Merge pull request #3 from RSS-Bridge/master

123

.travis.yml

@@ -2,20 +2,6 @@ dist: trusty
 sudo: false
 language: php
 
-before_install:
-  # Circumvent a bug in current Travis CI builds using Ubuntu Trusty, where the
-  # include_path is wrong.
-  #
-  # Default is:
-  # - include_path='.:/home/travis/.phpenv/versions/5.6.31/share/pear'
-  #
-  # Should be:
-  # - include_path='.:/home/travis/.phpenv/versions/5.6.31/lib/php/pear'
-  #
-  # This applies to all builds except hhvm and nightly. Once the distro is fixed
-  # the following line can be removed
-  - if [[ ${TRAVIS_PHP_VERSION:0:1} == "5" || ${TRAVIS_PHP_VERSION:0:1} == "7" ]]; then echo "include_path='.:/home/travis/.phpenv/versions/$(phpenv version-name)/lib/php/pear'" >> ~/.phpenv/versions/$(phpenv version-name)/etc/php.ini; fi
-
 install:
   - pear channel-update pear.php.net
   - pear install PHP_CodeSniffer
@@ -35,4 +21,4 @@ matrix:
 
   allow_failures:
     - php: hhvm
-    - php: nightly
+    - php: nightly

README.md

@@ -7,23 +7,23 @@ rss-bridge is a PHP project capable of generating ATOM feeds for websites which
 Supported sites/pages (main)
 ===
 
- * `FlickrExplore` : [Latest interesting images](http://www.flickr.com/explore) from Flickr
- * `GoogleSearch` : Most recent results from Google Search
- * `GooglePlus` : Most recent posts of user timeline
- * `Twitter` : Return keyword/hashtag search or user timeline
- * `Identi.ca` : Identica user timeline (Should be compatible with other Pump.io instances)
- * `YouTube` : YouTube user channel, playlist or search
- * `Cryptome` : Returns the most recent documents from [Cryptome.org](http://cryptome.org/)
- * `DansTonChat`: Most recent quotes from [danstonchat.com](http://danstonchat.com/)
- * `DuckDuckGo`: Most recent results from [DuckDuckGo.com](https://duckduckgo.com/)
- * `Instagram`: Most recent photos from an Instagram user
- * `OpenClassrooms`: Lastest tutorials from [fr.openclassrooms.com](http://fr.openclassrooms.com/)
- * `Pinterest`: Most recent photos from user or search
- * `ScmbBridge`: Newest stories from [secouchermoinsbete.fr](http://secouchermoinsbete.fr/)
- * `Wikipedia`: highlighted articles from [Wikipedia](https://wikipedia.org/) in English, German, French or Esperanto
- * `Bandcamp` : Returns last release from [bandcamp](https://bandcamp.com/) for a tag
- * `ThePirateBay` : Returns the newest indexed torrents from [The Pirate Bay](https://thepiratebay.se/) with keywords
- * `Facebook` : Returns the latest posts on a page or profile on [Facebook](https://facebook.com/)
+* `Bandcamp` : Returns last release from [bandcamp](https://bandcamp.com/) for a tag
+* `Cryptome` : Returns the most recent documents from [Cryptome.org](http://cryptome.org/)
+* `DansTonChat`: Most recent quotes from [danstonchat.com](http://danstonchat.com/)
+* `DuckDuckGo`: Most recent results from [DuckDuckGo.com](https://duckduckgo.com/)
+* `Facebook` : Returns the latest posts on a page or profile on [Facebook](https://facebook.com/)
+* `FlickrExplore` : [Latest interesting images](http://www.flickr.com/explore) from Flickr
+* `GooglePlus` : Most recent posts of user timeline
+* `GoogleSearch` : Most recent results from Google Search
+* `Identi.ca` : Identica user timeline (Should be compatible with other Pump.io instances)
+* `Instagram`: Most recent photos from an Instagram user
+* `OpenClassrooms`: Lastest tutorials from [fr.openclassrooms.com](http://fr.openclassrooms.com/)
+* `Pinterest`: Most recent photos from user or search
+* `ScmbBridge`: Newest stories from [secouchermoinsbete.fr](http://secouchermoinsbete.fr/)
+* `ThePirateBay` : Returns the newest indexed torrents from [The Pirate Bay](https://thepiratebay.se/) with keywords
+* `Twitter` : Return keyword/hashtag search or user timeline
+* `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
 
@@ -31,11 +31,11 @@ Output format
 ===
 Output format can take several forms:
 
- * `Atom` : ATOM Feed, for use in RSS/Feed readers
- * `Mrss` : MRSS Feed, for use in RSS/Feed readers
- * `Json` : Json, for consumption by other applications.
- * `Html` : Simple html page.
- * `Plaintext` : raw text (php object, as returned by print_r)
+* `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)
    
