From 1e40d6f492486658748dc12b7824d750525b780c Mon Sep 17 00:00:00 2001 From: Mitsukarenai Date: Wed, 14 May 2014 14:34:06 +0200 Subject: [PATCH] [pull] Fix Youtube, Twitter --- bridges/TwitterBridge.php | 10 +++++----- bridges/YoutubeBridge.php | 18 +++++++++++------- 2 files changed, 16 insertions(+), 12 deletions(-) diff --git a/bridges/TwitterBridge.php b/bridges/TwitterBridge.php index fcc3967..cf85cb6 100644 --- a/bridges/TwitterBridge.php +++ b/bridges/TwitterBridge.php @@ -26,15 +26,15 @@ class TwitterBridge extends BridgeAbstract{ $this->returnError('You must specify a keyword (?q=...) or a Twitter username (?u=...).', 400); } - foreach($html->find('div.tweet') as $tweet) { + foreach($html->find('div.js-stream-tweet') as $tweet) { $item = new \Item(); - $item->username = trim(substr($tweet->find('span.username', 0)->plaintext, 1)); // extract username and sanitize + $item->username = $tweet->getAttribute('data-screen-name'); // extract username and sanitize $item->fullname = $tweet->getAttribute('data-name'); // extract fullname (pseudonym) $item->avatar = $tweet->find('img', 0)->src; // get avatar link $item->id = $tweet->getAttribute('data-tweet-id'); // get TweetID - $item->uri = 'https://twitter.com'.$tweet->find('a.details', 0)->getAttribute('href'); // get tweet link - $item->timestamp = $tweet->find('span._timestamp', 0)->getAttribute('data-time'); // extract tweet timestamp - $item->content = str_replace('href="/', 'href="https://twitter.com/', strip_tags($tweet->find('p.tweet-text', 0)->innertext, '')); // extract tweet text + $item->uri = 'https://twitter.com'.$tweet->find('a.js-permalink', 0)->getAttribute('href'); // get tweet link + $item->timestamp = $tweet->find('span.js-short-timestamp', 0)->getAttribute('data-time'); // extract tweet timestamp + $item->content = str_replace('href="/', 'href="https://twitter.com/', strip_tags($tweet->find('p.js-tweet-text', 0)->innertext, '')); // extract tweet text $item->title = $item->fullname . ' (@'. $item->username . ') | ' . $item->content; $this->items[] = $item; } diff --git a/bridges/YoutubeBridge.php b/bridges/YoutubeBridge.php index c7d7111..974d169 100644 --- a/bridges/YoutubeBridge.php +++ b/bridges/YoutubeBridge.php @@ -8,6 +8,10 @@ * @use1(u="username") * @use2(p="playlist id") * @use3(s="search keyword",pa="page") +* +* WARNING: to parse big playlists (over ~90 videos), you need to edit simple_html_dom.php: +* change: define('MAX_FILE_SIZE', 600000); +* into: define('MAX_FILE_SIZE', 900000); (or more) */ class YoutubeBridge extends BridgeAbstract{ @@ -32,21 +36,21 @@ class YoutubeBridge extends BridgeAbstract{ $this->request = $param['p']; $html = file_get_html('https://www.youtube.com/playlist?list='.urlencode($this->request).'') or $this->returnError('Could not request Youtube.', 404); - foreach($html->find('li.playlist-video-item') as $element) { + foreach($html->find('tr.pl-video') as $element) { $item = new \Item(); - $item->uri = 'https://www.youtube.com'.$element->find('a',0)->href; - $item->thumbnailUri = 'https:'.$element->find('img',0)->src; - $item->title = trim($element->find('h3',0)->plaintext); + $item->uri = 'https://www.youtube.com'.$element->find('.pl-video-title a',0)->href; + $item->thumbnailUri = 'https:'.str_replace('/default.','/mqdefault.',$element->find('.pl-video-thumbnail img',0)->src); + $item->title = trim($element->find('.pl-video-title a',0)->plaintext); $item->content = '
' . $item->title . ''; $this->items[] = $item; } - $this->request = 'Playlist '.str_replace(' - YouTube', '', $html->find('title', 0)->plaintext).', by '.$html->find('h1', 0)->plaintext; + $this->request = 'Playlist '.trim(str_replace(' - YouTube', '', $html->find('title', 0)->plaintext)).', by '.$html->find('h1', 0)->plaintext; } else if (isset($param['s'])) { /* search mode */ $this->request = $param['s']; $page = 1; if (isset($param['pa'])) $page = (int)preg_replace("/[^0-9]/",'', $param['pa']); - $html = file_get_html('https://www.youtube.com/results?search_query='.urlencode($this->request).'&page='.$page.'&filters=video&search_sort=video_date_uploaded') or $this->returnError('Could not request Youtube.', 404); + $html = file_get_html('https://www.youtube.com/results?search_query='.urlencode($this->request).'&&page='.$page.'&filters=video&search_sort=video_date_uploaded') or $this->returnError('Could not request Youtube.', 404); - foreach($html->find('li.context-data-item') as $element) { + foreach($html->find('li.yt-lockup') as $element) { $item = new \Item(); $item->uri = 'https://www.youtube.com'.$element->find('a',0)->href; $checkthumb = $element->find('img', 0)->getAttribute('data-thumb');