mirror of
https://github.com/l1ving/youtube-dl
synced 2024-12-31 01:35:44 +08:00
1cc79574fc
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail. · Use _match_id consistently whenever possible · Fix some outdated tests · Use consistent valid URL (always match the whole protocol, no ^ at start required) · Use modern test definitions
54 lines
1.6 KiB
Python
54 lines
1.6 KiB
Python
from __future__ import unicode_literals
|
|
|
|
import os
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import (
|
|
compat_urllib_parse_urlparse,
|
|
compat_urllib_request,
|
|
compat_urllib_parse,
|
|
)
|
|
|
|
|
|
class MofosexIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<id>[0-9]+)/.*?\.html)'
|
|
_TEST = {
|
|
'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
|
|
'md5': '1b2eb47ac33cc75d4a80e3026b613c5a',
|
|
'info_dict': {
|
|
'id': '5018',
|
|
'ext': 'mp4',
|
|
'title': 'Japanese Teen Music Video',
|
|
'age_limit': 18,
|
|
}
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
mobj = re.match(self._VALID_URL, url)
|
|
video_id = mobj.group('id')
|
|
url = 'http://www.' + mobj.group('url')
|
|
|
|
req = compat_urllib_request.Request(url)
|
|
req.add_header('Cookie', 'age_verified=1')
|
|
webpage = self._download_webpage(req, video_id)
|
|
|
|
video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title')
|
|
video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url'))
|
|
path = compat_urllib_parse_urlparse(video_url).path
|
|
extension = os.path.splitext(path)[1][1:]
|
|
format = path.split('/')[5].split('_')[:2]
|
|
format = "-".join(format)
|
|
|
|
age_limit = self._rta_search(webpage)
|
|
|
|
return {
|
|
'id': video_id,
|
|
'title': video_title,
|
|
'url': video_url,
|
|
'ext': extension,
|
|
'format': format,
|
|
'format_id': format,
|
|
'age_limit': age_limit,
|
|
}
|