Unify coding cookie

[youtube-dl] / youtube_dl / extractor / porn91.py

diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py
index 377ca2c773289126f4a9534e2fe0cffd586e9e2e..073fc3e21db07f05deef1a337aca7685f62b4079 100644 (file)
--- a/youtube_dl/extractor/porn91.py
+++ b/youtube_dl/extractor/porn91.py
@@ -1,8 +1,16 @@
-# 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,
+)
 
 
 class Porn91IE(InfoExtractor):
@@ -15,15 +23,22 @@ 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,
         }
     }
 
     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'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title')
         title = title.replace('\n', '')
@@ -35,7 +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,
@@ -43,11 +58,21 @@ 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*</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),
         }