Bump version to dev.2020-11-10

This extension is required by filter_var()

README.md

@@ -65,6 +65,7 @@ RSS-Bridge requires PHP 5.6 or higher with following extensions enabled:
   - [`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)
+  - [`filter`](https://secure.php.net/manual/en/book.filter.php)
   - [`sqlite3`](http://php.net/manual/en/book.sqlite3.php) (only when using SQLiteCache)
 
 Find more information on our [Wiki](https://github.com/rss-bridge/rss-bridge/wiki)
@@ -109,8 +110,8 @@ We are RSS-Bridge community, a group of developers continuing the project initia
 Use this script to generate the list automatically (using the GitHub API):
 https://gist.github.com/LogMANOriginal/da00cd1e5f0ca31cef8e193509b17fd8
 -->
+
 * [16mhz](https://github.com/16mhz)
-* [86423355844265459587182778](https://github.com/86423355844265459587182778)
 * [adamchainz](https://github.com/adamchainz)
 * [Ahiles3005](https://github.com/Ahiles3005)
 * [Albirew](https://github.com/Albirew)
@@ -119,9 +120,12 @@ https://gist.github.com/LogMANOriginal/da00cd1e5f0ca31cef8e193509b17fd8
 * [alexAubin](https://github.com/alexAubin)
 * [AmauryCarrade](https://github.com/AmauryCarrade)
 * [AntoineTurmel](https://github.com/AntoineTurmel)
+* [arnd-s](https://github.com/arnd-s)
 * [ArthurHoaro](https://github.com/ArthurHoaro)
 * [Astalaseven](https://github.com/Astalaseven)
 * [Astyan-42](https://github.com/Astyan-42)
+* [AxorPL](https://github.com/AxorPL)
+* [ayacoo](https://github.com/ayacoo)
 * [az5he6ch](https://github.com/az5he6ch)
 * [azdkj532](https://github.com/azdkj532)
 * [b1nj](https://github.com/b1nj)
@@ -133,6 +137,7 @@ https://gist.github.com/LogMANOriginal/da00cd1e5f0ca31cef8e193509b17fd8
 * [cnlpete](https://github.com/cnlpete)
 * [corenting](https://github.com/corenting)
 * [couraudt](https://github.com/couraudt)
+* [csisoap](https://github.com/csisoap)
 * [cyberjacob](https://github.com/cyberjacob)
 * [da2x](https://github.com/da2x)
 * [Daiyousei](https://github.com/Daiyousei)
@@ -147,29 +152,36 @@ https://gist.github.com/LogMANOriginal/da00cd1e5f0ca31cef8e193509b17fd8
 * [em92](https://github.com/em92)
 * [eMerzh](https://github.com/eMerzh)
 * [EtienneM](https://github.com/EtienneM)
+* [fanch317](https://github.com/fanch317)
 * [floviolleau](https://github.com/floviolleau)
 * [fluffy-critter](https://github.com/fluffy-critter)
 * [Frenzie](https://github.com/Frenzie)
 * [fulmeek](https://github.com/fulmeek)
+* [ggiessen](https://github.com/ggiessen)
 * [Ginko-Aloe](https://github.com/Ginko-Aloe)
 * [Glandos](https://github.com/Glandos)
 * [gloony](https://github.com/gloony)
 * [GregThib](https://github.com/GregThib)
 * [griffaurel](https://github.com/griffaurel)
 * [Grummfy](https://github.com/Grummfy)
+* [gsantner](https://github.com/gsantner)
 * [hunhejj](https://github.com/hunhejj)
 * [husim0](https://github.com/husim0)
 * [IceWreck](https://github.com/IceWreck)
 * [j0k3r](https://github.com/j0k3r)
 * [JackNUMBER](https://github.com/JackNUMBER)
+* [jannyba](https://github.com/jannyba)
+* [JasonGhent](https://github.com/JasonGhent)
 * [jdesgats](https://github.com/jdesgats)
 * [jdigilio](https://github.com/jdigilio)
 * [JeremyRand](https://github.com/JeremyRand)
 * [Jocker666z](https://github.com/Jocker666z)
 * [johnnygroovy](https://github.com/johnnygroovy)
 * [johnpc](https://github.com/johnpc)
-* [killruana](https://github.com/killruana)
+* [joni1993](https://github.com/joni1993)
+* [joshcoales](https://github.com/joshcoales)
 * [klimplant](https://github.com/klimplant)
+* [kolarcz](https://github.com/kolarcz)
 * [kranack](https://github.com/kranack)
 * [kraoc](https://github.com/kraoc)
 * [l1n](https://github.com/l1n)
@@ -178,6 +190,7 @@ https://gist.github.com/LogMANOriginal/da00cd1e5f0ca31cef8e193509b17fd8
 * [lalannev](https://github.com/lalannev)
 * [ldidry](https://github.com/ldidry)
 * [Leomaradan](https://github.com/Leomaradan)
+* [liamka](https://github.com/liamka)
 * [Limero](https://github.com/Limero)
 * [LogMANOriginal](https://github.com/LogMANOriginal)
 * [lorenzos](https://github.com/lorenzos)
@@ -188,17 +201,25 @@ https://gist.github.com/LogMANOriginal/da00cd1e5f0ca31cef8e193509b17fd8
 * [mdemoss](https://github.com/mdemoss)
 * [melangue](https://github.com/melangue)
 * [metaMMA](https://github.com/metaMMA)
+* [mibe](https://github.com/mibe)
+* [mightymt](https://github.com/mightymt)
 * [mitsukarenai](https://github.com/mitsukarenai)
 * [MonsieurPoutounours](https://github.com/MonsieurPoutounours)
+* [mr-flibble](https://github.com/mr-flibble)
 * [mro](https://github.com/mro)
+* [mschwld](https://github.com/mschwld)
 * [mxmehl](https://github.com/mxmehl)
 * [nel50n](https://github.com/nel50n)
 * [niawag](https://github.com/niawag)
+* [Niehztog](https://github.com/Niehztog)
 * [Nono-m0le](https://github.com/Nono-m0le)
 * [ObsidianWitch](https://github.com/ObsidianWitch)
 * [OliverParoczai](https://github.com/OliverParoczai)
-* [oratosquilla-oratoria](https://github.com/oratosquilla-oratoria)
+* [Ololbu](https://github.com/Ololbu)
 * [ORelio](https://github.com/ORelio)
+* [otakuf](https://github.com/otakuf)
+* [Park0](https://github.com/Park0)
+* [Paroleen](https://github.com/Paroleen)
 * [PaulVayssiere](https://github.com/PaulVayssiere)
 * [pellaeon](https://github.com/pellaeon)
 * [Piranhaplant](https://github.com/Piranhaplant)
@@ -208,18 +229,23 @@ https://gist.github.com/LogMANOriginal/da00cd1e5f0ca31cef8e193509b17fd8
 * [Pofilo](https://github.com/Pofilo)
 * [prysme01](https://github.com/prysme01)
 * [quentinus95](https://github.com/quentinus95)
+* [RawkBob](https://github.com/RawkBob)
 * [regisenguehard](https://github.com/regisenguehard)
 * [Riduidel](https://github.com/Riduidel)
 * [rogerdc](https://github.com/rogerdc)
 * [Roliga](https://github.com/Roliga)
+* [ronansalmon](https://github.com/ronansalmon)
+* [rremizov](https://github.com/rremizov)
 * [sebsauvage](https://github.com/sebsauvage)
 * [shutosg](https://github.com/shutosg)
+* [Simounet](https://github.com/Simounet)
 * [somini](https://github.com/somini)
 * [squeek502](https://github.com/squeek502)
 * [stjohnjohnson](https://github.com/stjohnjohnson)
 * [Strubbl](https://github.com/Strubbl)
 * [sublimz](https://github.com/sublimz)
 * [sunchaserinfo](https://github.com/sunchaserinfo)
+* [SuperSandro2000](https://github.com/SuperSandro2000)
 * [sysadminstory](https://github.com/sysadminstory)
 * [tameroski](https://github.com/tameroski)
 * [teromene](https://github.com/teromene)
@@ -227,6 +253,7 @@ https://gist.github.com/LogMANOriginal/da00cd1e5f0ca31cef8e193509b17fd8
 * [thefranke](https://github.com/thefranke)
 * [ThePadawan](https://github.com/ThePadawan)
 * [TheRadialActive](https://github.com/TheRadialActive)
+* [theScrabi](https://github.com/theScrabi)
 * [TitiTestScalingo](https://github.com/TitiTestScalingo)
 * [triatic](https://github.com/triatic)
 * [VerifiedJoseph](https://github.com/VerifiedJoseph)
@@ -234,6 +261,7 @@ https://gist.github.com/LogMANOriginal/da00cd1e5f0ca31cef8e193509b17fd8
 * [wtuuju](https://github.com/wtuuju)
 * [xurxof](https://github.com/xurxof)
 * [yardenac](https://github.com/yardenac)
+* [ymeister](https://github.com/ymeister)
 * [ZeNairolf](https://github.com/ZeNairolf)
 
