'. $serie . '
- Disponibilité : ' . $dispo . ' '; + $item['content'] .= '
- Carburant : ' . $carburant . ' '; + $item['content'] .= '
- Transmission : ' . $transmission . ' '; + $item['content'] .= '
- Nombre de places : ' . $places . ' '; + $item['content'] .= '
- Nombre de portes : ' . $portes . ' '; + $item['content'] .= '
- Série : ' . $serie . ' '; + $item['content'] .= '
- Carosserie : ' . $carosserie . ' '; + $item['content'] .= '
- Remise : ' . $remise . ' '; + $item['content'] .= '
- Prix : ' . $prix . '
+ $item['title'] = trim(explode("\n", $element->find('div.text', 0)->plaintext)[0]); + + $item['content'] = strip_tags($element->find('div.text', 0)); + + // timestamp is part of: + //
Par {author} le {date} dans {category}
+ preg_match( + '/.+le(.+)dans.*/', + $element->find('div[class="blague-footer"]', 0)->plaintext, + $matches + ); + + $item['timestamp'] = strtotime($matches[1]); + + $this->items[] = $item; - if(isset($temp[2])) { - $item['content'] = trim($element->find('div.joke_text_contener', 0)->innertext); - $uri = $temp[2]->href; - $item['uri'] = $uri; - $item['title'] = substr($uri, (strrpos($uri, "/") + 1)); - $date = $element->find('li.bdm_date', 0)->innertext; - $time = mktime(0, 0, 0, substr($date, 3, 2), substr($date, 0, 2), substr($date, 6, 4)); - $item['timestamp'] = $time; - $item['author'] = $element->find('li.bdm_pseudo', 0)->innertext; - $this->items[] = $item; - } } + } + } diff --git a/bridges/BundesbankBridge.php b/bridges/BundesbankBridge.php new file mode 100644 index 00000000..972290bd --- /dev/null +++ b/bridges/BundesbankBridge.php @@ -0,0 +1,83 @@ + array( + 'name' => 'Language', + 'type' => 'list', + 'required' => true, + 'defaultValue' => self::LANG_DE, + 'values' => array( + 'English' => self::LANG_EN, + 'Deutsch' => self::LANG_DE + ) + ) + ) + ); + + public function getURI() { + switch($this->getInput(self::PARAM_LANG)) { + case self::LANG_EN: return self::URI . 'en/publications/reports/studies'; + case self::LANG_DE: return self::URI . 'de/publikationen/berichte/studien'; + } + + return parent::getURI(); + } + + public function collectData() { + + $html = getSimpleHTMLDOM($this->getURI()) + or returnServerError('No response for ' . $this->getURI()); + + $html = defaultLinkTo($html, $this->getURI()); + + foreach($html->find('ul.resultlist li') as $study) { + $item = array(); + + $item['uri'] = $study->find('.teasable__link', 0)->href; + + // Get title without child elements (i.e. subtitle) + $title = $study->find('.teasable__title div.h2', 0); + + foreach($title->children as &$child) { + $child->outertext = ''; + } + + $item['title'] = $title->innertext; + + // Add subtitle to the content if it exists + $item['content'] = ''; + + if($subtitle = $study->find('.teasable__subtitle', 0)) { + $item['content'] .= '' . $study->find('.teasable__subtitle', 0)->plaintext . ''; + } + + $item['content'] .= '' . $study->find('.teasable__text', 0)->plaintext . '
'; + + $item['timestamp'] = strtotime($study->find('.teasable__date', 0)->plaintext); + + // Downloads and older studies don't have images + if($study->find('.teasable__image', 0)) { + $item['enclosures'] = array( + $study->find('.teasable__image img', 0)->src + ); + } + + $this->items[] = $item; + } + + } + +} diff --git a/bridges/CADBridge.php b/bridges/CADBridge.php deleted file mode 100644 index 09e3e65a..00000000 --- a/bridges/CADBridge.php +++ /dev/null @@ -1,45 +0,0 @@ -collectExpandableDatas('http://cdn2.cad-comic.com/rss.xml', 10); - } - - protected function parseItem($newsItem){ - $item = parent::parseItem($newsItem); - $item['content'] = $this->extractCADContent($item['uri']); - return $item; - } - - private function extractCADContent($url) { - $html3 = getSimpleHTMLDOMCached($url); - - // The request might fail due to missing https support or wrong URL - if($html3 == false) - return 'Daily comic not released yet'; - - $htmlpart = explode("/", $url); - - switch ($htmlpart[3]) { - case 'cad': - preg_match_all("/http:\/\/cdn2\.cad-comic\.com\/comics\/cad-\S*png/", $html3, $url2); - break; - case 'sillies': - preg_match_all("/http:\/\/cdn2\.cad-comic\.com\/comics\/sillies-\S*gif/", $html3, $url2); - break; - default: - return 'Daily comic not released yet'; - } - $img = implode($url2[0]); - $html3->clear(); - unset($html3); - if ($img == '') - return 'Daily comic not released yet'; - return 'You may specify a -topic found in some section URLs, else all topics are selected.'; - - const PARAMETERS = array( array( - 'topic' => array( - 'name' => 'Topic name' + const URI = 'https://www.cnet.com/'; + const CACHE_TIMEOUT = 3600; // 1h + const DESCRIPTION = 'Returns the newest articles.'; + const PARAMETERS = array( + array( + 'topic' => array( + 'name' => 'Topic', + 'type' => 'list', + 'values' => array( + 'All articles' => '', + 'Apple' => 'apple', + 'Google' => 'google', + 'Microsoft' => 'tags-microsoft', + 'Computers' => 'topics-computers', + 'Mobile' => 'topics-mobile', + 'Sci-Tech' => 'topics-sci-tech', + 'Security' => 'topics-security', + 'Internet' => 'topics-internet', + 'Tech Industry' => 'topics-tech-industry' + ) + ) ) - )); + ); - public function collectData(){ + private function cleanArticle($article_html) { + $offset_p = strpos($article_html, '
');
+ $offset_figure = strpos($article_html, ' {$fullArticle} {$item['title']} ');
+ $content = strip_tags($content, ' Unfortunately, rss-bridge cannot fetch the requested page. Response:
+ Unfortunately, rss-bridge cannot fetch the requested page. Response:
- ');
- //Adapt link hrefs: convert relative links into absolute links and bypass external link redirection
- $content = preg_replace_callback('/ href=\"([^"]+)\"/i', $unescape_fb_link, $content);
+ $content = $this->unescape_fb_link($content);
- //Clean useless html tag properties and fix link closing tags
+ // Clean useless html tag properties and fix link closing tags
foreach (array(
'onmouseover',
'onclick',
@@ -252,35 +597,45 @@ EOD;
'aria-[^=]*',
'role',
'rel',
- 'id') as $property_name)
- $content = preg_replace('/ ' . $property_name . '=\"[^"]*\"/i', '', $content);
+ 'id') as $property_name) {
+ $content = preg_replace('/ ' . $property_name . '=\"[^"]*\"/i', '', $content);
+ }
+
$content = preg_replace('/<\/a [^>]+>/i', ' '
+ . $description
+ . ' '
- . $description
- . ' ');
- $contents = $this->stripWithDelimiters($contents, 'fs:definition="', '"');
- $contents = $this->stripWithDelimiters($contents, 'fs:xt:clicktype="', '"');
- $contents = $this->stripWithDelimiters($contents, 'fs:xt:clickname="', '"');
- $contents = $this->stripWithDelimiters($contents, '');
return $headline . trim($contents);
}
diff --git a/bridges/GBAtempBridge.php b/bridges/GBAtempBridge.php
index f80a25ce..1266b0de 100644
--- a/bridges/GBAtempBridge.php
