Merge branch 'master' of github.com:rg3/youtube-dl

This commit is contained in:
Philipp Hagemeister 2014-12-11 15:27:54 +01:00
commit 45c24df512

View file

@ -10,15 +10,15 @@ from ..utils import url_basename
class BehindKinkIE(InfoExtractor): class BehindKinkIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)' _VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
_TEST = { _TEST = {
'url': 'http://www.behindkink.com/2014/08/14/ab1576-performers-voice-finally-heard-the-bill-is-killed/', 'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/',
'md5': '41ad01222b8442089a55528fec43ec01', 'md5': '507b57d8fdcd75a41a9a7bdb7989c762',
'info_dict': { 'info_dict': {
'id': '36370', 'id': '37127',
'ext': 'mp4', 'ext': 'mp4',
'title': 'AB1576 - PERFORMERS VOICE FINALLY HEARD - THE BILL IS KILLED!', 'title': 'What are you passionate about Marley Blaze',
'description': 'The adult industry voice was finally heard as Assembly Bill 1576 remained\xa0 in suspense today at the Senate Appropriations Hearing. AB1576 was, among other industry damaging issues, a condom mandate...', 'description': 'md5:aee8e9611b4ff70186f752975d9b94b4',
'upload_date': '20140814', 'upload_date': '20141205',
'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/08/36370_AB1576_Win.jpg', 'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/12/blaze-1.jpg',
'age_limit': 18, 'age_limit': 18,
} }
} }
@ -26,26 +26,19 @@ class BehindKinkIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id') display_id = mobj.group('id')
year = mobj.group('year')
month = mobj.group('month')
day = mobj.group('day')
upload_date = year + month + day
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
video_url = self._search_regex( video_url = self._search_regex(
r"'file':\s*'([^']+)'", r'<source src="([^"]+)"', webpage, 'video URL')
webpage, 'URL base') video_id = url_basename(video_url).split('_')[0]
upload_date = mobj.group('year') + mobj.group('month') + mobj.group('day')
video_id = url_basename(video_url)
video_id = video_id.split('_')[0]
return { return {
'id': video_id, 'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': self._og_search_title(webpage),
'display_id': display_id, 'display_id': display_id,
'url': video_url,
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage), 'description': self._og_search_description(webpage),
'upload_date': upload_date, 'upload_date': upload_date,