 Licenses

bridges/AlbionOnlineBridge.php

@@ -10,13 +10,7 @@ class AlbionOnlineBridge extends BridgeAbstract {
 	const PARAMETERS = array( array(
 		'postcount' => array(
 			'name' => 'Limit',
-			'type' => 'list',
-			'values' => array(
-				'2' => 2,
-				'5' => 5,
-				'10' => 10,
-				'15' => 15,
-			 ),
+			'type' => 'number',
 			'title' => 'Maximum number of items to return',
 			'defaultValue' => 5,
 		),

bridges/BleepingComputerBridge.php

@@ -0,0 +1,29 @@
+<?php
+class BleepingComputerBridge extends FeedExpander {
+
+	const MAINTAINER = 'csisoap';
+	const NAME = 'Bleeping Computer';
+	const URI = 'https://www.bleepingcomputer.com/';
+	const DESCRIPTION = 'Returns the newest articles.';
+
+	protected function parseItem($item){
+		$item = parent::parseItem($item);
+
+		$article_html = getSimpleHTMLDOMCached($item['uri']);
+		if(!$article_html) {
+			$item['content'] .= '<p><em>Could not request ' . $this->getName() . ': ' . $item['uri'] . '</em></p>';
+			return $item;
+		}
+
+		$article_content = $article_html->find('div.articleBody', 0)->innertext;
+		$article_content = stripRecursiveHTMLSection($article_content, 'div', '<div class="cz-related-article-wrapp');
+		$item['content'] = trim($article_content);
+
+		return $item;
+	}
+
+	public function collectData(){
+		$feed = static::URI . 'feed/';
+		$this->collectExpandableDatas($feed);
+	}
+}

bridges/BlizzardNewsBridge.php

@@ -0,0 +1,60 @@
+<?php
+
+class BlizzardNewsBridge extends XPathAbstract {
+
+	const NAME = 'Blizzard News';
+	const URI = 'https://news.blizzard.com';
+	const DESCRIPTION = 'Blizzard (game company) newsfeed';
+	const MAINTAINER = 'Niehztog';
+	const PARAMETERS = array(
+		'' => array(
+			'locale' => array(
+				'name' => 'Language',
+				'type' => 'list',
+				'values' => array(
+					'Deutsch' => 'de-de',
+					'English (EU)' => 'en-gb',
+					'English (US)' => 'en-us',
+					'Español (EU)' => 'es-es',
+					'Español (AL)' => 'es-mx',
+					'Français' => 'fr-fr',
+					'Italiano' => 'it-it',
+					'日本語' => 'ja-jp',
+					'한국어' => 'ko-kr',
+					'Polski' => 'pl-pl',
+					'Português (AL)' => 'pt-br',
+					'Русский' => 'ru-ru',
+					'ภาษาไทย' => 'th-th',
+					'简体中文' => 'zh-cn',
+					'繁體中文' => 'zh-tw'
+				),
+				'defaultValue' => 'en-us',
+				'title' => 'Select your language'
+			)
+		)
+	);
+	const CACHE_TIMEOUT = 3600;
+
+	const XPATH_EXPRESSION_ITEM = '/html/body/div/div[4]/div[2]/div[2]/div/div/section/ol/li/article';
+	const XPATH_EXPRESSION_ITEM_TITLE = './/div/div[2]/h2';
+	const XPATH_EXPRESSION_ITEM_CONTENT = './/div[@class="ArticleListItem-description"]/div[@class="h6"]';
+	const XPATH_EXPRESSION_ITEM_URI = './/a[@class="ArticleLink ArticleLink"]/@href';
+	const XPATH_EXPRESSION_ITEM_AUTHOR = '';
+	const XPATH_EXPRESSION_ITEM_TIMESTAMP = './/time[@class="ArticleListItem-footerTimestamp"]/@timestamp';
+	const XPATH_EXPRESSION_ITEM_ENCLOSURES = './/div[@class="ArticleListItem-image"]/@style';
+	const XPATH_EXPRESSION_ITEM_CATEGORIES = './/div[@class="ArticleListItem-label"]';
+	const SETTING_FIX_ENCODING = true;
+
+	/**
+	 * Source Web page URL (should provide either HTML or XML content)
+	 * @return string
+	 */
+	protected function getSourceUrl(){
+
+		$locale = $this->getInput('locale');
+		if('zh-cn' === $locale) {
+			return 'https://cn.news.blizzard.com';
+		}
+		return 'https://news.blizzard.com/' . $locale;
+	}
+}

bridges/BrutBridge.php

@@ -16,6 +16,7 @@ class BrutBridge extends BridgeAbstract {
 					'Entertainment' => 'entertainment',
 					'Sports' => 'sport',
 					'Nature' => 'nature',
+					'Health' => 'health',
 				),
 				'defaultValue' => 'news',
 			),
@@ -26,6 +27,7 @@ class BrutBridge extends BridgeAbstract {
 						'United States' => 'us',
 						'United Kingdom' => 'uk',
 						'France' => 'fr',
+						'Spain' => 'es',
 						'India' => 'in',
 						'Mexico' => 'mx',
 				),

bridges/CeskaTelevizeBridge.php

@@ -74,8 +74,8 @@ class CeskaTelevizeBridge extends BridgeAbstract {
 		}
 	}
 
-	public function getUri() {
-		return isset($this->feedUri) ? $this->feedUri : parent::getUri();
+	public function getURI() {
+		return isset($this->feedUri) ? $this->feedUri : parent::getURI();
 	}
 
 	public function getName() {

bridges/DiarioDeNoticiasBridge.php

@@ -42,6 +42,7 @@ class DiarioDeNoticiasBridge extends BridgeAbstract {
 		}
 		return $name;
 	}
+
 	public function getURI() {
 		switch($this->queriedContext) {
 		case 'Tag':

bridges/DribbbleBridge.php

@@ -94,6 +94,6 @@ favicon-63b2904a073c89b52b19aa08cebc16a154bcf83fee8ecc6439968b1e6db569c7.ico';
 	}
 
 	private function getFullSizeImagePath($preview_path){
-		return explode("?compress=1", $preview_path)[0];
+		return explode('?compress=1', $preview_path)[0];
 	}
 }

bridges/EpicgamesBridge.php

@@ -10,14 +10,7 @@ class EpicgamesBridge extends BridgeAbstract {
 	const PARAMETERS = array( array(
 		'postcount' => array(
 			'name' => 'Limit',
-			'type' => 'list',
-			'values' => array(
-				'5' => 5,
-				'10' => 10,
-				'15' => 15,
-				'20' => 20,
-				'25' => 25,
-			 ),
+			'type' => 'number',
 			'title' => 'Maximum number of items to return',
 			'defaultValue' => 10,
 		),

bridges/FM4Bridge.php

@@ -28,9 +28,9 @@ class FM4Bridge extends BridgeAbstract
 		)
 	);
 
-	public function getPageData($tag, $page) {
+	private function getPageData($tag, $page) {
 		if($tag)
-			$uri = self::URI . "/tags/" . $tag;
+			$uri = self::URI . '/tags/' . $tag;
 		else
 			$uri = self::URI;
 
@@ -47,7 +47,7 @@ class FM4Bridge extends BridgeAbstract
 			$item['uri'] = $article->find('a', 0)->href;
 			$item['title'] = $article->find('h2', 0)->plaintext;
 			$item['author'] = $article->find('p[class*=keyword]', 0)->plaintext;
-			$item["timestamp"] = strtotime($article->find('p[class*=time]', 0)->plaintext);
+			$item['timestamp'] = strtotime($article->find('p[class*=time]', 0)->plaintext);
 
 			if ($this->getInput('loadcontent')) {
 				$item['content'] = getSimpleHTMLDOM($item['uri'])->find('div[class=storyText]', 0)->innertext
@@ -58,9 +58,10 @@ class FM4Bridge extends BridgeAbstract
 		}
 		return $page_items;
 	}
+
 	public function collectData() {
 		for ($cur_page = 1; $cur_page <= $this->getInput('pages'); $cur_page++) {
-			$this->items = array_merge($this->items,$this->getPageData($this->getInput('tag'), $cur_page));
+			$this->items = array_merge($this->items, $this->getPageData($this->getInput('tag'), $cur_page));
 		}
 	}
 }

bridges/FacebookBridge.php

@@ -175,7 +175,13 @@ class FacebookBridge extends BridgeAbstract {
 			$header = array();
 		}
 
-		$html = getSimpleHTMLDOM($this->getURI(), $header)
+		$touchURI = str_replace(
+			'https://www.facebook',
+			'https://touch.facebook',
+			$this->getURI()
+		);
+
+		$html = getSimpleHTMLDOM($touchURI, $header)
 			or returnServerError('Failed loading facebook page: ' . $this->getURI());
 
 		if(!$this->isPublicGroup($html)) {
@@ -186,19 +192,18 @@ class FacebookBridge extends BridgeAbstract {
 
 		$this->groupName = $this->extractGroupName($html);
 
-		$posts = $html->find('div.userContentWrapper')
+		$posts = $html->find('div.story_body_container')
 			or returnServerError('Failed finding posts!');
 
 		foreach($posts as $post) {
 
 			$item = array();
 
-			$item['uri'] = $this->extractGroupURI($post);
-			$item['title'] = $this->extractGroupTitle($post);
-			$item['author'] = $this->extractGroupAuthor($post);
-			$item['content'] = $this->extractGroupContent($post);
-			$item['timestamp'] = $this->extractGroupTimestamp($post);
-			$item['enclosures'] = $this->extractGroupEnclosures($post);
+			$item['uri'] = $this->extractGroupPostURI($post);
+			$item['title'] = $this->extractGroupPostTitle($post);
+			$item['author'] = $this->extractGroupPostAuthor($post);
+			$item['content'] = $this->extractGroupPostContent($post);
+			$item['enclosures'] = $this->extractGroupPostEnclosures($post);
 
 			$this->items[] = $item;
 
@@ -215,16 +220,7 @@ class FacebookBridge extends BridgeAbstract {
 
 			$urlparts = parse_url($group);
 
-			if($urlparts['host'] !== parse_url(self::URI)['host']
-			&& 'www.' . $urlparts['host'] !== parse_url(self::URI)['host']) {
-
-				returnClientError('The host you provided is invalid! Received "'
-				. $urlparts['host']
-				. '", expected "'
-				. parse_url(self::URI)['host']
-				. '"!');
-
-			}
+			$this->validateHost($urlparts['host']);
 
 			return explode('/', $urlparts['path'])[2];
 
@@ -236,24 +232,47 @@ class FacebookBridge extends BridgeAbstract {
 
 	}
 
+	private function validateHost($provided_host) {
+		// Handle mobile links
+		if (strpos($provided_host, 'm.') === 0) {
+			$provided_host = substr($provided_host, strlen('m.'));
+		}
+		if (strpos($provided_host, 'touch.') === 0) {
+			$provided_host = substr($provided_host, strlen('touch.'));
+		}
+
+		$facebook_host = parse_url(self::URI)['host'];
+
+		if ($provided_host !== $facebook_host
+			&& 'www.' . $provided_host !== $facebook_host) {
+			returnClientError('The host you provided is invalid! Received "'
+				. $provided_host
+				. '", expected "'
+				. $facebook_host
+				. '"!');
+		}
+	}
+
+	/**
+	 * @param $html simple_html_dom
+	 * @return bool
+	 */
 	private function isPublicGroup($html) {
 
