Revert "[CommonDreamBridge] Promote to secure bridge (fix #777) (#909)"

This reverts commit 8c97953211.

.travis.yml

@@ -9,6 +9,9 @@ install:
       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
@@ -17,6 +20,9 @@ script:
     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

CONTRIBUTING.md

@@ -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)

README.md

@@ -1,10 +1,12 @@
 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) [![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/)
+[![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`)
- * `curl` extension enabled in PHP config (`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.

bridges/ABCTabsBridge.php

@@ -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);

bridges/AllocineFRBridge.php

@@ -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']
 				);

bridges/AmazonBridge.php

@@ -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;
 		}

bridges/AnidexBridge.php

@@ -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;
+	}
+}

bridges/AnimeUltimeBridge.php

@@ -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++;

bridges/Arte7Bridge.php

@@ -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/'
+			)
 		)
 	);
 
@@ -54,15 +68,24 @@ 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 : '');
 
 		$header = array(
 			'Authorization: Bearer ' . self::API_TOKEN

bridges/AskfmBridge.php

@@ -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();

bridges/AutoJMBridge.php

@@ -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;
+		}
+
+	}
+}

bridges/BAEBridge.php

@@ -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;
+	}
+}

bridges/BandcampBridge.php

@@ -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.');

bridges/BlaguesDeMerdeBridge.php

@@ -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;
-			}
 		}
+
 	}
+
 }

bridges/BloombergBridge.php

@@ -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) {

bridges/BundesbankBridge.php

@@ -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;
+		}
+
+	}
+
+}

bridges/CADBridge.php

@@ -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 . '"/>';
-	}
-}

bridges/CNETBridge.php

@@ -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();
-	}
 }

bridges/ChristianDailyReporterBridge.php

@@ -7,6 +7,9 @@ class ChristianDailyReporterBridge extends BridgeAbstract {
 	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/';

bridges/ContainerLinuxReleasesBridge.php

@@ -26,12 +26,16 @@ class ContainerLinuxReleasesBridge extends BridgeAbstract {
 		]
 	];
 
-	public function getReleaseFeed($jsonUrl) {
+	private function getReleaseFeed($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());
 

bridges/DailymotionBridge.php

@@ -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;

bridges/DanbooruBridge.php

@@ -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
@@ -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;
+	}
+}

bridges/DauphineLibereBridge.php

@@ -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;
 	}
 }

bridges/DesoutterBridge.php

@@ -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;
+	}
+
+}

bridges/DevToBridge.php

@@ -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);
+	}
+
+}

bridges/DiceBridge.php

@@ -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'));

bridges/DilbertBridge.php

@@ -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) {
 

bridges/DiscogsBridge.php

@@ -81,7 +81,7 @@ class DiscogsBridge extends BridgeAbstract {
 						. $this->getInput('username_folder')
 						. '/collection/folders/'
 						. $this->getInput('folderid')
-						.'/releases?sort=added&sort_order=desc')
+						. '/releases?sort=added&sort_order=desc')
 						or returnServerError('Unable to query discogs !');
 				$jsonData = json_decode($data, true)['releases'];
 			}

bridges/DribbbleBridge.php

@@ -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');

bridges/ETTVBridge.php

@@ -94,17 +94,20 @@ class ETTVBridge extends BridgeAbstract {
 		)
 	));
 
+	protected $results_link;
+
 	public function collectData(){
-		// No control on inputs, because all have defaultValue set
+		// 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 .= '?search=' . urlencode('+' . str_replace(' ', ' +', $this->getInput('query')));
 		$query_str .= '&cat=' . $this->getInput('cat');
-		$query_str .= 'incldead&=' . $this->getInput('status');
+		$query_str .= '&incldead=' . $this->getInput('status');
 		$query_str .= '&lang=' . $this->getInput('lang');
 		$query_str .= '&sort=id&order=desc';
 
 		// Get results page
-		$html = getSimpleHTMLDOM(self::URI . $query_str)
+		$this->results_link = self::URI . $query_str;
+		$html = getSimpleHTMLDOM($this->results_link)
 			or returnServerError('Could not request ' . $this->getName());
 
 		// Loop on each entry
@@ -125,7 +128,7 @@ class ETTVBridge extends BridgeAbstract {
 			$item = array();
 			$item['author'] = $details->children(6)->children(1)->plaintext;
 			$item['title'] = $entry->title;
-			$item['uri'] = $dllinks->children(0)->children(0)->children(0)->href;
+			$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;
@@ -139,4 +142,20 @@ class ETTVBridge extends BridgeAbstract {
 			$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;
+	}
 }

bridges/EliteDangerousGalnetBridge.php

@@ -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');

bridges/ElloBridge.php

@@ -58,7 +58,7 @@ class ElloBridge extends BridgeAbstract {
 
 	}
 
-	public function findText($path) {
+	private function findText($path) {
 
 		foreach($path as $summaryElement) {
 
@@ -72,7 +72,7 @@ class ElloBridge extends BridgeAbstract {
 
 	}
 
-	public function getPostContent($path) {
+	private function getPostContent($path) {
 
 		$content = '';
 		foreach($path as $summaryElement) {
@@ -93,7 +93,7 @@ class ElloBridge extends BridgeAbstract {
 
 	}
 
-	public function getEnclosures($post, $postData) {
+	private function getEnclosures($post, $postData) {
 
 		$assets = [];
 		foreach($post->links->assets as $asset) {
@@ -109,7 +109,7 @@ class ElloBridge extends BridgeAbstract {
 
 	}
 
-	public function getUsername($post, $postData) {
+	private function getUsername($post, $postData) {
 
 		foreach($postData->linked->users as $user) {
 			if($user->id == $post->links->author->id) {
@@ -119,7 +119,7 @@ class ElloBridge extends BridgeAbstract {
 
 	}
 
-	public function getAPIKey() {
+	private function getAPIKey() {
 		$cache = Cache::create('FileCache');
 		$cache->setPath(CACHE_DIR);
 		$cache->setParameters(['key']);

bridges/ElsevierBridge.php

@@ -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)

bridges/EstCeQuonMetEnProdBridge.php

@@ -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;

bridges/EtsyBridge.php

@@ -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 . '">';

bridges/ExtremeDownloadBridge.php

@@ -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;
+	}
+
+}

bridges/FB2Bridge.php

@@ -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;
@@ -91,24 +85,31 @@ 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';
-
+		$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);
-
-		$articleIndex = 0;
-		$maxArticle = 3;
-
 		$html = $this->buildContent($fileContent);
-		$author = $this->getInput('u');
+		$author = $pageInfo['username'];
 
 		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);
+
+			//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 = '';
@@ -118,8 +119,13 @@ EOD;
 				$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){
 		// 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);
 	}
 
 
@@ -234,8 +240,8 @@ EOD;
 		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(
@@ -251,19 +257,28 @@ EOD;
 			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
 		$regex = '/page_id=([0-9]*)&/';
 		preg_match($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
 		$regex = '/"pageID":"([0-9]*)"/';
 		preg_match($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
-	}
 }

bridges/FDroidBridge.php

@@ -19,6 +19,10 @@ class FDroidBridge extends BridgeAbstract {
 		)
 	));
 
+	public function getIcon() {
+		return self::URI . 'assets/favicon.ico?v=8j6PKzW9Mk';
+	}
+
 	public function collectData(){
 		$url = self::URI;
 		$html = getSimpleHTMLDOM($url)
@@ -45,9 +49,9 @@ class FDroidBridge extends BridgeAbstract {
 				$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'];
+					<a href="' . $item['uri'] . '">
+						<img alt="" style="max-height:128px" src="' . $item['icon'] . '">
+					</a><br>' . $item['summary'];
 				$this->items[] = $item;
 		}
 	}

bridges/FacebookBridge.php

@@ -2,7 +2,7 @@
 class FacebookBridge extends BridgeAbstract {
 
 	const MAINTAINER = 'teromene, logmanoriginal';
-	const NAME = 'Facebook';
+	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,
@@ -41,23 +41,75 @@ class FacebookBridge extends BridgeAbstract {
 				'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 getIcon() {
+		return 'https://static.xx.fbcdn.net/rsrc.php/yo/r/iRmz9lCMBD2.ico';
+	}
+
+	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 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';
 	}
 
@@ -78,6 +130,12 @@ class FacebookBridge extends BridgeAbstract {
 
 		}
 
+		$limit = $this->getInput('limit') ?: -1;
+
+		if($limit > 0 && count($this->items) > $limit) {
+			$this->items = array_slice($this->items, 0, $limit);
+		}
+
 	}
 
 	#region Group
@@ -249,173 +307,205 @@ class FacebookBridge extends BridgeAbstract {
 
 	}
 
-	#endregion
+	#endregion (Group)
 
-	private function collectUserData(){
+	#region User
 
-		//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;
+	/**
+	 * 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']
+				. '"!');
 			}
 
-			return false;
-		}
+			if(!array_key_exists('path', $urlparts)
+			|| $urlparts['path'] === '/') {
+				returnClientError('The URL you provided doesn\'t contain the user name!');
+			}
 
-		//Utility function for cleaning a Facebook link
-		$unescape_fb_link = function($matches){
+			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']);
 
-				$header = array("Content-type:
-application/x-www-form-urlencoded\r\nReferer: $captcha_action\r\nCookie: noscript=1\r\n");
+				$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)
 				);
 
-				$html = getContents($captcha_action, $header, $opts);
+				$html = getSimpleHTMLDOM($captcha_action, $header, $opts)
+					or returnServerError('Failed to submit captcha response back to Facebook');
 
-				if($html === false) {
-					returnServerError('Failed to submit captcha response back to Facebook');
-				}
-				unset($_SESSION['captcha_fields']);
-				$html = str_get_html($html);
+				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)) {
-			$header = array('Accept-Language: ' . getEnv('HTTP_ACCEPT_LANGUAGE') . "\r\n");
 
-			// Check if the user provided a fully qualified URL
-			if (filter_var($this->getInput('u'), FILTER_VALIDATE_URL)) {
+			$header = array('Accept-Language: ' . getEnv('HTTP_ACCEPT_LANGUAGE'));
 
-				$urlparts = parse_url($this->getInput('u'));
+			$html = getSimpleHTMLDOM($this->getURI(), $header)
+				or returnServerError('No results for this query.');
 
