1
0
mirror of https://github.com/RSS-Bridge/rss-bridge.git synced 2025-08-30 11:30:11 +02:00

Compare commits

..

22 Commits

Author SHA1 Message Date
teromene
b0c7a62f74 [index] Bumped version to 2018-04-20 2018-04-20 17:15:25 +02:00
teromene
57b15a089e Added DiscogsBridge. Closes #615 2018-04-20 16:57:09 +02:00
teromene
4b7fbe4188 DansTonChatBridge: test before accessing plaintext 2018-04-19 21:00:18 +02:00
Teromene
2390fb58b3 Merge pull request #673 from GregThib/patch-1
DansTonChatBridge: Update to follow DTC website changes
2018-04-19 20:58:01 +02:00
Teromene
1e8d29f6ec Merge pull request #672 from em92/patch-3
[YoutubeBridge] Removed duration in titles on search mode
2018-04-19 20:56:34 +02:00
Eugene Molotov
644d13686c [YoutubeBridge] Removed duration in titles on search mode 2018-04-19 09:03:29 +05:00
teromene
aa0ff1c9b1 Added YGGTorrentBridge. 2018-04-18 21:57:27 +02:00
teromene
539d9f1f06 Add SupInfoBridge, fixes #668 2018-04-18 12:39:45 +02:00
teromene
5ece801ce7 Fix h* display size in HtmlFormat, and fix images being wider than the page. 2018-04-18 12:29:22 +02:00
GregThib
4dcea6d9c9 Update to follow DTC website changes
Now, entry title is optionnal and may be found in h3 HTML element.
Entry content is mandatory and may be found in div[class="item-content"] HTML element.

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

* [VkBridge] Generate feed item title

* [VkBridge] Remove double backslashes in feed item link

* [VkBridge] Unpin post if pinned

* [VkBridge] Mark reposted messages

* [VkBridge] Correct external link parsing

* [VkBridge] Added article parsing

* [VkBridge] Added video parsing

* [VkBridge] Added photo parsing

* [VkBridge] Added album link parsing

* [VkBridge] Added one more external link selector

* [VkBridge] Using array of link selectors to remove

* [VkBridge] Added document parsing

* [VkBridge] Added sign parsing

* [VkBridge] Fixed incorrect sorting with pinned item

* [VkBridge] More methods to parse documents

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

* [VkBridge] Using post signed as feed item author

* [VkBridge] Fixed document link

* [VkBridge] Coding policy fixes
2018-04-16 10:55:31 +01:00
Mitsukarenai
208fff801d [FDroid] minor fixes for Travis CI 2018-04-15 13:21:48 +02:00
Mitsukarenai
3c9860de43 [FDroid] new bridge 2018-04-15 13:13:10 +02:00
Adam Tygart
a16ec196c5 [NotAlways] Add a bridge for the NotAlways family of sites (#537)
NotAlways right found it necessary to remove their RSS feeds recently. This is a *simple* bridge to grab the ones on the front page. It allows you to filter the articles based on their classification (right, working, romantic, related, learning, friendly, hopeless, unfiltered, or all).
2018-04-15 12:02:37 +01:00
teromene
887fc7b037 Fix GoComics, website completely changed. Fixes #663 2018-04-14 18:15:44 +01:00
teromene
1bd4a40f71 Added GNOME Builder configuration to gitignore. 2018-04-14 18:15:13 +01:00
teromene
494169f959 Added bridge for Pixiv.
This bridge is slow, as caching of images is required (REFERER header required to access the full size images)
2018-04-14 16:19:35 +01:00
17 changed files with 872 additions and 257 deletions

5
.gitignore vendored
View File

@@ -231,4 +231,7 @@ DEBUG
######################
## VisualStudioCode ##
######################
.vscode/*
.vscode/*
#Builder
.buildconfig

