X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/46113edab215c2211a604c06245c16d5d4e57dcf..39393b81acfaf4045fb7f20454a0226f0dc9142e:/youtube_dl/extractor/extremetube.py?ds=inline diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py index aacbf14..acd4090 100644 --- a/youtube_dl/extractor/extremetube.py +++ b/youtube_dl/extractor/extremetube.py @@ -1,65 +1,50 @@ from __future__ import unicode_literals -import re +from ..utils import str_to_int +from .keezmovies import KeezMoviesIE -from .common import InfoExtractor -from ..utils import ( - compat_urllib_parse_urlparse, - compat_urllib_request, - compat_urllib_parse, - str_to_int, -) - -class ExtremeTubeIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Pextremetube\.com/.*?video/.+?(?P[0-9]+))(?:[/?&]|$)' +class ExtremeTubeIE(KeezMoviesIE): + _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P[^/#?&]+)' _TESTS = [{ 'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', - 'md5': '1fb9228f5e3332ec8c057d6ac36f33e0', + 'md5': '92feaafa4b58e82f261e5419f39c60cb', 'info_dict': { - 'id': '652431', + 'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431', 'ext': 'mp4', 'title': 'Music Video 14 british euro brit european cumshots swallow', - 'uploader': 'unknown', + 'uploader': 'anonim', 'view_count': int, 'age_limit': 18, } }, { 'url': 'http://www.extremetube.com/gay/video/abcde-1234', 'only_matching': True, + }, { + 'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick', + 'only_matching': True, + }, { + 'url': 'http://www.extremetube.com/video/652431', + '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') + webpage, info = self._extract_info(url) - req = compat_urllib_request.Request(url) - req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, video_id) + if not info['title']: + info['title'] = self._search_regex( + r']+title="([^"]+)"[^>]*>', webpage, 'title') - video_title = self._html_search_regex( - r'

]*?title="([^"]+)"[^>]*>', webpage, 'title') uploader = self._html_search_regex( - r'Uploaded by:\s*\s*(.+?)\s*', + r'Uploaded by:\s*]+>\s*]+>(.+?)', webpage, 'uploader', fatal=False) - view_count = str_to_int(self._html_search_regex( - r'Views:\s*\s*([\d,\.]+)', + view_count = str_to_int(self._search_regex( + r'Views:\s*]+>\s*<[^>]+>([\d,\.]+)