X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9815bb0a551468e4939cacfffbc2d5cb8dd12431..2e86127b07f6a63b7ce457331d600d9486b22b44:/youtube_dl/extractor/worldstarhiphop.py diff --git a/youtube_dl/extractor/worldstarhiphop.py b/youtube_dl/extractor/worldstarhiphop.py index 54a77b6..d5c26a0 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 @@ -5,40 +7,47 @@ from .common import InfoExtractor class WorldStarHipHopIE(InfoExtractor): _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P.*)' - IE_NAME = u'WorldStarHipHop' + _TEST = { + "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!" + } + } def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - webpage_src = self._download_webpage(url, video_id) + 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') - video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)', - webpage_src, u'video URL') + video_url = self._search_regex( + r'so\.addVariable\("file","(.*?)"\)', webpage, 'video URL') - if 'mp4' in video_url: - ext = 'mp4' - else: - ext = 'flv' + if 'youtube' in video_url: + return self.url_result(video_url, ie='Youtube') - 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, + }