-				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!');
-				}
-
-				$user = explode('/', $urlparts['path'])[1];
-
-				$html = getSimpleHTMLDOM(self::URI . urlencode($user) . '?_fb_noscript=1', $header)
-						or returnServerError('No results for this query.');
-
-			} else {
-
-				// First character cannot be a forward slash
-				if(strpos($this->getInput('u'), '/') === 0) {
-					returnClientError('Remove leading slash "/" from the username!');
-				}
-
-				if(!strpos($this->getInput('u'), '/')) {
-					$html = getSimpleHTMLDOM(self::URI . urlencode($this->getInput('u')) . '?_fb_noscript=1', $header)
-						or returnServerError('No results for this query.');
-				} else {
-					$html = getSimpleHTMLDOM(self::URI . 'pages/' . $this->getInput('u') . '?_fb_noscript=1', $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
+		// 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.');
 		}
@@ -424,16 +514,14 @@ EOD;
 		->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;
 
@@ -468,11 +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',
@@ -489,13 +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',
@@ -508,35 +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);
 
-						//Retrieve date of the post
+						// 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 = $post->find('abbr')[0];
+
 						if(isset($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);
@@ -544,6 +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;
 					}
 				}
@@ -551,25 +655,6 @@ EOD;
 		}
 	}
 
-	public function getName(){
+	#endregion (User)
 
-		switch($this->queriedContext) {
-
-			case 'User':
-				if(!empty($this->authorName)) {
-					return isset($this->extraInfos['name']) ? $this->extraInfos['name'] : $this->authorName
-					. ' - Facebook Bridge';
-				}
-				break;
-
-			case 'Group':
-				if(!empty($this->groupName)) {
-					return $this->groupName . ' - Facebook Bridge';
-				}
-				break;
-
-		}
-
-		return parent::getName();
-	}
 }

bridges/FierPandaBridge.php

@@ -7,6 +7,10 @@ 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)

bridges/FilterBridge.php

@@ -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(

bridges/FourchanBridge.php

@@ -69,7 +69,7 @@ class FourchanBridge extends BridgeAbstract {
 				. '" src="'
 				. $item['imageThumb']
 				. '" /></a><br>'
-				.$item['content'];
+				. $item['content'];
 			}
 			$this->items[] = $item;
 		}

bridges/FuturaSciencesBridge.php

@@ -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);
 	}

bridges/GBAtempBridge.php

@@ -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:', '➤', $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;
 		}
 	}
 

bridges/GOGBridge.php

@@ -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;
+
+	}
+
+}

bridges/GQMagazineBridge.php

@@ -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;
+	}
+}

bridges/GitHubGistBridge.php

@@ -54,7 +54,7 @@ class GitHubGistBridge extends BridgeAbstract {
 		DEFAULT_SPAN_TEXT)
 			or returnServerError('Could not request ' . $this->getURI());
 
-		$html = defaultLinkTo($html, static::URI);
+		$html = defaultLinkTo($html, $this->getURI());
 
 		$fileinfo = $html->find('[class="file-info"]', 0)
 			or returnServerError('Could not find file info!');
@@ -69,7 +69,7 @@ class GitHubGistBridge extends BridgeAbstract {
 
 		foreach($comments as $comment) {
 
-			$uri = $comment->find('a[href^=#gistcomment]', 0)
+			$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)
@@ -86,7 +86,7 @@ class GitHubGistBridge extends BridgeAbstract {
 
 			$item = array();
 
-			$item['uri'] = $this->getURI() . $uri->href;
+			$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>';

bridges/GithubSearchBridge.php

@@ -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);
 

bridges/GlassdoorBridge.php

@@ -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;
+	}
+}

bridges/GooglePlusPostBridge.php

@@ -22,6 +22,10 @@ class GooglePlusPostBridge extends BridgeAbstract{
 		)
 	));
 
+	public function getIcon() {
+		return 'https://ssl.gstatic.com/images/branding/product/ico/google_plus_alldp.ico';
+	}
+
 	public function collectData(){
 
 		$username = $this->getInput('username');
@@ -74,7 +78,9 @@ class GooglePlusPostBridge extends BridgeAbstract{
 
 			// 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);
+				$end = strpos($message->plaintext, ' ', 50) ?: strlen($message->plaintext);
+			} else {
+				$end = strlen($message->plaintext);
 			}
 
 			if(strlen(substr($message->plaintext, 0, $end)) === strlen($message->plaintext)) {

bridges/GoogleSearchBridge.php

@@ -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);

bridges/GrandComicsDatabaseBridge.php

@@ -49,6 +49,7 @@ class GrandComicsDatabaseBridge extends BridgeAbstract {
 			}
 
 			// Build final item
+			$content = str_replace('href="/', 'href="' . static::URI, $content);
 			$item = array();
 			$item['title'] = $seriesName . ' - ' . $key_date;
 			$item['timestamp'] = strtotime($key_date);

bridges/InstagramBridge.php

@@ -3,7 +3,7 @@ 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(
@@ -85,7 +85,7 @@ class InstagramBridge extends BridgeAbstract {
 				$item['content'] = $data[0];
 				$item['enclosures'] = $data[1];
 			} else {
-				$item['content'] = '<img src="' . htmlentities($media->display_url) . '" alt="'. $item['title'] . '" />';
+				$item['content'] = '<img src="' . htmlentities($media->display_url) . '" alt="' . $item['title'] . '" />';
 				$item['enclosures'] = array($media->display_url);
 			}
 
@@ -101,16 +101,21 @@ class InstagramBridge extends BridgeAbstract {
 		$mediaInfo = $data->entry_data->PostPage[0]->graphql->shortcode_media;
 
 		//Process the first element, that isn't in the node graph
-		$caption = $mediaInfo->edge_media_to_caption->edges[0]->node->text;
+		if (count($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 . '" />';
+		$content = '<img src="' . htmlentities($mediaInfo->display_url) . '" alt="' . $caption . '" />';
 
 		foreach($mediaInfo->edge_sidecar_to_children->edges as $media) {
-
-			$content .= '<img src="' . htmlentities($media->node->display_url) . '" alt="'. $caption . '" />';
-			$enclosures[] = $media->node->display_url;
-
+			$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];
@@ -139,7 +144,7 @@ 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'));
 		}

bridges/JapanExpoBridge.php

@@ -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++;

bridges/KATBridge.php

@@ -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');

bridges/KernelBugTrackerBridge.php

@@ -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');

bridges/KununuBridge.php

@@ -64,7 +64,7 @@ class KununuBridge extends BridgeAbstract {
 		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');
 
-		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 = $article->find('h1.review-title a', 0);
-		if(is_null($anchor))
-			returnServerError('Cannot find article URI!');
-
-		return self::URI . $anchor->href;
+		return preg_replace($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);

bridges/LWNprevBridge.php

@@ -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));
 		}
 

bridges/LeBonCoinBridge.php

@@ -8,8 +8,8 @@ class LeBonCoinBridge extends BridgeAbstract {
 
 	const PARAMETERS = array(
 		array(
-			'k' => array('name' => 'Mot Clé'),
-			'r' => array(
+			'keywords' => array('name' => 'Mots-Clés'),
+			'region' => array(
 				'name' => 'Région',
 				'type' => 'list',
 				'values' => array(
@@ -42,8 +42,114 @@ class LeBonCoinBridge extends BridgeAbstract {
 					'Réunion' => '26'
 				)
 			),
-			'cities' => array('name' => 'Ville'),
-			'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(
@@ -52,7 +158,7 @@ class LeBonCoinBridge extends BridgeAbstract {
 						'Emploi et recrutement' => '71',
 						'Offres d\'emploi et jobs' => '33'
 					),
-					'VEHICULES' => array(
+					'VÉHICULES' => array(
 						'Tous' => '1',
 						'Voitures' => '2',
 						'Motos' => '3',
@@ -79,7 +185,7 @@ class LeBonCoinBridge extends BridgeAbstract {
 						'Hôtels' => '69',
 						'Hébergements insolites' => '70'
 					),
-					'MULTIMEDIA' => array(
+					'MULTIMÉDIA' => array(
 						'Tous' => '14',
 						'Informatique' => '15',
 						'Consoles & Jeux vidéo' => '43',
@@ -99,7 +205,7 @@ class LeBonCoinBridge extends BridgeAbstract {
 						'Jeux & Jouets' => '41',
 						'Vins & Gastronomie' => '48'
 					),
-					'MATERIEL PROFESSIONNEL' => array(
+					'MATÉRIEL PROFESSIONNEL' => array(
 						'Tous' => '56',
 						'Matériel Agricole' => '57',
 						'Transport - Manutention' => '58',
@@ -115,14 +221,14 @@ class LeBonCoinBridge extends BridgeAbstract {
 						'Tous' => '31',
 						'Prestations de services' => '34',
 						'Billetterie' => '35',
-						'Evénements' => '49',
+						'Événements' => '49',
 						'Cours particuliers' => '36',
 						'Covoiturage' => '65'
 					),
 					'MAISON' => array(
 						'Tous' => '18',
 						'Ameublement' => '19',
-						'Electroménager' => '20',
+						'Électroménager' => '20',
 						'Arts de la table' => '45',
 						'Décoration' => '39',
 						'Linge de maison' => '46',
@@ -132,54 +238,145 @@ class LeBonCoinBridge extends BridgeAbstract {
 						'Chaussures' => '53',
 						'Accessoires & Bagagerie' => '47',
 						'Montres & Bijoux' => '42',
-						'Equipement bébé' => '23',
+						'Équipement bébé' => '23',
 						'Vêtements bébé' => '54',
 					),
 					'AUTRES' => '37'
 				)
 			),
-			'o' => array(
+			'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',
+					'Professionnels' => 'pro'
 				)
 			)
 		)
 	);
 
-	public function collectData(){
+	public static $LBC_API_KEY = 'ba0c2dad52b3ec';
 
-		$params = array(
-			'text' => $this->getInput('k'),
-			'region' => $this->getInput('r'),
-			'cities' => $this->getInput('cities'),
-			'category' => $this->getInput('c'),
-			'owner_type' => $this->getInput('o'),
-		);
+	private function getRange($field, $range_min, $range_max){
 
-		$url = self::URI . 'recherche/?' . http_build_query($params);
-		$html = getContents($url)
-			or returnServerError('Could not request LeBonCoin. Tried: ' . $url);
-
-		if(!preg_match('/^<script>window.FLUX_STATE[^\r\n]*/m', $html, $matches)) {
-			returnServerError('Could not parse JSON in page content.');
+		if(!is_null($range_min)
+		&& !is_null($range_max)
+		&& $range_min > $range_max) {
+			returnClientError('Min-' . $field . ' must be lower than max-' . $field . '.');
 		}
 
-		$clean_match = str_replace(
-			array('</script>', '<script>window.FLUX_STATE = '),
-			array('', ''),
-			$matches[0]
-		);
-		$json = json_decode($clean_match);
+		if(!is_null($range_min)
+		&& is_null($range_max)) {
+			returnClientError('Max-' . $field . ' is needed when min-' . $field . ' is setted (range).');
+		}
 
-		if($json->adSearch->data->total === 0) {
+		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;
 		}
 
