w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[mofosex] Extract all formats and modernize (Closes #10335)

Browse source
This commit is contained in:
Sergey M․ 2016-08-17 05:45:49 +07:00
parent 8652770bd2
commit 6be17c0870
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 42 additions and 39 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

81
youtube_dl/extractor/mofosex.py
View file

@ -1,53 +1,56 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import os from ..utils import (
import re int_or_none,
str_to_int,
from .common import InfoExtractor unified_strdate,
from ..compat import (
compat_urllib_parse_unquote,
compat_urllib_parse_urlparse,
) )
from ..utils import sanitized_Request from .keezmovies import KeezMoviesIE
class MofosexIE(InfoExtractor): class MofosexIE(KeezMoviesIE):
_VALID_URL = r'https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<id>[0-9]+)/.*?\.html)' _VALID_URL = r'https?://(?:www\.)?mofosex\.com/videos/(?P<id>\d+)/(?P<display_id>[^/?#&.]+)\.html'
_TEST = { _TESTS = [{
'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html', 'url': 'http://www.mofosex.com/videos/318131/amateur-teen-playing-and-masturbating-318131.html',
'md5': '1b2eb47ac33cc75d4a80e3026b613c5a', 'md5': '39a15853632b7b2e5679f92f69b78e91',
'info_dict': { 'info_dict': {
'id': '5018', 'id': '318131',
'display_id': 'amateur-teen-playing-and-masturbating-318131',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Japanese Teen Music Video', 'title': 'amateur teen playing and masturbating',
'thumbnail': 're:^https?://.*\.jpg$',
'upload_date': '20121114',
'view_count': int,
'like_count': int,
'dislike_count': int,
'age_limit': 18, 'age_limit': 18,
} }
} }, {
# This video is no longer available
'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
'only_matching': True,
}]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) webpage, info = self._extract_info(url)
video_id = mobj.group('id')
url = 'http://www.' + mobj.group('url')
req = sanitized_Request(url) view_count = str_to_int(self._search_regex(
req.add_header('Cookie', 'age_verified=1') r'VIEWS:</span>\s*([\d,.]+)', webpage, 'view count', fatal=False))
webpage = self._download_webpage(req, video_id) like_count = int_or_none(self._search_regex(
r'id=["\']amountLikes["\'][^>]*>(\d+)', webpage,
'like count', fatal=False))
dislike_count = int_or_none(self._search_regex(
r'id=["\']amountDislikes["\'][^>]*>(\d+)', webpage,
'like count', fatal=False))
upload_date = unified_strdate(self._html_search_regex(
r'Added:</span>([^<]+)', webpage, 'upload date', fatal=False))
video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title') info.update({
video_url = compat_urllib_parse_unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url')) 'view_count': view_count,
path = compat_urllib_parse_urlparse(video_url).path 'like_count': like_count,
extension = os.path.splitext(path)[1][1:] 'dislike_count': dislike_count,
format = path.split('/')[5].split('_')[:2] 'upload_date': upload_date,
format = '-'.join(format) 'thumbnail': self._og_search_thumbnail(webpage),
})
age_limit = self._rta_search(webpage) return info
return {
'id': video_id,
'title': video_title,
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
'age_limit': age_limit,
}