 Screenshot
 ===

bridges/BloombergBridge.php

@@ -0,0 +1,65 @@
+<?php
+class BloombergBridge extends BridgeAbstract
+{
+	const NAME = 'Bloomberg';
+	const URI = 'https://www.bloomberg.com/';
+	const DESCRIPTION = 'Trending stories from Bloomberg';
+	const MAINTAINER = 'mdemoss';
+
+	const PARAMETERS = array(
+	'Trending Stories' => array(),
+	'From Search' => array(
+	'q' => array(
+				'name' => 'Keyword',
+				'required' => true
+	)
+	)
+	);
+
+	public function getName()
+	{
+		switch($this->queriedContext) {
+		case 'Trending Stories':
+			return self::NAME . ' Trending Stories';
+		case 'From Search':
+			if (!is_null($this->getInput('q'))) {
+					return self::NAME . ' Search : ' . $this->getInput('q');
+			}
+			break;
+		}
+
+		return parent::getName();
+	}
+
+	public function collectData()
+	{
+		switch($this->queriedContext) {
+		case 'Trending Stories': // Get list of top new <article>s from the front page.
+			$html = getSimpleHTMLDOMCached($this->getURI(), 300);
+			$stories = $html->find('ul.top-news-v3__stories article.top-news-v3-story');
+			break;
+		case 'From Search': // Get list of <article> elements from search.
+			$html = getSimpleHTMLDOMCached(
+				$this->getURI() .
+				'search?sort=time:desc&page=1&query=' .
+				urlencode($this->getInput('q')), 300
+			);
+			$stories = $html->find('div.search-result-items article.search-result-story');
+			break;
+		}
+		foreach ($stories as $element) {
+			$item['uri'] = $element->find('h1 a', 0)->href;
+			if (preg_match('#^https://#i', $item['uri']) !== 1) {
+				$item['uri'] = $this->getURI() . $item['uri'];
+			}
+			$articleHtml = getSimpleHTMLDOMCached($item['uri']);
+			if (!$articleHtml) {
+				continue;
+			}
+			$item['title'] = $element->find('h1 a', 0)->plaintext;
+			$item['timestamp'] = strtotime($articleHtml->find('meta[name=iso-8601-publish-date],meta[name=date]', 0)->content);
+			$item['content'] = $articleHtml->find('meta[name=description]', 0)->content;
+			$this->items[] = $item;
+		}
+	}
+}

bridges/FacebookBridge.php

@@ -46,7 +46,7 @@ class FacebookBridge extends BridgeAbstract {
 			if(is_array($matches) && count($matches) > 1) {
 				$link = $matches[1];
 				if(strpos($link, '/') === 0)
-					$link = self::URI . $link . '"';
+					$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 . '"';

bridges/LegifranceJOBridge.php

@@ -42,10 +42,10 @@ class LegifranceJOBridge extends BridgeAbstract {
 		$html = getSimpleHTMLDOM(self::URI)
 			or $this->returnServer('Unable to download ' . self::URI);
 
-		$this->author = trim($html->find('h2.title', 0)->plaintext);
+		$this->author = trim($html->find('h2.titleJO', 0)->plaintext);
 		$uri = $html->find('h2.titleELI', 0)->plaintext;
 		$this->uri = trim(substr($uri, strpos($uri, 'https')));
-		$this->timestamp = strtotime(substr($this->uri, strpos($this->uri, 'eli/jo/') + strlen('eli/jo/')));
+		$this->timestamp = strtotime(substr($this->uri, strpos($this->uri, 'eli/jo/') + strlen('eli/jo/'), -5));
 
 		foreach($html->find('h3') as $section) {
 			$subsections = $section->nextSibling()->find('h4');

bridges/MixCloudBridge.php

@@ -4,7 +4,7 @@ class MixCloudBridge extends BridgeAbstract {
 
 	const MAINTAINER = 'Alexis CHEMEL';
 	const NAME = 'MixCloud';
-	const URI = 'https://mixcloud.com/';
+	const URI = 'https://www.mixcloud.com';
 	const CACHE_TIMEOUT = 3600; // 1h
 	const DESCRIPTION = 'Returns latest musics on user stream';
 
@@ -24,8 +24,9 @@ class MixCloudBridge extends BridgeAbstract {
 	}
 
 	public function collectData(){
+		ini_set('user_agent', 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:53.0) Gecko/20100101 Firefox/53.0');
 