View File

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

View File

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

112
bridges/DiscogsBridge.php Normal file
View File

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

54
bridges/FDroidBridge.php Normal file
View File

@@ -0,0 +1,54 @@
<?php
class FDroidBridge extends BridgeAbstract {
const MAINTAINER = 'Mitsukarenai';
const NAME = 'F-Droid Bridge';
const URI = 'https://f-droid.org/';
const CACHE_TIMEOUT = 60 * 60 * 2; // 2 hours
const DESCRIPTION = 'Returns latest added/updated apps on the open-source Android apps repository F-Droid';
const PARAMETERS = array( array(
'u' => array(
'name' => 'Widget selection',
'type' => 'list',
'required' => true,
'values' => array(
'Latest added apps' => 'added',
'Latest updated apps' => 'updated'
)
)
));
public function collectData(){
$url = self::URI;
$html = getSimpleHTMLDOM($url)
or returnServerError('Could not request F-Droid.');
// targetting the corresponding widget based on user selection
// "updated" is the 4th widget on the page, "added" is the 5th
switch($this->getInput('u')) {
case 'updated':
$html_widget = $html->find('div.sidebar-widget', 4);
break;
default:
$html_widget = $html->find('div.sidebar-widget', 5);
break;
}
// and now extracting app info from the selected widget (and yeah turns out icons are of heterogeneous sizes)
foreach($html_widget->find('a') as $element) {
$item = array();
$item['uri'] = self::URI . $element->href;
$item['title'] = $element->find('h4', 0)->plaintext;
$item['icon'] = $element->find('img', 0)->src;
$item['summary'] = $element->find('span.package-summary', 0)->plaintext;
$item['content'] = '
<a href="'.$item['uri'].'">
<img alt="" style="max-height:128px" src="'.$item['icon'].'">
</a><br>'.$item['summary'];
$this->items[] = $item;
}
}
}

View File

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

View File

@@ -95,6 +95,7 @@ class InstagramBridge extends BridgeAbstract {
$item['title'] = basename($media->display_url);
}
$item['timestamp'] = $media->taken_at_timestamp;
$item['enclosures'] = array($media->display_url);
$this->items[] = $item;
}
}

View File

@@ -0,0 +1,57 @@
<?php
class NotAlwaysBridge extends BridgeAbstract {
const MAINTAINER = 'mozes';
const NAME = 'Not Always family Bridge';
const URI = 'https://notalwaysright.com/';
const DESCRIPTION = 'Returns the latest stories';
const CACHE_TIMEOUT = 1800; // 30 minutes
const PARAMETERS = array( array(
'filter' => array(
'type' => 'list',
'name' => 'Filter',
'values' => array(
'All' => 'all',
'Right' => 'right',
'Working' => 'working',
'Romantic' => 'romantic',
'Related' => 'related',
'Learning' => 'learning',
'Friendly' => 'friendly',
'Hopeless' => 'hopeless',
'Unfiltered' => 'unfiltered'
),
'required' => true
)
));
public function collectData(){
$html = getSimpleHTMLDOM($this->getURI())
or returnServerError('Could not request NotAlways.');
foreach($html->find('.post') as $post) {
#print_r($post);
$item = array();
$item['uri'] = $post->find('h1', 0)->find('a', 0)->href;
$item['content'] = $post;
$item['title'] = $post->find('h1', 0)->find('a', 0)->innertext;
$this->items[] = $item;
}
}
public function getName(){
if(!is_null($this->getInput('filter'))) {
return $this->getInput('filter') . ' - NotAlways Bridge';
}
return parent::getName();
}
public function getURI(){
if(!is_null($this->getInput('filter'))) {
return self::URI . $this->getInput('filter') . "/";
}
return parent::getURI();
}
}

