X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fworldstarhiphop.py;h=d5c26a032bcf28a9c8ae79e1d083d67ed29b2726;hb=e793f7671c3e303e4fbe2c4cd18e80ad4b5e5417;hp=8a52c7a99147c4c871ac1cdf97272941effbc104;hpb=99c7bc94af6e845ffe38244608a6c4e10236e28d;p=youtube-dl diff --git a/youtube_dl/extractor/worldstarhiphop.py b/youtube_dl/extractor/worldstarhiphop.py index 8a52c7a99..d5c26a032 100644 --- a/youtube_dl/extractor/worldstarhiphop.py +++ b/youtube_dl/extractor/worldstarhiphop.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -7,64 +9,45 @@ 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!" + "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_url = re.search(r'videoId=(.*?)&?', - webpage_src) - - if video_url: - self.to_screen(u'Vevo video detected:') - return self.url_result('vevo:%s' % video_url.group(1), ie='Vevo') + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)', - webpage_src, u'video URL') + m_vevo_id = re.search(r'videoId=(.*?)&?', webpage) + if m_vevo_id is not None: + return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo') - if video_url is None: - video_url = self._search_regex(r'videoId=(.*?)&?', - webpage_src, u'video URL') - self.to_screen(u'Vevo video detected:') - vevo_id = 'vevo:%s' % video_url - return self.url_result(vevo_id, ie='Vevo') + video_url = self._search_regex( + r'so\.addVariable\("file","(.*?)"\)', 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*

(.*?)

', + 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', + fatal=False) 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, + }