+++ b/bridges/GBAtempBridge.php
@@ -20,50 +20,58 @@ class GBAtempBridge extends BridgeAbstract {
)
));
- private function extractFromDelimiters($string, $start, $end){
- if(strpos($string, $start) !== false) {
- $section_retrieved = substr($string, strpos($string, $start) + strlen($start));
- $section_retrieved = substr($section_retrieved, 0, strpos($section_retrieved, $end));
- return $section_retrieved;
- }
-
- return false;
- }
-
- private function stripWithDelimiters($string, $start, $end){
- while(strpos($string, $start) !== false) {
- $section_to_remove = substr($string, strpos($string, $start));
- $section_to_remove = substr($section_to_remove, 0, strpos($section_to_remove, $end) + strlen($end));
- $string = str_replace($section_to_remove, '', $string);
- }
-
- return $string;
- }
-
- private function buildItem($uri, $title, $author, $timestamp, $content){
+ private function buildItem($uri, $title, $author, $timestamp, $thumbnail, $content){
$item = array();
$item['uri'] = $uri;
$item['title'] = $title;
$item['author'] = $author;
$item['timestamp'] = $timestamp;
$item['content'] = $content;
+ if (!empty($thumbnail)) {
+ $item['enclosures'] = array($thumbnail);
+ }
return $item;
}
private function cleanupPostContent($content, $site_url){
$content = str_replace(':arrow:', '➤', $content);
$content = str_replace('href="attachments/', 'href="'.$site_url.'attachments/', $content);
- $content = $this->stripWithDelimiters($content, ' ' . ($content->find('div#review_intro', 0)->plaintext) . ' ' . $content->find('div.review_subheader', 0)->plaintext . '\1
';
+ $item['content'] = preg_replace($regex, $replacement, $item['content']);
+
+ // Lists
+ $regex = '/\n\s*[\*|\-](.*)/';
+ $item['content'] = preg_replace_callback ($regex, function($regs) {
+ $item = $regs[1];
+ return sprintf ('
', trim ($item));
+ }, $item['content']);
+
+ $this->items[] = $item;
+ }
+ }
+
+ private function getJsonUri() {
+ $channel = $this->getInput('channel');
+
+ return "https://coreos.com/releases/releases-$channel.json";
+ }
+
+ public function getURI() {
+ return self::URI;
+ }
+
+ public function getName(){
+ if(!is_null($this->getInput('channel'))) {
+ return 'Container Linux Releases: ' . $this->getInput('channel') . ' Channel';
+ }
+
+ return parent::getName();
+ }
+}
diff --git a/bridges/CopieDoubleBridge.php b/bridges/CopieDoubleBridge.php
index 767cdce3..3545c6fc 100644
--- a/bridges/CopieDoubleBridge.php
+++ b/bridges/CopieDoubleBridge.php
@@ -25,7 +25,7 @@ class CopieDoubleBridge extends BridgeAbstract {
} elseif(strpos($element->innertext, '/images/suivant.gif') === false) {
$a = $element->find('a', 0);
$item['uri'] = self::URI . $a->href;
- $content = str_replace('src="/', 'src="/' . self::URI, $element->find("td", 0)->innertext);
+ $content = str_replace('src="/', 'src="/' . self::URI, $element->find('td', 0)->innertext);
$content = str_replace('href="/', 'href="' . self::URI, $content);
$item['content'] = $content;
$this->items[] = $item;
diff --git a/bridges/CourrierInternationalBridge.php b/bridges/CourrierInternationalBridge.php
index 15738633..1e7c93e8 100644
--- a/bridges/CourrierInternationalBridge.php
+++ b/bridges/CourrierInternationalBridge.php
@@ -11,7 +11,7 @@ class CourrierInternationalBridge extends BridgeAbstract {
$html = getSimpleHTMLDOM(self::URI)
or returnServerError('Error.');
- $element = $html->find("article");
+ $element = $html->find('article');
$article_count = 1;
foreach($element as $article) {
diff --git a/bridges/CpasbienBridge.php b/bridges/CpasbienBridge.php
deleted file mode 100644
index 19efd84a..00000000
--- a/bridges/CpasbienBridge.php
+++ /dev/null
@@ -1,74 +0,0 @@
- array(
- 'name' => 'Search',
- 'required' => true,
- 'title' => 'Type your search'
- )
- ));
-
- public function collectData(){
- $request = str_replace(" ", "-", trim($this->getInput('q')));
- $html = getSimpleHTMLDOM(self::URI . '/recherche/' . urlencode($request) . '.html')
- or returnServerError('No results for this query.');
-
- foreach($html->find('#gauche', 0)->find('div') as $episode) {
- if($episode->getAttribute('class') == 'ligne0'
- || $episode->getAttribute('class') == 'ligne1') {
-
- $urlepisode = $episode->find('a', 0)->getAttribute('href');
- $htmlepisode = getSimpleHTMLDOMCached($urlepisode, 86400 * 366 * 30);
-
- $item = array();
- $item['author'] = $episode->find('a', 0)->text();
- $item['title'] = $episode->find('a', 0)->text();
- $item['pubdate'] = $this->getCachedDate($urlepisode);
- $textefiche = $htmlepisode->find('#textefiche', 0)->find('p', 1);
-
- if(isset($textefiche)) {
- $item['content'] = $textefiche->text();
- } else {
- $p = $htmlepisode->find('#textefiche', 0)->find('p');
- if(!empty($p)) {
- $item['content'] = $htmlepisode->find('#textefiche', 0)->find('p', 0)->text();
- }
- }
-
- $item['id'] = $episode->find('a', 0)->getAttribute('href');
- $item['uri'] = self::URI . $htmlepisode->find('#telecharger', 0)->getAttribute('href');
- $this->items[] = $item;
- }
- }
- }
-
- public function getName(){
- if(!is_null($this->getInput('q'))) {
- return $this->getInput('q') . ' : ' . self::NAME;
- }
-
- return parent::getName();
- }
-
- private function getCachedDate($url){
- debugMessage('getting pubdate from url ' . $url . '');
-
- // Initialize cache
- $cache = Cache::create('FileCache');
- $cache->setPath(CACHE_DIR . '/pages');
-
- $params = [$url];
- $cache->setParameters($params);
-
- // Get cachefile timestamp
- $time = $cache->getTime();
- return ($time !== false ? $time : time());
- }
-}
diff --git a/bridges/DanbooruBridge.php b/bridges/DanbooruBridge.php
index 36b8c08a..755399f4 100644
--- a/bridges/DanbooruBridge.php
+++ b/bridges/DanbooruBridge.php
@@ -1,7 +1,7 @@
find('a', 0)->href;
- $item['postid'] = (int)preg_replace("/[^0-9]/", '', $element->getAttribute(static::IDATTRIBUTE));
+ $item['postid'] = (int)preg_replace('/[^0-9]/', '', $element->getAttribute(static::IDATTRIBUTE));
$item['timestamp'] = time();
$thumbnailUri = $element->find('img', 0)->src;
$item['tags'] = $this->getTags($element);
@@ -57,11 +57,80 @@ class DanbooruBridge extends BridgeAbstract {
}
public function collectData(){
- $html = getSimpleHTMLDOM($this->getFullURI())
+ $content = getContents($this->getFullURI())
or returnServerError('Could not request ' . $this->getName());
+ $html = Fix_Simple_Html_Dom::str_get_html($content);
+
foreach($html->find(static::PATHTODATA) as $element) {
$this->items[] = $this->getItemFromElement($element);
}
}
}
+
+/**
+ * This class is a monkey patch to 'extend' simplehtmldom to recognize element to provide versions of an image for different
+ * display device scenarios. The browser will consider each of the child
+ * element's src attribute is selected. The selected image is then presented in
+ * the space occupied by the
element.
