X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/453698570f26bebd37b39df8537d993b57d77b8b..d9d7cd0e85dc712461d9185db9df9d6c900a573b:/youtube_dl/extractor/extremetube.py diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py index 36ba331..445f943 100644 --- a/youtube_dl/extractor/extremetube.py +++ b/youtube_dl/extractor/extremetube.py @@ -1,25 +1,16 @@ from __future__ import unicode_literals -import re +from ..utils import str_to_int +from .keezmovies import KeezMoviesIE -from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_urlparse, - compat_urllib_request, - compat_urllib_parse, -) -from ..utils import ( - 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', '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', @@ -29,39 +20,31 @@ class ExtremeTubeIE(InfoExtractor): }, { '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('id') - 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*', webpage, 'uploader', fatal=False) - view_count = str_to_int(self._html_search_regex( + view_count = str_to_int(self._search_regex( r'Views:\s*\s*([\d,\.]+)', webpage, 'view count', fatal=False)) - video_url = compat_urllib_parse.unquote(self._html_search_regex( - r'video_url=(.+?)&', webpage, 'video_url')) - path = compat_urllib_parse_urlparse(video_url).path - format = path.split('/')[5].split('_')[:2] - format = "-".join(format) - - return { - 'id': video_id, - 'title': video_title, + info.update({ 'uploader': uploader, 'view_count': view_count, - 'url': video_url, - 'format': format, - 'format_id': format, - 'age_limit': 18, - } + }) + + return info