yt-dlc/youtube_dl/extractor/redtube.py

52 lines
1.4 KiB
Python
Raw Normal View History

2014-01-21 13:16:44 +00:00
from __future__ import unicode_literals
2013-06-23 20:27:16 +00:00
import re
from .common import InfoExtractor
class RedTubeIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
2013-06-27 18:46:46 +00:00
_TEST = {
2014-01-21 13:16:44 +00:00
'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
2014-01-21 13:16:44 +00:00
#'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
'info_dict': {
"title": "Sucked on a toilet",
"age_limit": 18,
2013-06-27 18:46:46 +00:00
}
}
2013-06-23 20:27:16 +00:00
2013-10-04 09:41:57 +00:00
def _real_extract(self, url):
2013-06-23 20:27:16 +00:00
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
2013-10-04 09:41:57 +00:00
video_extension = 'mp4'
2013-06-23 20:27:16 +00:00
webpage = self._download_webpage(url, video_id)
self.report_extraction(video_id)
2013-10-04 09:41:57 +00:00
video_url = self._html_search_regex(
r'<source src="(.+?)" type="video/mp4">', webpage, u'video URL')
2013-06-23 20:27:16 +00:00
2013-10-04 09:41:57 +00:00
video_title = self._html_search_regex(
2013-12-03 13:08:16 +00:00
r'<h1 class="videoTitle[^"]*">(.+?)</h1>',
2013-06-23 20:27:16 +00:00
webpage, u'title')
video_thumbnail = self._og_search_thumbnail(webpage)
2013-10-06 14:39:35 +00:00
# No self-labeling, but they describe themselves as
# "Home of Videos Porno"
age_limit = 18
2013-10-04 09:41:57 +00:00
return {
2014-01-21 13:16:44 +00:00
'id': video_id,
'url': video_url,
'ext': video_extension,
'title': video_title,
'thumbnail': video_thumbnail,
2013-10-06 14:39:35 +00:00
'age_limit': age_limit,
2013-10-04 09:41:57 +00:00
}