diff options
| -rw-r--r-- | youtube_dl/extractor/worldstarhiphop.py | 23 |
1 files changed, 17 insertions, 6 deletions
diff --git a/youtube_dl/extractor/worldstarhiphop.py b/youtube_dl/extractor/worldstarhiphop.py index d5c26a032..a3ea26feb 100644 --- a/youtube_dl/extractor/worldstarhiphop.py +++ b/youtube_dl/extractor/worldstarhiphop.py @@ -6,8 +6,8 @@ from .common import InfoExtractor class WorldStarHipHopIE(InfoExtractor): - _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)' - _TEST = { + _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/(?:videos|android)/video\.php\?v=(?P<id>.*)' + _TESTS = [{ "url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO", "md5": "9d04de741161603bf7071bbf4e883186", "info_dict": { @@ -15,7 +15,15 @@ class WorldStarHipHopIE(InfoExtractor): "ext": "mp4", "title": "KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!" } - } + }, { + 'url': 'http://m.worldstarhiphop.com/android/video.php?v=wshh6a7q1ny0G34ZwuIO', + 'md5': 'dc1c76c83ecc4190bb1eb143899b87d3', + 'info_dict': { + 'id': 'wshh6a7q1ny0G34ZwuIO', + 'ext': 'mp4', + "title": "KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!" + } + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -26,19 +34,22 @@ class WorldStarHipHopIE(InfoExtractor): return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo') video_url = self._search_regex( - r'so\.addVariable\("file","(.*?)"\)', webpage, 'video URL') + [r'so\.addVariable\("file","(.*?)"\)', + r'<div class="artlist">\s*<a[^>]+href="([^"]+)">'], + webpage, 'video URL') if 'youtube' in video_url: return self.url_result(video_url, ie='Youtube') video_title = self._html_search_regex( - r'(?s)<div class="content-heading">\s*<h1>(.*?)</h1>', + [r'(?s)<div class="content-heading">\s*<h1>(.*?)</h1>', + r'<span[^>]+class="tc-sp-pinned-title">(.*)</span>'], webpage, 'title') # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video. thumbnail = self._html_search_regex( r'rel="image_src" href="(.*)" />', webpage, 'thumbnail', - fatal=False) + default=None) if not thumbnail: _title = r'candytitles.*>(.*)</span>' mobj = re.search(_title, webpage) |