsList = explode(";", $this->getInput('q'));
$keywordsList = explode(';', $this->getInput('q'));
foreach($keywordsList as $keywords) {
$html = $this->getSimpleHTMLDOM(self::URI . 'comic/' . rawurlencode($keywords))
or $this->returnServerError('Could not request readcomics.tv.');

Some files were not shown because too many files have changed in this diff Show More