X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9fb40a4e5f59ba243dee2edad23a2c5555338113..0e3c5183a16fb2d7b1ffb838220cc72b7578234e:/youtube_dl/extractor/twentyfourvideo.py diff --git a/youtube_dl/extractor/twentyfourvideo.py b/youtube_dl/extractor/twentyfourvideo.py index f3541b6..74d1404 100644 --- a/youtube_dl/extractor/twentyfourvideo.py +++ b/youtube_dl/extractor/twentyfourvideo.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( parse_iso8601, @@ -12,7 +14,18 @@ from ..utils import ( class TwentyFourVideoIE(InfoExtractor): IE_NAME = '24video' - _VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx|sex|tube)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P\d+)' + _VALID_URL = r'''(?x) + https?:// + (?P + (?:(?:www|porno?)\.)?24video\. + (?:net|me|xxx|sexy?|tube|adult|site|vip) + )/ + (?: + video/(?:(?:view|xml)/)?| + player/new24_play\.swf\?id= + ) + (?P\d+) + ''' _TESTS = [{ 'url': 'http://www.24video.net/video/view/1044982', @@ -40,13 +53,27 @@ class TwentyFourVideoIE(InfoExtractor): }, { 'url': 'http://www.24video.tube/video/view/2363750', 'only_matching': True, + }, { + 'url': 'https://www.24video.site/video/view/2640421', + 'only_matching': True, + }, { + 'url': 'https://porno.24video.net/video/2640421-vsya-takaya-gibkaya-i-v-masle', + 'only_matching': True, + }, { + 'url': 'https://www.24video.vip/video/view/1044982', + 'only_matching': True, + }, { + 'url': 'https://porn.24video.net/video/2640421-vsya-takay', + '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.sex/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( @@ -56,8 +83,8 @@ class TwentyFourVideoIE(InfoExtractor): duration = int_or_none(self._og_search_property( 'duration', webpage, 'duration', fatal=False)) timestamp = parse_iso8601(self._search_regex( - r'