-		// Facebook redirects to the groups about page for non-public groups
-		$about = $html->find('#pagelet_group_about', 0);
-
-		return !($about);
-
+		// Facebook touch just presents a login page for non-public groups
+		$title = $html->find('title', 0);
+		return $title->plaintext !== 'Log in to Facebook | Facebook';
 	}
 
 	private function extractGroupName($html) {
 
-		$ogtitle = $html->find('meta[property="og:title"]', 0)
+		$ogtitle = $html->find('._de1', 0)
 			or returnServerError('Unable to find group title!');
 
-		return html_entity_decode($ogtitle->content, ENT_QUOTES);
+		return html_entity_decode($ogtitle->plaintext, ENT_QUOTES);
 	}
 
-	private function extractGroupURI($post) {
+	private function extractGroupPostURI($post) {
 
 		$elements = $post->find('a')
 			or returnServerError('Unable to find URI!');
@@ -262,7 +281,8 @@ class FacebookBridge extends BridgeAbstract {
 
 			// Find the one that is a permalink
 			if(strpos($anchor->href, 'permalink') !== false) {
-				return $anchor->href;
+				$arr = explode('?', $anchor->href, 2);
+				return $arr[0];
 			}
 
 		}
@@ -271,57 +291,61 @@ class FacebookBridge extends BridgeAbstract {
 
 	}
 
-	private function extractGroupContent($post) {
+	private function extractGroupPostContent($post) {
 
-		$content = $post->find('div.userContent', 0)
+		$content = $post->find('div._5rgt', 0)
 			or returnServerError('Unable to find user content!');
 
-		return $content->innertext . $content->next_sibling()->innertext;
+		$context_text = $content->innertext;
+		if ($content->next_sibling() !== null) {
+			$context_text .= $content->next_sibling()->innertext;
+		}
+		return $context_text;
 
 	}
 
-	private function extractGroupTimestamp($post) {
+	private function extractGroupPostAuthor($post) {
 
-		$element = $post->find('abbr[data-utime]', 0)
-			or returnServerError('Unable to find timestamp!');
-
-		return $element->getAttribute('data-utime');
-
-	}
-
-	private function extractGroupAuthor($post) {
-
-		$element = $post->find('img', 0)
+		$element = $post->find('h3 a', 0)
 			or returnServerError('Unable to find author information!');
 
-		return $element->{'aria-label'};
+		return $element->plaintext;
 
 	}
 
-	private function extractGroupEnclosures($post) {
+	private function extractGroupPostEnclosures($post) {
 
-		$elements = $post->find('div.userContent', 0)->next_sibling()->find('img');
+		$elements = $post->find('span._6qdm');
+		if ($post->find('div._5rgt', 0)->next_sibling() !== null) {
+			array_push($elements, ...$post->find('div._5rgt', 0)->next_sibling()->find('i.img'));
+		}
 
 		$enclosures = array();
 
+		$background_img_regex = '/background-image: ?url\\((.+?)\\);/';
+
 		foreach($elements as $enclosure) {
-			$enclosures[] = $enclosure->src;
+			if(preg_match($background_img_regex, $enclosure, $matches) > 0) {
+				$bg_img_value = trim(html_entity_decode($matches[1], ENT_QUOTES), "'\"");
+				$bg_img_url = urldecode(preg_replace('/\\\([0-9a-z]{2}) /', '%$1', $bg_img_value));
+				$enclosures[] = urldecode($bg_img_url);
+			}
 		}
 
 		return empty($enclosures) ? null : $enclosures;
 
 	}
 
-	private function extractGroupTitle($post) {
+	private function extractGroupPostTitle($post) {
 
-		$element = $post->find('h5', 0)
+		$element = $post->find('h3', 0)
 			or returnServerError('Unable to find title!');
 
 		if(strpos($element->plaintext, 'shared') === false) {
 
-			$content = strip_tags($this->extractGroupContent($post));
+			$content = strip_tags($this->extractGroupPostContent($post));
 
-			return $this->extractGroupAuthor($post)
+			return $this->extractGroupPostAuthor($post)
 			. ' posted: '
 			. substr(
 					$content,
@@ -348,13 +372,7 @@ class FacebookBridge extends BridgeAbstract {
 
 			$urlparts = parse_url($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']
-				. '"!');
-			}
+			$this->validateHost($urlparts['host']);
 
 			if(!array_key_exists('path', $urlparts)
 			|| $urlparts['path'] === '/') {
@@ -555,7 +573,7 @@ EOD;
 		}
 
 		// No captcha? We can carry on retrieving page contents :)
-		// First, we check wether the page is public or not
+		// First, we check whether the page is public or not
 		$loginForm = $html->find('._585r', 0);
 
 		if($loginForm != null) {

bridges/FicbookBridge.php

@@ -82,7 +82,7 @@ class FicbookBridge extends BridgeAbstract {
 
 		$html = defaultLinkTo($html, self::URI);
 
-		if ($this->queriedContext == 'Fiction Updates' or $this->queriedContext == 'Fiction Comments' ) {
+		if ($this->queriedContext == 'Fiction Updates' or $this->queriedContext == 'Fiction Comments') {
 			$this->titleName = $html->find('.fanfic-main-info > h1', 0)->innertext;
 		}
 

bridges/GoogleSearchBridge.php

@@ -38,7 +38,7 @@ class GoogleSearchBridge extends BridgeAbstract {
 				$t = $element->find('a[href]', 0)->href;
 				$item['uri'] = htmlspecialchars_decode($t);
 				$item['title'] = $element->find('h3', 0)->plaintext;
-				$item['content'] = $element->find('span[class=st]', 0)->plaintext;
+				$item['content'] = $element->find('span[class=aCOpRe]', 0)->plaintext;
 
 				$this->items[] = $item;
 			}

bridges/HeiseBridge.php

@@ -45,8 +45,10 @@ class HeiseBridge extends FeedExpander {
 		$article = getSimpleHTMLDOMCached($uri)
 			or returnServerError('Could not open article: ' . $uri);
 
-		$article = defaultLinkTo($article, $uri);
-		$item = $this->addArticleToItem($item, $article);
+		if ($article) {
+			$article = defaultLinkTo($article, $uri);
+			$item = $this->addArticleToItem($item, $article);
+		}
 
 		return $item;
 	}

bridges/KoreusBridge.php

@@ -3,7 +3,7 @@ class KoreusBridge extends FeedExpander {
 
 	const MAINTAINER = 'pit-fgfjiudghdf';
 	const NAME = 'Koreus';
-	const URI = 'http://www.koreus.com/';
+	const URI = 'https://www.koreus.com/';
 	const DESCRIPTION = 'Returns the newest posts from Koreus (full text)';
 
 	protected function parseItem($item){
@@ -17,6 +17,6 @@ class KoreusBridge extends FeedExpander {
 	}
 
 	public function collectData(){
-		$this->collectExpandableDatas('http://feeds.feedburner.com/Koreus-articles');
+		$this->collectExpandableDatas('https://feeds.feedburner.com/Koreus-articles');
 	}
 }

bridges/MallTvBridge.php

@@ -0,0 +1,73 @@
+<?php
+
+class MallTvBridge extends BridgeAbstract {
+
+	const NAME = 'MALL.TV Bridge';
+	const URI = 'https://www.mall.tv';
+	const CACHE_TIMEOUT = 3600;
+	const DESCRIPTION = 'Return newest videos';
+	const MAINTAINER = 'kolarcz';
+
+	const PARAMETERS = array(
+		array(
+			'url' => array(
+				'name' => 'url to the show',
+				'required' => true,
+				'exampleValue' => 'https://www.mall.tv/zivot-je-hra'
+			)
+		)
+	);
+
+	private function fixChars($text) {
+		return html_entity_decode($text, ENT_QUOTES, 'UTF-8');
+	}
+
+	private function getUploadTimeFromUrl($url) {
+		$html = getSimpleHTMLDOM($url)
+			or returnServerError('Could not request MALL.TV detail page');
+
+		$scriptLdJson = $html->find('script[type="application/ld+json"]', 0)->innertext;
+		if (!preg_match('/[\'"]uploadDate[\'"]\s*:\s*[\'"](\d{4}-\d{2}-\d{2})[\'"]/', $scriptLdJson, $match)) {
+			returnServerError('Could not get date from MALL.TV detail page');
+		}
+
+		return strtotime($match[1]);
+	}
+
+	public function collectData() {
+		$url = $this->getInput('url');
+
+		if (!preg_match('/^https:\/\/www\.mall\.tv\/[a-z0-9-]+(\/[a-z0-9-]+)?\/?$/', $url)) {
+			returnServerError('Invalid url');
+		}
+
+		$html = getSimpleHTMLDOM($url)
+			or returnServerError('Could not request MALL.TV');
+
+		$this->feedUri = $url;
+		$this->feedName = $this->fixChars($html->find('title', 0)->plaintext);
+
+		foreach ($html->find('section.isVideo .video-card') as $element) {
+			$itemTitle = $element->find('.video-card__details-link', 0);
+			$itemThumbnail = $element->find('.video-card__thumbnail', 0);
+			$itemUri = self::URI . $itemTitle->getAttribute('href');
+
+			$item = array(
+				'title' => $this->fixChars($itemTitle->plaintext),
+				'uri' => $itemUri,
+				'content' => '<img src="' . $itemThumbnail->getAttribute('data-src') . '" />',
+				'timestamp' => $this->getUploadTimeFromUrl($itemUri)
+			);
+
+			$this->items[] = $item;
+		}
+	}
+
+	public function getURI() {
+		return isset($this->feedUri) ? $this->feedUri : parent::getURI();
+	}
+
+	public function getName() {
+		return isset($this->feedName) ? $this->feedName : parent::getName();
+	}
+}