+ *
+ * -- https://developer.mozilla.org/en-US/docs/Web/HTML/Element/picture
+ *
+ * Notice: This class uses parts of the original simplehtmldom, adjusted to pass
+ * the guidelines of RSS-Bridge (formatting)
+ */
+final class Fix_Simple_Html_Dom extends simple_html_dom {
+
+ /* copy from simple_html_dom, added 'source' at the end */
+ protected $self_closing_tags = array(
+ 'img' => 1,
+ 'br' => 1,
+ 'input' => 1,
+ 'meta' => 1,
+ 'link' => 1,
+ 'hr' => 1,
+ 'base' => 1,
+ 'embed' => 1,
+ 'spacer' => 1,
+ 'source' => 1
+ );
+
+ /* copy from simplehtmldom, changed 'simple_html_dom' to 'Fix_Simple_Html_Dom' */
+ public static function str_get_html($str,
+ $lowercase = true,
+ $forceTagsClosed = true,
+ $target_charset = DEFAULT_TARGET_CHARSET,
+ $stripRN = true,
+ $defaultBRText = DEFAULT_BR_TEXT,
+ $defaultSpanText = DEFAULT_SPAN_TEXT)
+ {
+ $dom = new Fix_Simple_Html_Dom(null,
+ $lowercase,
+ $forceTagsClosed,
+ $target_charset,
+ $stripRN,
+ $defaultBRText,
+ $defaultSpanText);
+
+ if (empty($str) || strlen($str) > MAX_FILE_SIZE) {
+
+ $dom->clear();
+ return false;
+
+ }
+
+ $dom->load($str, $lowercase, $stripRN);
+
+ return $dom;
+ }
+}
diff --git a/bridges/DauphineLibereBridge.php b/bridges/DauphineLibereBridge.php
index 7547d740..20c82070 100644
--- a/bridges/DauphineLibereBridge.php
+++ b/bridges/DauphineLibereBridge.php
@@ -3,7 +3,7 @@ class DauphineLibereBridge extends FeedExpander {
const MAINTAINER = 'qwertygc';
const NAME = 'Dauphine Bridge';
- const URI = 'http://www.ledauphine.com/';
+ const URI = 'https://www.ledauphine.com/';
const CACHE_TIMEOUT = 7200; // 2h
const DESCRIPTION = 'Returns the newest articles.';
@@ -49,8 +49,9 @@ class DauphineLibereBridge extends FeedExpander {
private function extractContent($url){
$html2 = getSimpleHTMLDOMCached($url);
- $text = $html2->find('div.column', 0)->innertext;
- $text = preg_replace('@
';
- $dealDateDiv = $deal->find('div[class='. $selectorDate .']', 0)
+ . '">'
- . $deal->find('a[class*='. $selectorLink .']', 0)->innertext
- . '
'
- . $this->getPrix($deal)
- . $this->getReduction($deal)
- . $this->getExpedition($deal)
- . $this->getLivraison($deal)
- . $this->getOrigine($deal)
- . $deal->find('div[class='. $selectorDescription .']', 0)->innertext
- . ''
- . $deal->find('div[class='. $selectorHot .']', 0)->children(0)->outertext
- . ' '
+ . $deal->find('a[class*='. $selectorLink .']', 0)->innertext
+ . '
'
+ . $this->getPrice($deal)
+ . $this->getDiscount($deal)
+ . $this->getShipsFrom($deal)
+ . $this->getShippingCost($deal)
+ . $this->GetSource($deal)
+ . $deal->find('div[class*='. $selectorDescription .']', 0)->innertext
+ . ''
+ . $deal->find('div[class*='. $selectorHot .']', 0)
+ ->find('span', 1)->outertext
+ . ' ';
+ $dealDateDiv = $deal->find('div[class*='. $selectorDate .']', 0)
->find('span[class=hide--toW3]');
$itemDate = end($dealDateDiv)->plaintext;
- if(substr( $itemDate, 0, 6 ) === 'il y a') {
+ // In case of a Local deal, there is no date, but we can use
+ // this case for other reason (like date not in the last field)
+ if ($this->contains($itemDate, $this->i8n('localdeal'))) {
+ $item['timestamp'] = time();
+ } else if ($this->contains($itemDate, $this->i8n('relative-date-indicator'))) {
$item['timestamp'] = $this->relativeDateToTimestamp($itemDate);
- } else {
+ } else {
$item['timestamp'] = $this->parseDate($itemDate);
}
$this->items[] = $item;
@@ -240,15 +1192,29 @@ class DealabsBridge extends BridgeAbstract {
}
}
+ /**
+ * Check if the string $str contains any of the string of the array $arr
+ * @return boolean true if the string matched anything otherwise false
+ */
+ private function contains($str, array $arr)
+ {
+ foreach ($arr as $a) {
+ if (stripos($str, $a) !== false) {
+ return true;
+ }
+ }
+ return false;
+ }
+
/**
* Get the Price from a Deal if it exists
* @return string String of the deal price
*/
- private function getPrix($deal)
+ private function getPrice($deal)
{
- if($deal->find(
+ if ($deal->find(
'span[class*=thread-price]', 0) != null) {
- return '
Name: ' . $details->children(0)->children(1)->innertext;
@@ -139,4 +142,20 @@ class ETTVBridge extends BridgeAbstract {
$this->items[] = $item;
}
}
+
+ public function getName(){
+ if($this->getInput('query')) {
+ return '[' . self::NAME . '] ' . $this->getInput('query');
+ }
+
+ return self::NAME;
+ }
+
+ public function getURI(){
+ if(isset($this->results_link) && !empty($this->results_link)) {
+ return $this->results_link;
+ }
+
+ return self::URI;
+ }
}
diff --git a/bridges/EZTVBridge.php b/bridges/EZTVBridge.php
index 4fb9e578..c016ff33 100644
--- a/bridges/EZTVBridge.php
+++ b/bridges/EZTVBridge.php
@@ -1,7 +1,7 @@
getInput('i'));
+ $showList = explode(',', $this->getInput('i'));
foreach($showList as $showID) {
// Get show page
diff --git a/bridges/ElloBridge.php b/bridges/ElloBridge.php
index c0e266e1..07a91085 100644
--- a/bridges/ElloBridge.php
+++ b/bridges/ElloBridge.php
@@ -45,9 +45,10 @@ class ElloBridge extends BridgeAbstract {
$item = array();
$item['author'] = $this->getUsername($post, $postData);
$item['timestamp'] = strtotime($post->created_at);
- $item['title'] = $this->findText($post->summary);
+ $item['title'] = strip_tags($this->findText($post->summary));
$item['content'] = $this->getPostContent($post->body);
$item['enclosures'] = $this->getEnclosures($post, $postData);
+ $item['uri'] = self::URI . $item['author'] . '/post/' . $post->token;
$content = $post->body;
$this->items[] = $item;
@@ -57,7 +58,7 @@ class ElloBridge extends BridgeAbstract {
}
- public function findText($path) {
+ private function findText($path) {
foreach($path as $summaryElement) {
@@ -71,7 +72,7 @@ class ElloBridge extends BridgeAbstract {
}
- public function getPostContent($path) {
+ private function getPostContent($path) {
$content = '';
foreach($path as $summaryElement) {
@@ -92,7 +93,7 @@ class ElloBridge extends BridgeAbstract {
}
- public function getEnclosures($post, $postData) {
+ private function getEnclosures($post, $postData) {
$assets = [];
foreach($post->links->assets as $asset) {
@@ -108,7 +109,7 @@ class ElloBridge extends BridgeAbstract {
}
- public function getUsername($post, $postData) {
+ private function getUsername($post, $postData) {
foreach($postData->linked->users as $user) {
