X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/453698570f26bebd37b39df8537d993b57d77b8b..abc36f0474141930338eef35e2444365fab932b6:/youtube_dl/extractor/twentyfourvideo.py diff --git a/youtube_dl/extractor/twentyfourvideo.py b/youtube_dl/extractor/twentyfourvideo.py index 67e8bfe..7af1165 100644 --- a/youtube_dl/extractor/twentyfourvideo.py +++ b/youtube_dl/extractor/twentyfourvideo.py @@ -1,51 +1,61 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( parse_iso8601, int_or_none, + xpath_attr, + xpath_element, ) class TwentyFourVideoIE(InfoExtractor): IE_NAME = '24video' - _VALID_URL = r'https?://(?:www\.)?24video\.net/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P\d+)' - - _TESTS = [ - { - 'url': 'http://www.24video.net/video/view/1044982', - 'md5': '48dd7646775690a80447a8dca6a2df76', - 'info_dict': { - 'id': '1044982', - 'ext': 'mp4', - 'title': 'Эротика каменного века', - 'description': 'Как смотрели порно в каменном веке.', - 'thumbnail': 're:^https?://.*\.jpg$', - 'uploader': 'SUPERTELO', - 'duration': 31, - 'timestamp': 1275937857, - 'upload_date': '20100607', - 'age_limit': 18, - 'like_count': int, - 'dislike_count': int, - }, + _VALID_URL = r'https?://(?P(?:www\.)?24video\.(?:net|me|xxx|sex|tube))/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P\d+)' + + _TESTS = [{ + 'url': 'http://www.24video.net/video/view/1044982', + 'md5': 'e09fc0901d9eaeedac872f154931deeb', + 'info_dict': { + 'id': '1044982', + 'ext': 'mp4', + 'title': 'Эротика каменного века', + 'description': 'Как смотрели порно в каменном веке.', + 'thumbnail': r're:^https?://.*\.jpg$', + 'uploader': 'SUPERTELO', + 'duration': 31, + 'timestamp': 1275937857, + 'upload_date': '20100607', + 'age_limit': 18, + 'like_count': int, + 'dislike_count': int, }, - { - 'url': 'http://www.24video.net/player/new24_play.swf?id=1044982', - 'only_matching': True, - } - ] + }, { + 'url': 'http://www.24video.net/player/new24_play.swf?id=1044982', + 'only_matching': True, + }, { + 'url': 'http://www.24video.me/video/view/1044982', + 'only_matching': True, + }, { + 'url': 'http://www.24video.tube/video/view/2363750', + 'only_matching': True, + }] def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + host = mobj.group('host') webpage = self._download_webpage( - 'http://www.24video.net/video/view/%s' % video_id, video_id) + 'http://%s/video/view/%s' % (host, video_id), video_id) title = self._og_search_title(webpage) description = self._html_search_regex( - r'([^<]+)', webpage, 'description', fatal=False) + r'<(p|span)[^>]+itemprop="description"[^>]*>(?P[^<]+)', + webpage, 'description', fatal=False, group='description') thumbnail = self._og_search_thumbnail(webpage) duration = int_or_none(self._og_search_property( 'duration', webpage, 'duration', fatal=False)) @@ -54,43 +64,34 @@ class TwentyFourVideoIE(InfoExtractor): webpage, 'upload date')) uploader = self._html_search_regex( - r'Загрузил\s*([^<]+)', + r'class="video-uploaded"[^>]*>\s*]*>([^<]+)', webpage, 'uploader', fatal=False) view_count = int_or_none(self._html_search_regex( r'(\d+) просмотр', webpage, 'view count', fatal=False)) comment_count = int_or_none(self._html_search_regex( - r'
(\d+) комментари', + r']+href="#tab-comments"[^>]*>(\d+) комментари', webpage, 'comment count', fatal=False)) - formats = [] - - pc_video = self._download_xml( - 'http://www.24video.net/video/xml/%s?mode=play' % video_id, - video_id, 'Downloading PC video URL').find('.//video') - - formats.append({ - 'url': pc_video.attrib['url'], - 'format_id': 'pc', - 'quality': 1, - }) + # Sets some cookies + self._download_xml( + r'http://%s/video/xml/%s?mode=init' % (host, video_id), + video_id, 'Downloading init XML') - like_count = int_or_none(pc_video.get('ratingPlus')) - dislike_count = int_or_none(pc_video.get('ratingMinus')) - age_limit = 18 if pc_video.get('adult') == 'true' else 0 + video_xml = self._download_xml( + 'http://%s/video/xml/%s?mode=play' % (host, video_id), + video_id, 'Downloading video XML') - mobile_video = self._download_xml( - 'http://www.24video.net/video/xml/%s' % video_id, - video_id, 'Downloading mobile video URL').find('.//video') + video = xpath_element(video_xml, './/video', 'video', fatal=True) - formats.append({ - 'url': mobile_video.attrib['url'], - 'format_id': 'mobile', - 'quality': 0, - }) + formats = [{ + 'url': xpath_attr(video, '', 'url', 'video URL', fatal=True), + }] - self._sort_formats(formats) + like_count = int_or_none(video.get('ratingPlus')) + dislike_count = int_or_none(video.get('ratingMinus')) + age_limit = 18 if video.get('adult') == 'true' else 0 return { 'id': video_id,