bridges/MarktplaatsBridge.php

@@ -103,8 +103,8 @@ class MarktplaatsBridge extends BridgeAbstract {
 						$item['content'] .= "<br />\n<br />\n<br />\n" . json_encode($listing);
 					}
 				}
-				$item['content'] .= "<br>\n<br>\nPrice: " . $listing->priceInfo->priceCents/100;
-				$item['content'] .= "&nbsp;&nbsp;(" . $listing->priceInfo->priceType .")";
+				$item['content'] .= "<br>\n<br>\nPrice: " . $listing->priceInfo->priceCents / 100;
+				$item['content'] .= '&nbsp;&nbsp;(' . $listing->priceInfo->priceType . ')';
 				if(!empty($listing->location->cityName)) {
 					$item['content'] .= "<br><br>\n" . $listing->location->cityName;
 				}
@@ -117,11 +117,11 @@ class MarktplaatsBridge extends BridgeAbstract {
 			}
 		}
 	}
-	
+
 	public function getName(){
-                if(!is_null($this->getInput('q'))) {
-                        return $this->getInput('q') . ' - Marktplaats';
-                }
-                return parent::getName();
-        }
+				if(!is_null($this->getInput('q'))) {
+						return $this->getInput('q') . ' - Marktplaats';
+				}
+				return parent::getName();
+		}
 }

bridges/MondeDiploBridge.php

@@ -7,9 +7,9 @@ class MondeDiploBridge extends BridgeAbstract {
 	const CACHE_TIMEOUT = 21600; //6h
 	const DESCRIPTION = 'Returns most recent results from MondeDiplo.';
 
-        private function cleanText($text) {
-            return trim(str_replace([' ', '&nbsp'], ' ', $text));
-        }
+		private function cleanText($text) {
+			return trim(str_replace(array(' ', '&nbsp'), ' ', $text));
+		}
 
 	public function collectData(){
 		$html = getSimpleHTMLDOM(self::URI)
@@ -22,7 +22,7 @@ class MondeDiploBridge extends BridgeAbstract {
 			$item = array();
 			$item['uri'] = self::URI . $element->href;
 			$item['title'] = $this->cleanText($title) . ' - ' . $this->cleanText($datesAuteurs);
-			$item['content'] = $this->cleanText(str_replace([$title, $datesAuteurs], '', $element->plaintext));
+			$item['content'] = $this->cleanText(str_replace(array($title, $datesAuteurs), '', $element->plaintext));
 
 			$this->items[] = $item;
 		}

bridges/NasaApodBridge.php

@@ -24,7 +24,7 @@ class NasaApodBridge extends BridgeAbstract {
 			$picture_html_string = $picture_html->innertext;
 
 			//Extract image and explanation
-			$image_wrapper = $picture_html->find('a',1);
+			$image_wrapper = $picture_html->find('a', 1);
 			$image_path = $image_wrapper->href;
 			$img_placeholder = $image_wrapper->find('img', 0);
 			$img_alt = $img_placeholder->alt;

bridges/NineGagBridge.php

@@ -148,7 +148,7 @@ class NineGagBridge extends BridgeAbstract {
 			}
 
 			if (!$AvoidElement) {
-				$item['uri'] = $post['url'];
+				$item['uri'] = preg_replace('/^http:/i', 'https:', $post['url']);
 				$item['title'] = $post['title'];
 				$item['content'] = self::getContent($post);
 				$item['categories'] = self::getCategories($post);

bridges/NordbayernBridge.php

@@ -48,11 +48,16 @@ class NordbayernBridge extends BridgeAbstract {
 	));
 
 	private function getImageUrlFromScript($script) {
-		preg_match("#src=\\\\'(https:[-:\\.\\\\/a-zA-Z0-9%_]*\\.(jpg|JPG))#", $script->innertext, $matches, PREG_OFFSET_CAPTURE);
+		preg_match(
+			"#src=\\\\'(https:[-:\\.\\\\/a-zA-Z0-9%_]*\\.(jpg|JPG))#",
+			$script->innertext,
+			$matches,
+			PREG_OFFSET_CAPTURE
+		);
 		if(isset($matches[1][0])) {
 			return stripcslashes($matches[1][0]) . '?w=800';
 		}
-        return null;
+		return null;
 	}
 
 	private function handleArticle($link) {

bridges/OpenwrtSecurityBridge.php

@@ -0,0 +1,37 @@
+<?php
+class OpenwrtSecurityBridge extends BridgeAbstract {
+	const NAME = 'OpenWrt Security Advisories';
+	const URI = 'https://openwrt.org/advisory/start';
+	const DESCRIPTION = 'Security Advisories published by openwrt.org';
+	const MAINTAINER = 'mschwld';
+	const CACHE_TIMEOUT = 3600;
+	const WEBROOT = 'https://openwrt.org';
+
+	public function collectData() {
+		$item = array();
+		$html = getSimpleHTMLDOM(self::URI)
+			or returnServerError('Could not request entries');
+
+		$advisories = $html->find('div[class=plugin_nspages]', 0);
+
+		foreach($advisories->find('a[class=wikilink1]') as $element) {
+			$item = array();
+
+			$row = $element->innertext;
+
+			$item['title'] = substr($row, 0, strpos($row, ' - '));
+			$item['timestamp'] = $this->getDate($element->href);
+			$item['uri'] = self::WEBROOT . $element->href;
+			$item['uid'] = self::WEBROOT . $element->href;
+			$item['content'] = substr($row, strpos($row, ' - ') + 3);
+			$item['author'] = 'OpenWrt Project';
+
+			$this->items[] = $item;
+		}
+	}
+
+	private function getDate($href) {
+		$date = substr($href, -12);
+		return $date;
+	}
+}

bridges/OtrkeyFinderBridge.php

@@ -11,13 +11,11 @@ class OtrkeyFinderBridge extends BridgeAbstract {
 			'searchterm' => array(
 				'name' => 'Search term',
 				'exampleValue' => 'Terminator',
-				'defaultValue' => '',
 				'title' => 'The search term is case-insensitive',
 			),
 			'station' => array(
 				'name' => 'Station name',
 				'exampleValue' => 'ARD',
-				'defaultValue' => '',
 			),
 			'type' => array(
 				'name' => 'Media type',
@@ -143,7 +141,11 @@ class OtrkeyFinderBridge extends BridgeAbstract {
 			$item['content'] = $content;
 
 		if (preg_match(self::TIME_REGEX, $file, $matches) === 1) {
-			$item['timestamp'] = DateTime::createFromFormat('y.m.d_H-i', $matches[0], new DateTimeZone('Europe/Berlin'))->getTimestamp();
+			$item['timestamp'] = DateTime::createFromFormat(
+				'y.m.d_H-i',
+				$matches[0],
+				new DateTimeZone('Europe/Berlin')
+			)->getTimestamp();
 		}
 
 		return $item;

bridges/ReleasesSwitchBridge.php

@@ -1,7 +1,7 @@
 <?php
 
 // This bridge depends on Releases3DSBridge
-if (!class_exists('Releases3DSBridge')){
+if (!class_exists('Releases3DSBridge')) {
 	include('Releases3DSBridge.php');
 }
 

bridges/TwitchBridge.php

@@ -20,7 +20,9 @@ class TwitchBridge extends BridgeAbstract {
 				'All' => 'all',
 				'Archive' => 'archive',
 				'Highlights' => 'highlight',
-				'Uploads' => 'upload'
+				'Uploads' => 'upload',
+				'Past Premieres' => 'past_premiere',
+				'Premiere Uploads' => 'premiere_upload'
 			),
 			'defaultValue' => 'archive'
 		)
@@ -32,43 +34,90 @@ class TwitchBridge extends BridgeAbstract {
 	 */
 	const CLIENT_ID = 'kimne78kx3ncx6brgo4mv6wki5h1ko';
 
+	const API_ENDPOINT = 'https://gql.twitch.tv/gql';
+	const BROADCAST_TYPES = array(
+		'all' => array(
+			'ARCHIVE',
+			'HIGHLIGHT',
+			'UPLOAD',
+			'PAST_PREMIERE',
+			'PREMIERE_UPLOAD'
+		),
+		'archive' => 'ARCHIVE',
+		'highlight' => 'HIGHLIGHT',
+		'upload' => 'UPLOAD',
+		'past_premiere' => 'PAST_PREMIERE',
+		'premiere_upload' => 'PREMIERE_UPLOAD'
+	);
+
 	public function collectData(){
-		// get channel user
-		$query_data = array(
-			'login' => $this->getInput('channel')
+		$query = <<<'EOD'
+query VODList($channel: String!, $types: [BroadcastType!]) {
+  user(login: $channel) {
+    displayName
+    videos(types: $types, sort: TIME) {
+      edges {
+        node {
+          id
+          title
+          publishedAt
+          lengthSeconds
+          viewCount
+          thumbnailURLs(width: 640, height: 360)
+          previewThumbnailURL(width: 640, height: 360)
+          description
+          tags
+          contentTags {
+            isLanguageTag
+            localizedName
+          }
+          game {
+            displayName
+          }
+          moments(momentRequestType: VIDEO_CHAPTER_MARKERS) {
+            edges {
+              node {
+                description
+                positionMilliseconds
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+}
+EOD;
+		$variables = array(
+			'channel' => $this->getInput('channel'),
+			'types' => self::BROADCAST_TYPES[$this->getInput('type')]
 		);
-		$users = $this->apiGet('users', $query_data)->users;
-		if(count($users) === 0)
-			returnClientError('User "'
-			. $this->getInput('channel')
-			. '" could not be found');
-		$user = $users[0];
+		$data = $this->apiRequest($query, $variables);
 
-		// get video list
-		$query_endpoint = 'channels/' . $user->_id . '/videos';
-		$query_data = array(
-			'broadcast_type' => $this->getInput('type'),
-			'limit' => 10
-		);
-		$videos = $this->apiGet($query_endpoint, $query_data)->videos;
+		$user = $data->user;
+		foreach($user->videos->edges as $edge) {
+			$video = $edge->node;
+
+			$url = 'https://www.twitch.tv/videos/' . $video->id;
 
