X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fextremetube.py;h=14a196ffc63336ae7d016b035cfb28cc7f7d28a0;hb=199ece7eb83ffe7ba069b50080fe971df1db2d6c;hp=0f1eec40f86de4a7ac52507f77398b7d20039de2;hpb=fa5d47af4b82356c39c1e8d7b2ada9b539371735;p=youtube-dl diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py index 0f1eec40f..14a196ffc 100644 --- a/youtube_dl/extractor/extremetube.py +++ b/youtube_dl/extractor/extremetube.py @@ -1,4 +1,5 @@ -import os +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -8,18 +9,23 @@ from ..utils import ( compat_urllib_parse, ) + class ExtremeTubeIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Pextremetube\.com/video/.+?(?P[0-9]+))(?:[/?&]|$)' - _TEST = { - u'url': u'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', - u'file': u'652431.mp4', - u'md5': u'1fb9228f5e3332ec8c057d6ac36f33e0', - u'info_dict': { - u"title": u"Music Video 14 british euro brit european cumshots swallow", - u"uploader": u"unknown", - u"age_limit": 18, + _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Pextremetube\.com/.*?video/.+?(?P[0-9]+))(?:[/?&]|$)' + _TESTS = [{ + 'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', + 'md5': '1fb9228f5e3332ec8c057d6ac36f33e0', + 'info_dict': { + 'id': '652431', + 'ext': 'mp4', + 'title': 'Music Video 14 british euro brit european cumshots swallow', + 'uploader': 'unknown', + 'age_limit': 18, } - } + }, { + 'url': 'http://www.extremetube.com/gay/video/abcde-1234', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -30,20 +36,22 @@ class ExtremeTubeIE(InfoExtractor): req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - video_title = self._html_search_regex(r'

]*?title="([^"]+)"[^>]*>\1<', webpage, u'title') - uploader = self._html_search_regex(r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, u'uploader', fatal=False) - video_url = compat_urllib_parse.unquote(self._html_search_regex(r'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'

]*?title="([^"]+)"[^>]*>', webpage, 'title') + uploader = self._html_search_regex( + r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader', + 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 ) + format = "-".join(format) return { 'id': video_id, 'title': video_title, 'uploader': uploader, 'url': video_url, - 'ext': extension, 'format': format, 'format_id': format, 'age_limit': 18,