Merge tag 'upstream/2014.02.17'

[youtubedl] / youtube_dl / extractor / pornhd.py

diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py
index 71abd5013bf272ffbb2812a87a6838fd3aeedd7e..58f9c690e18b4330f7b47e862d0367913e17582a 100644 (file)
--- a/youtube_dl/extractor/pornhd.py
+++ b/youtube_dl/extractor/pornhd.py
@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+

 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor


@@ -5,14 +7,14 @@ from ..utils import compat_urllib_parse
 
 
 class PornHdIE(InfoExtractor):
 
 
 class PornHdIE(InfoExtractor):

-    _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
+    _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'

     _TEST = {
     _TEST = {

-        u'url': u'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
-        u'file': u'1962.flv',
-        u'md5': u'35272469887dca97abd30abecc6cdf75',
-        u'info_dict': {
-            u"title": u"sierra-day-gets-his-cum-all-over-herself-hd-porn-video",
-            u"age_limit": 18,
+        'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
+        'file': '1962.flv',
+        'md5': '35272469887dca97abd30abecc6cdf75',
+        'info_dict': {
+            "title": "sierra-day-gets-his-cum-all-over-herself-hd-porn-video",
+            "age_limit": 18,

         }
     }
 
         }
     }
 


@@ -24,9 +26,13 @@ class PornHdIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
 
         webpage = self._download_webpage(url, video_id)
 

-        video_url = self._html_search_regex(
-            r'&hd=(http.+?)&', webpage, u'video URL')
-        video_url = compat_urllib_parse.unquote(video_url)
+        next_url = self._html_search_regex(
+            r'&hd=(http.+?)&', webpage, 'video URL')
+        next_url = compat_urllib_parse.unquote(next_url)
+
+        video_url = self._download_webpage(
+            next_url, video_id, note='Retrieving video URL',
+            errnote='Could not retrieve video URL')

         age_limit = 18
 
         return {
         age_limit = 18
 
         return {