X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fporn91.py;h=073fc3e21db07f05deef1a337aca7685f62b4079;hb=dcdb292fddc82ae11f4c0b647815a45c88a6b6d5;hp=af06af2b70a608b03d6e01f36dbeaa245bc1b7f5;hpb=d90b3854ca9e8602f440cc9439e1cba240192286;p=youtube-dl

diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py
index af06af2b7..073fc3e21 100644
--- a/youtube_dl/extractor/porn91.py
+++ b/youtube_dl/extractor/porn91.py
@@ -1,12 +1,16 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
-import json
-
-from ..compat import compat_urllib_parse
+from ..compat import (
+    compat_urllib_parse_unquote,
+    compat_urllib_parse_urlencode,
+)
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    parse_duration,
+    int_or_none,
+    ExtractorError,
+)
 
 
 class Porn91IE(InfoExtractor):
@@ -14,49 +18,61 @@ class Porn91IE(InfoExtractor):
     _VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\w\d]+)'
 
     _TEST = {
-            'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
-            'md5': '6df8f6d028bc8b14f5dbd73af742fb20',
-            'info_dict': {
-                'id': '7e42283b4f5ab36da134',
-                'title': '18岁大一漂亮学妹，水嫩性感，再爽一次！',
-                'ext': 'mp4'
-            }
+        'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
+        'md5': '6df8f6d028bc8b14f5dbd73af742fb20',
+        'info_dict': {
+            'id': '7e42283b4f5ab36da134',
+            '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):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        url = 'http://91porn.com/view_video.php?viewkey=%s' % video_id
+        video_id = self._match_id(url)
         self._set_cookie('91porn.com', 'language', 'cn_CN')
-        webpage = self._download_webpage(url, video_id, "get HTML content")
-        title = re.search(
-            r'<div id="viewvideo-title">(.+?)</div>',
-            webpage,
-            re.DOTALL)
-        assert title
-        title = title.group(1).replace('\n', '')
+
+        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', '')
 
         # get real url
-        n1 = re.search(r'so.addVariable\(\'file\',\'(\d+)\'', webpage)
-        n2 = re.search(r'so.addVariable\(\'seccode\',\'(.+?)\'', webpage)
-        n3 = re.search(r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage)
-        if not (n1 and n2 and n3):
-            raise ExtractorError("You are Blocked by Server.")
-
-        url_params = compat_urllib_parse.urlencode({
-            'VID': n1.group(1),
+        file_id = self._search_regex(
+            r'so.addVariable\(\'file\',\'(\d+)\'', webpage, 'file id')
+        sec_code = self._search_regex(
+            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({
+            'VID': file_id,
             'mp4': '1',
-            'seccode': n2.group(1),
-            'max_vid': n3.group(1),
+            'seccode': sec_code,
+            'max_vid': max_vid,
         })
-        t_url = 'http://91porn.com/getfile.php?' + url_params
-        info_cn = self._download_webpage(t_url, video_id, "get real video_url")
-        video_url = re.search(r'file=(http.+?)&', info_cn).group(1)
+        info_cn = self._download_webpage(
+            'http://91porn.com/getfile.php?' + url_params, video_id,
+            '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))
 
-        info = {
+        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),
         }
-
-        return info