X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/e8cd8c4bd832446f1971215b9fedc4531555dc1a..38bb9b1b0a044cabaf5691553815e334cd2e9213:/youtube_dl/extractor/youporn.py

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index 77ad423..4ba7c36 100644
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -1,12 +1,16 @@
+from __future__ import unicode_literals
+
+
 import json
 import re
 import sys
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
-
+)
+from ..utils import (
     ExtractorError,
     unescapeHTML,
     unified_strdate,
@@ -17,24 +21,24 @@ from ..aes import (
 
 
 class YouPornIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
+    _VALID_URL = r'^(?P<proto>https?://)(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
     _TEST = {
-        u'url': u'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
-        u'file': u'505835.mp4',
-        u'md5': u'71ec5fcfddacf80f495efa8b6a8d9a89',
-        u'info_dict': {
-            u"upload_date": u"20101221",
-            u"description": u"Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?",
-            u"uploader": u"Ask Dan And Jennifer",
-            u"title": u"Sex Ed: Is It Safe To Masturbate Daily?",
-            u"age_limit": 18,
+        'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
+        'info_dict': {
+            'id': '505835',
+            'ext': 'mp4',
+            'upload_date': '20101221',
+            'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
+            'uploader': 'Ask Dan And Jennifer',
+            'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
+            'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
-        url = 'http://www.' + mobj.group('url')
+        url = mobj.group('proto') + 'www.' + mobj.group('url')
 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')
@@ -42,11 +46,14 @@ class YouPornIE(InfoExtractor):
         age_limit = self._rta_search(webpage)
 
         # Get JSON parameters
-        json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
+        json_params = self._search_regex(
+            [r'videoJa?son\s*=\s*({.+})',
+             r'var\s+currentVideo\s*=\s*new\s+Video\((.+?)\)[,;]'],
+            webpage, 'JSON parameters')
         try:
             params = json.loads(json_params)
-        except:
-            raise ExtractorError(u'Invalid JSON')
+        except ValueError:
+            raise ExtractorError('Invalid JSON')
 
         self.report_extraction(video_id)
         try:
@@ -61,7 +68,7 @@ class YouPornIE(InfoExtractor):
         # Get all of the links from the page
         DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
         download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
-            webpage, u'download list').strip()
+                                                webpage, 'download list').strip()
         LINK_RE = r'<a href="([^"]+)">'
         links = re.findall(LINK_RE, download_list_html)
 
@@ -70,7 +77,7 @@ class YouPornIE(InfoExtractor):
         for encrypted_link in encrypted_links:
             link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
             links.append(link)
-        
+
         formats = []
         for link in links:
             # A link looks like this:
@@ -86,7 +93,7 @@ class YouPornIE(InfoExtractor):
             resolution = format_parts[0]
             height = int(resolution[:-len('p')])
             bitrate = int(format_parts[1][:-len('k')])
-            format = u'-'.join(format_parts) + u'-' + dn
+            format = '-'.join(format_parts) + '-' + dn
 
             formats.append({
                 'url': video_url,
@@ -100,8 +107,8 @@ class YouPornIE(InfoExtractor):
         self._sort_formats(formats)
 
         if not formats:
-            raise ExtractorError(u'ERROR: no known formats available for video')
-        
+            raise ExtractorError('ERROR: no known formats available for video')
+
         return {
             'id': video_id,
             'uploader': video_uploader,