-		foreach($json->adSearch->data->ads as $element) {
+		foreach($json->ads as $element) {
 
 			$item['title'] = $element->subject;
 			$item['content'] = $element->body;
@@ -221,4 +418,121 @@ class LeBonCoinBridge extends BridgeAbstract {
 			$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);
+
+	}
+
 }

bridges/LeMondeInformatiqueBridge.php

@@ -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;
 	}
 }

bridges/LegifranceJOBridge.php

@@ -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);

bridges/LesJoiesDuCodeBridge.php

@@ -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';
 
@@ -27,15 +27,7 @@ class LesJoiesDuCodeBridge extends BridgeAbstract {
 			}
 			$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);
 

bridges/NeuviemeArtBridge.php

@@ -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;
 

bridges/NextInpactBridge.php

@@ -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;
 	}
 }

bridges/NextgovBridge.php

@@ -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>'));
 	}
 }

bridges/NineGagBridge.php

@@ -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;
+	}
+}

bridges/NotAlwaysBridge.php

@@ -26,6 +26,10 @@ class NotAlwaysBridge extends BridgeAbstract {
 				)
 		));
 
+		public function getIcon() {
+			return self::URI . 'favicon_nar.png';
+		}
+
 		public function collectData(){
 				$html = getSimpleHTMLDOM($this->getURI())
 						or returnServerError('Could not request NotAlways.');

bridges/NyaaTorrentsBridge.php

@@ -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;
+	}
+}

bridges/PikabuBridge.php

@@ -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;
+		}
+	}
+}

bridges/PinterestBridge.php

@@ -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':

bridges/PixivBridge.php

@@ -18,7 +18,7 @@ class PixivBridge extends BridgeAbstract {
 
 	public function collectData(){
 
-		$html = getContents(static::URI.'search.php?word=' . urlencode($this->getInput('tag')))
+		$html = getContents(static::URI . 'search.php?word=' . urlencode($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})\//';
@@ -40,7 +40,8 @@ class PixivBridge extends BridgeAbstract {
 
 			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]);
+						$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']) . "' />";
@@ -48,7 +49,7 @@ class PixivBridge extends BridgeAbstract {
 		}
 	}
 
-	public function cacheImage($url, $illustId) {
+	private function cacheImage($url, $illustId) {
 
 		$url = str_replace('_master1200', '', $url);
 		$url = str_replace('c/240x240/img-master/', 'img-original/', $url);

bridges/RTBFBridge.php

@@ -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();

bridges/RadioMelodieBridge.php

@@ -5,6 +5,10 @@ class RadioMelodieBridge extends BridgeAbstract {
 	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.');
@@ -23,7 +27,7 @@ class RadioMelodieBridge extends BridgeAbstract {
 			$item['enclosures'] = array($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.'"/>';
+			$item['content'] = $element->find('p', 0)->plaintext . '<br/><img src="' . $pictureURL . '"/>';
 			$this->items[] = $item;
 		}
 	}

bridges/RainbowSixSiegeBridge.php

@@ -7,6 +7,10 @@ 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';

bridges/Releases3DSBridge.php

@@ -9,16 +9,6 @@ class Releases3DSBridge extends BridgeAbstract {
 
 	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 $section_retrieved;
-			}
-
-			return false;
-		}
-
 		function typeToString($type){
 			switch($type) {
 				case 1: return '3DS Game';
@@ -76,8 +66,8 @@ class Releases3DSBridge extends BridgeAbstract {
 			$ignDate = time();
 			$ignCoverArt = '';
 
-			$ignSearchUrl = 'http://www.ign.com/search?q=' . urlencode($name);
-			if($ignResult = getSimpleHTMLDOM($ignSearchUrl)) {
+			$ignSearchUrl = 'https://www.ign.com/search?q=' . urlencode($name);
+			if($ignResult = getSimpleHTMLDOMCached($ignSearchUrl)) {
 				$ignCoverArt = $ignResult->find('div.search-item-media', 0)->find('img', 0)->src;
 				$ignDesc = $ignResult->find('div.search-item-description', 0)->plaintext;
 				$ignLink = $ignResult->find('div.search-item-sub-title', 0)->find('a', 1)->href;
@@ -127,6 +117,7 @@ class Releases3DSBridge extends BridgeAbstract {
 			$item['title'] = $name;
 			$item['author'] = $publisher;
 			$item['timestamp'] = $ignDate;
+			$item['enclosures'] = array($ignCoverArt);
 			$item['uri'] = empty($ignLink) ? $searchLinkDuckDuckGo : $ignLink;
 			$item['content'] = $ignDescription . $releaseDescription . $releaseSearchLinks;
 			$this->items[] = $item;

bridges/SexactuBridge.php

@@ -1,88 +0,0 @@
-<?php
-class SexactuBridge extends BridgeAbstract {
-
-	const MAINTAINER = 'Riduidel';
-	const NAME = 'Sexactu';
-	const AUTHOR = 'Maïa Mazaurette';
-	const URI = 'http://www.gqmagazine.fr';
-	const CACHE_TIMEOUT = 7200; // 2h
-	const DESCRIPTION = 'Sexactu via rss-bridge';
-
-	const REPLACED_ATTRIBUTES = array(
-			'href' => 'href',
-			'src' => 'src',
-			'data-original' => 'src'
-	);
-
-	public function getURI(){
-		return self::URI . '/sexactu';
-	}
-
-	public function collectData(){
-		$html = getSimpleHTMLDOM($this->getURI())
-			or returnServerError('Could not request ' . $this->getURI());
-
-		$sexactu = $html->find('.container_sexactu', 0);
-		$rowList = $sexactu->find('.row');
-		foreach($rowList as $row) {
-			// only use first list as second one only contains pages numbers
-
-			$title = $row->find('.title', 0);
-			if($title) {
-				$item = array();
-				$item['author'] = self::AUTHOR;
-				$item['title'] = $title->plaintext;
-				$urlAttribute = 'data-href';
-				$uri = $title->$urlAttribute;
-				if($uri === false)
-					continue;
-				if(substr($uri, 0, 1) === 'h') { // absolute uri
-					$item['uri'] = $uri;
-				} else if(substr($uri, 0, 1) === '/') { // domain relative url
-					$item['uri'] = self::URI . $uri;
-				} else {
-					$item['uri'] = $this->getURI() . $uri;
-				}
-				$article = $this->loadFullArticle($item['uri']);
-				$item['content'] = $this->replaceUriInHtmlElement($article->find('.article_content', 0));
-
-				$publicationDate = $article->find('time[itemprop=datePublished]', 0);
-				$short_date = $publicationDate->datetime;
-				$item['timestamp'] = strtotime($short_date);
-			} else {
-				// Sometimes we get rubbish, ignore.
-				continue;
-			}
-			$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);
-
-		$content = $html->find('#article', 0);
-		if($content) {
-			return $content;
-		}
-
-		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;
-	}
-}

bridges/SupInfoBridge.php

@@ -13,6 +13,10 @@ class SupInfoBridge extends BridgeAbstract {
 		)
 	));
 
+	public function getIcon() {
+		return self::URI . '/favicon.png';
+	}
+
 	public function collectData() {
 
 		if(empty($this->getInput('tag'))) {
@@ -31,7 +35,7 @@ class SupInfoBridge extends BridgeAbstract {
 		}
 	}
 
-	public function fetchArticle($link) {
+	private function fetchArticle($link) {
 
 		$articleHTML = getSimpleHTMLDOM(self::URI . $link)
 			or returnServerError('Unable to fetch article !');

bridges/SuperSmashBlogBridge.php

@@ -25,7 +25,7 @@ class SuperSmashBlogBridge extends BridgeAbstract {
 
 			$video = $article['acf']['link_url'];
 			if (strlen($video) != 0) {
-				$video = str_get_html('<a href="' . $video .'">Youtube video</a>');
+				$video = str_get_html('<a href="' . $video . '">Youtube video</a>');
 			} else {
 				$video = '';
 			}

bridges/TagBoardBridge.php

@@ -14,6 +14,10 @@ class TagBoardBridge extends BridgeAbstract {
 		)
 	));
 
+	public function getIcon() {
+		return 'https://static.tagboard.com/public/favicon-32x32.png';
+	}
+
 	public function collectData(){
 		$link = 'https://post-cache.tagboard.com/search/' . $this->getInput('u');
 

bridges/TebeoBridge.php

@@ -21,6 +21,10 @@ class TebeoBridge extends FeedExpander {
 		)
 	));
 
+	public function getIcon() {
+		return self::URI . 'images/header_logo.png';
+	}
+
 	public function collectData(){
 		$url = self::URI . '/le-replay/' . $this->getInput('cat');
 		$html = getSimpleHTMLDOM($url)
@@ -31,7 +35,7 @@ class TebeoBridge extends FeedExpander {
 			$item['uri'] = $element->find('a', 0)->href;
 			$item['title'] = $element->find('h3', 0)->plaintext;
 			$item['timestamp'] = strtotime($element->find('p.moment-format-day', 0)->plaintext);
-			$item['content'] = '<a href="'.$item['uri'].'"><img alt="" src="'.$element->find('img', 0)->src.'"></a>';
+			$item['content'] = '<a href="' . $item['uri'] . '"><img alt="" src="' . $element->find('img', 0)->src . '"></a>';
 			$this->items[] = $item;
 		}
 	}

bridges/TheHackerNewsBridge.php

@@ -8,67 +8,66 @@ class TheHackerNewsBridge extends BridgeAbstract {
 
 	public function collectData(){
 
-		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 $string;
-		}
-
-		function stripRecursiveHtmlSection($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;
-		}
-
 		$html = getSimpleHTMLDOM($this->getURI())
 			or returnServerError('Could not request TheHackerNews: ' . $this->getURI());
 		$limit = 0;
 
-		foreach($html->find('article') as $element) {
+		foreach($html->find('div.body-post') as $element) {
 			if($limit < 5) {
 
-				$article_url = $element->find('a.entry-title', 0)->href;
-				$article_author = trim($element->find('span.vcard', 0)->plaintext);
-				$article_title = $element->find('a.entry-title', 0)->plaintext;
-				$article_timestamp = strtotime($element->find('span.updated', 0)->plaintext);
-				$article = getSimpleHTMLDOM($article_url)
-					or returnServerError('Could not request TheHackerNews: ' . $article_url);
+				$article_url = $element->find('a.story-link', 0)->href;
+				$article_author = trim($element->find('i.fa-user', 0)->parent()->plaintext);
+				$article_title = $element->find('h2.home-title', 0)->plaintext;
 