if($user->id == $post->links->author->id) {
@@ -118,7 +119,7 @@ class ElloBridge extends BridgeAbstract {
}
- public function getAPIKey() {
+ private function getAPIKey() {
$cache = Cache::create('FileCache');
$cache->setPath(CACHE_DIR);
$cache->setParameters(['key']);
diff --git a/bridges/EstCeQuonMetEnProdBridge.php b/bridges/EstCeQuonMetEnProdBridge.php
index db9d1d5f..4439d694 100644
--- a/bridges/EstCeQuonMetEnProdBridge.php
+++ b/bridges/EstCeQuonMetEnProdBridge.php
@@ -7,19 +7,9 @@ class EstCeQuonMetEnProdBridge extends BridgeAbstract {
const CACHE_TIMEOUT = 21600; // 6h
const DESCRIPTION = 'Should we put a website in production today? (French)';
- public function collectData(){
- function extractFromDelimiters($string, $start, $end){
- if(strpos($string, $start) !== false) {
- $section_retrieved = substr($string, strpos($string, $start) + strlen($start));
- $section_retrieved = substr($section_retrieved, 0, strpos($section_retrieved, $end));
- return $section_retrieved;
- }
-
- return false;
- }
-
- $html = getSimpleHTMLDOM($this->getURI())
- or returnServerError('Could not request EstCeQuonMetEnProd: ' . $this->getURI());
+ public function collectData() {
+ $html = getSimpleHTMLDOM(self::URI)
+ or returnServerError('Could not request EstCeQuonMetEnProd: ' . self::URI);
$item = array();
$item['uri'] = $this->getURI() . '#' . date('Y-m-d');
@@ -28,8 +18,8 @@ class EstCeQuonMetEnProdBridge extends BridgeAbstract {
$item['timestamp'] = strtotime('today midnight');
$item['content'] = str_replace(
'src="/',
- 'src="' . $this->getURI(),
- trim(extractFromDelimiters($html->outertext, '', '
'))
+ 'src="' . self::URI,
+ trim(extractFromDelimiters($html->outertext, '', '');
//Adapt link hrefs: convert relative links into absolute links and bypass external link redirection
$content = preg_replace_callback('/ href=\"([^"]+)\"/i', $unescape_fb_link, $content);
@@ -145,7 +146,7 @@ EOD;
// "smile emoticon" back to ASCII emoticons eg ":)"
$content = preg_replace_callback('/([^ <>]+) ([^<>]+)<\/u><\/i>/i', $unescape_fb_emote, $content);
- $item['content'] = $content;
+ $item['content'] = html_entity_decode($content, ENT_QUOTES);
$title = $author;
if (strlen($title) > 24)
@@ -154,10 +155,12 @@ EOD;
if (strlen($title) > 64)
$title = substr($title, 0, strpos(wordwrap($title, 64), "\n")) . '...';
- $item['title'] = $title;
- $item['author'] = $author;
+ $item['title'] = html_entity_decode($title, ENT_QUOTES);
+ $item['author'] = html_entity_decode($author, ENT_QUOTES);
+ $item['timestamp'] = html_entity_decode($timestamp, ENT_QUOTES);
- array_push($this->items, $item);
+ if($item['timestamp'] != 0)
+ array_push($this->items, $item);
}
}
@@ -168,7 +171,7 @@ EOD;
$regex = implode(
'',
array(
- "/timeline_unit",
+ '/timeline_unit',
"\\\\\\\\u00253A1",
"\\\\\\\\u00253A([0-9]*)",
"\\\\\\\\u00253A([0-9]*)",
@@ -182,29 +185,29 @@ EOD;
return implode(
'',
array(
- "https://touch.facebook.com/pages_reaction_units/more/?page_id=",
+ 'https://touch.facebook.com/pages_reaction_units/more/?page_id=',
$pageID,
- "&cursor=%7B%22timeline_cursor%22%3A%22timeline_unit%3A1%3A",
+ '&cursor=%7B%22timeline_cursor%22%3A%22timeline_unit%3A1%3A',
$result[1],
- "%3A",
+ '%3A',
$result[2],
- "%3A",
+ '%3A',
$result[3],
- "%3A",
+ '%3A',
$result[4],
- "%22%2C%22timeline_section_cursor%22%3A%7B%7D%2C%22",
- "has_next_page%22%3Atrue%7D&surface=mobile_page_home&unit_count=3"
+ '%22%2C%22timeline_section_cursor%22%3A%7B%7D%2C%22',
+ 'has_next_page%22%3Atrue%7D&surface=mobile_page_home&unit_count=3'
)
);
}
//Builds the HTML from the encoded JS that Facebook provides.
private function buildContent($pageContent){
-
- $regex = "/\\\"html\\\":\\\"(.*?)\\\",\\\"replace/";
+ // The html ends with:
+ // /div>","replaceifexists
+ $regex = '/\\"html\\":(\".+\/div>"),"replace/';
preg_match($regex, $pageContent, $result);
-
- return str_get_html(html_entity_decode(json_decode('"' . $result[1] . '"')));
+ return str_get_html(json_decode($result[1]));
}
@@ -214,7 +217,7 @@ EOD;
$ctx = stream_context_create(array(
'http' => array(
- 'user_agent' => "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:46.0) Gecko/20100101 Firefox/46.0",
+ 'user_agent' => 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:46.0) Gecko/20100101 Firefox/46.0',
'Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'
)
)
@@ -222,12 +225,12 @@ EOD;
$a = file_get_contents($pageURL, 0, $ctx);
//First request to get the cookie
- $cookies = "";
+ $cookies = '';
foreach($http_response_header as $hdr) {
- if(strpos($hdr, "Set-Cookie") !== false) {
- $cLine = explode(":", $hdr)[1];
- $cLine = explode(";", $cLine)[0];
- $cookies .= ";" . $cLine;
+ if(strpos($hdr, 'Set-Cookie') !== false) {
+ $cLine = explode(':', $hdr)[1];
+ $cLine = explode(';', $cLine)[0];
+ $cookies .= ';' . $cLine;
}
}
@@ -239,7 +242,7 @@ EOD;
$context = stream_context_create(array(
'http' => array(
- 'user_agent' => "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:46.0) Gecko/20100101 Firefox/46.0",
+ 'user_agent' => 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:46.0) Gecko/20100101 Firefox/46.0',
'header' => 'Cookie: ' . $cookies
)
)
@@ -247,12 +250,12 @@ EOD;
$pageContent = file_get_contents($page, 0, $context);
- if(strpos($pageContent, "signup-button") != false) {
+ if(strpos($pageContent, 'signup-button') != false) {
return -1;
}
//Get the page ID if we don't have a captcha
- $regex = "/page_id=([0-9]*)&/";
+ $regex = '/page_id=([0-9]*)&/';
preg_match($regex, $pageContent, $matches);
if(count($matches) > 0) {
@@ -260,7 +263,7 @@ EOD;
}
//Get the page ID if we do have a captcha
- $regex = "/\"pageID\":\"([0-9]*)\"/";
+ $regex = '/"pageID":"([0-9]*)"/';
preg_match($regex, $pageContent, $matches);
return $matches[1];
@@ -275,7 +278,4 @@ EOD;
return 'http://facebook.com';
}
- public function getCacheDuration(){
- return 60 * 60 * 3; // 5 minutes
- }
}
diff --git a/bridges/FacebookBridge.php b/bridges/FacebookBridge.php
index a5b328dc..d7e8f913 100644
--- a/bridges/FacebookBridge.php
+++ b/bridges/FacebookBridge.php
@@ -1,171 +1,507 @@
array(
- 'name' => 'Username',
- 'required' => true
- ),
- 'media_type' => array(
- 'name' => 'Media type',
- 'type' => 'list',
- 'required' => false,
- 'values' => array(
