|
@ -1,7 +1,5 @@ |
|
|
from __future__ import unicode_literals |
|
|
from __future__ import unicode_literals |
|
|
|
|
|
|
|
|
import re |
|
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor |
|
|
from .common import InfoExtractor |
|
|
|
|
|
|
|
|
|
|
|
|
|
@ -9,32 +7,23 @@ class RedTubeIE(InfoExtractor): |
|
|
_VALID_URL = r'http://(?:www\.)?redtube\.com/(?P<id>[0-9]+)' |
|
|
_VALID_URL = r'http://(?:www\.)?redtube\.com/(?P<id>[0-9]+)' |
|
|
_TEST = { |
|
|
_TEST = { |
|
|
'url': 'http://www.redtube.com/66418', |
|
|
'url': 'http://www.redtube.com/66418', |
|
|
'file': '66418.mp4', |
|
|
|
|
|
# md5 varies from time to time, as in |
|
|
|
|
|
# https://travis-ci.org/rg3/youtube-dl/jobs/14052463#L295 |
|
|
|
|
|
#'md5': u'7b8c22b5e7098a3e1c09709df1126d2d', |
|
|
|
|
|
'info_dict': { |
|
|
'info_dict': { |
|
|
|
|
|
'id': '66418', |
|
|
|
|
|
'ext': 'mp4', |
|
|
"title": "Sucked on a toilet", |
|
|
"title": "Sucked on a toilet", |
|
|
"age_limit": 18, |
|
|
"age_limit": 18, |
|
|
} |
|
|
} |
|
|
} |
|
|
} |
|
|
|
|
|
|
|
|
def _real_extract(self, url): |
|
|
def _real_extract(self, url): |
|
|
mobj = re.match(self._VALID_URL, url) |
|
|
|
|
|
|
|
|
|
|
|
video_id = mobj.group('id') |
|
|
|
|
|
video_extension = 'mp4' |
|
|
|
|
|
|
|
|
video_id = self._match_id(url) |
|
|
webpage = self._download_webpage(url, video_id) |
|
|
webpage = self._download_webpage(url, video_id) |
|
|
|
|
|
|
|
|
self.report_extraction(video_id) |
|
|
|
|
|
|
|
|
|
|
|
video_url = self._html_search_regex( |
|
|
video_url = self._html_search_regex( |
|
|
r'<source src="(.+?)" type="video/mp4">', webpage, u'video URL') |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL') |
|
|
video_title = self._html_search_regex( |
|
|
video_title = self._html_search_regex( |
|
|
r'<h1 class="videoTitle[^"]*">(.+?)</h1>', |
|
|
r'<h1 class="videoTitle[^"]*">(.+?)</h1>', |
|
|
webpage, u'title') |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
webpage, 'title') |
|
|
video_thumbnail = self._og_search_thumbnail(webpage) |
|
|
video_thumbnail = self._og_search_thumbnail(webpage) |
|
|
|
|
|
|
|
|
# No self-labeling, but they describe themselves as |
|
|
# No self-labeling, but they describe themselves as |
|
@ -44,7 +33,7 @@ class RedTubeIE(InfoExtractor): |
|
|
return { |
|
|
return { |
|
|
'id': video_id, |
|
|
'id': video_id, |
|
|
'url': video_url, |
|
|
'url': video_url, |
|
|
'ext': video_extension, |
|
|
|
|
|
|
|
|
'ext': 'mp4', |
|
|
'title': video_title, |
|
|
'title': video_title, |
|
|
'thumbnail': video_thumbnail, |
|
|
'thumbnail': video_thumbnail, |
|
|
'age_limit': age_limit, |
|
|
'age_limit': age_limit, |
|
|