[worldstarhiphop] Modernize

This commit is contained in:
Philipp Hagemeister 2014-03-23 13:49:15 +01:00
parent bfcb6e3917
commit c9aa111b4f

View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -7,14 +9,14 @@ class WorldStarHipHopIE(InfoExtractor):
_VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)' _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
_TEST = { _TEST = {
"url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO", "url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO",
"file": "wshh6a7q1ny0G34ZwuIO.mp4",
"md5": "9d04de741161603bf7071bbf4e883186", "md5": "9d04de741161603bf7071bbf4e883186",
"info_dict": { "info_dict": {
"id": "wshh6a7q1ny0G34ZwuIO",
"ext": "mp4",
"title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!" "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
m = re.match(self._VALID_URL, url) m = re.match(self._VALID_URL, url)
video_id = m.group('id') video_id = m.group('id')
@ -23,41 +25,32 @@ class WorldStarHipHopIE(InfoExtractor):
m_vevo_id = re.search(r'videoId=(.*?)&amp?', m_vevo_id = re.search(r'videoId=(.*?)&amp?',
webpage_src) webpage_src)
if m_vevo_id is not None: 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') return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo')
video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)', video_url = self._search_regex(
webpage_src, u'video URL') r'so\.addVariable\("file","(.*?)"\)', webpage_src, 'video URL')
if 'youtube' in video_url: if 'youtube' in video_url:
self.to_screen(u'Youtube video detected:')
return self.url_result(video_url, ie='Youtube') return self.url_result(video_url, ie='Youtube')
if 'mp4' in video_url: video_title = self._html_search_regex(
ext = 'mp4' r"<title>(.*)</title>", webpage_src, 'title')
else:
ext = 'flv'
video_title = self._html_search_regex(r"<title>(.*)</title>",
webpage_src, u'title')
# Getting thumbnail and if not thumbnail sets correct title for WSHH candy video. # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
thumbnail = self._html_search_regex(r'rel="image_src" href="(.*)" />', thumbnail = self._html_search_regex(
webpage_src, u'thumbnail', fatal=False) r'rel="image_src" href="(.*)" />', webpage_src, 'thumbnail',
fatal=False)
if not thumbnail: if not thumbnail:
_title = r"""candytitles.*>(.*)</span>""" _title = r"""candytitles.*>(.*)</span>"""
mobj = re.search(_title, webpage_src) mobj = re.search(_title, webpage_src)
if mobj is not None: if mobj is not None:
video_title = mobj.group(1) video_title = mobj.group(1)
results = [{ return {
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'title': video_title, 'title': video_title,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'ext' : ext, }
}]
return results