73
bridges/PixivBridge.php Normal file
View File

@@ -0,0 +1,73 @@
<?php
class PixivBridge extends BridgeAbstract {
const MAINTAINER = 'teromene';
const NAME = 'Pixiv Bridge';
const URI = 'https://www.pixiv.net/';
const DESCRIPTION = 'Returns the tag search from pixiv.net';
const PARAMETERS = array( array(
'tag' => array(
'name' => 'Tag to search',
'exampleValue' => 'example',
'required' => true
),
));
public function collectData(){
$html = getContents(static::URI.'search.php?word=' . urlencode($this->getInput('tag')))
or returnClientError('Unable to query pixiv.net');
$regex = '/<input type="hidden"id="js-mount-point-search-result-list"data-items="([^"]*)/';
$timeRegex = '/img\/([0-9]{4})\/([0-9]{2})\/([0-9]{2})\/([0-9]{2})\/([0-9]{2})\/([0-9]{2})\//';
preg_match_all($regex, $html, $matches, PREG_SET_ORDER, 0);
if(!$matches) return;
$content = json_decode(html_entity_decode($matches[0][1]), true);
$count = 0;
foreach($content as $result) {
if($count == 10) break;
$count++;
$item = array();
$item["id"] = $result["illustId"];
$item["uri"] = "https://www.pixiv.net/member_illust.php?mode=medium&illust_id=" . $result["illustId"];
$item["title"] = $result["illustTitle"];
$item["author"] = $result["userName"];
preg_match_all($timeRegex, $result["url"], $dt, PREG_SET_ORDER, 0);
$elementDate = DateTime::createFromFormat("YmdHis",
$dt[0][1] . $dt[0][2] . $dt[0][3] . $dt[0][4] . $dt[0][5] . $dt[0][6]);
$item["timestamp"] = $elementDate->getTimestamp();
$item["content"] = "<img src='" . $this->cacheImage($result['url'], $item["id"]) . "' />";
$this->items[] = $item;
}
}
public function cacheImage($url, $illustId) {
$url = str_replace("_master1200", "", $url);
$url = str_replace("c/240x240/img-master/", "img-original/", $url);
$path = CACHE_DIR . '/pixiv_img';
if(!is_dir($path))
mkdir($path, 0755, true);
if(!is_file($path . '/' . $illustId . '.jpeg')) {
$headers = array("Referer: https://www.pixiv.net/member_illust.php?mode=medium&illust_id=" . $illustId);
$illust = getContents($url, $headers);
if(strpos($illust, "404 Not Found") !== false) {
$illust = getContents(str_replace("jpg", "png", $url), $headers);
}
file_put_contents($path . '/' . $illustId . '.jpeg', $illust);
}
return 'cache/pixiv_img/' . $illustId . ".jpeg";
}
}

View File

@@ -14,7 +14,7 @@ class SoundCloudBridge extends BridgeAbstract {
)
));
const CLIENT_ID = '0aca19eae3843844e4053c6d8fdb7875';
const CLIENT_ID = '4jkoEFmZEDaqjwJ9Eih4ATNhcH3vMVfp';
public function collectData(){

57
bridges/SupInfoBridge.php Normal file
View File

@@ -0,0 +1,57 @@
<?php
class SupInfoBridge extends BridgeAbstract {
const MAINTAINER = 'teromene';
const NAME = 'SupInfoBridge';
const URI = 'https://www.supinfo.com';
const DESCRIPTION = 'Returns the newest articles.';
const PARAMETERS = array(array(
'tag' => array(
'name' => 'Category (not mandatory)',
'type' => 'text',
)
));
public function collectData() {
if(empty($this->getInput('tag'))) {
$html = getSimpleHTMLDOM(self::URI . '/articles/')
or returnServerError('Unable to fetch articles !');
} else {
$html = getSimpleHTMLDOM(self::URI . '/articles/tag/' . $this->getInput('tag'))
or returnServerError('Unable to fetch articles !');
}
$content = $html->find('#latest', 0)->find('ul[class=courseContent]', 0);
for($i = 0; $i < 5; $i++) {
$this->items[] = $this->fetchArticle($content->find('h4', $i)->find('a', 0)->href);
}
}
public function fetchArticle($link) {
$articleHTML = getSimpleHTMLDOM(self::URI . $link)
or returnServerError('Unable to fetch article !');
$article = $articleHTML->find('div[id=courseDocZero]', 0);
$item = array();
$item['author'] = $article->find('#courseMetas', 0)->find('a', 0)->plaintext;
$item['id'] = $link;
$item['uri'] = self::URI . $link;
$item['title'] = $article->find('h1', 0)->plaintext;
$date = explode(' ', $article->find('#courseMetas', 0)->find('span', 1)->plaintext);
$item['timestamp'] = DateTime::createFromFormat('d/m/Y H:i:s', $date[2] . ' ' . $date[4])->getTimestamp();
$article->find('div[id=courseHeader]', 0)->innertext = '';
$article->find('div[id=author-infos]', 0)->innertext = '';
$article->find('div[id=cartouche-tete]', 0)->innertext = '';
$item['content'] = $article;
return $item;
}
}

View File

@@ -1,96 +0,0 @@
<?php
class T411Bridge extends BridgeAbstract {
const MAINTAINER = 'ORelio';
const NAME = 'T411 Bridge';
const URI = 'https://www.t411.al/';
const DESCRIPTION = 'Returns the 10 newest torrents with specified search
terms <br /> Use url part after "?" mark when using their search engine.';
const PARAMETERS = array( array(
'search' => array(
'name' => 'Search criteria',
'required' => true
)
));
public function collectData(){
//Utility function for retrieving text based on 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;
}
return false;
}
//Retrieve torrent listing from search results, which does not contain torrent description
$url = self::URI
. 'torrents/search/?search='
. urlencode($this->getInput('search'))
. '&order=added&type=desc';
$html = getSimpleHTMLDOM($url)
or returnServerError('Could not request t411: ' . $url);
$results = $html->find('table.results', 0);
if (is_null($results))
returnServerError('No results from t411: ' . $url);
$limit = 0;
//Process each item individually
foreach($results->find('tr') as $element) {
//Limit total amount of requests and ignore table header
if($limit >= 10) {
break;
}
if(is_object($element->find('th', 0))) {
continue;
}
//Requests are rate-limited
usleep(500000); //So we need to wait (500ms)
//Retrieve data from RSS entry
$item_uri = self::URI
. 'torrents/details/?id='
. extractFromDelimiters($element->find('a.nfo', 0)->outertext, '?id=', '"');
$item_title = extractFromDelimiters($element->outertext, '" title="', '"');
$item_date = strtotime($element->find('dd', 0)->plaintext);
//Retrieve full description from torrent page
$item_html = getSimpleHTMLDOM($item_uri);
if(!$item_html) {
continue;
}
//Retrieve data from page contents
$item_desc = $item_html->find('div.description', 0);
$item_author = $item_html->find('a.profile', 0)->innertext;
//Cleanup advertisments
$divs = explode('<div class="align-center">', $item_desc->innertext);
$item_desc = '';
foreach ($divs as $text)
if (strpos($text, 'adprovider.adlure.net') === false)
$item_desc = $item_desc . '<div class="align-center">' . $text;
$item_desc = preg_replace('/<h2 class="align-center">LIENS DE T..?L..?CHARGEMENT<\/h2>/i', '', $item_desc);
//Build and add final item
$item = array();
$item['uri'] = $item_uri;
$item['title'] = $item_title;
$item['author'] = $item_author;
$item['timestamp'] = $item_date;
$item['content'] = $item_desc;
$this->items[] = $item;
$limit++;
}
}
}

