X-Git-Url: http://git.bitcoin.ninja/index.cgi?p=youtube-dl;a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fporn91.py;h=073fc3e21db07f05deef1a337aca7685f62b4079;hp=3e15533e9d445e96884974af398e0461438bcc8b;hb=dcdb292fddc82ae11f4c0b647815a45c88a6b6d5;hpb=11bed5827dace09b5483b159476ce9f8c29d6078 diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py index 3e15533e9..073fc3e21 100644 --- a/youtube_dl/extractor/porn91.py +++ b/youtube_dl/extractor/porn91.py @@ -1,7 +1,10 @@ -# 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, @@ -28,9 +31,10 @@ class Porn91IE(InfoExtractor): 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) @@ -46,7 +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, @@ -54,8 +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))