X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fmiaopai.py;h=f9e35ac7f6a56044e13fe31d18590e12bdf3ac03;hb=HEAD;hp=c36b441b8edf145cc43ede9c1558608357c7dc4e;hpb=95be19d436d1938d104310e194e85ea5a10c3353;p=youtube-dl

diff --git a/youtube_dl/extractor/miaopai.py b/youtube_dl/extractor/miaopai.py
index c36b441b8..f9e35ac7f 100644
--- a/youtube_dl/extractor/miaopai.py
+++ b/youtube_dl/extractor/miaopai.py
@@ -2,11 +2,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import sanitized_Request
 
 
 class MiaoPaiIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P<id>[-A-Za-z0-9~_]+).htm'
+    _VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P<id>[-A-Za-z0-9~_]+)'
     _TEST = {
         'url': 'http://www.miaopai.com/show/n~0hO7sfV1nBEw4Y29-Hqg__.htm',
         'md5': '095ed3f1cd96b821add957bdc29f845b',
@@ -18,27 +17,24 @@ class MiaoPaiIE(InfoExtractor):
         }
     }
 
-    _USER_AGENT_IPAD = 'User-Agent:Mozilla/5.0 ' \
-                       '(iPad; CPU OS 9_1 like Mac OS X) ' \
-                       'AppleWebKit/601.1.46 (KHTML, like Gecko) ' \
-                       'Version/9.0 Mobile/13B143 Safari/601.1'
+    _USER_AGENT_IPAD = 'Mozilla/5.0 (iPad; CPU OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1'
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        request = sanitized_Request(url)
-        request.add_header('User-Agent', self._USER_AGENT_IPAD)
-        webpage = self._download_webpage(request, video_id)
+        webpage = self._download_webpage(
+            url, video_id, headers={'User-Agent': self._USER_AGENT_IPAD})
 
-        title = self._html_search_regex(r'<title>([^<]*)</title>',
-                                        webpage,
-                                        'title')
-        regex = r"""<div *class=['"]video_img[^>]*data-url=['"]([^'"]*\.jpg)['"]"""
-        thumbnail = self._html_search_regex(regex, webpage, '')
-        regex = r"""<video *[^>]*src=['"]([^'"]*)['"]""",
-        video_url = self._html_search_regex(regex, webpage, '')
+        title = self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title')
+        thumbnail = self._html_search_regex(
+            r'<div[^>]+class=(?P<q1>[\'"]).*\bvideo_img\b.*(?P=q1)[^>]+data-url=(?P<q2>[\'"])(?P<url>[^\'"]+)(?P=q2)',
+            webpage, 'thumbnail', fatal=False, group='url')
+        videos = self._parse_html5_media_entries(url, webpage, video_id)
+        info = videos[0]
 
-        return {'id': video_id,
-                'title': title,
-                'url': video_url,
-                'thumbnail': thumbnail,
-                }
+        info.update({
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+        })
+        return info