View File

@@ -43,40 +43,225 @@ class VkBridge extends BridgeAbstract
or returnServerError('No results for group or user name "' . $this->getInput('u') . '".');
$text_html = iconv('windows-1251', 'utf-8', $text_html);
// makes album link generating work correctly
$text_html = str_replace('"class="page_album_link">', '" class="page_album_link">', $text_html);
$html = str_get_html($text_html);
$pageName = $html->find('.page_name', 0)->plaintext;
$this->pageName = $pageName;
$pageName = $html->find('.page_name', 0);
if (is_object($pageName)) {
$pageName = $pageName->plaintext;
$this->pageName = htmlspecialchars_decode($pageName);
}
$pinned_post_item = null;
$last_post_id = 0;
foreach ($html->find('.post') as $post) {
$is_pinned_post = false;
if (strpos($post->getAttribute('class'), 'post_fixed') !== false) {
$is_pinned_post = true;
}
if (is_object($post->find('a.wall_post_more', 0))) {
//delete link "show full" in content
$post->find('a.wall_post_more', 0)->outertext = '';
}
$content_suffix = "";
// looking for external links
$external_link_selectors = array(
'a.page_media_link_title',
'div.page_media_link_title > a',
'div.media_desc > a.lnk',
);
foreach($external_link_selectors as $sel) {
if (is_object($post->find($sel, 0))) {
$a = $post->find($sel, 0);
$innertext = $a->innertext;
$parsed_url = parse_url($a->getAttribute('href'));
if (strpos($parsed_url['path'], '/away.php') !== 0) continue;
parse_str($parsed_url["query"], $parsed_query);
$content_suffix .= "<br>External link: <a href='" . $parsed_query["to"] . "'>$innertext</a>";
}
}
// remove external link from content
$external_link_selectors_to_remove = array(
'div.page_media_thumbed_link',
'div.page_media_link_desc_wrap',
'div.media_desc > a.lnk',
);
foreach($external_link_selectors_to_remove as $sel) {
if (is_object($post->find($sel, 0))) {
$post->find($sel, 0)->outertext = '';
}
}
// looking for article
$article = $post->find("a.article_snippet", 0);
if (is_object($article)) {
$article_title = $article->find("div.article_snippet__title", 0)->innertext;
$article_author = $article->find("div.article_snippet__author", 0)->innertext;
$article_link = self::URI . ltrim($article->getAttribute('href'), '/');
$article_img_element_style = $article->find("div.article_snippet__image", 0)->getAttribute('style');
preg_match('/background-image: url\((.*)\)/', $article_img_element_style, $matches);
if (count($matches) > 0) {
$content_suffix .= "<br><img src='" . $matches[1] . "'>";
}
$content_suffix .= "<br>Article: <a href='$article_link'>$article_title ($article_author)</a>";
$article->outertext = '';
}
// get video on post
$video = $post->find('div.post_video_desc', 0);
if (is_object($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>";
$video->outertext = '';
}
// get all photos
foreach($post->find('div.wall_text > a.page_post_thumb_wrap') as $a) {
$result = $this->getPhoto($a);
if ($result == null) continue;
$a->outertext = '';
$content_suffix .= "<br>$result";
}
// get albums
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'), '/');
$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_gif_label_element = $a->find(".page_gif_label", 0);
$doc_title_element = $a->find(".doc_label", 0);
if (is_object($doc_gif_label_element)) {
$gif_preview_img = backgroundToImg($a->find('.page_doc_photo', 0));
