X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fporn91.py;h=3e15533e9d445e96884974af398e0461438bcc8b;hb=11bed5827dace09b5483b159476ce9f8c29d6078;hp=377ca2c773289126f4a9534e2fe0cffd586e9e2e;hpb=1c2223875664f99325b73fe7765677db9b87e105;p=youtube-dl

diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py
index 377ca2c77..3e15533e9 100644
--- a/youtube_dl/extractor/porn91.py
+++ b/youtube_dl/extractor/porn91.py
@@ -3,6 +3,11 @@ from __future__ import unicode_literals
 
 from ..compat import compat_urllib_parse
 from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+    ExtractorError,
+)
 
 
 class Porn91IE(InfoExtractor):
@@ -15,7 +20,9 @@ class Porn91IE(InfoExtractor):
         'info_dict': {
             'id': '7e42283b4f5ab36da134',
             'title': '18岁大一漂亮学妹，水嫩性感，再爽一次！',
-            'ext': 'mp4'
+            'ext': 'mp4',
+            'duration': 431,
+            'age_limit': 18,
         }
     }
 
@@ -23,7 +30,11 @@ class Porn91IE(InfoExtractor):
         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(url, video_id, 'get HTML content')
+
+        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'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title')
         title = title.replace('\n', '')
@@ -43,11 +54,20 @@ class Porn91IE(InfoExtractor):
         })
         info_cn = self._download_webpage(
             'http://91porn.com/getfile.php?' + url_params, video_id,
-            "get real video url")
+            'get real video url')
         video_url = self._search_regex(r'file=([^&]+)&', info_cn, 'url')
 
+        duration = parse_duration(self._search_regex(
+            r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False))
+
+        comment_count = int_or_none(self._search_regex(
+            r'留言:\s*</span>\s*(\d+)', webpage, 'comment count', fatal=False))
+
         return {
             'id': video_id,
             'title': title,
             'url': video_url,
+            'duration': duration,
+            'comment_count': comment_count,
+            'age_limit': self._rta_search(webpage),
         }