-		foreach($videos as $video) {
 			$item = array(
-				'uri' => $video->url,
+				'uri' => $url,
 				'title' => $video->title,
-				'timestamp' => $video->published_at,
-				'author' => $video->channel->display_name,
+				'timestamp' => $video->publishedAt,
+				'author' => $user->displayName,
 			);
 
 			// Add categories for tags and played game
-			$item['categories'] = array_filter(explode(' ', $video->tag_list));
-			if(!empty($video->game))
-				$item['categories'][] = $video->game;
+			$item['categories'] = $video->tags;
+			if(!is_null($video->game))
+				$item['categories'][] = $video->game->displayName;
+			foreach($video->contentTags as $tag)
+				if(!$tag->isLanguageTag)
+					$item['categories'][] = $tag->localizedName;
 
 			// Add enclosures for thumbnails from a few points in the video
-			$item['enclosures'] = array();
-			foreach($video->thumbnails->large as $thumbnail)
-				$item['enclosures'][] = $thumbnail->url;
+			// Thumbnail list has duplicate entries sometimes so remove those
+			$item['enclosures'] = array_unique($video->thumbnailURLs);
 
 			/*
 			 * Content format example:
@@ -86,44 +135,45 @@ class TwitchBridge extends BridgeAbstract {
 			 *
 			 */
 			$item['content'] = '<p><a href="'
-				. $video->url
+				. $url
 				. '"><img src="'
-				. $video->preview->large
+				. $video->previewThumbnailURL
 				. '" /></a></p><p>'
-				. $video->description_html
+				. $video->description // in markdown format
 				. '</p><p><b>Duration:</b> '
-				. $this->formatTimestampTime($video->length)
+				. $this->formatTimestampTime($video->lengthSeconds)
 				. '<br/><b>Views:</b> '
-				. $video->views
+				. $video->viewCount
 				. '</p>';
 
 			// Add played games list to content
-			$video_id = trim($video->_id, 'v'); // _id gives 'v1234' but API wants '1234'
-			$markers = $this->apiGet('videos/' . $video_id . '/markers')->markers;
-			$item['content'] .= '<p><b>Played games:</b></b><ul><li><a href="'
-				. $video->url
-				. '">00:00:00</a> - '
-				. $video->game
-				. '</li>';
-			if(isset($markers->game_changes)) {
-				usort($markers->game_changes, function($a, $b) {
-					return $a->time - $b->time;
-				});
-				foreach($markers->game_changes as $game_change) {
-					$item['categories'][] = $game_change->label;
+			$item['content'] .= '<p><b>Played games:</b><ul>';
+			if(count($video->moments->edges) > 0) {
+				foreach($video->moments->edges as $edge) {
+					$moment = $edge->node;
+
+					$item['categories'][] = $moment->description;
 					$item['content'] .= '<li><a href="'
-						. $video->url
+						. $url
 						. '?t='
-						. $this->formatQueryTime($game_change->time)
+						. $this->formatQueryTime($moment->positionMilliseconds / 1000)
 						. '">'
-						. $this->formatTimestampTime($game_change->time)
+						. $this->formatTimestampTime($moment->positionMilliseconds / 1000)
 						. '</a> - '
-						. $game_change->label
+						. $moment->description
 						. '</li>';
 				}
+			} else {
+				$item['content'] .= '<li><a href="'
+					. $url
+					. '">00:00:00</a> - '
+					. ($video->game ? $video->game->displayName : 'No Game')
+					. '</li>';
 			}
 			$item['content'] .= '</ul></p>';
 
+			$item['categories'] = array_unique($item['categories']);
+
 			$this->items[] = $item;
 		}
 	}
@@ -144,25 +194,37 @@ class TwitchBridge extends BridgeAbstract {
 			$seconds % 60);
 	}
 
-	/*
-	 * Ideally the new 'helix' API should be used as v5/'kraken' is deprecated.
-	 * The new API however still misses many features (markers, played game..) of
-	 * the old one, so let's use the old one for as long as it's available.
-	 */
-	private function apiGet($endpoint, $query_data = array()) {
-		$query_data['api_version'] = 5;
-		$url = 'https://api.twitch.tv/kraken/'
-			. $endpoint
-			. '?'
-			. http_build_query($query_data);
+	// GraphQL: https://graphql.org/
+	// Tool for developing/testing queries: https://github.com/skevy/graphiql-app
+	private function apiRequest($query, $variables) {
+		$request = array(
+			'query' => $query,
+			'variables' => $variables
+		);
 		$header = array(
 			'Client-ID: ' . self::CLIENT_ID
 		);
+		$opts = array(
+			CURLOPT_CUSTOMREQUEST => 'POST',
+			CURLOPT_POSTFIELDS => json_encode($request)
+		);
 
-		$data = json_decode(getContents($url, $header))
-			or returnServerError('API request to "' . $url . '" failed.');
+		Debug::log("Sending GraphQL query:\n" . $query);
+		Debug::log("Sending GraphQL variables:\n"
+			. json_encode($variables, JSON_PRETTY_PRINT));
 
-		return $data;
+		$response = json_decode(getContents(self::API_ENDPOINT, $header, $opts))
+			or returnServerError('API request to "' . self::API_ENDPOINT . '" failed.');
+
+		Debug::log("Got GraphQL response:\n"
+			. json_encode($response, JSON_PRETTY_PRINT));
+
+		if(isset($response->errors)) {
+			$messages = array_column($response->errors, 'message');
+			returnServerError('API error(s): ' . implode("\n", $messages));
+		}
+
+		return $response->data;
 	}
 
 	public function getName(){

bridges/TwitterBridge.php

@@ -95,6 +95,20 @@ EOD
 				'required' => false,
 				'title' => 'Specify term to search for'
 			)
+		),
+		'By list ID' => array(
+			'listid' => array(
+				'name' => 'List ID',
+				'exampleValue' => '31748',
+				'required' => true,
+				'title' => 'Insert the list id'
+			),
+			'filter' => array(
+				'name' => 'Filter',
+				'exampleValue' => '#rss-bridge',
+				'required' => false,
+				'title' => 'Specify term to search for'
+			)
 		)
 	);
 
@@ -145,6 +159,8 @@ EOD
 			break;
 		case 'By list':
 			return $this->getInput('list') . ' - Twitter list by ' . $this->getInput('user');
+		case 'By list ID':
+			return 'Twitter List #' . $this->getInput('listid');
 		default: return parent::getName();
 		}
 		return 'Twitter ' . $specific . $this->getInput($param);
@@ -167,6 +183,10 @@ EOD
 			. urlencode($this->getInput('user'))
 			. '/lists/'
 			. str_replace(' ', '-', strtolower($this->getInput('list')));
+		case 'By list ID':
+			return self::URI
+			. 'i/lists/'
+			. urlencode($this->getInput('listid'));
 		default: return parent::getURI();
 		}
 	}
@@ -188,6 +208,11 @@ EOD
 			. '/2/timeline/list.json?list_id='
 			. $this->getListId($this->getInput('user'), $this->getInput('list'))
 			. '&tweet_mode=extended';
+		case 'By list ID':
+			return self::API_URI
+			. '/2/timeline/list.json?list_id='
+			. $this->getInput('listid')
+			. '&tweet_mode=extended';
 		default: returnServerError('Invalid query context !');
 		}
 	}
@@ -354,6 +379,7 @@ EOD;
 
 			switch($this->queriedContext) {
 				case 'By list':
+				case 'By list ID':
 					// Check if filter applies to list (using raw content)
 					if($this->getInput('filter')) {
 						if(stripos($cleanedTweet, $this->getInput('filter')) === false) {

bridges/VarietyBridge.php

@@ -8,7 +8,7 @@ class VarietyBridge extends FeedExpander {
 	const DESCRIPTION = 'RSS feed for Variety';
 
 	public function collectData(){
-		$this->collectExpandableDatas('http://feeds.feedburner.com/variety/headlines', 15);
+		$this->collectExpandableDatas('https://feeds.feedburner.com/variety/headlines', 15);
 	}
 
 	protected function parseItem($newsItem){

bridges/WordPressBridge.php

@@ -92,9 +92,9 @@ class WordPressBridge extends FeedExpander {
 			returnClientError('The url parameter must either refer to http or https protocol.');
 		}
 		try{
-			$this->collectExpandableDatas($this->getURI() . '/feed/atom/');
+			$this->collectExpandableDatas($this->getURI() . '/feed/atom/', 20);
 		} catch (Exception $e) {
-			$this->collectExpandableDatas($this->getURI() . '/?feed=atom');
+			$this->collectExpandableDatas($this->getURI() . '/?feed=atom', 20);
 		}
 
 	}

bridges/WorldCosplayBridge.php

@@ -2,7 +2,7 @@
 class WorldCosplayBridge extends BridgeAbstract {
 	const NAME = 'WorldCosplay Bridge';
 	const URI = 'https://worldcosplay.net/';
-	const DESCRIPTION ='Returns WorldCosplay photos';
+	const DESCRIPTION = 'Returns WorldCosplay photos';
 	const MAINTAINER = 'AxorPL';
 
 	const API_CHARACTER = 'api/photo/list.json?character_id=%u&limit=%u';
@@ -95,14 +95,12 @@ class WorldCosplayBridge extends BridgeAbstract {
 
 		$json = json_decode(getContents($url))
 			or returnServerError(sprintf(self::ERR_QUERY, $url));
-		if($json->has_error)
-		{
+		if($json->has_error) {
 			returnServerError($json->message);
 		}
 		$list = $json->list;
 