- 'All' => 'all',
- 'Video' => 'video',
- 'No Video' => 'novideo'
+ const PARAMETERS = array(
+ 'User' => array(
+ 'u' => array(
+ 'name' => 'Username',
+ 'required' => true
),
- 'defaultValue' => 'all'
+ 'media_type' => array(
+ 'name' => 'Media type',
+ 'type' => 'list',
+ 'required' => false,
+ 'values' => array(
+ 'All' => 'all',
+ 'Video' => 'video',
+ 'No Video' => 'novideo'
+ ),
+ 'defaultValue' => 'all'
+ ),
+ 'skip_reviews' => array(
+ 'name' => 'Skip reviews',
+ 'type' => 'checkbox',
+ 'required' => false,
+ 'defaultValue' => false,
+ 'title' => 'Feed includes reviews when checked'
+ )
+ ),
+ 'Group' => array(
+ 'g' => array(
+ 'name' => 'Group',
+ 'type' => 'text',
+ 'required' => true,
+ 'exampleValue' => 'https://www.facebook.com/groups/743149642484225',
+ 'title' => 'Insert group name or facebook group URL'
+ )
+ ),
+ 'global' => array(
+ 'limit' => array(
+ 'name' => 'Limit',
+ 'type' => 'number',
+ 'required' => false,
+ 'title' => 'Specify the number of items to return (default: -1)',
+ 'defaultValue' => -1
+ )
)
- ));
+ );
private $authorName = '';
+ private $groupName = '';
- public function collectData(){
+ public function getName(){
- //Extract a string using start and end delimiters
- function extractFromDelimiters($string, $start, $end){
- if(strpos($string, $start) !== false) {
- $section_retrieved = substr($string, strpos($string, $start) + strlen($start));
- $section_retrieved = substr($section_retrieved, 0, strpos($section_retrieved, $end));
- return $section_retrieved;
- }
+ switch($this->queriedContext) {
+
+ case 'User':
+ if(!empty($this->authorName)) {
+ return isset($this->extraInfos['name']) ? $this->extraInfos['name'] : $this->authorName
+ . ' - ' . static::NAME;
+ }
+ break;
+
+ case 'Group':
+ if(!empty($this->groupName)) {
+ return $this->groupName . ' - ' . static::NAME;
+ }
+ break;
- return false;
}
- //Utility function for cleaning a Facebook link
- $unescape_fb_link = function($matches){
+ return parent::getName();
+ }
+
+ public function getURI() {
+ $uri = self::URI;
+
+ switch($this->queriedContext) {
+
+ case 'Group':
+ // Discover groups via https://www.facebook.com/groups/
+ // Example group: https://www.facebook.com/groups/sailors.worldwide
+ $uri .= 'groups/' . $this->sanitizeGroup(filter_var($this->getInput('g'), FILTER_SANITIZE_URL));
+ break;
+
+ case 'User':
+ // Example user 1: https://www.facebook.com/artetv/
+ // Example user 2: artetv
+ $user = $this->sanitizeUser($this->getInput('u'));
+
+ if(!strpos($user, '/')) {
+ $uri .= '/pg/' . urlencode($user) . '/posts';
+ } else {
+ $uri .= 'pages/' . $user;
+ }
+
+ break;
+
+ }
+
+ // Request the mobile version to reduce page size (no javascript)
+ // More information: https://stackoverflow.com/a/11103592
+ return $uri .= '?_fb_noscript=1';
+ }
+
+ public function collectData() {
+
+ switch($this->queriedContext) {
+
+ case 'Group':
+ $this->collectGroupData();
+ break;
+
+ case 'User':
+ $this->collectUserData();
+ break;
+
+ default:
+ returnClientError('Unknown context: "' . $this->queriedContext . '"!');
+
+ }
+
+ $limit = $this->getInput('limit') ?: -1;
+
+ if($limit > 0 && count($this->items) > $limit) {
+ $this->items = array_slice($this->items, 0, $limit);
+ }
+
+ }
+
+ #region Group
+
+ private function collectGroupData() {
+
+ $header = array('Accept-Language: ' . getEnv('HTTP_ACCEPT_LANGUAGE') . "\r\n");
+
+ $html = getSimpleHTMLDOM($this->getURI(), $header)
+ or returnServerError('Failed loading facebook page: ' . $this->getURI());
+
+ if(!$this->isPublicGroup($html)) {
+ returnClientError('This group is not public! RSS-Bridge only supports public groups!');
+ }
+
+ defaultLinkTo($html, substr(self::URI, 0, strlen(self::URI) - 1));
+
+ $this->groupName = $this->extractGroupName($html);
+
+ $posts = $html->find('div.userContentWrapper')
+ or returnServerError('Failed finding posts!');
+
+ foreach($posts as $post) {
+
+ $item = array();
+
+ $item['uri'] = $this->extractGroupURI($post);
+ $item['title'] = $this->extractGroupTitle($post);
+ $item['author'] = $this->extractGroupAuthor($post);
+ $item['content'] = $this->extractGroupContent($post);
+ $item['timestamp'] = $this->extractGroupTimestamp($post);
+ $item['enclosures'] = $this->extractGroupEnclosures($post);
+
+ $this->items[] = $item;
+
+ }
+
+ }
+
+ private function sanitizeGroup($group) {
+
+ if(filter_var(
+ $group,
+ FILTER_VALIDATE_URL,
+ FILTER_FLAG_HOST_REQUIRED | FILTER_FLAG_PATH_REQUIRED)) {
+ // User provided a URL
+
+ $urlparts = parse_url($group);
+
+ if($urlparts['host'] !== parse_url(self::URI)['host']
+ && 'www.' . $urlparts['host'] !== parse_url(self::URI)['host']) {
+
+ returnClientError('The host you provided is invalid! Received "'
+ . $urlparts['host']
+ . '", expected "'
+ . parse_url(self::URI)['host']
+ . '"!');
+
+ }
+
+ return explode('/', $urlparts['path'])[2];
+
+ } elseif(strpos($group, '/') !== false) {
+ returnClientError('The group you provided is invalid: ' . $group);
+ } else {
+ return $group;
+ }
+
+ }
+
+ private function isPublicGroup($html) {
+
+ // Facebook redirects to the groups about page for non-public groups
+ $about = $html->find('#pagelet_group_about', 0);
+
+ return !($about);
+
+ }
+
+ private function extractGroupName($html) {
+
+ $ogtitle = $html->find('meta[property="og:title"]', 0)
+ or returnServerError('Unable to find group title!');
+
+ return htmlspecialchars_decode($ogtitle->content, ENT_QUOTES);
+
+ }
+
+ private function extractGroupURI($post) {
+
+ $elements = $post->find('a')
+ or returnServerError('Unable to find URI!');
+
+ foreach($elements as $anchor) {
+
+ // Find the one that is a permalink
+ if(strpos($anchor->href, 'permalink') !== false) {
+ return $anchor->href;
+ }
+
+ }
+
+ return null;
+
+ }
+
+ private function extractGroupContent($post) {
+
+ $content = $post->find('div.userContent', 0)
+ or returnServerError('Unable to find user content!');
+
+ return $content->innertext . $content->next_sibling()->innertext;
+
+ }
+
+ private function extractGroupTimestamp($post) {
+
+ $element = $post->find('abbr[data-utime]', 0)
+ or returnServerError('Unable to find timestamp!');
+
+ return $element->getAttribute('data-utime');
+
+ }
+
+ private function extractGroupAuthor($post) {
+
