X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fpornhub.py;h=91e574dc24268c36ecd4861e930769f95c6eeac8;hb=611c1dd96efc36a788475e14cc4de64d554d28a0;hp=a656ad85a1d5a6b7773e98c2a9be585803898db1;hpb=272e4db5c746ef4c94b7c9e7bac0fc008319b158;p=youtube-dl diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index a656ad85a..91e574dc2 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -8,10 +8,10 @@ from ..compat import ( compat_urllib_parse_unquote, compat_urllib_parse_unquote_plus, compat_urllib_parse_urlparse, - compat_urllib_request, ) from ..utils import ( ExtractorError, + sanitized_Request, str_to_int, ) from ..aes import ( @@ -27,9 +27,9 @@ class PornHubIE(InfoExtractor): 'info_dict': { 'id': '648719015', 'ext': 'mp4', - "uploader": "Babes", - "title": "Seductive Indian beauty strips down and fingers her pink pussy", - "age_limit": 18 + 'uploader': 'Babes', + 'title': 'Seductive Indian beauty strips down and fingers her pink pussy', + 'age_limit': 18 } }, { 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d', @@ -53,7 +53,7 @@ class PornHubIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - req = compat_urllib_request.Request( + req = sanitized_Request( 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) @@ -95,7 +95,7 @@ class PornHubIE(InfoExtractor): path = compat_urllib_parse_urlparse(video_url).path extension = os.path.splitext(path)[1][1:] format = path.split('/')[5].split('_')[:2] - format = "-".join(format) + format = '-'.join(format) m = re.match(r'^(?P[0-9]+)[pP]-(?P[0-9]+)[kK]$', format) if m is None: @@ -147,7 +147,8 @@ class PornHubPlaylistIE(InfoExtractor): entries = [ self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub') - for video_url in set(re.findall('href="/?(view_video\.php\?viewkey=\d+[^"]*)"', webpage)) + for video_url in set(re.findall( + r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"', webpage)) ] playlist = self._parse_json(