-		$html = getSimpleHTMLDOM(self::URI . $this->getInput('u'))
+		$html = getSimpleHTMLDOM(self::URI . '/' . $this->getInput('u'))
 			or returnServerError('Could not request MixCloud.');
 
 		foreach($html->find('section.card') as $element) {

bridges/PcGamerBridge.php

@@ -0,0 +1,23 @@
+<?php
+class PcGamerBridge extends BridgeAbstract
+{
+	const NAME = 'PC Gamer';
+	const URI = 'https://www.pcgamer.com/';
+	const DESCRIPTION = 'PC Gamer Most Read Stories';
+	const MAINTAINER = 'mdemoss';
+
+	public function collectData()
+	{
+		$html = getSimpleHTMLDOMCached($this->getURI(), 300);
+		$stories = $html->find('div#popularcontent li.most-popular-item');
+		foreach ($stories as $element) {
+			$item['uri'] = $element->find('a', 0)->href;
+			$articleHtml = getSimpleHTMLDOMCached($item['uri']);
+			$item['title'] = $element->find('h4 a', 0)->plaintext;
+			$item['timestamp'] = strtotime($articleHtml->find('meta[name=pub_date]', 0)->content);
+			$item['content'] = $articleHtml->find('meta[name=description]', 0)->content;
+			$item['author'] = $articleHtml->find('a[itemprop=author]', 0)->plaintext;
+			$this->items[] = $item;
+		}
+	}
+}

bridges/TwitterBridge.php

@@ -77,9 +77,7 @@ class TwitterBridge extends BridgeAbstract {
 			$param = 'u';
 			break;
 		case 'By list':
-			$specific = $this->getInput('user');
-			$param = 'list';
-			break;
+			return $this->getInput('list') . ' - Twitter list by ' . $this->getInput('user');
 		default: return parent::getName();
 		}
 		return 'Twitter ' . $specific . $this->getInput($param);
@@ -165,7 +163,7 @@ class TwitterBridge extends BridgeAbstract {
 			switch($this->queriedContext) {
 				case 'By list':
 					// Check if filter applies to list (using raw content)
-					if(!is_null($this->getInput('filter'))) {
+					if($this->getInput('filter')) {
 						if(stripos($tweet->find('p.js-tweet-text', 0)->plaintext, $this->getInput('filter')) === false) {
 							continue 2; // switch + for-loop!
 						}

bridges/YoutubeBridge.php

@@ -91,7 +91,7 @@ class YoutubeBridge extends BridgeAbstract {
 			if(strpos($vid, 'googleads') === false)
 				$this->ytBridgeAddItem($vid, $title, $author, $desc, $time);
 		}
-		$this->request = $this->ytBridgeFixTitle($xml->find('feed > title', 0)->plaintext);
+		$this->feedName = $this->ytBridgeFixTitle($xml->find('feed > title', 0)->plaintext);  // feedName will be used by getName()
 	}
 
 	private function ytBridgeParseHtmlListing($html, $element_selector, $title_selector){
@@ -164,7 +164,7 @@ class YoutubeBridge extends BridgeAbstract {
 			$html = $this->ytGetSimpleHTMLDOM($url_listing)
 				or returnServerError("Could not request YouTube. Tried:\n - $url_listing");
 			$this->ytBridgeParseHtmlListing($html, 'tr.pl-video', '.pl-video-title a');
-			$this->request = 'Playlist: ' . str_replace(' - YouTube', '', $html->find('title', 0)->plaintext);
+			$this->feedName = 'Playlist: ' . str_replace(' - YouTube', '', $html->find('title', 0)->plaintext); // feedName will be used by getName()
 		} elseif($this->getInput('s')) { /* search mode */
 			$this->request = $this->getInput('s');
 			$page = 1;
@@ -182,7 +182,7 @@ class YoutubeBridge extends BridgeAbstract {
 				or returnServerError("Could not request YouTube. Tried:\n - $url_listing");
 
 			$this->ytBridgeParseHtmlListing($html, 'div.yt-lockup', 'h3');
-			$this->request = 'Search: ' . str_replace(' - YouTube', '', $html->find('title', 0)->plaintext);
+			$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
  username (?u=...)\n - Channel id (?c=...)\n - Playlist id (?p=...)\n - Search (?s=...)");
@@ -190,6 +190,15 @@ class YoutubeBridge extends BridgeAbstract {
 	}
 
 	public function getName(){
-		return (!empty($this->request) ? $this->request . ' - ' : '') . 'YouTube Bridge';
-	}
+	  // Name depends on queriedContext:
+		switch($this->queriedContext) {
+		case 'By username':
+		case 'By channel id':
+		case 'By playlist Id':
+		case 'Search result':
+			return $this->feedName . ' - YouTube'; // We already know it's a bridge, right?
+		default:
+			return parent::getName();
+		}
+  }
 }