-				$contents = $article->find('div.articlebodyonly', 0)->innertext;
-				$contents = stripRecursiveHtmlSection($contents, 'div', '<div class=\'clear\'');
-				$contents = stripWithDelimiters($contents, '<script', '</script>');
+				//Date without time
+				$article_timestamp = strtotime(
+					extractFromDelimiters(
+						$element->find('i.fa-calendar', 0)->parent()->outertext,
+						'</i>',
+						'<span>'
+					)
+				);
+
+				//Article thumbnail in lazy-loading image
+				if (is_object($element->find('img[data-echo]', 0))) {
+					$article_thumbnail = array(
+						extractFromDelimiters(
+							$element->find('img[data-echo]', 0)->outertext,
+							"data-echo='",
+							"'"
+						)
+					);
+				} else {
+					$article_thumbnail = array();
+				}
+
+				if ($article = getSimpleHTMLDOMCached($article_url)) {
+
+					//Article body
+					$contents = $article->find('div.articlebody', 0)->innertext;
+					$contents = stripRecursiveHtmlSection($contents, 'div', '<div class="ad_');
+					$contents = stripWithDelimiters($contents, 'id="google_ads', '</iframe>');
+					$contents = stripWithDelimiters($contents, '<script', '</script>');
+
+					//Date with time
+					if (is_object($article->find('meta[itemprop=dateModified]', 0))) {
+						$article_timestamp = strtotime(
+							extractFromDelimiters(
+								$article->find('meta[itemprop=dateModified]', 0)->outertext,
+								"content='",
+								"'"
+							)
+						);
+					}
+				} else {
+					$contents = 'Could not request TheHackerNews: ' . $article_url;
+				}
 
 				$item = array();
 				$item['uri'] = $article_url;
 				$item['title'] = $article_title;
 				$item['author'] = $article_author;
+				$item['enclosures'] = $article_thumbnail;
 				$item['timestamp'] = $article_timestamp;
 				$item['content'] = trim($contents);
 				$this->items[] = $item;

bridges/TheTVDBBridge.php

@@ -158,6 +158,10 @@ class TheTVDBBridge extends BridgeAbstract {
 		}
 	}
 
+	public function getIcon() {
+		return self::URI . 'application/themes/thetvdb/images/logo.png';
+	}
+
 	public function collectData(){
 		$serie_id = $this->getInput('serie_id');
 		$nbepisode = $this->getInput('nb_episode');

bridges/TheYeteeBridge.php

@@ -0,0 +1,41 @@
+<?php
+class TheYeteeBridge extends BridgeAbstract {
+
+	const MAINTAINER = 'Monsieur Poutounours';
+	const NAME = 'TheYetee';
+	const URI = 'https://theyetee.com';
+	const CACHE_TIMEOUT = 14400; // 4 h
+	const DESCRIPTION = 'Fetch daily shirts from The Yetee';
+
+	public function collectData(){
+
+		$html = getSimpleHTMLDOM(self::URI)
+			or returnServerError('Could not request The Yetee.');
+
+		$div = $html->find('.hero-col');
+		foreach($div as $element) {
+
+				$item = array();
+				$item['enclosures'] = array();
+
+				$title = $element->find('h2', 0)->plaintext;
+				$item['title'] = $title;
+
+				$author = trim($element->find('div[class=credit]', 0)->plaintext);
+				$item['author'] = $author;
+
+				$uri = $element->find('div[class=controls] a', 0)->href;
+				$item['uri'] = static::URI . $uri;
+
+				$content = '<p>' . $element->find('section[class=product-listing-info] p', -1)->plaintext . '</p>';
+				$photos = $element->find('a[class=js-modaal-gallery] img');
+				foreach($photos as $photo) {
+					$content = $content . "<br /><img src='$photo->src' />";
+					$item['enclosures'][] = $photo->src;
+				}
+				$item['content'] = $content;
+
+				$this->items[] = $item;
+		}
+	}
+}

bridges/ThingiverseBridge.php

@@ -0,0 +1,167 @@
+<?php
+class ThingiverseBridge extends BridgeAbstract {
+
+	const NAME = 'Thingiverse Search';
+	const URI = 'https://thingiverse.com';
+	const DESCRIPTION = 'Returns feeds for search results';
+	const MAINTAINER = 'AntoineTurmel';
+	const PARAMETERS = array(
+		array(
+			'query' => array(
+				'name' => 'Search query',
+				'type' => 'text',
+				'required' => true,
+				'title' => 'Insert your search term here',
+				'exampleValue' => 'Enter your search term'
+			),
+			'sortby' => array(
+				'name' => 'Sort by',
+				'type' => 'list',
+				'required' => false,
+				'values' => array(
+					'Relevant' => 'relevant',
+					'Text' => 'text',
+					'Popular' => 'popular',
+					'# of Makes' => 'makes',
+					'Newest' => 'newest',
+				),
+				'defaultValue' => 'newest'
+			),
+			'category' => array(
+				'name' => 'Category',
+				'type' => 'list',
+				'required' => false,
+				'values' => array(
+					'Any' => '',
+					'3D Printing' => '73',
+					'Art' => '63',
+					'Fashion' => '64',
+					'Gadgets' => '65',
+					'Hobby' => '66',
+					'Household' => '67',
+					'Learning' => '69',
+					'Models' => '70',
+					'Tools' => '71',
+					'Toys &amp; Games' => '72',
+					'2D Art' => '144',
+					'Art Tools' => '75',
+					'Coins &amp; Badges' => '143',
+					'Interactive Art' => '78',
+					'Math Art' => '79',
+					'Scans &amp; Replicas' => '145',
+					'Sculptures' => '80',
+					'Signs &amp; Logos' => '76',
+					'Accessories' => '81',
+					'Bracelets' => '82',
+					'Costume' => '142',
+					'Earrings' => '139',
+					'Glasses' => '83',
+					'Jewelry' => '84',
+					'Keychains' => '130',
+					'Rings' => '85',
+					'Audio' => '141',
+					'Camera' => '86',
+					'Computer' => '87',
+					'Mobile Phone' => '88',
+					'Tablet' => '90',
+					'Video Games' => '91',
+					'Automotive' => '155',
+					'DIY' => '93',
+					'Electronics' => '92',
+					'Music' => '94',
+					'R/C Vehicles' => '95',
+					'Robotics' => '96',
+					'Sport &amp; Outdoors' => '140',
+					'Bathroom' => '147',
+					'Containers' => '146',
+					'Decor' => '97',
+					'Household Supplies' => '99',
+					'Kitchen &amp; Dining' => '100',
+					'Office' => '101',
+					'Organization' => '102',
+					'Outdoor &amp; Garden' => '98',
+					'Pets' => '103',
+					'Replacement Parts' => '153',
+					'Biology' => '106',
+					'Engineering' => '104',
+					'Math' => '105',
+					'Physics &amp; Astronomy' => '148',
+					'Animals' => '107',
+					'Buildings &amp; Structures' => '108',
+					'Creatures' => '109',
+					'Food &amp; Drink' => '110',
+					'Model Furniture' => '111',
+					'Model Robots' => '115',
+					'People' => '112',
+					'Props' => '114',
+					'Vehicles' => '116',
+					'Hand Tools' => '118',
+					'Machine Tools' => '117',
+					'Parts' => '119',
+					'Tool Holders &amp; Boxes' => '120',
+					'Chess' => '151',
+					'Construction Toys' => '121',
+					'Dice' => '122',
+					'Games' => '123',
+					'Mechanical Toys' => '124',
+					'Playsets' => '113',
+					'Puzzles' => '125',
+					'Toy &amp; Game Accessories' => '149',
+					'3D Printer Accessories' => '127',
+					'3D Printer Extruders' => '152',
+					'3D Printer Parts' => '128',
+					'3D Printers' => '126',
+					'3D Printing Tests' => '129',
+				),
+				'defaultValue' => ''
+			),
+			'showimage' => array(
+				'name' => 'Show image in content',
+				'type' => 'checkbox',
+				'required' => false,
+				'title' => 'Activate to show the image in the content',
+				'defaultValue' => 'checked'
+			)
+		)
+	);
+
+	public function collectData(){
+		$html = getSimpleHTMLDOM($this->getURI())
+			or returnServerError('Failed to receive ' . $this->getURI());
+
+		$results = $html->find('div.thing-card');
+
+		foreach($results as $result) {
+
+			$item = array();
+
+			$item['title'] = $result->find('span.ellipsis', 0);
+			$item['uri'] = self::URI . $result->find('a', 1)->href;
+			$item['author'] = $result->find('span.item-creator', 0);
+			$item['content'] = '';
+
+			$image = $result->find('img.card-img', 0)->src;
+
+			if($this->getInput('showimage')) {
+				$item['content'] .= '<img src="' . $image . '">';
+			}
+
+			$item['enclosures'] = array($image);
+
+			$this->items[] = $item;
+		}
+	}
+
+	public function getURI(){
+		if(!is_null($this->getInput('query'))) {
+			$uri = self::URI . '/search?q=' . urlencode($this->getInput('query'));
+			$uri .= '&sort=' . $this->getInput('sortby');
+			$uri .= '&category_id=' . $this->getInput('category');
+
+			return $uri;
+		}
+
+		return parent::getURI();
+	}
+
+}

bridges/UnsplashBridge.php

@@ -55,7 +55,7 @@ class UnsplashBridge extends BridgeAbstract {
 				$item['uri'] = str_replace(
 					array('q=75', 'w=400'),
 					array("q=$quality", "w=$width"),
-					$thumbnail->src).'.jpg'; // '.jpg' only for format hint
+					$thumbnail->src) . '.jpg'; // '.jpg' only for format hint
 
 				$item['timestamp'] = time();
 				$item['title'] = $thumbnail->alt;

bridges/VkBridge.php

@@ -17,8 +17,14 @@ class VkBridge extends BridgeAbstract
 		)
 	);
 
+	protected $videos = array();
 	protected $pageName;
 
+	protected function getAccessToken()
+	{
+		return 'c8071613517c155c6cfbd2a059b2718e9c37b89094c4766834969dda75f657a2c1cbb49bab4c5e649f1db';
+	}
+
 	public function getURI()
 	{
 		if (!is_null($this->getInput('u'))) {
@@ -51,11 +57,20 @@ class VkBridge extends BridgeAbstract
 			$pageName = $pageName->plaintext;
 			$this->pageName = htmlspecialchars_decode($pageName);
 		}
+		foreach ($html->find('div.replies') as $comment_block) {
+			$comment_block->outertext = '';
+		}
+		$html->load($html->save());
+
 		$pinned_post_item = null;
 		$last_post_id = 0;
 
 		foreach ($html->find('.post') as $post) {
 
+			defaultLinkTo($post, self::URI);
+
+			$post_videos = array();
+
 			$is_pinned_post = false;
 			if (strpos($post->getAttribute('class'), 'post_fixed') !== false) {
 				$is_pinned_post = true;
@@ -114,7 +129,7 @@ class VkBridge extends BridgeAbstract
 				}
 				$article_title = $article->find($article_title_selector, 0)->innertext;
 				$article_author = $article->find($article_author_selector, 0)->innertext;
-				$article_link = self::URI . ltrim($article->getAttribute('href'), '/');
+				$article_link = $article->getAttribute('href');
 				$article_img_element_style = $article->find($article_thumb_selector, 0)->getAttribute('style');
 				preg_match('/background-image: url\((.*)\)/', $article_img_element_style, $matches);
 				if (count($matches) > 0) {
@@ -126,20 +141,22 @@ class VkBridge extends BridgeAbstract
 