-		foreach($list as $img)
-		{
+		foreach($list as $img) {
 			$item = array();
 			$item['uri'] = self::URI . substr($img->photo->url, 1);
 			$item['title'] = $img->photo->subject;

bridges/XPathBridge.php

@@ -0,0 +1,251 @@
+<?php
+
+class XPathBridge extends XPathAbstract {
+	const NAME = 'XPathBridge';
+	const URI = 'https://github.com/rss-bridge/rss-bridge';
+	const DESCRIPTION
+		= 'Parse any webpage using <a href="https://devhints.io/xpath" target="_blank">XPath expressions</a>';
+	const MAINTAINER = 'Niehztog';
+	const PARAMETERS = array(
+		'' => array(
+
+			'url' => array(
+				'name' => 'Enter web page URL',
+				'title' => <<<"EOL"
+You can specify any website URL which serves data suited for display in RSS feeds
+(for example a news blog).
+EOL
+				, 'type' => 'text',
+				'exampleValue' => 'https://news.blizzard.com/en-en',
+				'defaultValue' => 'https://news.blizzard.com/en-en',
+				'required' => true
+			),
+
+			'item' => array(
+				'name' => 'Item selector',
+				'title' => <<<"EOL"
+Enter an XPath expression matching a list of dom nodes, each node containing one
+feed article item in total (usually a surrounding &lt;div&gt; or &lt;span&gt; tag). This will
+be the context nodes for all of the following expressions. This expression usually
+starts with a single forward slash.
+EOL
+				, 'type' => 'text',
+				'exampleValue' => '/html/body/div/div[4]/div[2]/div[2]/div/div/section/ol/li/article',
+				'defaultValue' => '/html/body/div/div[4]/div[2]/div[2]/div/div/section/ol/li/article',
+				'required' => true
+			),
+
+			'title' => array(
+				'name' => 'Item title selector',
+				'title' => <<<"EOL"
+This expression should match a node contained within each article item node
+containing the article headline. It should start with a dot followed by two
+forward slashes, referring to any descendant nodes of the article item node.
+EOL
+				, 'type' => 'text',
+				'exampleValue' => './/div/div[2]/h2',
+				'defaultValue' => './/div/div[2]/h2',
+				'required' => true
+			),
+
+			'content' => array(
+				'name' => 'Item description selector',
+				'title' => <<<"EOL"
+This expression should match a node contained within each article item node
+containing the article content or description. It should start with a dot
+followed by two forward slashes, referring to any descendant nodes of the
+article item node.
+EOL
+				, 'type' => 'text',
+				'exampleValue' => './/div[@class="ArticleListItem-description"]/div[@class="h6"]',
+				'defaultValue' => './/div[@class="ArticleListItem-description"]/div[@class="h6"]',
+				'required' => false
+			),
+
+			'uri' => array(
+				'name' => 'Item URL selector',
+				'title' => <<<"EOL"
+This expression should match a node's attribute containing the article URL
+(usually the href attribute of an &lt;a&gt; tag). It should start with a dot
+followed by two forward slashes, referring to any descendant nodes of
+the article item node. Attributes can be selected by prepending an @ char
+before the attributes name.
+EOL
+				, 'type' => 'text',
+				'exampleValue' => './/a[@class="ArticleLink ArticleLink"]/@href',
+				'defaultValue' => './/a[@class="ArticleLink ArticleLink"]/@href',
+				'required' => false
+			),
+
+			'author' => array(
+				'name' => 'Item author selector',
+				'title' => <<<"EOL"
+This expression should match a node contained within each article item
+node containing the article author's name. It should start with a dot
+followed by two forward slashes, referring to any descendant nodes of
+the article item node.
+EOL
+				, 'type' => 'text',
+				'required' => false
+			),
+
+			'timestamp' => array(
+				'name' => 'Item date selector',
+				'title' => <<<"EOL"
+This expression should match a node or node's attribute containing the
+article timestamp or date (parsable by PHP's strtotime function). It
+should start with a dot followed by two forward slashes, referring to
+any descendant nodes of the article item node. Attributes can be
+selected by prepending an @ char before the attributes name.
+EOL
+				, 'type' => 'text',
+				'exampleValue' => './/time[@class="ArticleListItem-footerTimestamp"]/@timestamp',
+				'defaultValue' => './/time[@class="ArticleListItem-footerTimestamp"]/@timestamp',
+				'required' => false
+			),
+
+			'enclosures' => array(
+				'name' => 'Item image selector',
+				'title' => <<<"EOL"
+This expression should match a node's attribute containing an article
+image URL (usually the src attribute of an &lt;img&gt; tag or a style
+attribute). It should start with a dot followed by two forward slashes,
+referring to any descendant nodes of the article item node. Attributes
+can be selected by prepending an @ char before the attributes name.
+EOL
+				, 'type' => 'text',
+				'exampleValue' => './/div[@class="ArticleListItem-image"]/@style',
+				'defaultValue' => './/div[@class="ArticleListItem-image"]/@style',
+				'required' => false
+			),
+
+			'categories' => array(
+				'name' => 'Item category selector',
+				'title' => <<<"EOL"
+This expression should match a node or node's attribute contained
+within each article item node containing the article category. This
+could be inside &lt;div&gt; or &lt;span&gt; tags or sometimes be hidden
+in a data attribute. It should start with a dot followed by two
+forward slashes, referring to any descendant nodes of the article
+item node. Attributes can be selected by prepending an @ char
+before the attributes name.
+EOL
+				, 'type' => 'text',
+				'exampleValue' => './/div[@class="ArticleListItem-label"]',
+				'defaultValue' => './/div[@class="ArticleListItem-label"]',
+				'required' => false
+			),
+
+			'fix_encoding' => array(
+				'name' => 'Fix encoding',
+				'title' => <<<"EOL"
+Check this to fix feed encoding by invoking PHP's utf8_decode
+function on all extracted texts. Try this in case you see "broken" or
+"weird" characters in your feed where you'd normally expect umlauts
+or any other non-ascii characters.
+EOL
+				, 'type' => 'checkbox',
+				'required' => false
+			),
+
+		)
+	);
+
+	/**
+	 * Source Web page URL (should provide either HTML or XML content)
+	 * @return string
+	 */
+	protected function getSourceUrl(){
+		return $this->encodeUri($this->getInput('url'));
+	}
+
+	/**
+	 * XPath expression for extracting the feed items from the source page
+	 * @return string
+	 */
+	protected function getExpressionItem(){
+		return urldecode($this->getInput('item'));
+	}
+
+	/**
+	 * XPath expression for extracting an item title from the item context
+	 * @return string
+	 */
+	protected function getExpressionItemTitle(){
+		return urldecode($this->getInput('title'));
+	}
+
+	/**
+	 * XPath expression for extracting an item's content from the item context
+	 * @return string
+	 */
+	protected function getExpressionItemContent(){
+		return urldecode($this->getInput('content'));
+	}
+
+	/**
+	 * XPath expression for extracting an item link from the item context
+	 * @return string
+	 */
+	protected function getExpressionItemUri(){
+		return urldecode($this->getInput('uri'));
+	}
+
+	/**
+	 * XPath expression for extracting an item author from the item context
+	 * @return string
+	 */
+	protected function getExpressionItemAuthor(){
+		return urldecode($this->getInput('author'));
+	}
+
+	/**
+	 * XPath expression for extracting an item timestamp from the item context
+	 * @return string
+	 */
+	protected function getExpressionItemTimestamp(){
+		return urldecode($this->getInput('timestamp'));
+	}
+
+	/**
+	 * XPath expression for extracting item enclosures (media content like
+	 * images or movies) from the item context
+	 * @return string
+	 */
+	protected function getExpressionItemEnclosures(){
+		return urldecode($this->getInput('enclosures'));
+	}
+
+	/**
+	 * XPath expression for extracting an item category from the item context
+	 * @return string
+	 */
+	protected function getExpressionItemCategories(){
+		return urldecode($this->getInput('categories'));
+	}
+
+	/**
+	 * Fix encoding
+	 * @return string
+	 */
+	protected function getSettingFixEncoding(){
+		return $this->getInput('fix_encoding');
+	}
+
+	/**
+	 * Fixes URL encoding issues in input URL's
+	 * @param $uri
+	 * @return string|string[]
+	 */
+	private function encodeUri($uri)
+	{
+		if (strpos($uri, 'https%3A%2F%2F') === 0
+			|| strpos($uri, 'http%3A%2F%2F') === 0) {
+			$uri = urldecode($uri);
+		}
+
+		$uri = str_replace('|', '%7C', $uri);
+
+		return $uri;
+	}
+}

composer.json

@@ -34,6 +34,7 @@
     },
     "suggest": {
         "ext-memcached": "Allows to use memcached as cache type",
-        "ext-sqlite3": "Allows to use an SQLite database for caching"
+        "ext-sqlite3": "Allows to use an SQLite database for caching",
+        "ext-dom": "Allows to use some bridges based on XPath expressions"
     }
 }

lib/BridgeCard.php

@@ -126,7 +126,7 @@ This bridge is not fetching its content through a secure connection</div>';
 				if(isset($inputEntry['title']))
 					$form .= '<i class="info" title="' . filter_var($inputEntry['title'], FILTER_SANITIZE_STRING) . '">i</i>';
 				else
-					$form .= '<i></i>';
+					$form .= '<i class="no-info"></i>';
 			}
 
 			$form .= '</div>';

lib/BridgeList.php

@@ -129,7 +129,7 @@ EOD;
 	 * @return string The searchbar
 	 */
 	private static function getSearchbar() {
-		$query = filter_input(INPUT_GET, 'q');
+		$query = filter_input(INPUT_GET, 'q', FILTER_SANITIZE_SPECIAL_CHARS);
 
 		return <<<EOD
 <section class="searchbar">

lib/Configuration.php

@@ -28,7 +28,7 @@ final class Configuration {
 	 *
 	 * @todo Replace this property by a constant.
 	 */
-	public static $VERSION = 'dev.2020-02-26';
+	public static $VERSION = 'dev.2020-11-10';
 
 	/**
 	 * Holds the configuration data.