+ $element = $post->find('img', 0)
+ or returnServerError('Unable to find author information!');
+
+ return $element->{'aria-label'};
+
+ }
+
+ private function extractGroupEnclosures($post) {
+
+ $elements = $post->find('div.userContent', 0)->next_sibling()->find('img');
+
+ $enclosures = array();
+
+ foreach($elements as $enclosure) {
+ $enclosures[] = $enclosure->src;
+ }
+
+ return empty($enclosures) ? null : $enclosures;
+
+ }
+
+ private function extractGroupTitle($post) {
+
+ $element = $post->find('h5', 0)
+ or returnServerError('Unable to find title!');
+
+ if(strpos($element->plaintext, 'shared') === false) {
+
+ $content = strip_tags($this->extractGroupContent($post));
+
+ return $this->extractGroupAuthor($post)
+ . ' posted: '
+ . substr(
+ $content,
+ 0,
+ strpos(wordwrap($content, 64), "\n")
+ )
+ . '...';
+
+ }
+
+ return $element->plaintext;
+
+ }
+
+ #endregion (Group)
+
+ #region User
+
+ /**
+ * Checks if $user is a valid username or URI and returns the username
+ */
+ private function sanitizeUser($user) {
+ if (filter_var($user, FILTER_VALIDATE_URL)) {
+
+ $urlparts = parse_url($user);
+
+ if($urlparts['host'] !== parse_url(self::URI)['host']) {
+ returnClientError('The host you provided is invalid! Received "'
+ . $urlparts['host']
+ . '", expected "'
+ . parse_url(self::URI)['host']
+ . '"!');
+ }
+
+ if(!array_key_exists('path', $urlparts)
+ || $urlparts['path'] === '/') {
+ returnClientError('The URL you provided doesn\'t contain the user name!');
+ }
+
+ return explode('/', $urlparts['path'])[1];
+
+ } else {
+
+ // First character cannot be a forward slash
+ if(strpos($user, '/') === 0) {
+ returnClientError('Remove leading slash "/" from the username!');
+ }
+
+ return $user;
+
+ }
+ }
+
+ /**
+ * Bypass external link redirection
+ */
+ private function unescape_fb_link($content){
+ return preg_replace_callback('/ href=\"([^"]+)\"/i', function($matches){
if(is_array($matches) && count($matches) > 1) {
+
$link = $matches[1];
- if(strpos($link, '/') === 0)
- $link = self::URI . $link;
+
if(strpos($link, 'facebook.com/l.php?u=') !== false)
$link = urldecode(extractFromDelimiters($link, 'facebook.com/l.php?u=', '&'));
+
return ' href="' . $link . '"';
+
}
- };
+ }, $content);
+ }
- //Utility function for converting facebook emoticons
- $unescape_fb_emote = function($matches){
- static $facebook_emoticons = array(
- 'smile' => ':)',
- 'frown' => ':(',
- 'tongue' => ':P',
- 'grin' => ':D',
- 'gasp' => ':O',
- 'wink' => ';)',
- 'pacman' => ':<',
- 'grumpy' => '>_<',
- 'unsure' => ':/',
- 'cry' => ':\'(',
- 'kiki' => '^_^',
- 'glasses' => '8-)',
- 'sunglasses' => 'B-)',
- 'heart' => '<3',
- 'devil' => ']:D',
- 'angel' => '0:)',
- 'squint' => '-_-',
- 'confused' => 'o_O',
- 'upset' => 'xD',
- 'colonthree' => ':3',
- 'like' => '👍');
- $len = count($matches);
- if ($len > 1)
- for ($i = 1; $i < $len; $i++)
- foreach ($facebook_emoticons as $name => $emote)
- if ($matches[$i] === $name)
- return $emote;
- return $matches[0];
- };
+ /**
+ * Convert textual representation of emoticons back to ASCII emoticons.
+ * i.e. "smile emoticon" => ":)"
+ */
+ private function unescape_fb_emote($content){
+ return preg_replace_callback('/([^ <>]+) ([^<>]+)<\/u><\/i>/i', function($matches){
+ static $facebook_emoticons = array(
+ 'smile' => ':)',
+ 'frown' => ':(',
+ 'tongue' => ':P',
+ 'grin' => ':D',
+ 'gasp' => ':O',
+ 'wink' => ';)',
+ 'pacman' => ':<',
+ 'grumpy' => '>_<',
+ 'unsure' => ':/',
+ 'cry' => ':\'(',
+ 'kiki' => '^_^',
+ 'glasses' => '8-)',
+ 'sunglasses' => 'B-)',
+ 'heart' => '<3',
+ 'devil' => ']:D',
+ 'angel' => '0:)',
+ 'squint' => '-_-',
+ 'confused' => 'o_O',
+ 'upset' => 'xD',
+ 'colonthree' => ':3',
+ 'like' => '👍');
- $html = null;
+ $len = count($matches);
- //Handle captcha response sent by the viewer
+ if ($len > 1)
+ for ($i = 1; $i < $len; $i++)
+ foreach ($facebook_emoticons as $name => $emote)
+ if ($matches[$i] === $name)
+ return $emote;
+
+ return $matches[0];
+ }, $content);
+ }
+
+ /**
+ * Returns the captcha message for the given captcha
+ */
+ private function returnCaptchaMessage($captcha) {
+ // Save form for submitting after getting captcha response
+ if (session_status() == PHP_SESSION_NONE) {
+ session_start();
+ }
+
+ $captcha_fields = array();
+
+ foreach ($captcha->find('input, button') as $input) {
+ $captcha_fields[$input->name] = $input->value;
+ }
+
+ $_SESSION['captcha_fields'] = $captcha_fields;
+ $_SESSION['captcha_action'] = $captcha->find('form', 0)->action;
+
+ // Show captcha filling form to the viewer, proxying the captcha image
+ $img = base64_encode(getContents($captcha->find('img', 0)->src));
+
+ http_response_code(500);
+ header('Content-Type: text/html');
+
+ $message = <<
Facebook captcha challenge
+
+Facebook wants rss-bridge to resolve the following captcha:
Facebook captcha challenge
-
- Facebook wants rss-bridge to resolve the following captcha:
');
- $contents = $this->stripWithDelimiters($contents, '
Supported Platforms: ';
+ if($game->worksOn->Windows) {
+ $content .= 'Windows ';
+ }
+ if($game->worksOn->Mac) {
+ $content .= 'Mac ';
+ }
+ if($game->worksOn->Linux) {
+ $content .= 'Linux ';
+ }
+
+ $content .= '
' . $gameDescriptionValue->description->full;
+
+ return $content;
+
+ }
+
+}
diff --git a/bridges/GQMagazineBridge.php b/bridges/GQMagazineBridge.php
new file mode 100644
index 00000000..fa36c4e7
--- /dev/null
+++ b/bridges/GQMagazineBridge.php
@@ -0,0 +1,119 @@
+ array(
+ 'name' => 'Domain to use',
+ 'required' => true,
+ 'values' => array(
+ 'www.gqmagazine.fr' => 'www.gqmagazine.fr'
+ ),
+ 'defaultValue' => 'www.gqmagazine.fr'
+ ),
+ 'page' => array(
+ 'name' => 'Initial page to load',
+ 'required' => true
+ ),
+ ));
+
+ const REPLACED_ATTRIBUTES = array(
+ 'href' => 'href',
+ 'src' => 'src',
+ 'data-original' => 'src'
+ );
+
+ private function getDomain() {
+ return $this->getInput('domain');
+ }
+
+ public function getURI()
+ {
+ return $this->getDomain() . '/' . $this->getInput('page');
+ }
+
+ public function collectData()
+ {
+ $html = getSimpleHTMLDOM($this->getURI()) or returnServerError('Could not request ' . $this->getURI());
+
+ // Since GQ don't want simple class scrapping, let's do it the hard way and ... discover content !
