X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fporn91.py;h=073fc3e21db07f05deef1a337aca7685f62b4079;hb=e2628fb6a028bd48f39ee556ca5ecb07aceba7f5;hp=ea1efc71b2b99d94206bf4bf2a2779964be585d1;hpb=a80601f8d9789e27c0a916e63d7192c3f398d5d5;p=youtube-dl diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py index ea1efc71b..073fc3e21 100644 --- a/youtube_dl/extractor/porn91.py +++ b/youtube_dl/extractor/porn91.py @@ -1,11 +1,15 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals -from ..compat import compat_urllib_parse +from ..compat import ( + compat_urllib_parse_unquote, + compat_urllib_parse_urlencode, +) from .common import InfoExtractor from ..utils import ( parse_duration, int_or_none, + ExtractorError, ) @@ -21,14 +25,20 @@ class Porn91IE(InfoExtractor): 'title': '18岁大一漂亮学妹,水嫩性感,再爽一次!', 'ext': 'mp4', 'duration': 431, + 'age_limit': 18, } } def _real_extract(self, url): video_id = self._match_id(url) - url = 'http://91porn.com/view_video.php?viewkey=%s' % video_id self._set_cookie('91porn.com', 'language', 'cn_CN') - webpage = self._download_webpage(url, video_id, "get HTML content") + + webpage = self._download_webpage( + 'http://91porn.com/view_video.php?viewkey=%s' % video_id, video_id) + + if '作为游客,你每天只可观看10个视频' in webpage: + raise ExtractorError('91 Porn says: Daily limit 10 videos exceeded', expected=True) + title = self._search_regex( r'
([^<]+)
', webpage, 'title') title = title.replace('\n', '') @@ -40,7 +50,7 @@ class Porn91IE(InfoExtractor): r'so.addVariable\(\'seccode\',\'([^\']+)\'', webpage, 'sec code') max_vid = self._search_regex( r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage, 'max vid') - url_params = compat_urllib_parse.urlencode({ + url_params = compat_urllib_parse_urlencode({ 'VID': file_id, 'mp4': '1', 'seccode': sec_code, @@ -48,8 +58,9 @@ class Porn91IE(InfoExtractor): }) info_cn = self._download_webpage( 'http://91porn.com/getfile.php?' + url_params, video_id, - "get real video url") - video_url = self._search_regex(r'file=([^&]+)&', info_cn, 'url') + 'Downloading real video url') + video_url = compat_urllib_parse_unquote(self._search_regex( + r'file=([^&]+)&', info_cn, 'url')) duration = parse_duration(self._search_regex( r'时长:\s*\s*(\d+:\d+)', webpage, 'duration', fatal=False)) @@ -63,4 +74,5 @@ class Porn91IE(InfoExtractor): 'url': video_url, 'duration': duration, 'comment_count': comment_count, + 'age_limit': self._rta_search(webpage), }