 			// get video on post
 			$video = $post->find('div.post_video_desc', 0);
+			$main_video_link = '';
 			if (is_object($video)) {
 				$video_title = $video->find('div.post_video_title', 0)->plaintext;
-				$video_link = self::URI . ltrim( $video->find('a.lnk', 0)->getAttribute('href'), '/' );
-				$content_suffix .= "<br>Video: <a href='$video_link'>$video_title</a>";
+				$video_link = $video->find('a.lnk', 0)->getAttribute('href');
+				$this->appendVideo($video_title, $video_link, $content_suffix, $post_videos);
 				$video->outertext = '';
+				$main_video_link = $video_link;
 			}
 
 			// get all other videos
 			foreach($post->find('a.page_post_thumb_video') as $a) {
-				$video_title = $a->getAttribute('aria-label');
+				$video_title = htmlspecialchars_decode($a->getAttribute('aria-label'));
 				$temp = explode(' ', $video_title, 2);
 				if (count($temp) > 1) $video_title = $temp[1];
-				$video_link = self::URI . ltrim( $a->getAttribute('href'), '/' );
-				$content_suffix .= "<br>Video: <a href='$video_link'>$video_title</a>";
+				$video_link = $a->getAttribute('href');
+				if ($video_link != $main_video_link) $this->appendVideo($video_title, $video_link, $content_suffix, $post_videos);
 				$a->outertext = '';
 			}
 
@@ -155,14 +172,14 @@ class VkBridge extends BridgeAbstract
 			foreach($post->find('.page_album_wrap') as $el) {
 				$a = $el->find('.page_album_link', 0);
 				$album_title = $a->find('.page_album_title_text', 0)->getAttribute('title');
-				$album_link = self::URI . ltrim($a->getAttribute('href'), '/');
+				$album_link = $a->getAttribute('href');
 				$el->outertext = '';
 				$content_suffix .= "<br>Album: <a href='$album_link'>$album_title</a>";
 			}
 
 			// get photo documents
 			foreach($post->find('a.page_doc_photo_href') as $a) {
-				$doc_link = self::URI . ltrim($a->getAttribute('href'), '/');
+				$doc_link = $a->getAttribute('href');
 				$doc_gif_label_element = $a->find('.page_gif_label', 0);
 				$doc_title_element = $a->find('.doc_label', 0);
 
@@ -188,7 +205,7 @@ class VkBridge extends BridgeAbstract
 
 				if (is_object($doc_title_element)) {
 					$doc_title = $doc_title_element->innertext;
-					$doc_link = self::URI . ltrim($doc_title_element->getAttribute('href'), '/');
+					$doc_link = $doc_title_element->getAttribute('href');
 					$content_suffix .= "<br>Doc: <a href='$doc_link'>$doc_title</a>";
 
 				} else {
@@ -246,15 +263,11 @@ class VkBridge extends BridgeAbstract
 			$post_link = $post->find('a.post_link', 0)->getAttribute('href');
 			preg_match('/wall-?\d+_(\d+)/', $post_link, $preg_match_result);
 			$item['post_id'] = intval($preg_match_result[1]);
-			if (substr(self::URI, -1) == '/') {
-				$post_link = self::URI . ltrim($post_link, '/');
-			} else {
-				$post_link = self::URI . $post_link;
-			}
 			$item['uri'] = $post_link;
 			$item['timestamp'] = $this->getTime($post);
 			$item['title'] = $this->getTitle($item['content']);
 			$item['author'] = $post_author;
+			$item['videos'] = $post_videos;
 			if ($is_pinned_post) {
 				// do not append it now
 				$pinned_post_item = $item;
@@ -265,16 +278,18 @@ class VkBridge extends BridgeAbstract
 
 		}
 
-		if (is_null($pinned_post_item)) {
-			return;
-		} else if (count($this->items) == 0) {
-			$this->items[] = $pinned_post_item;
-		} else if ($last_post_id < $pinned_post_item['post_id']) {
-			$this->items[] = $pinned_post_item;
-			usort($this->items, function ($item1, $item2) {
-				return $item2['post_id'] - $item1['post_id'];
-			});
+		if (!is_null($pinned_post_item)) {
+			if (count($this->items) == 0) {
+				$this->items[] = $pinned_post_item;
+			} else if ($last_post_id < $pinned_post_item['post_id']) {
+				$this->items[] = $pinned_post_item;
+				usort($this->items, function ($item1, $item2) {
+					return $item2['post_id'] - $item1['post_id'];
+				});
+			}
 		}
+
+		$this->getCleanVideoLinks();
 	}
 
 	private function getPhoto($a) {
@@ -339,7 +354,7 @@ class VkBridge extends BridgeAbstract
 
 	}
 
-	public function getContents()
+	private function getContents()
 	{
 		ini_set('user-agent', 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:53.0) Gecko/20100101 Firefox/53.0');
 
@@ -348,5 +363,51 @@ class VkBridge extends BridgeAbstract
 		return getContents($this->getURI(), $header);
 	}
 
+	protected function appendVideo($video_title, $video_link, &$content_suffix, array &$post_videos)
+	{
+		if (!$video_title) $video_title = '(empty)';
 
+		preg_match('/video([0-9-]+_[0-9]+)/', $video_link, $preg_match_result);
+
+		if (count($preg_match_result) > 1) {
+			$video_id = $preg_match_result[1];
+			$this->videos[ $video_id ] = array(
+				'url' => $video_link,
+				'title' => $video_title,
+			);
+			$post_videos[] = $video_id;
+		} else {
+			$content_suffix .= '<br>Video: <a href="' . htmlspecialchars($video_link) . '">' . $video_title . '</a>';
+		}
+	}
+
+	protected function getCleanVideoLinks() {
+		$result = $this->api('video.get', array(
+			'videos' => implode(',', array_keys($this->videos)),
+			'count' => 200
+		));
+
+		if (isset($result['error'])) return;
+
+		foreach($result['response']['items'] as $item) {
+			$video_id = strval($item['owner_id']) . '_' . strval($item['id']);
+			$this->videos[$video_id]['url'] = $item['player'];
+		}
+
+		foreach($this->items as &$item) {
+			foreach($item['videos'] as $video_id) {
+				$video_link = $this->videos[$video_id]['url'];
+				$video_title = $this->videos[$video_id]['title'];
+				$item['content'] .= '<br>Video: <a href="' . htmlspecialchars($video_link) . '">' . $video_title . '</a>';
+			}
+			unset($item['videos']);
+		}
+	}
+
+	protected function api($method, array $params)
+	{
+		$params['v'] = '5.80';
+		$params['access_token'] = $this->getAccessToken();
+		return json_decode( getContents('https://api.vk.com/method/' . $method . '?' . http_build_query($params)), true );
+	}
 }

bridges/WeLiveSecurityBridge.php

@@ -3,37 +3,24 @@ class WeLiveSecurityBridge extends FeedExpander {
 
 	const MAINTAINER = 'ORelio';
 	const NAME = 'We Live Security';
-	const URI = 'http://www.welivesecurity.com/';
+	const URI = 'https://www.welivesecurity.com/';
 	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);
 
 		$article_html = getSimpleHTMLDOMCached($item['uri']);
 		if(!$article_html) {
-			$item['content'] .= '<p>Could not request ' . $this->getName() . ': ' . $item['uri'] . '</p>';
+			$item['content'] .= '<p><em>Could not request ' . $this->getName() . ': ' . $item['uri'] . '</em></p>';
 			return $item;
 		}
 
-		$article_content = $article_html->find('div.wlistingsingletext', 0)->innertext;
-		$article_content = $this->stripWithDelimiters($article_content, '<script', '</script>');
-		$article_content = '<p><b>'
-		. $item['content']
-		. '</b></p>'
-		. trim($article_content);
-
-		$item['content'] = $article_content;
+		$article_content = $article_html->find('div.formatted', 0)->innertext;
+		$article_content = stripWithDelimiters($article_content, '<script', '</script>');
+		$article_content = stripRecursiveHTMLSection($article_content, 'div', '<div class="comments');
+		$article_content = stripRecursiveHTMLSection($article_content, 'div', '<div class="similar-articles');
+		$article_content = stripRecursiveHTMLSection($article_content, 'span', '<span class="meta');
+		$item['content'] = trim($article_content);
 
 		return $item;
 	}

bridges/WhydBridge.php

@@ -16,6 +16,11 @@ class WhydBridge extends BridgeAbstract {
 
 	private $userName = '';
 
+	public function getIcon() {
+		return self::URI . 'assets/favicons/
+32-6b62a9f14d5e1a9213090d8f00f286bba3a6022381a76390d1d0926493b12593.png?v=6';
+	}
+
 	public function collectData(){
 		$html = '';
 		if(strlen(preg_replace('/[^0-9a-f]/', '', $this->getInput('u'))) == 24) {

bridges/WordPressBridge.php

@@ -3,8 +3,7 @@ class WordPressBridge extends FeedExpander {
 	const MAINTAINER = 'aledeg';
 	const NAME = 'Wordpress Bridge';
 	const URI = 'https://wordpress.org/';
-	const CACHE_TIMEOUT = 10800; // 3h
-	const DESCRIPTION = 'Returns the newest full posts of a Wordpress powered website';
+	const DESCRIPTION = 'Returns the newest full posts of a WordPress powered website';
 
 	const PARAMETERS = array( array(
 		'url' => array(
@@ -13,8 +12,8 @@ class WordPressBridge extends FeedExpander {
 		)
 	));
 
-	private function clearContent($content){
-		$content = preg_replace('/<script[^>]*>[^<]*<\/script>/', '', $content);
+	private function cleanContent($content){
+		$content = stripWithDelimiters($content, '<script', '</script>');
 		$content = preg_replace('/<div class="wpa".*/', '', $content);
 		$content = preg_replace('/<form.*\/form>/', '', $content);
 		return $content;
@@ -27,6 +26,10 @@ class WordPressBridge extends FeedExpander {
 
