w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[syfy] Add suppor for generic URLs (Fixes #2827)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-04-30 01:35:52 +02:00
parent 57b8d84cd9
commit 22d99a801a
2 changed files with 25 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

28
youtube_dl/extractor/syfy.py
View file

@ -6,9 +6,9 @@ from .common import InfoExtractor
class SyfyIE(InfoExtractor):
_VALID_URL = r'https?://www\.syfy\.com/videos/.+?vid:(?P<id>\d+)'
_VALID_URL = r'https?://www\.syfy\.com/(?:videos/.+?vid:(?P<id>[0-9]+)|(?!videos)(?P<video_name>[^/]+)(?:$|[?#]))'
_TEST = {
_TESTS = [{
'url': 'http://www.syfy.com/videos/Robot%20Combat%20League/Behind%20the%20Scenes/vid:2631458',
'md5': 'e07de1d52c7278adbb9b9b1c93a66849',
'info_dict': {
@ -18,10 +18,30 @@ class SyfyIE(InfoExtractor):
'description': 'Listen to what insights George Lucas give his daughter Amanda.',
},
'add_ie': ['ThePlatform'],
}
}, {
'url': 'http://www.syfy.com/wilwheaton',
'md5': '94dfa54ee3ccb63295b276da08c415f6',
'info_dict': {
'id': '4yoffOOXC767',
'ext': 'flv',
'title': 'The Wil Wheaton Project - Premiering May 27th at 10/9c.',
'description': 'The Wil Wheaton Project premieres May 27th at 10/9c. Don\'t miss it.',
},
'add_ie': ['ThePlatform'],
'skip': 'Blocked outside the US',
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_name = mobj.group('video_name')
if video_name:
generic_webpage = self._download_webpage(url, video_name)
video_id = self._search_regex(
r'<iframe.*?class="video_iframe_page"\s+src="/_utils/video/thP_video_controller.php.*?_vid([0-9]+)">',
generic_webpage, 'video ID')
url = 'http://www.syfy.com/videos/%s/%s/vid:%s' % (
video_name, video_name, video_id)
else:
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
return self.url_result(self._og_search_video_url(webpage))

2
youtube_dl/extractor/theplatform.py
View file

@ -52,7 +52,7 @@ class ThePlatformIE(InfoExtractor):
head = meta.find(_x('smil:head'))
body = meta.find(_x('smil:body'))
f4m_node = body.find(_x('smil:seq/smil:video'))
f4m_node = body.find(_x('smil:seq//smil:video'))
if f4m_node is not None:
f4m_url = f4m_node.attrib['src']
if 'manifest.f4m?' not in f4m_url: