external/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-10 09:07:58 +01:00
Code Issues Projects Releases Packages Wiki Activity

add _search_regex to the new IEs

Browse source
This commit is contained in:
Filippo Valsorda 2013-06-17 19:47:44 +02:00
parent 8bc7c3d858
commit 0251f9c9c0
1 changed files with 8 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
youtube_dl/InfoExtractors.py
View file

@ -4465,11 +4465,12 @@ def _real_extract(self,url):
video_id = mobj.group(1)
redirect_page, urlh = self._download_webpage_handle(url, video_id)
redirect_url = urlh.geturl() + re.search(r'window\.location = \'(.*)\';', redirect_page).group(1)
new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location')
redirect_url = urlh.geturl() + new_location
webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page')
title = re.search(r'<title>(.*)</title>', webpage)
title = (title.group(1)).split('/')[0].strip()
title = self._html_search_regex(r'<title>(.*)</title>',
webpage, u'title').split('/')[0].strip()
ext = "flv"
info_url = "http://vbox7.com/play/magare.do"
@ -4503,10 +4504,7 @@ def _real_extract(self, url):
mgid_re = r'data-video="(?P<mgid>mgid:.*?)"'
else:
mgid_re = r'data-contentId=\'(?P<mgid>mgid:.*?)\''
m_mgid = re.search(mgid_re, webpage)
if m_mgid is None:
raise ExtractorError(u'Unable to extract mgid')
mgid = m_mgid.group(1)
mgid = self._search_regex(mgid_re, webpage, u'mgid')
data = compat_urllib_parse.urlencode({'uri': mgid, 'acceptMethods': 'fms'})
info_page = self._download_webpage('http://www.gametrailers.com/feeds/mrss?' + data,
@ -4528,11 +4526,11 @@ def _real_extract(self, url):
video_description = m_info.group('description')
video_thumb = m_info.group('thumb')
m_urls = re.finditer(r'<src>(?P<url>.*)</src>', links_webpage)
if m_urls is None:
m_urls = list(re.finditer(r'<src>(?P<url>.*)</src>', links_webpage))
if m_urls is None or len(m_urls) == 0:
raise ExtractError(u'Unable to extrat video url')
# They are sorted from worst to best quality
video_url = list(m_urls)[-1].group('url')
video_url = m_urls[-1].group('url')
return {'url': video_url,
'id': video_id,