 		$article = null;
 		switch(true) {
+		case !is_null($article_html->find('[itemprop=articleBody]', 0)):
+			// highest priority content div
+			$article = $article_html->find('[itemprop=articleBody]', 0);
+			break;
 		case !is_null($article_html->find('article', 0)):
 			// most common content div
 			$article = $article_html->find('article', 0);
@@ -39,15 +42,37 @@ class WordPressBridge extends FeedExpander {
 			// another common content div
 			$article = $article_html->find('.post-content', 0);
 			break;
-
 		case !is_null($article_html->find('.post', 0)):
 			// for old WordPress themes without HTML5
 			$article = $article_html->find('.post', 0);
 			break;
 		}
 
+		foreach ($article->find('h1.entry-title') as $title)
+			if ($title->plaintext == $item['title'])
+				$title->outertext = '';
+
+		$article_image = $article_html->find('img.wp-post-image', 0);
+		if(!empty($item['content']) && (!is_object($article_image) || empty($article_image->src))) {
+			$article_image = str_get_html($item['content'])->find('img.wp-post-image', 0);
+		}
+		if(is_object($article_image) && !empty($article_image->src)) {
+			if(empty($article_image->getAttribute('data-lazy-src'))) {
+				$article_image = $article_image->src;
+			} else {
+				$article_image = $article_image->getAttribute('data-lazy-src');
+			}
+			$mime_type = getMimeType($article_image);
+			if (strpos($mime_type, 'image') === false)
+				$article_image .= '#.image'; // force image
+			if (empty($item['enclosures']))
+				$item['enclosures'] = array($article_image);
+			else
+				$item['enclosures'] = array_merge($item['enclosures'], $article_image);
+		}
+
 		if(!is_null($article)) {
-			$item['content'] = $this->clearContent($article->innertext);
+			$item['content'] = $this->cleanContent($article->innertext);
 		}
 
 		return $item;

bridges/XenForoBridge.php

@@ -0,0 +1,462 @@
+<?php
+/**
+ * This bridge generates feeds for threads from forums running XenForo version 2
+ *
+ * Examples:
+ * - https://xenforo.com/community/
+ * - http://www.ign.com/boards/
+ *
+ * Notice: XenForo does provide RSS feeds for forums. For example:
+ * - https://xenforo.com/community/forums/-/index.rss
+ *
+ * For more information on XenForo, visit
+ * - https://xenforo.com/
+ * - https://en.wikipedia.org/wiki/XenForo
+ */
+class XenForoBridge extends BridgeAbstract {
+
+	// Bridge specific constants
+	const CONTEXT_THREAD = 'Thread';
+	const XENFORO_VERSION_1 = '1.0';
+	const XENFORO_VERSION_2 = '2.0';
+
+	// RSS-Bridge constants
+	const NAME = 'XenForo Bridge';
+	const URI = 'https://xenforo.com/';
+	const DESCRIPTION = 'Generates feeds for threads in forums powered by XenForo';
+	const MAINTAINER = 'logmanoriginal';
+	const PARAMETERS = array(
+		self::CONTEXT_THREAD => array(
+			'url' => array(
+				'name' => 'Thread URL',
+				'type' => 'text',
+				'required' => true,
+				'title' => 'Insert URL to the thread for which the feed should be generated',
+				'exampleValue' => 'https://xenforo.com/community/threads/guide-to-suggestions.2285/'
+			)
+		),
+		'global' => array(
+			'limit' => array(
+				'name' => 'Limit',
+				'type' => 'number',
+				'required' => false,
+				'title' => 'Specify maximum number of elements to return in the feed',
+				'defaultValue' => 10
+			)
+		)
+	);
+	const CACHE_TIMEOUT = 7200; // 10 minutes
+
+	private $title = '';
+	private $threadurl = '';
+	private $version; // Holds the XenForo version
+
+	public function getName() {
+
+		switch($this->queriedContext) {
+			case self::CONTEXT_THREAD: return $this->title . ' - ' . static::NAME;
+		}
+
+		return parent::getName();
+
+	}
+
+	public function getURI() {
+
+		switch($this->queriedContext) {
+			case self::CONTEXT_THREAD: return $this->threadurl;
+		}
+
+		return parent::getURI();
+
+	}
+
+	public function collectData() {
+
+		$this->threadurl = filter_var(
+			$this->getInput('url'),
+			FILTER_VALIDATE_URL,
+			FILTER_FLAG_SCHEME_REQUIRED | FILTER_FLAG_HOST_REQUIRED | FILTER_FLAG_PATH_REQUIRED);
+
+		if($this->threadurl === false) {
+			returnClientError('The URL you provided is invalid!');
+		}
+
+		$urlparts = parse_url($this->threadurl, PHP_URL_SCHEME);
+
+		// Scheme must be "http" or "https"
+		if(preg_match('/http[s]{0,1}/', parse_url($this->threadurl, PHP_URL_SCHEME)) == false) {
+			returnClientError('The URL you provided doesn\'t specify a valid scheme (http or https)!');
+		}
+
+		// Path cannot be root (../)
+		if(parse_url($this->threadurl, PHP_URL_PATH) === '/') {
+			returnClientError('The URL you provided doesn\'t link to a valid thread (root path)!');
+		}
+
+		// XenForo adds a thread ID to the URL, like "...-thread.454934283". It must be present
+		if(preg_match('/.+\.\d+[\/]{0,1}/', parse_URL($this->threadurl, PHP_URL_PATH)) == false) {
+			returnClientError('The URL you provided doesn\'t link to a valid thread (ID missing)!');
+		}
+
+		// We want to start at the first page in the thread. XenForo uses "../page-n" syntax
+		// to identify pages (except for the first page).
+		// Notice: XenForo uses the concept of "sentinels" to find and replace parts in the
+		// URL. Technically forum hosts can change the syntax!
+		if(preg_match('/.+\/(page-\d+.*)$/', $this->threadurl, $matches) != false) {
+
+			// before: https://xenforo.com/community/threads/guide-to-suggestions.2285/page-5
+			// after : https://xenforo.com/community/threads/guide-to-suggestions.2285/
+			$this->threadurl = str_replace($matches[1], '', $this->threadurl);
+
+		}
+
+		$html = getSimpleHTMLDOMCached($this->threadurl)
+			or returnServerError('Failed loading data from "' . $this->threadurl . '"!');
+
+		$html = defaultLinkTo($html, $this->threadurl);
+
+		// Notice: The DOM structure changes depending on the XenForo version used
+		if($mainContent = $html->find('div.mainContent', 0)) {
+			$this->version = self::XENFORO_VERSION_1;
+		} elseif ($mainContent = $html->find('div[class="p-body"]', 0)) {
+			$this->version = self::XENFORO_VERSION_2;
+		} else {
+			returnServerError('This forum is currently not supported!');
+		}
+
+		switch($this->version) {
+			case self::XENFORO_VERSION_1:
+
+				$titleBar = $mainContent->find('div.titleBar h1', 0)
+					or returnServerError('Error finding title bar!');
+
+				$this->title = $titleBar->plaintext;
+
+				// Store items from current page (we'll use $this->items as LIFO buffer)
+				$this->extractThreadPostsV1($html, $this->threadurl);
+				$this->extractPagesV1($html);
+
+				break;
+
+			case self::XENFORO_VERSION_2:
+
+				$titleBar = $mainContent->find('div[class="p-title"] h1', 0)
+					or returnServerError('Error finding title bar!');
+
+				$this->title = $titleBar->plaintext;
+				$this->extractThreadPostsV2($html, $this->threadurl);
+				$this->extractPagesV2($html);
+
+				break;
+		}
+
+		while(count($this->items) > $this->getInput('limit')) {
+			array_shift($this->items);
+		}
+
+	}
+
+	/**
+	 * Extracts thread posts
+	 * @param $html A simplehtmldom object
+	 * @param $url The url from which $html was loaded
+	 */
+	private function extractThreadPostsV1($html, $url) {
+
+		$lang = $html->find('html', 0)->lang;
+
+		// Posts are contained in an "ol"
+		$messageList = $html->find('#messageList li')
+			or returnServerError('Error finding message list!');
+
+		foreach($messageList as $post) {
+
+			if(!isset($post->attr['id'])) { // Skip ads
+				continue;
+			}
+
+			$item = array();
+
+			$item['uri'] = $url . '#' . $post->getAttribute('id');
+
+			$content = $post->find('.messageContent article', 0);
+
+			// Add some style to quotes
+			foreach($content->find('.bbCodeQuote') as $quote) {
+				$quote->style = '
+					color: #495566;
+					background-color: rgb(248,251,253);
+					border: 1px solid rgb(111, 140, 180);
+					border-color: rgb(111, 140, 180);
+					font-style: italic;';
+			}
+
+			// Remove script tags
+			foreach($content->find('script') as $script) {
+				$script->outertext = '';
+			}
+
+			$item['content'] = $content->innertext;
+
+			// Remove quotes (for the title)
+			foreach($content->find('.bbCodeQuote') as $quote) {
+				$quote->innertext = '';
+			}
+
+			$title = trim($content->plaintext);
+
+			if(strlen($title) > 70) {
+				$item['title'] = substr($title, 0, strpos($title, ' ', 70)) . '...';
+			} else {
+				$item['title'] = $title;
+			}
+
+			/**
+			 * Timestamps are presented in two forms:
+			 *
+			 * 1) short version (for older posts?)
+			 * <span
+			 * 	class="DateTime"
+			 * 	title="22 Oct. 2018 at 23:47"
+			 * >22 Oct. 2018</span>
+			 *
+			 * This form has to be interpreted depending on the current language.
+			 *
+			 * 2) long version (for newer posts?)
+			 * <abbr
+			 * 	class="DateTime"
+			 * 	data-time="1541008785"
+			 * 	data-diff="310694"
+			 * 	data-datestring="31 Oct. 2018"
+			 * 	data-timestring="18:59"
+			 * 	title="31 Oct. 2018 at 18:59"
+			 * >Wednesday at 18:59</abbr>
+			 *
+			 * This form has the timestamp embedded (data-time)
+			 */
+			if($timestamp = $post->find('abbr.DateTime', 0)) { // long version (preffered)
+				$item['timestamp'] = $timestamp->{'data-time'};
+			} elseif($timestamp = $post->find('span.DateTime', 0)) { // short version
+				$item['timestamp'] = $this->fixDate($timestamp->title, $lang);
+			}
+
+			$item['author'] = $post->getAttribute('data-author');
+
+			// Bridge specific properties
+			$item['id'] = $post->getAttribute('id');
+
+			$this->items[] = $item;
+
+		}
+
+	}
+
+	private function extractThreadPostsV2($html, $url) {
+
+		$lang = $html->find('html', 0)->lang;
+
+		$messageList = $html->find('div[class="block-body"] article')
+			or returnServerError('Error finding message list!');
+
+		foreach($messageList as $post) {
+
+			if(!isset($post->attr['id'])) { // Skip ads
+				continue;
+			}
+
+			$item = array();
+
+			$item['uri'] = $url . '#' . $post->getAttribute('id');
+
+			$title = $post->find('div[class="message-content"] article', 0)->plaintext;
+			$end = strpos($title, ' ', 70);
+			$item['title'] = substr($title, 0, $end);
+
+			$item['timestamp'] = $this->fixDate($post->find('time', 0)->title, $lang);
+			$item['author'] = $post->getAttribute('data-author');
+			$item['content'] = $post->find('div[class="message-content"] article', 0);
+
+			// Bridge specific properties
+			$item['id'] = $post->getAttribute('id');
+
+			$this->items[] = $item;
+
+		}
+
+	}
+
+	private function extractPagesV1($html) {
+
+		// A navigation bar becomes available if the number of posts grows too
+		// high. When this happens we need to load further pages (from last backwards)
+		if(($pageNav = $html->find('div.PageNav', 0))) {
+
+			$lastpage = $pageNav->{'data-last'};
+			$baseurl  = $pageNav->{'data-baseurl'};
+			$sentinel = $pageNav->{'data-sentinel'};
+
+			$hosturl  = parse_url($this->threadurl, PHP_URL_SCHEME)
+			. '://'
+			. parse_url($this->threadurl, PHP_URL_HOST)
+			. '/';
+
+			$page = $lastpage;
+
+			// Load at least the last page
+			do {
+
+				$pageurl = $hosturl . str_replace($sentinel, $lastpage, $baseurl);
+
+				// We can optimize performance by caching all but the last page
+				if($page != $lastpage) {
+					$html = getSimpleHTMLDOMCached($pageurl)
+						or returnServerError('Error loading contents from ' . $pageurl . '!');
+				} else {
+					$html = getSimpleHTMLDOM($pageurl)
+						or returnServerError('Error loading contents from ' . $pageurl . '!');
+				}
+
+				$html = defaultLinkTo($html, $hosturl);
+
+				$this->extractThreadPostsV1($html, $pageurl);
+
+				$page--;
+
+			} while (count($this->items) < $this->getInput('limit') && $page != 1);
+
+		}
+
+	}
+
+	private function extractPagesV2($html) {
+
+		// A navigation bar becomes available if the number of posts grows too
+		// high. When this happens we need to load further pages (from last backwards)
+		if(($pageNav = $html->find('div.pageNav', 0))) {
+
+			foreach($pageNav->find('li') as $nav) {
+				$lastpage = $nav->plaintext;
+			}
+
+			// Manually extract baseurl and inject sentinel
+			$baseurl = $pageNav->find('li a', -1)->href;
+			$baseurl = str_replace('page-' . $lastpage, 'page-{{sentinel}}', $baseurl);
+
+			$sentinel = '{{sentinel}}';
+
+			$hosturl  = parse_url($this->threadurl, PHP_URL_SCHEME)
+			. '://'
+			. parse_url($this->threadurl, PHP_URL_HOST);
+
+			$page = $lastpage;
+
+			// Load at least the last page
+			do {
+
+				$pageurl = $hosturl . str_replace($sentinel, $lastpage, $baseurl);
+
+				// We can optimize performance by caching all but the last page
+				if($page != $lastpage) {
+					$html = getSimpleHTMLDOMCached($pageurl)
+						or returnServerError('Error loading contents from ' . $pageurl . '!');
+				} else {
+					$html = getSimpleHTMLDOM($pageurl)
+						or returnServerError('Error loading contents from ' . $pageurl . '!');
+				}
+
+				$html = defaultLinkTo($html, $this->hosturl);
+
+				$this->extractThreadPostsV2($html, $this->pageurl);
+
+				$page--;
+
+			} while (count($this->items) < $this->getInput('limit') && $page != 1);
+
+		}
+
+	}
+
+	/**
+	 * Fixes dates depending on the choosen language:
+	 *
+	 * de : dd.mm.yy
+	 * en : dd.mm.yy
+	 * it : dd/mm/yy
+	 *
+	 * Basically strtotime doesn't convert dates correctly due to formats
+	 * being hard to interpret. So we use the DateTime object.
+	 *
+	 * We don't know the timezone, so just assume +00:00 (or whatever
+	 * DateTime chooses)
+	 */
+	private function fixDate($date, $lang = 'en-US') {
+
+		$mnamesen = [
+			'January',
+			'Feburary',
+			'March',
+			'April',
+			'May',
+			'June',
+			'July',
+			'August',
+			'September',
+			'October',
+			'November',
+			'December'
+		];
+
+		switch($lang) {
+			case 'en-US': // example: Jun 9, 2018 at 11:46 PM
+
+				$df = date_create_from_format('M d, Y \a\t H:i A', $date);
+				break;
+
+			case 'de-DE': // example: 19 Juli 2018 um 19:27 Uhr
+
+				$mnamesde = [
+					'Januar',
+					'Februar',
+					'März',
+					'April',
+					'Mai',
+					'Juni',
+					'Juli',
+					'August',
+					'September',
+					'Oktober',
+					'November',
+					'Dezember'
+				];
+
+				$mnamesdeshort = [
+					'Jan.',
+					'Feb.',
+					'Mär.',
+					'Apr.',
+					'Mai',
+					'Juni',
+					'Juli',
+					'Aug.',
+					'Sep.',
+					'Okt.',
+					'Nov.',
+					'Dez.'
+				];
+
+				$date = str_ireplace($mnamesde, $mnamesen, $date);
+				$date = str_ireplace($mnamesdeshort, $mnamesen, $date);
+
+				$df = date_create_from_format('d M Y \u\m H:i \U\h\r', $date);
+				break;
+
+		}
+
+		// debugMessage(date_format($df, 'U'));
+
+		return date_format($df, 'U');
+
+	}
+
+}