lib/XPathAbstract.php

@@ -0,0 +1,583 @@
+<?php
+
+/**
+ * An alternative abstract class for bridges utilizing XPath expressions
+ *
+ * This class is meant as an alternative base class for bridge implementations.
+ * It offers preliminary functionality for generating feeds based on XPath
+ * expressions.
+ * As a minimum, extending classes should define XPath expressions pointing
+ * to the feed items contents in the class constants below. In case there is
+ * more manual fine tuning required, it offers a bunch of methods which can
+ * be overridden, for example in order to specify formatting of field values
+ * or more flexible definition of dynamic XPath expressions.
+ *
+ * This class extends {@see BridgeAbstract}, which means it incorporates and
+ * extends all of its functionality.
+ **/
+abstract class XPathAbstract extends BridgeAbstract {
+
+	/**
+	 * Source Web page URL (should provide either HTML or XML content)
+	 * You can specify any website URL which serves data suited for display in RSS feeds
+	 * (for example a news blog).
+	 *
+	 * Use {@see XPathAbstract::getSourceUrl()} to read this parameter
+	 */
+	const FEED_SOURCE_URL = '';
+
+	/**
+	 * XPath expression for extracting the feed title from the source page.
+	 * If this is left blank or does not provide any data {@see BridgeAbstract::getName()}
+	 * is used instead as the feed's title.
+	 *
+	 * Use {@see XPathAbstract::getExpressionTitle()} to read this parameter
+	 */
+	const XPATH_EXPRESSION_FEED_TITLE = './/title';
+
+	/**
+	 * XPath expression for extracting the feed favicon URL from the source page.
+	 * If this is left blank or does not provide any data {@see BridgeAbstract::getIcon()}
+	 * is used instead as the feed's favicon URL.
+	 *
+	 * Use {@see XPathAbstract::getExpressionIcon()} to read this parameter
+	 */
+	const XPATH_EXPRESSION_FEED_ICON = './/link[@rel="icon"]/@href';
+
+	/**
+	 * XPath expression for extracting the feed items from the source page
+	 * Enter an XPath expression matching a list of dom nodes, each node containing one
+	 * feed article item in total (usually a surrounding <div> or <span> tag). This will
+	 * be the context nodes for all of the following expressions. This expression usually
+	 * starts with a single forward slash.
+	 *
+	 * Use {@see XPathAbstract::getExpressionItem()} to read this parameter
+	 */
+	const XPATH_EXPRESSION_ITEM = '';
+
+	/**
+	 * XPath expression for extracting an item title from the item context
+	 * This expression should match a node contained within each article item node
+	 * containing the article headline. It should start with a dot followed by two
+	 * forward slashes, referring to any descendant nodes of the article item node.
+	 *
+	 * Use {@see XPathAbstract::getExpressionItemTitle()} to read this parameter
+	 */
+	const XPATH_EXPRESSION_ITEM_TITLE = '';
+
+	/**
+	 * XPath expression for extracting an item's content from the item context
+	 * This expression should match a node contained within each article item node
+	 * containing the article content or description. It should start with a dot
+	 * followed by two forward slashes, referring to any descendant nodes of the
+	 * article item node.
+	 *
+	 * Use {@see XPathAbstract::getExpressionItemContent()} to read this parameter
+	 */
+	const XPATH_EXPRESSION_ITEM_CONTENT = '';
+
+	/**
+	 * XPath expression for extracting an item link from the item context
+	 * This expression should match a node's attribute containing the article URL
+	 * (usually the href attribute of an <a> tag). It should start with a dot
+	 * followed by two forward slashes, referring to any descendant nodes of
+	 * the article item node. Attributes can be selected by prepending an @ char
+	 * before the attributes name.
+	 *
+	 * Use {@see XPathAbstract::getExpressionItemUri()} to read this parameter
+	 */
+	const XPATH_EXPRESSION_ITEM_URI = '';
+
+	/**
+	 * XPath expression for extracting an item author from the item context
+	 * This expression should match a node contained within each article item
+	 * node containing the article author's name. It should start with a dot
+	 * followed by two forward slashes, referring to any descendant nodes of
+	 * the article item node.
+	 *
+	 * Use {@see XPathAbstract::getExpressionItemAuthor()} to read this parameter
+	 */
+	const XPATH_EXPRESSION_ITEM_AUTHOR = '';
+
+	/**
+	 * XPath expression for extracting an item timestamp from the item context
+	 * This expression should match a node or node's attribute containing the
+	 * article timestamp or date (parsable by PHP's strtotime function). It
+	 * should start with a dot followed by two forward slashes, referring to
+	 * any descendant nodes of the article item node. Attributes can be
+	 * selected by prepending an @ char before the attributes name.
+	 *
+	 * Use {@see XPathAbstract::getExpressionItemTimestamp()} to read this parameter
+	 */
+	const XPATH_EXPRESSION_ITEM_TIMESTAMP = '';
+
+	/**
+	 * XPath expression for extracting item enclosures (media content like
+	 * images or movies) from the item context
+	 * This expression should match a node's attribute containing an article
+	 * image URL (usually the src attribute of an <img> tag or a style
+	 * attribute). It should start with a dot followed by two forward slashes,
+	 * referring to any descendant nodes of the article item node. Attributes
+	 * can be selected by prepending an @ char before the attributes name.
+	 *
+	 * Use {@see XPathAbstract::getExpressionItemEnclosures()} to read this parameter
+	 */
+	const XPATH_EXPRESSION_ITEM_ENCLOSURES = '';
+
+	/**
+	 * XPath expression for extracting an item category from the item context
+	 * This expression should match a node or node's attribute contained
+	 * within each article item node containing the article category. This
+	 * could be inside <div> or <span> tags or sometimes be hidden
+	 * in a data attribute. It should start with a dot followed by two
+	 * forward slashes, referring to any descendant nodes of the article
+	 * item node. Attributes can be selected by prepending an @ char
+	 * before the attributes name.
+	 *
+	 * Use {@see XPathAbstract::getExpressionItemCategories()} to read this parameter
+	 */
+	const XPATH_EXPRESSION_ITEM_CATEGORIES = '';
+
+	/**
+	 * Fix encoding
+	 * Set this to true for fixing feed encoding by invoking PHP's utf8_decode
+	 * function on all extracted texts. Try this in case you see "broken" or
+	 * "weird" characters in your feed where you'd normally expect umlauts
+	 * or any other non-ascii characters.
+	 *
+	 * Use {@see XPathAbstract::getSettingFixEncoding()} to read this parameter
+	 */
+	const SETTING_FIX_ENCODING = false;
+
+	/**
+	 * Internal storage for resulting feed name, automatically detected
+	 * @var string
+	 */
+	private $feedName;
+
+	/**
+	 * Internal storage for resulting feed name, automatically detected
+	 * @var string
+	 */
+	private $feedUri;
+
+	/**
+	 * Internal storage for resulting feed favicon, automatically detected
+	 * @var string
+	 */
+	private $feedIcon;
+
+	public function getName(){
+		return $this->feedName ?: parent::getName();
+	}
+
+	public function getURI() {
+		return $this->feedUri ?: parent::getURI();
+	}
+
+	public function getIcon() {
+		return $this->feedIcon ?: parent::getIcon();
+	}
+
+	/**
+	 * Source Web page URL (should provide either HTML or XML content)
+	 * @return string
+	 */
+	protected function getSourceUrl(){
+		return static::FEED_SOURCE_URL;
+	}
+
+	/**
+	 * XPath expression for extracting the feed title from the source page
+	 * @return string
+	 */
+	protected function getExpressionTitle(){
+		return static::XPATH_EXPRESSION_FEED_TITLE;
+	}
+
+	/**
+	 * XPath expression for extracting the feed favicon from the source page
+	 * @return string
+	 */
+	protected function getExpressionIcon(){
+		return static::XPATH_EXPRESSION_FEED_ICON;
+	}
+
+	/**
+	 * XPath expression for extracting the feed items from the source page
+	 * @return string
+	 */
+	protected function getExpressionItem(){
+		return static::XPATH_EXPRESSION_ITEM;
+	}
+
+	/**
+	 * XPath expression for extracting an item title from the item context
+	 * @return string
+	 */
+	protected function getExpressionItemTitle(){
+		return static::XPATH_EXPRESSION_ITEM_TITLE;
+	}
+
+	/**
+	 * XPath expression for extracting an item's content from the item context
+	 * @return string
+	 */
+	protected function getExpressionItemContent(){
+		return static::XPATH_EXPRESSION_ITEM_CONTENT;
+	}
+
+	/**
+	 * XPath expression for extracting an item link from the item context
+	 * @return string
+	 */
+	protected function getExpressionItemUri(){
+		return static::XPATH_EXPRESSION_ITEM_URI;
+	}
+
+	/**
+	 * XPath expression for extracting an item author from the item context
+	 * @return string
+	 */
+	protected function getExpressionItemAuthor(){
+		return static::XPATH_EXPRESSION_ITEM_AUTHOR;
+	}
+
+	/**
+	 * XPath expression for extracting an item timestamp from the item context
+	 * @return string
+	 */
+	protected function getExpressionItemTimestamp(){
+		return static::XPATH_EXPRESSION_ITEM_TIMESTAMP;
+	}
+
+	/**
+	 * XPath expression for extracting item enclosures (media content like
+	 * images or movies) from the item context
+	 * @return string
+	 */
+	protected function getExpressionItemEnclosures(){
+		return static::XPATH_EXPRESSION_ITEM_ENCLOSURES;
+	}
+
+	/**
+	 * XPath expression for extracting an item category from the item context
+	 * @return string
+	 */
+	protected function getExpressionItemCategories(){
+		return static::XPATH_EXPRESSION_ITEM_CATEGORIES;
+	}
+
+	/**
+	 * Fix encoding
+	 * @return string
+	 */
+	protected function getSettingFixEncoding(){
+		return static::SETTING_FIX_ENCODING;
+	}
+
+	/**
+	 * Internal helper method for quickly accessing all the user defined constants
+	 * in derived classes
+	 *
+	 * @param $name
+	 * @return bool|string
+	 */
+	private function getParam($name){
+		switch($name) {
+
+			case 'url':
+				return $this->getSourceUrl();
+			case 'feed_title':
+				return $this->getExpressionTitle();
+			case 'feed_icon':
+				return $this->getExpressionIcon();
+			case 'item':
+				return $this->getExpressionItem();
+			case 'title':
+				return $this->getExpressionItemTitle();
+			case 'content':
+				return $this->getExpressionItemContent();
+			case 'uri':
+				return $this->getExpressionItemUri();
+			case 'author':
+				return $this->getExpressionItemAuthor();
+			case 'timestamp':
+				return $this->getExpressionItemTimestamp();
+			case 'enclosures':
+				return $this->getExpressionItemEnclosures();
+			case 'categories':
+				return $this->getExpressionItemCategories();
+			case 'fix_encoding':
+				return $this->getSettingFixEncoding();
+		}
+	}
+
+	/**
+	 * Should provide the source website HTML content
+	 * can be easily overwritten for example if special headers or auth infos are required
+	 * @return string
+	 */
+	protected function provideWebsiteContent() {
+		return getContents($this->feedUri);
+	}
+
+	/**
+	 * Should provide the feeds title
+	 *
+	 * @param DOMXPath $xpath
+	 * @return string
+	 */
+	protected function provideFeedTitle(DOMXPath $xpath) {
+		$title = $xpath->query($this->getParam('feed_title'));
+		if(count($title) === 1) {
+			return $this->getItemValueOrNodeValue($title);
+		}
+	}
+
+	/**
+	 * Should provide the URL of the feed's favicon
+	 *
+	 * @param DOMXPath $xpath
+	 * @return string
+	 */
+	protected function provideFeedIcon(DOMXPath $xpath) {
+		$icon = $xpath->query($this->getParam('feed_icon'));
+		if(count($icon) === 1) {
+			return $this->cleanImageUrl($this->getItemValueOrNodeValue($icon));
+		}
+	}
+
+	/**
+	 * Should provide the feed's items.
+	 *
+	 * @param DOMXPath $xpath
+	 * @return DOMNodeList
+	 */
+	protected function provideFeedItems(DOMXPath $xpath) {
+		return @$xpath->query($this->getParam('item'));
+	}
+
+	public function collectData() {
+
+		$this->feedUri = $this->getParam('url');
+
+		$webPageHtml = new DOMDocument();
+		libxml_use_internal_errors(true);
+		$webPageHtml->loadHTML($this->provideWebsiteContent());
+		libxml_clear_errors();
+		libxml_use_internal_errors(false);
+
+		$xpath = new DOMXPath($webPageHtml);
+
+		$this->feedName = $this->provideFeedTitle($xpath);
+		$this->feedIcon = $this->provideFeedIcon($xpath);
+
+		$entries = $this->provideFeedItems($xpath);
+		if($entries === false) {
+			return;
+		}
+
+		foreach ($entries as $entry) {
+			$item = new \FeedItem();
+			foreach(array('title', 'content', 'uri', 'author', 'timestamp', 'enclosures', 'categories') as $param) {
+
+				$expression = $this->getParam($param);
+				if('' === $expression) {
+					continue;
+				}
+
+				//can be a string or DOMNodeList, depending on the expression result
+				$typedResult = @$xpath->evaluate($expression, $entry);
+				if ($typedResult === false || ($typedResult instanceof DOMNodeList && count($typedResult) === 0)
+					|| (is_string($typedResult) && strlen(trim($typedResult)) === 0)) {
+					continue;
+				}
+
+				$item->__set($param, $this->formatParamValue($param, $this->getItemValueOrNodeValue($typedResult)));
+
+			}
+
+			$itemId = $this->generateItemId($item);
+			if(null !== $itemId) {
+				$item->setUid($itemId);
+			}
+
+			$this->items[] = $item;
+		}
+
+	}
+
+	/**
+	 * @param $param
+	 * @param $value
+	 * @return string|array
+	 */
+	protected function formatParamValue($param, $value)
+	{
+		$value = $this->fixEncoding($value);
+		switch ($param) {
+			case 'title':
+				return $this->formatItemTitle($value);
+			case 'content':
+				return $this->formatItemContent($value);
+			case 'uri':
+				return $this->formatItemUri($value);
+			case 'author':
+				return $this->formatItemAuthor($value);
+			case 'timestamp':
+				return $this->formatItemTimestamp($value);
+			case 'enclosures':
+				return array($this->cleanImageUrl($value));
+			case 'categories':
+				return array($this->fixEncoding($value));
+		}
+		return $value;
+	}
+
+	/**
+	 * Formats the title of a feed item. Takes extracted raw title and returns it formatted
+	 * as string.
+	 * Can be easily overwritten for in case the value needs to be transformed into something
+	 * else.
+	 * @param string $value
+	 * @return string
+	 */
+	protected function formatItemTitle($value) {
+		return $value;
+	}
+
+	/**
+	 * Formats the timestamp of a feed item. Takes extracted raw timestamp and returns unix
+	 * timestamp as integer.
+	 * Can be easily overwritten for example if a special format has to be expected on the
+	 * source website.
+	 * @param string $value
+	 * @return string
+	 */
+	protected function formatItemContent($value) {
+		return $value;
+	}
+
+	/**
+	 * Formats the URI of a feed item. Takes extracted raw URI and returns it formatted
+	 * as string.
+	 * Can be easily overwritten for in case the value needs to be transformed into something
+	 * else.
+	 * @param string $value
+	 * @return string
+	 */
+	protected function formatItemUri($value) {
+		if(strlen($value) === 0) {
+			return '';
+		}
+		if(strpos($value, 'http://') === 0 || strpos($value, 'https://') === 0) {
+			return $value;
+		}
+
+		return urljoin($this->feedUri, $value);
+	}
+
+	/**
+	 * Formats the author of a feed item. Takes extracted raw author and returns it formatted
+	 * as string.
+	 * Can be easily overwritten for in case the value needs to be transformed into something
+	 * else.
+	 * @param string $value
+	 * @return string
+	 */
+	protected function formatItemAuthor($value) {
+		return $value;
+	}
+
+	/**
+	 * Formats the timestamp of a feed item. Takes extracted raw timestamp and returns unix
+	 * timestamp as integer.
+	 * Can be easily overwritten for example if a special format has to be expected on the
+	 * source website.
+	 * @param string $value
+	 * @return false|int
+	 */
+	protected function formatItemTimestamp($value) {
+		return strtotime($value);
+	}
+
+	/**
+	 * Formats the enclosures of a feed item. Takes extracted raw enclosures and returns them
+	 * formatted as array.
+	 * Can be easily overwritten for in case the values need to be transformed into something
+	 * else.
+	 * @param string $value
+	 * @return array
+	 */
+	protected function formatItemEnclosures($value) {
+		return array($this->cleanImageUrl($value));
+	}
+
+	/**
+	 * Formats the categories of a feed item. Takes extracted raw categories and returns them
+	 * formatted as array.
+	 * Can be easily overwritten for in case the values need to be transformed into something
+	 * else.
+	 * @param string $value
+	 * @return array
+	 */
+	protected function formatItemCategories($value) {
+		return array($value);
+	}
+
+	/**
+	 * @param $imageUrl
+	 * @return string|void
+	 */
+	protected function cleanImageUrl($imageUrl)
+	{
+		$result = preg_match('~(?:http(?:s)?:)?[\/a-zA-Z0-9\-_\.]+\.(?:jpg|gif|png|jpeg|ico){1}~', $imageUrl, $matches);
+		if(1 !== $result) {
+			return;
+		}
+		return urljoin($this->feedUri, $matches[0]);
+	}
+
+	/**
+	 * @param $typedResult
+	 * @return string
+	 */
+	protected function getItemValueOrNodeValue($typedResult)
+	{
+		if($typedResult instanceof DOMNodeList) {
+			$item = $typedResult->item(0);
+			if ($item instanceof DOMElement) {
+				return trim($item->nodeValue);
+			} elseif ($item instanceof DOMAttr) {
+				return trim($item->value);
+			}
+		} elseif(is_string($typedResult) && strlen($typedResult) > 0) {
+			return trim($typedResult);
+		}
+		returnServerError('Unknown type of XPath expression result.');
+	}
+
+	/**
+	 * Fixes feed encoding by invoking PHP's utf8_decode function on extracted texts.
+	 * Useful in case of "broken" or "weird" characters in the feed where you'd normally
+	 * expect umlauts.
+	 *
+	 * @param $input
+	 * @return string
+	 */
+	protected function fixEncoding($input)
+	{
+		return $this->getParam('fix_encoding') ? utf8_decode($input) : $input;
+	}
+
+	/**
+	 * Allows overriding default mechanism determining items Uid's
+	 *
+	 * @param FeedItem $item
+	 * @return string|null
+	 */
+	protected function generateItemId(\FeedItem $item) {
+		return null; //auto generation
+	}
+}