$content_suffix .= "<br>Gif: <a href='$doc_link'>$gif_preview_img</a>";
} else if (is_object($doc_title_element)) {
$doc_title = $doc_title_element->innertext;
$content_suffix .= "<br>Doc: <a href='$doc_link'>$doc_title</a>";
} else {
continue;
}
$a->outertext = '';
}
// get other documents
foreach($post->find('div.page_doc_row') as $div) {
$doc_title_element = $div->find("a.page_doc_title", 0);
if (is_object($doc_title_element)) {
$doc_title = $doc_title_element->innertext;
$doc_link = self::URI . ltrim($doc_title_element->getAttribute('href'), '/');
$content_suffix .= "<br>Doc: <a href='$doc_link'>$doc_title</a>";
} else {
continue;
}
$div->outertext = '';
}
// get sign
$post_author = $pageName;
foreach($post->find('a.wall_signed_by') as $a) {
$post_author = $a->innertext;
$a->outertext = '';
}
if (is_object($post->find('div.copy_quote', 0))) {
$copy_quote = $post->find('div.copy_quote', 0);
if ($copy_post_header = $copy_quote->find('div.copy_post_header', 0)) {
$copy_post_header->outertext = '';
}
$copy_quote_content = $copy_quote->innertext;
$copy_quote->outertext = "<br>Reposted: <br>$copy_quote_content";
}
$item = array();
$item['content'] = strip_tags(backgroundToImg($post->find('div.wall_text', 0)->innertext), '<br><img>');
if (is_object($post->find('a.page_media_link_title', 0))) {
$link = $post->find('a.page_media_link_title', 0)->getAttribute('href');
//external link in the post
$item['content'] .= "\n\rExternal link: "
. str_replace('/away.php?to=', '', urldecode($link));
}
//get video on post
if (is_object($post->find('span.post_video_title_content', 0))) {
$titleVideo = $post->find('span.post_video_title_content', 0)->plaintext;
$linkToVideo = self::URI . $post->find('a.page_post_thumb_video', 0)->getAttribute('href');
$item['content'] .= "\n\r {$titleVideo}: {$linkToVideo}";
}
$item['content'] .= $content_suffix;
// get post link
$item['uri'] = self::URI . $post->find('a.post_link', 0)->getAttribute('href');
$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['author'] = $pageName;
$this->items[] = $item;
$item['title'] = $this->getTitle($item['content']);
$item['author'] = $post_author;
if ($is_pinned_post) {
// do not append it now
$pinned_post_item = $item;
} else {
$last_post_id = $item['post_id'];
$this->items[] = $item;
}
}
if (is_null($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'] - $item1['post_id'];
});
}
}
private function getPhoto($a) {
$onclick = $a->getAttribute('onclick');
preg_match('/return showPhoto\(.+?({.*})/', $onclick, $preg_match_result);
if (count($preg_match_result) == 0) return;
$arg = htmlspecialchars_decode( str_replace('queue:1', '"queue":1', $preg_match_result[1]) );
$data = json_decode($arg, true);
if ($data == null) return;
$thumb = $data['temp']['base'] . $data['temp']['x_'][0] . ".jpg";
$original = '';
foreach(array('y_', 'z_', 'w_') as $key) {
if (!isset($data['temp'][$key])) continue;
$original = $data['temp']['base'] . $data['temp'][$key][0] . ".jpg";
}
if ($original) {
return "<a href='$original'><img src='$thumb'></a>";
} else {
return "<img src='$thumb'>";
}
}
private function getTitle($content)
{
preg_match('/^["\w\ \p{Cyrillic}\(\)\?#«»-]+/mu', htmlspecialchars_decode($content), $result);
if (count($result) == 0) return "untitled";
return $result[0];
}
private function getTime($post)