bridges/YGGTorrentBridge.php

@@ -110,8 +110,8 @@ class YGGTorrentBridge extends BridgeAbstract {
 
 		foreach($results->find('tr') as $row) {
 			$count++;
-			if($count == 1) continue;
-			if($count == 12) break;
+			if($count == 1) continue; // Skip table header
+			if($count == 22) break; // Stop processing after 21 items (20 + 1 table header)
 			$item = array();
 			$item['timestamp'] = $row->find('.hidden', 1)->plaintext;
 			$item['title'] = $row->find('a', 1)->plaintext;
@@ -127,7 +127,7 @@ class YGGTorrentBridge extends BridgeAbstract {
 
 	}
 
-	public function collectTorrentData($url) {
+	private function collectTorrentData($url) {
 
 		//For weird reason, the link we get can be invalid, we fix it.
 		$url_full = explode('/', $url);
@@ -135,7 +135,7 @@ class YGGTorrentBridge extends BridgeAbstract {
 		$url_full[5] = urlencode($url_full[5]);
 		$url_full[6] = urlencode($url_full[6]);
 		$url = implode('/', $url_full);
-		$page = getSimpleHTMLDOM($url) or returnServerError('Unable to query Yggtorrent page !');
+		$page = getSimpleHTMLDOMCached($url) or returnServerError('Unable to query Yggtorrent page !');
 		$author = $page->find('.informations', 0)->find('a', 4)->plaintext;
 		$content = $page->find('.default', 1);
 		return array('author' => $author, 'content' => $content);

bridges/YoutubeBridge.php

@@ -147,12 +147,19 @@ class YoutubeBridge extends BridgeAbstract {
 				$time = 0;
 				$vid = str_replace('/watch?v=', '', $element->find('a', 0)->href);
 				$vid = substr($vid, 0, strpos($vid, '&') ?: strlen($vid));
-				$title = $this->ytBridgeFixTitle($element->find($title_selector, 0)->plaintext);
+				$title = trim($this->ytBridgeFixTitle($element->find($title_selector, 0)->plaintext));
+
+				if (strpos($vid, 'googleads') !== false
+					|| $title == '[Private video]'
+					|| $title == '[Deleted video]'
+				) {
+					continue;
+				}
 
 				// The duration comes in one of the formats:
 				// hh:mm:ss / mm:ss / m:ss
 				// 01:03:30 / 15:06 / 1:24
-				$durationText = trim($element->find('span[class="video-time"]', 0)->plaintext);
+				$durationText = trim($element->find('div.timestamp span', 0)->plaintext);
 				$durationText = preg_replace('/([\d]{1,2})\:([\d]{2})/', '00:$1:$2', $durationText);
 
 				sscanf($durationText, '%d:%d:%d', $hours, $minutes, $seconds);
@@ -162,13 +169,11 @@ class YoutubeBridge extends BridgeAbstract {
 					continue;
 				}
 
-				if($title != '[Private Video]' && strpos($vid, 'googleads') === false) {
-					if ($add_parsed_items) {
-						$this->ytBridgeQueryVideoInfo($vid, $author, $desc, $time);
-						$this->ytBridgeAddItem($vid, $title, $author, $desc, $time);
-					}
-					$count++;
+				if ($add_parsed_items) {
+					$this->ytBridgeQueryVideoInfo($vid, $author, $desc, $time);
+					$this->ytBridgeAddItem($vid, $title, $author, $desc, $time);
 				}
+				$count++;
 			}
 		}
 		return $count;
@@ -181,7 +186,9 @@ class YoutubeBridge extends BridgeAbstract {
 
 	private function ytGetSimpleHTMLDOM($url){
 		return getSimpleHTMLDOM($url,
-			$header = array(),
+			$header = array(
+				'Accept-Language: en-US'
+			),
 			$opts = array(),
 			$lowercase = true,
 			$forceTagsClosed = true,

bridges/ZDNetBridge.php

@@ -1,9 +1,9 @@
 <?php
-class ZDNetBridge extends BridgeAbstract {
+class ZDNetBridge extends FeedExpander {
 
 	const MAINTAINER = 'ORelio';
 	const NAME = 'ZDNet Bridge';
-	const URI = 'http://www.zdnet.com/';
+	const URI = 'https://www.zdnet.com/';
 	const DESCRIPTION = 'Technology News, Analysis, Comments and Product Reviews for IT Professionals.';
 
 	//http://www.zdnet.com/zdnet.opml
@@ -160,143 +160,42 @@ class ZDNetBridge extends BridgeAbstract {
 	));
 
 	public function collectData(){
-
-		function stripCdata($string){
-			$string = str_replace('<![CDATA[', '', $string);
-			$string = str_replace(']]>', '', $string);
-			return trim($string);
-		}
-
-		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 $section_retrieved;
-			}
-
-			return false;
-		}
-
-		function stripWithDelimiters($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 $string;
-		}
-
-		function stripRecursiveHtmlSection($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;
-		}
-
-		$baseUri = self::URI;
+		$baseUri = static::URI;
 		$feed = $this->getInput('feed');
 		if(strpos($feed, 'downloads!') !== false) {
 			$feed = str_replace('downloads!', '', $feed);
 			$baseUri = str_replace('www.', 'downloads.', $baseUri);
 		}
 		$url = $baseUri . trim($feed, '/') . '/rss.xml';
-		$html = getSimpleHTMLDOM($url)
-			or returnServerError('Could not request ZDNet: ' . $url);
-		$limit = 0;
+		$this->collectExpandableDatas($url);
+	}
 
