X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/90cd207d52d77e075e62cc256cc39dceee05bbf3..684fbbb940adb6ea4043bc437e527888687a53da:/youtube_dl/extractor/mofosex.py diff --git a/youtube_dl/extractor/mofosex.py b/youtube_dl/extractor/mofosex.py index b9430b0..1c65281 100644 --- a/youtube_dl/extractor/mofosex.py +++ b/youtube_dl/extractor/mofosex.py @@ -1,49 +1,56 @@ -import os -import re +from __future__ import unicode_literals -from .common import InfoExtractor from ..utils import ( - compat_urllib_parse_urlparse, - compat_urllib_request, - compat_urllib_parse, + int_or_none, + str_to_int, + unified_strdate, ) +from .keezmovies import KeezMoviesIE -class MofosexIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Pmofosex\.com/videos/(?P[0-9]+)/.*?\.html)' - _TEST = { - u'url': u'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html', - u'file': u'5018.mp4', - u'md5': u'1b2eb47ac33cc75d4a80e3026b613c5a', - u'info_dict': { - u"title": u"Japanese Teen Music Video", - u"age_limit": 18, + +class MofosexIE(KeezMoviesIE): + _VALID_URL = r'https?://(?:www\.)?mofosex\.com/videos/(?P\d+)/(?P[^/?#&.]+)\.html' + _TESTS = [{ + 'url': 'http://www.mofosex.com/videos/318131/amateur-teen-playing-and-masturbating-318131.html', + 'md5': '558fcdafbb63a87c019218d6e49daf8a', + 'info_dict': { + 'id': '318131', + 'display_id': 'amateur-teen-playing-and-masturbating-318131', + 'ext': 'mp4', + 'title': 'amateur teen playing and masturbating', + 'thumbnail': r're:^https?://.*\.jpg$', + 'upload_date': '20121114', + 'view_count': int, + 'like_count': int, + 'dislike_count': int, + '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): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - 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) + webpage, info = self._extract_info(url) - video_title = self._html_search_regex(r'

(.+?)<', webpage, u'title') - video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, u'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) + view_count = str_to_int(self._search_regex( + r'VIEWS:\s*([\d,.]+)', webpage, 'view count', fatal=False)) + 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:([^<]+)', webpage, 'upload date', fatal=False)) - age_limit = self._rta_search(webpage) + info.update({ + 'view_count': view_count, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'upload_date': upload_date, + 'thumbnail': self._og_search_thumbnail(webpage), + }) - return { - 'id': video_id, - 'title': video_title, - 'url': video_url, - 'ext': extension, - 'format': format, - 'format_id': format, - 'age_limit': age_limit, - } + return info