X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fmofosex.py;h=e47c8011924cb0f5ecddefd33b35debd0324d5a9;hb=611c1dd96efc36a788475e14cc4de64d554d28a0;hp=a0c926cd12b924519abfa5070176c30b11702219;hpb=77ae65877e7b4b71d446ea928fd14f973826f07b;p=youtube-dl diff --git a/youtube_dl/extractor/mofosex.py b/youtube_dl/extractor/mofosex.py index a0c926cd1..e47c80119 100644 --- a/youtube_dl/extractor/mofosex.py +++ b/youtube_dl/extractor/mofosex.py @@ -1,40 +1,44 @@ +from __future__ import unicode_literals + import os import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( + compat_urllib_parse_unquote, compat_urllib_parse_urlparse, - compat_urllib_request, - compat_urllib_parse, ) +from ..utils import sanitized_Request + class MofosexIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Pmofosex\.com/videos/(?P[0-9]+)/.*?\.html)' + _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, + '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('videoid') + video_id = mobj.group('id') url = 'http://www.' + mobj.group('url') - req = compat_urllib_request.Request(url) + req = sanitized_Request(url) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - 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:] + video_title = self._html_search_regex(r'

(.+?)<', 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 ) + format = '-'.join(format) age_limit = self._rta_search(webpage)