+ $main = $html->find('main', 0);
+ foreach ($main->find('a') as $link) {
+ $uri = $link->href;
+ $title = $link->find('h2', 0);
+ $date = $link->find('time', 0);
+
+ $item = array();
+ $author = $link->find('span[itemprop=name]', 0);
+ $item['author'] = $author->plaintext;
+ $item['title'] = $title->plaintext;
+ if(substr($uri, 0, 1) === 'h') { // absolute uri
+ $item['uri'] = $uri;
+ } else if(substr($uri, 0, 1) === '/') { // domain relative url
+ $item['uri'] = $this->getDomain() . $uri;
+ } else {
+ $item['uri'] = $this->getDomain() . '/' . $uri;
+ }
+
+ $article = $this->loadFullArticle($item['uri']);
+ if($article) {
+ $item['content'] = $this->replaceUriInHtmlElement($article);
+ } else {
+ $item['content'] = "Article body couldn't be loaded. It must be a bug!";
+ }
+ $short_date = $date->datetime;
+ $item['timestamp'] = strtotime($short_date);
+ $this->items[] = $item;
+ }
+ }
+
+ /**
+ * Loads the full article and returns the contents
+ * @param $uri The article URI
+ * @return The article content
+ */
+ private function loadFullArticle($uri){
+ $html = getSimpleHTMLDOMCached($uri);
+ // Once again, that generated css classes madness is an obstacle ... which i can go over easily
+ foreach($html->find('div') as $div) {
+ // List the CSS classes of that div
+ $classes = $div->class;
+ // I can't directly lookup that class since GQ since to generate random names like "ArticleBodySection-fkggUW"
+ if(strpos($classes, 'ArticleBodySection') !== false) {
+ return $div;
+ }
+ }
+ return null;
+ }
+
+ /**
+ * Replaces all relative URIs with absolute ones
+ * @param $element A simplehtmldom element
+ * @return The $element->innertext with all URIs replaced
+ */
+ private function replaceUriInHtmlElement($element){
+ $returned = $element->innertext;
+ foreach (self::REPLACED_ATTRIBUTES as $initial => $final) {
+ $returned = str_replace($initial . '="/', $final . '="' . self::URI . '/', $returned);
+ }
+ return $returned;
+ }
+}
diff --git a/bridges/GitHubGistBridge.php b/bridges/GitHubGistBridge.php
new file mode 100644
index 00000000..6abd2ecd
--- /dev/null
+++ b/bridges/GitHubGistBridge.php
@@ -0,0 +1,164 @@
+ array(
+ 'name' => 'Gist',
+ 'type' => 'text',
+ 'required' => true,
+ 'title' => 'Insert Gist ID or URI',
+ 'exampleValue' => '2646763, https://gist.github.com/2646763'
+ )
+ ));
+
+ private $filename;
+
+ public function getURI() {
+
+ $id = $this->getInput('id') ?: '';
+
+ $urlpath = parse_url($id, PHP_URL_PATH);
+
+ if($urlpath) {
+
+ $components = explode('/', $urlpath);
+ $id = end($components);
+
+ }
+
+ return static::URI . '/' . $id;
+
+ }
+
+ public function getName() {
+ return $this->filename ? $this->filename . ' - ' . static::NAME : static::NAME;
+ }
+
+ public function collectData() {
+
+ $html = getSimpleHTMLDOM($this->getURI(),
+ null,
+ null,
+ true,
+ true,
+ DEFAULT_TARGET_CHARSET,
+ false, // Do NOT remove line breaks
+ DEFAULT_BR_TEXT,
+ DEFAULT_SPAN_TEXT)
+ or returnServerError('Could not request ' . $this->getURI());
+
+ $html = defaultLinkTo($html, static::URI);
+
+ $fileinfo = $html->find('[class="file-info"]', 0)
+ or returnServerError('Could not find file info!');
+
+ $this->filename = $fileinfo->plaintext;
+
+ $comments = $html->find('div[class="timeline-comment-wrapper"]');
+
+ if(is_null($comments)) { // no comments yet
+ return;
+ }
+
+ foreach($comments as $comment) {
+
+ $uri = $comment->find('a[href^=#gistcomment]', 0)
+ or returnServerError('Could not find comment anchor!');
+
+ $title = $comment->find('div[class="unminimized-comment"] h3[class="timeline-comment-header-text"]', 0)
+ or returnServerError('Could not find comment header text!');
+
+ $datetime = $comment->find('[datetime]', 0)
+ or returnServerError('Could not find comment datetime!');
+
+ $author = $comment->find('a.author', 0)
+ or returnServerError('Could not find author name!');
+
+ $message = $comment->find('[class="comment-body"]', 0)
+ or returnServerError('Could not find comment body!');
+
+ $item = array();
+
+ $item['uri'] = $this->getURI() . $uri->href;
+ $item['title'] = str_replace('commented', 'commented on', $title->plaintext);
+ $item['timestamp'] = strtotime($datetime->datetime);
+ $item['author'] = '' . $author->plaintext . '';
+ $item['content'] = $this->fixContent($message);
+ // $item['enclosures'] = array();
+ // $item['categories'] = array();
+
+ $this->items[] = $item;
+
+ }
+
+ }
+
+ /** Removes all unnecessary tags and adds formatting */
+ private function fixContent($content){
+
+ // Restore code (inside ) highlighting
+ foreach($content->find('pre') as $pre) {
+
+ $pre->style = <<
' - . $article_subtitle - . '
' - . $contents; - - $item = array(); - $item['author'] = $author; - $item['uri'] = $article_url; - $item['title'] = $article_title; - $item['timestamp'] = $article_timestamp; - $item['content'] = $contents; - $this->items[] = $item; - $limit++; - } + $contents = $article->find('article', 0)->innertext; + foreach(array( + 'Categories:
'; + + foreach($item['categories'] as $category) { + + $entryCategories .= 'RSS-Bridge
-·Reconnecting the Web·
-{$status}
- -Search
- -- / active bridges.