lib/contents.php

@@ -41,7 +41,7 @@
  * 'content' if enabled.
  *
  * For more information see http://php.net/manual/en/function.curl-setopt.php
- * @return string The contents.
+ * @return string|array The contents.
  */
 function getContents($url, $header = array(), $opts = array(), $returnHeader = false){
 	Debug::log('Reading contents from "' . $url . '"');
@@ -233,7 +233,7 @@ EOD
  * when returning plaintext.
  * @param string $defaultSpanText Specifies the replacement text for `<span />`
  * tags when returning plaintext.
- * @return string Contents as simplehtmldom object.
+ * @return false|simple_html_dom Contents as simplehtmldom object.
  */
 function getSimpleHTMLDOM($url,
 	$header = array(),
@@ -283,7 +283,7 @@ function getSimpleHTMLDOM($url,
  * when returning plaintext.
  * @param string $defaultSpanText Specifies the replacement text for `<span />`
  * tags when returning plaintext.
- * @return string Contents as simplehtmldom object.
+ * @return false|simple_html_dom Contents as simplehtmldom object.
  */
 function getSimpleHTMLDOMCached($url,
 	$duration = 86400,

lib/rssbridge.php

@@ -74,6 +74,7 @@ require_once PATH_LIB . 'BridgeList.php';
 require_once PATH_LIB . 'ParameterValidator.php';
 require_once PATH_LIB . 'ActionFactory.php';
 require_once PATH_LIB . 'ActionAbstract.php';
+require_once PATH_LIB . 'XPathAbstract.php';
 
 // Functions
 require_once PATH_LIB . 'html.php';

static/style.css

@@ -360,7 +360,7 @@ h5 {
 		margin: 3px auto 0;
 	}
 
-	.info {
+	.info, .no-info {
 		display: none;
 	}