X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/33cd347759d6d999325ebf3c69b7ed5692c343b2..abc36f0474141930338eef35e2444365fab932b6:/youtube_dl/extractor/worldstarhiphop.py?ds=sidebyside diff --git a/youtube_dl/extractor/worldstarhiphop.py b/youtube_dl/extractor/worldstarhiphop.py index 3237596..09415b5 100644 --- a/youtube_dl/extractor/worldstarhiphop.py +++ b/youtube_dl/extractor/worldstarhiphop.py @@ -1,63 +1,64 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor class WorldStarHipHopIE(InfoExtractor): - _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P.*)' - _TEST = { - "url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO", - "file": "wshh6a7q1ny0G34ZwuIO.mp4", - "md5": "9d04de741161603bf7071bbf4e883186", - "info_dict": { - "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!" + _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/(?:videos|android)/video\.php\?v=(?P.*)' + _TESTS = [{ + 'url': 'http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO', + 'md5': '9d04de741161603bf7071bbf4e883186', + 'info_dict': { + 'id': 'wshh6a7q1ny0G34ZwuIO', + '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): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') - - webpage_src = self._download_webpage(url, video_id) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - m_vevo_id = re.search(r'videoId=(.*?)&?', - webpage_src) - + m_vevo_id = re.search(r'videoId=(.*?)&?', webpage) if m_vevo_id is not None: - self.to_screen(u'Vevo video detected:') return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo') - video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)', - webpage_src, u'video URL') + video_url = self._search_regex( + [r'so\.addVariable\("file","(.*?)"\)', + r'
\s*]+href="([^"]+)">'], + webpage, 'video URL') if 'youtube' in video_url: - self.to_screen(u'Youtube video detected:') return self.url_result(video_url, ie='Youtube') - if 'mp4' in video_url: - ext = 'mp4' - else: - ext = 'flv' - - video_title = self._html_search_regex(r"(.*)", - webpage_src, u'title') + video_title = self._html_search_regex( + [r'(?s)
\s*

(.*?)

', + r']+class="tc-sp-pinned-title">(.*)'], + 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_src, u'thumbnail', fatal=False) - + thumbnail = self._html_search_regex( + r'rel="image_src" href="(.*)" />', webpage, 'thumbnail', + default=None) if not thumbnail: - _title = r"""candytitles.*>(.*)""" - mobj = re.search(_title, webpage_src) + _title = r'candytitles.*>(.*)' + mobj = re.search(_title, webpage) if mobj is not None: video_title = mobj.group(1) - results = [{ - 'id': video_id, - 'url' : video_url, - 'title' : video_title, - 'thumbnail' : thumbnail, - 'ext' : ext, - }] - return results + return { + 'id': video_id, + 'url': video_url, + 'title': video_title, + 'thumbnail': thumbnail, + }