-
'; - else - echo '
'; - } - ?> -
{$name}
+{$description}
+ + +CARD; + + // If we don't have any parameter for the bridge, we print a generic form to load it. + if(count($parameters) === 0 + || count($parameters) === 1 && array_key_exists('global', $parameters)) { + + $card .= BridgeCard::getForm($bridgeName, $formats, $isActive, $isHttps); + + } else { + + foreach($parameters as $parameterName => $parameter) { + if(!is_numeric($parameterName) && $parameterName === 'global') + continue; + + if(array_key_exists('global', $parameters)) + $parameter = array_merge($parameter, $parameters['global']); + + if(!is_numeric($parameterName)) + $card .= '' . $parameterName . '
' . PHP_EOL; + + $card .= BridgeCard::getForm($bridgeName, $formats, $isActive, $isHttps, $parameterName, $parameter); + } + + } + + $card .= ''; + $card .= '' . $bridge->getMaintainer() . '
'; + $card .= ''; + + return $card; + } +} diff --git a/lib/BridgeInterface.php b/lib/BridgeInterface.php index b8f5cf47..f2ff11d5 100644 --- a/lib/BridgeInterface.php +++ b/lib/BridgeInterface.php @@ -6,13 +6,6 @@ interface BridgeInterface { */ public function collectData(); - /** - * Returns an array of cachable elements - * - * @return array Associative array of cachable elements - */ - public function getCachable(); - /** * Returns the description * @@ -20,13 +13,6 @@ interface BridgeInterface { */ public function getDescription(); - /** - * Return an array of extra information - * - * @return array Associative array of extra information - */ - public function getExtraInfos(); - /** * Returns an array of collected items * @@ -48,6 +34,13 @@ interface BridgeInterface { */ public function getName(); + /** + * Returns the bridge icon + * + * @return string Bridge icon + */ + public function getIcon(); + /** * Returns the bridge parameters * @@ -62,22 +55,6 @@ interface BridgeInterface { */ public function getURI(); - /** - * Sets the cache instance - * - * @param object CacheInterface The cache instance - */ - public function setCache(\CacheInterface $cache); - - /** - * Sets the timeout for clearing the cache files. The timeout must be - * specified between 1..86400 seconds (max. 24 hours). The default timeout - * (specified by the bridge maintainer) applies for invalid values. - * - * @param int $timeout The cache timeout in seconds - */ - public function setCacheTimeout($timeout); - /** * Returns the cache timeout * diff --git a/lib/BridgeList.php b/lib/BridgeList.php new file mode 100644 index 00000000..4d069a97 --- /dev/null +++ b/lib/BridgeList.php @@ -0,0 +1,139 @@ + + + + +RSS-Bridge
+Reconnecting the Web
+ {$warning} + +EOD; + } + + private static function getSearchbar() { + $query = filter_input(INPUT_GET, 'q'); + + return <<Search
+ + +EOD; + } + + private static function getFooter($totalBridges, $totalActiveBridges, $showInactive) { + $version = Configuration::getVersion(); + + $inactive = ''; + + if($totalActiveBridges !== $totalBridges) { + + if(!$showInactive) { + $inactive = ''; + } else { + $inactive = '
'; + } + + } + + return <<
+
{$version}
+ {$totalActiveBridges}/{$totalBridges} active bridges.+ {$inactive} + +EOD; + } + + static function create($whitelist, $showInactive = true) { + + $totalBridges = 0; + $totalActiveBridges = 0; + + return '' + . BridgeList::getHead() + . '' + . BridgeList::getHeader() + . BridgeList::getSearchbar() + . '
+{$body_html} +EOD; $section = buildSection($e, $bridge, $message, $link); - return buildPage($title, $header, $section); + return $section; } /** @@ -124,7 +131,7 @@ function buildSection($e, $bridge, $message, $link){
{$name}
-- {$description} -
- - -CARD; - - // If we don't have any parameter for the bridge, we print a generic form to load it. - if(count($bridge->getParameters()) == 0) { - - $card .= $getFormHeader($bridgeName); - $card .= $HTTPSWarning; - - if($isActive) { - if(defined('PROXY_URL') && PROXY_BYBRIDGE) { - $idArg = 'arg-' - . urlencode($bridgeName) - . '-' - . urlencode('proxyoff') - . '-' - . urlencode('_noproxy'); - - $card .= '' - . PHP_EOL; - - $card .= '' - . PHP_EOL; - } if(CUSTOM_CACHE_TIMEOUT) { - $idArg = 'arg-' - . urlencode($bridgeName) - . '-' - . urlencode('_cache_timeout'); - - $card .= '' - . PHP_EOL; - - $card .= '
' - . PHP_EOL; - } - $card .= $getHelperButtonsFormat($formats); - } else { - $card .= 'Inactive'; - } - - $card .= '' . PHP_EOL; - } - - $hasGlobalParameter = array_key_exists('global', $bridge->getParameters()); - - if($hasGlobalParameter) { - $globalParameters = $bridge->getParameters()['global']; - } - - foreach($bridge->getParameters() as $parameterName => $parameter) { - if(!is_numeric($parameterName) && $parameterName == 'global') - continue; - - if($hasGlobalParameter) - $parameter = array_merge($parameter, $globalParameters); - - if(!is_numeric($parameterName)) - $card .= '
' . $parameterName . '
' . PHP_EOL; - - $card .= $getFormHeader($bridgeName); - $card .= $HTTPSWarning; - - foreach($parameter as $id => $inputEntry) { - $additionalInfoString = ''; - - if(isset($inputEntry['required']) && $inputEntry['required'] === true) - $additionalInfoString .= ' required'; - - if(isset($inputEntry['pattern'])) - $additionalInfoString .= ' pattern="' . $inputEntry['pattern'] . '"'; - - if(isset($inputEntry['title'])) - $additionalInfoString .= ' title="' . $inputEntry['title'] . '"'; - - if(!isset($inputEntry['exampleValue'])) - $inputEntry['exampleValue'] = ''; - - if(!isset($inputEntry['defaultValue'])) - $inputEntry['defaultValue'] = ''; - - $idArg = 'arg-' - . urlencode($bridgeName) - . '-' - . urlencode($parameterName) - . '-' - . urlencode($id); - - $card .= '' - . PHP_EOL; - - if(!isset($inputEntry['type']) || $inputEntry['type'] == 'text') { - $card .= '' - . PHP_EOL; - } elseif($inputEntry['type'] == 'number') { - $card .= '
' - . PHP_EOL; - } else if($inputEntry['type'] == 'list') { - $card .= '
'; - } elseif($inputEntry['type'] == 'checkbox') { - if($inputEntry['defaultValue'] === 'checked') - $card .= '
' - . PHP_EOL; - else - $card .= '
' - . PHP_EOL; - } - } - - if($isActive) { - if(defined('PROXY_URL') && PROXY_BYBRIDGE) { - $idArg = 'arg-' - . urlencode($bridgeName) - . '-' - . urlencode('proxyoff') - . '-' - . urlencode('_noproxy'); - - $card .= '' - . PHP_EOL; - - $card .= '
' - . PHP_EOL; - } if(CUSTOM_CACHE_TIMEOUT) { - $idArg = 'arg-' - . urlencode($bridgeName) - . '-' - . urlencode('_cache_timeout'); - - $card .= '' - . PHP_EOL; - - $card .= '
' - . PHP_EOL; - } - $card .= $getHelperButtonsFormat($formats); - } else { - $card .= 'Inactive'; - } - $card .= '' . PHP_EOL; - } - - $card .= ''; - $card .= '
' . $bridge->getMaintainer() . '
'; - $card .= ''; - - return $card; -} - function sanitize($textToSanitize, $removedTags = array('script', 'iframe', 'input', 'form'), $keptAttributes = array('title', 'href', 'src'), @@ -340,21 +40,137 @@ function backgroundToImg($htmlContent) { } +/** + * Convert relative links in HTML into absolute links + * @param $content HTML content to fix. Supports HTML objects or string objects + * @param $server full URL to the page containing relative links + * @return content with fixed URLs, as HTML object or string depending on input type + */ function defaultLinkTo($content, $server){ + $string_convert = false; + if (is_string($content)) { + $string_convert = true; + $content = str_get_html($content); + } + foreach($content->find('img') as $image) { - if(strpos($image->src, 'http') === false - && strpos($image->src, '//') === false - && strpos($image->src, 'data:') === false) - $image->src = $server . $image->src; + $image->src = urljoin($server, $image->src); } foreach($content->find('a') as $anchor) { - if(strpos($anchor->href, 'http') === false - && strpos($anchor->href, '//') === false - && strpos($anchor->href, '#') !== 0 - && strpos($anchor->href, '?') !== 0) - $anchor->href = $server . $anchor->href; + $anchor->href = urljoin($server, $anchor->href); + } + + if ($string_convert) { + $content = $content->outertext; } return $content; } + +/** + * Extract the first part of a string matching the specified start and end delimiters + * @param $string input string, e.g. '', $string); + $string = str_replace(' ', '
', $string); + $string = preg_replace('/([^"])(https?:\/\/[^ "<]+)([^"])/', '$1$2$3', $string.' '); + $string = preg_replace('/([^"\/])(www\.[^ "<]+)([^"])/', '$1$2$3', $string.' '); + + //As the regex are not perfect, we need to fix and that are introduced in URLs + // Fixup regex : https://regex101.com/r/NTRPf6/1 + // Fixup regex : https://regex101.com/r/aNklRp/1 + + $count = 1; + while($count > 0) { + $string = preg_replace('/ (src|href)="([^"]+)([^"]+)"/U', ' $1="$2_$3"', $string, -1, $count); + } + + $count = 1; + while($count > 0) { + $string = preg_replace('/ (src|href)="([^"]+)<\/i>([^"]+)"/U', ' $1="$2_$3"', $string, -1, $count); + } + + return '