yt-dlp/youtube_dl/extractor/redtube.py

46 lines
1.4 KiB
Python
Raw Normal View History

2014-01-21 08:16:44 -05:00
from __future__ import unicode_literals
2013-06-23 16:27:16 -04:00
from .common import InfoExtractor
from ..utils import ExtractorError
2013-06-23 16:27:16 -04:00
class RedTubeIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
2013-06-27 14:46:46 -04:00
_TEST = {
2014-01-21 08:16:44 -05:00
'url': 'http://www.redtube.com/66418',
2015-03-25 10:09:01 -04:00
'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
2014-01-21 08:16:44 -05:00
'info_dict': {
2014-11-26 06:52:45 -05:00
'id': '66418',
'ext': 'mp4',
2015-03-25 10:09:01 -04:00
'title': 'Sucked on a toilet',
'age_limit': 18,
2013-06-27 14:46:46 -04:00
}
}
2013-06-23 16:27:16 -04:00
2013-10-04 05:41:57 -04:00
def _real_extract(self, url):
2014-11-26 06:52:45 -05:00
video_id = self._match_id(url)
2013-06-23 16:27:16 -04:00
webpage = self._download_webpage(url, video_id)
if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
raise ExtractorError('Video %s has been removed' % video_id, expected=True)
2013-10-04 05:41:57 -04:00
video_url = self._html_search_regex(
2014-11-26 06:52:45 -05:00
r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
2013-10-04 05:41:57 -04:00
video_title = self._html_search_regex(
2013-12-03 08:08:16 -05:00
r'<h1 class="videoTitle[^"]*">(.+?)</h1>',
2014-11-26 06:52:45 -05:00
webpage, 'title')
video_thumbnail = self._og_search_thumbnail(webpage)
2013-10-06 10:39:35 -04:00
# No self-labeling, but they describe themselves as
# "Home of Videos Porno"
age_limit = 18
2013-10-04 05:41:57 -04:00
return {
2014-01-21 08:16:44 -05:00
'id': video_id,
'url': video_url,
2014-11-26 06:52:45 -05:00
'ext': 'mp4',
2014-01-21 08:16:44 -05:00
'title': video_title,
'thumbnail': video_thumbnail,
2013-10-06 10:39:35 -04:00
'age_limit': age_limit,
2013-10-04 05:41:57 -04:00
}