View File

@@ -0,0 +1,138 @@
<?php
/* This is a mashup of FlickrExploreBridge by sebsauvage and FlickrTagBridge
* by erwang.providing the functionality of both in one.
*/
class YGGTorrentBridge extends BridgeAbstract {
const MAINTAINER = 'teromene';
const NAME = 'Yggtorrent Bridge';
const URI = 'https://yggtorrent.is';
const DESCRIPTION = 'Returns torrent search from Yggtorrent';
const PARAMETERS = array(
array(
"cat" => array(
"name" => "category",
"type" => "list",
"values" => array(
"Toute les catégories" => "all.all",
"Film/Vidéo - Toutes les sous-catégories" => "2145.all",
"Film/Vidéo - Animation" => "2145.2178",
"Film/Vidéo - Animation Série" => "2145.2179",
"Film/Vidéo - Concert" => "2145.2180",
"Film/Vidéo - Documentaire" => "2145.2181",
"Film/Vidéo - Émission TV" => "2145.2182",
"Film/Vidéo - Film" => "2145.2183",
"Film/Vidéo - Série TV" => "2145.2184",
"Film/Vidéo - Spectacle" => "2145.2185",
"Film/Vidéo - Sport" => "2145.2186",
"Film/Vidéo - Vidéo-clips" => "2145.2186",
"Audio - Toutes les sous-catégories" => "2139.all",
"Audio - Karaoké" => "2139.2147",
"Audio - Musique" => "2139.2148",
"Audio - Podcast Radio" => "2139.2150",
"Audio - Samples" => "2139.2149",
"Jeu vidéo - Toutes les sous-catégories" => "2142.all",
"Jeu vidéo - Autre" => "2142.2167",
"Jeu vidéo - Linux" => "2142.2159",
"Jeu vidéo - MacOS" => "2142.2160",
"Jeu vidéo - Microsoft" => "2142.2162",
"Jeu vidéo - Nintendo" => "2142.2163",
"Jeu vidéo - Smartphone" => "2142.2165",
"Jeu vidéo - Sony" => "2142.2164",
"Jeu vidéo - Tablette" => "2142.2166",
"Jeu vidéo - Windows" => "2142.2161",
"eBook - Toutes les sous-catégories" => "2140.all",
"eBook - Audio" => "2140.2151",
"eBook - Bds" => "2140.2152",
"eBook - Comics" => "2140.2153",
"eBook - Livres" => "2140.2154",
"eBook - Mangas" => "2140.2155",
"eBook - Presse" => "2140.2156",
"Emulation - Toutes les sous-catégories" => "2141.all",
"Emulation - Emulateurs" => "2141.2157",
"Emulation - Roms" => "2141.2158",
"GPS - Toutes les sous-catégories" => "2141.all",
"GPS - Applications" => "2141.2168",
"GPS - Cartes" => "2141.2169",
"GPS - Divers" => "2141.2170"
)
),
"nom" => array(
"name" => "Nom",
"description" => "Nom du torrent",
"type" => "text"
),
"description" => array(
"name" => "Description",
"description" => "Description du torrent",
"type" => "text"
),
"fichier" => array(
"name" => "Fichier",
"description" => "Fichier du torrent",
"type" => "text"
),
"uploader" => array(
"name" => "Uploader",
"description" => "Uploader du torrent",
"type" => "text"
),
)
);
public function collectData() {
$catInfo = explode(".", $this->getInput("cat"));
$category = $catInfo[0];
$subcategory = $catInfo[1];
$html = getSimpleHTMLDOM(self::URI . "/engine/search?name="
. $this->getInput("nom")
. "&description="
. $this->getInput("description")
. "&fichier="
. $this->getInput("fichier")
. "&file="
. $this->getInput("uploader")
. "&category="
. $category
. "&sub_category="
. $subcategory
. "&do=search")
or returnServerError("Unable to query Yggtorrent !");
$count = 0;
foreach($html->find(".results", 0)->find("tr") as $row) {
$count++;
if($count == 1) continue;
if($count == 12) break;
$item = array();
$item["timestamp"] = $row->find(".hidden", 1)->plaintext;
$item["title"] = $row->find("a", 1)->plaintext;
$torrentData = $this->collectTorrentData($row->find("a", 1)->href);
$item["author"] = $torrentData["author"];
$item["content"] = $torrentData["content"];
$item["seeders"] = $row->find("td", 7)->plaintext;
$item["leechers"] = $row->find("td", 8)->plaintext;
$item["size"] = $row->find("td", 5)->plaintext;
$this->items[] = $item;
}
}
public function collectTorrentData($url) {
//For weird reason, the link we get can be invalid, we fix it.
$url_full = explode("/", $url);
$url_full[6] = urlencode($url_full[6]);
$url = implode("/", $url_full);
$page = getSimpleHTMLDOM($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);
}
}

View File

@@ -207,7 +207,7 @@ class YoutubeBridge extends BridgeAbstract {
$html = $this->ytGetSimpleHTMLDOM($url_listing)
or returnServerError("Could not request YouTube. Tried:\n - $url_listing");
$this->ytBridgeParseHtmlListing($html, 'div.yt-lockup', 'h3');
$this->ytBridgeParseHtmlListing($html, 'div.yt-lockup', 'h3 > a');
$this->feedName = 'Search: ' . str_replace(' - YouTube', '', $html->find('title', 0)->plaintext); // feedName will be used by getName()
} else { /* no valid mode */
returnClientError("You must either specify either:\n - YouTube

View File

@@ -303,7 +303,7 @@ EOD;
echo $inactiveBridges;
?>
<section class="footer">
<a href="https://github.com/RSS-Bridge/rss-bridge">RSS-Bridge 2018-04-06 ~ Public Domain</a><br />
<a href="https://github.com/RSS-Bridge/rss-bridge">RSS-Bridge 2018-04-20 ~ Public Domain</a><br />
<?= $activeFoundBridgeCount; ?>/<?= count($bridgeList) ?> active bridges. <br />
<?php
if($activeFoundBridgeCount !== count($bridgeList)) {

View File

@@ -5,7 +5,6 @@ html, body, div, span, applet, object, iframe, h1, h2, h3, h4, h5, h6, p, blockq
border: 0;
outline: 0;
font-size: 100%;
font: inherit;
vertical-align: baseline;
}
@@ -111,3 +110,8 @@ button.backbutton, button.rss-feed {
}
img {
max-width: 100%;
}