mirror of
https://github.com/yt-dlp/yt-dlp
synced 2024-12-29 14:26:24 +01:00
c11529618a
If the url doesn’t specify the protocol we can’t directly use it to download the webpage, we would need to build a new url. Instead, we let the generic extractor add the protocol.
47 lines
1.3 KiB
Python
47 lines
1.3 KiB
Python
import re
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
|
class RedTubeIE(InfoExtractor):
|
|
_VALID_URL = r'http://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
|
|
_TEST = {
|
|
u'url': u'http://www.redtube.com/66418',
|
|
u'file': u'66418.mp4',
|
|
# md5 varies from time to time, as in
|
|
# https://travis-ci.org/rg3/youtube-dl/jobs/14052463#L295
|
|
#u'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
|
|
u'info_dict': {
|
|
u"title": u"Sucked on a toilet",
|
|
u"age_limit": 18,
|
|
}
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
video_id = mobj.group('id')
|
|
video_extension = 'mp4'
|
|
webpage = self._download_webpage(url, video_id)
|
|
|
|
self.report_extraction(video_id)
|
|
|
|
video_url = self._html_search_regex(
|
|
r'<source src="(.+?)" type="video/mp4">', webpage, u'video URL')
|
|
|
|
video_title = self._html_search_regex(
|
|
r'<h1 class="videoTitle[^"]*">(.+?)</h1>',
|
|
webpage, u'title')
|
|
|
|
# No self-labeling, but they describe themselves as
|
|
# "Home of Videos Porno"
|
|
age_limit = 18
|
|
|
|
return {
|
|
'id': video_id,
|
|
'url': video_url,
|
|
'ext': video_extension,
|
|
'title': video_title,
|
|
'age_limit': age_limit,
|
|
}
|