-		foreach($html->find('item') as $element) {
-			if($limit < 10) {
-				$article_url = preg_replace(
-					'/([^#]+)#ftag=.*/',
-					'$1',
-					stripCdata(extractFromDelimiters($element->innertext, '<link>', '</link>'))
-				);
+	protected function parseItem($item){
+		$item = parent::parseItem($item);
 
-				$article_author = stripCdata(extractFromDelimiters($element->innertext, 'role="author">', '<'));
-				$article_title = stripCdata($element->find('title', 0)->plaintext);
-				$article_subtitle = stripCdata($element->find('description', 0)->plaintext);
-				$article_timestamp = strtotime(stripCdata($element->find('pubDate', 0)->plaintext));
-				$article = getSimpleHTMLDOM($article_url)
-					or returnServerError('Could not request ZDNet: ' . $article_url);
+		$article = getSimpleHTMLDOMCached($item['uri']);
+		if(!$article)
+			returnServerError('Could not request ZDNet: ' . $url);
 
-				if(!empty($article_author)) {
-					$author = $article_author;
-				} else {
-					$author = $article->find('meta[name=author]', 0);
-					if(is_object($author)) {
-						$author = $author->content;
-					} else {
-						$author = 'ZDNet';
-					}
-				}
-
-				$thumbnail = $article->find('meta[itemprop=image]', 0);
-				if(is_object($thumbnail)) {
-					$thumbnail = $thumbnail->content;
-				} else {
-					$thumbnail = '';
-				}
-
-				$contents = $article->find('article', 0)->innertext;
-				foreach(array(
-					'<div class="shareBar"',
-					'<div class="shortcodeGalleryWrapper"',
-					'<div class="relatedContent',
-					'<div class="downloadNow',
-					'<div data-shortcode',
-					'<div id="sharethrough',
-					'<div id="inpage-video'
-				) as $div_start) {
-					$contents = stripRecursiveHtmlSection($contents, 'div', $div_start);
-				}
-				$contents = stripWithDelimiters($contents, '<script', '</script>');
-				$contents = stripWithDelimiters($contents, '<meta itemprop="image"', '>');
-				$contents = trim(stripWithDelimiters($contents, '<section class="sharethrough-top', '</section>'));
-				$content_img = strpos($contents, '<img'); //Look for first image
-				if (($content_img !== false && $content_img < 512) || $thumbnail == '') {
-					$content_img = ''; //Image already present on article beginning or no thumbnail
-				} else {
-					$content_img = '<p><img src="'.$thumbnail.'" /></p>'; //Include thumbnail
-				}
-				$contents = $content_img
-				. '<p><b>'
-				. $article_subtitle
-				. '</b></p>'
-				. $contents;
-
-				$item = array();
-				$item['author'] = $author;
-				$item['uri'] = $article_url;
-				$item['title'] = $article_title;
-				$item['timestamp'] = $article_timestamp;
-				$item['content'] = $contents;
-				$this->items[] = $item;
-				$limit++;
-			}
+		$contents = $article->find('article', 0)->innertext;
+		foreach(array(
+			'<div class="shareBar"',
+			'<div class="shortcodeGalleryWrapper"',
+			'<div class="relatedContent',
+			'<div class="downloadNow',
+			'<div data-shortcode',
+			'<div id="sharethrough',
+			'<div id="inpage-video'
+		) as $div_start) {
+			$contents = stripRecursiveHtmlSection($contents, 'div', $div_start);
 		}
+		$contents = stripWithDelimiters($contents, '<script', '</script>');
+		$contents = stripWithDelimiters($contents, '<meta itemprop="image"', '>');
+		$contents = stripWithDelimiters($contents, '<svg class="svg-symbol', '</svg>');
+		$contents = trim(stripWithDelimiters($contents, '<section class="sharethrough-top', '</section>'));
+		$item['content'] = $contents;
+
+		return $item;
 
 	}
 }

bridges/ZoneTelechargementBridge.php

@@ -0,0 +1,88 @@
+<?php
+class ZoneTelechargementBridge extends BridgeAbstract {
+	const NAME = 'Zone Telechargement';
+	const URI = 'https://www.zone-telechargement1.org/';
+	const DESCRIPTION = 'Suivi de série sur Zone Telechargement';
+	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://ww4.zone-telechargement1.org/',
+				'exampleValue' => 'telecharger-series/31079-halt-and-catch-fire-saison-4-french-hd720p.html'
+			)
+		)
+	);
+
+	public function getIcon() {
+		return 'https://ww7.zone-telechargement1.org/templates/Default/images/favicon.ico';
+	}
+
+	public function collectData(){
+		$html = getSimpleHTMLDOM(self::URI . $this->getInput('url'))
+			or returnServerError('Could not request Zone Telechargement.');
+
+		// Get the TV show title
+		$qualityselector = 'div[style=font-size: 18px;margin: 10px auto;color:red;font-weight:bold;text-align:center;]';
+		$show = trim($html->find('div[class=smallsep]', 0)->next_sibling()->plaintext);
+		$quality = trim(explode("\n", $html->find($qualityselector, 0)->plaintext)[0]);
+		$this->showTitle = $show . ' ' . $quality;
+
+		// Get the post content
+		$linkshtml = $html->find('div[class=postinfo]', 0);
+
+		$episodes = array();
+
+		$list = $linkshtml->find('a');
+		// Construct the tabble of episodes using the links
+		foreach($list as $element) {
+			// Retrieve episode number from link text
+			$epnumber = explode(' ', $element->plaintext)[1];
+			$hoster = $this->findLinkHoster($element);
+
+			// Format the link and add the link to the corresponding episode table
+			$episodes[$epnumber][] = '<a href="' . $element->href . '">' . $hoster . ' - '
+				. $this->showTitle . ' Episode ' . $epnumber . '</a>';
+
+		}
+
+		// Finally construct the items array
+		foreach($episodes as $epnum => $episode) {
+			$item = array();
+			// Add every link available in the episode table separated by a <br/> tag
+			$item['content'] = implode('<br/>', $episode);
+			$item['title'] = $this->showTitle . ' Episode ' . $epnum;
+			// 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', $item['title']);
+			// Insert the episode at the beginning of the item list, to show the newest episode first
+			array_unshift($this->items, $item);
+		}
+	}
+
+	public function getName() {
+		switch($this->queriedContext) {
+		case 'Suivre la publication des épisodes d\'une série en cours de diffusion':
+			return $this->showTitle . ' - ' . self::NAME;
+			break;
+		default:
+			return self::NAME;
+		}
+	}
+
+	private function findLinkHoster($element) {
+		// The hoster name is one level higher than the link tag : get the parent element
+		$element = $element->parent();
+		//echo "PARENT : $element \n";
+		$continue = true;
+		// Walk through all elements in the reverse order until finding the one with a div and that is not a <br/>
+		while(!($element->find('div', 0) != null && $element->tag != 'br')) {
+			$element = $element->prev_sibling();
+		}
+		// Return the text of the div : it's the file hoster name !
+		return $element->find('div', 0)->plaintext;
+
+	}
+}

caches/FileCache.php

@@ -27,6 +27,7 @@ class FileCache implements CacheInterface {
 
 	public function getTime(){
 		$cacheFile = $this->getCacheFile();
+		clearstatcache(false, $cacheFile);
 		if(file_exists($cacheFile)) {
 			return filemtime($cacheFile);
 		}

config.default.ini.php

@@ -11,6 +11,12 @@
 ; false = disabled (default)
 custom_timeout = false
 
+[admin]
+; Advertise an email address where people can reach the administrator.
+; This address is displayed on the main page, visible to everyone!
+; ""    = Disabled (default)
+email = ""
+
 [proxy]
 
 ; Sets the proxy url (i.e. "tcp://192.168.0.0:32")

formats/AtomFormat.php

@@ -11,14 +11,18 @@ class AtomFormat extends FormatAbstract{
 		$httpHost = isset($_SERVER['HTTP_HOST']) ? $_SERVER['HTTP_HOST'] : '';
 		$httpInfo = isset($_SERVER['PATH_INFO']) ? $_SERVER['PATH_INFO'] : '';
 
-		$serverRequestUri = $this->xml_encode($_SERVER['REQUEST_URI']);
+		$serverRequestUri = isset($_SERVER['REQUEST_URI']) ? $this->xml_encode($_SERVER['REQUEST_URI']) : '';
 
 		$extraInfos = $this->getExtraInfos();
 		$title = $this->xml_encode($extraInfos['name']);
 		$uri = !empty($extraInfos['uri']) ? $extraInfos['uri'] : 'https://github.com/RSS-Bridge/rss-bridge';
 
 		$uriparts = parse_url($uri);
-		$icon = $this->xml_encode($uriparts['scheme'] . '://' . $uriparts['host'] .'/favicon.ico');
+		if(!empty($extraInfos['icon'])) {
+			$icon = $extraInfos['icon'];
+		} else {
+			$icon = $this->xml_encode($uriparts['scheme'] . '://' . $uriparts['host'] . '/favicon.ico');
+		}
 
 		$uri = $this->xml_encode($uri);
 
@@ -35,7 +39,7 @@ class AtomFormat extends FormatAbstract{
 				foreach($item['enclosures'] as $enclosure) {
 					$entryEnclosures .= '<link rel="enclosure" href="'
 					. $this->xml_encode($enclosure)
-					. '"/>'
+					. '" type="' . getMimeType($enclosure) . '" />'
 					. PHP_EOL;
 				}
 			}

formats/HtmlFormat.php

@@ -48,7 +48,7 @@ class HtmlFormat extends FormatAbstract {
 			}
 
 			$entryCategories = '';
-			if(isset($item['categories'])) {
+			if(isset($item['categories']) && count($item['categories']) > 0) {
 				$entryCategories = '<div class="categories"><p>Categories:</p>';
 
 				foreach($item['categories'] as $category) {
@@ -85,6 +85,8 @@ EOD;
 	<meta charset="{$charset}">
 	<title>{$title}</title>
 	<link href="static/HtmlFormat.css" rel="stylesheet">
+	<link rel="alternate" type="application/atom+xml" title="Atom" href="./?{$atomquery}" />
+	<link rel="alternate" type="application/rss+xml" title="RSS" href="/?{$mrssquery}" />
 	<meta name="robots" content="noindex, follow">
 </head>
 <body>