[youtube] Fix extraction.

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

diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py
index ff7c0cd3e6595740f1c98b834f1d2b818d04d25c..acd4090fa351c56147245983b3b1b7dd0c1e5495 100644 (file)
--- a/youtube_dl/extractor/extremetube.py
+++ b/youtube_dl/extractor/extremetube.py
@@ -1,58 +1,50 @@
 from __future__ import unicode_literals
 
-import re
+from ..utils import str_to_int
+from .keezmovies import KeezMoviesIE
 
-from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_parse_urlparse,
-    compat_urllib_request,
-    compat_urllib_parse,
-)
 
-
-class ExtremeTubeIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
+class ExtremeTubeIE(KeezMoviesIE):
+    _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'
     _TESTS = [{
         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
-        'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
+        'md5': '92feaafa4b58e82f261e5419f39c60cb',
         'info_dict': {
-            'id': '652431',
+            'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
             'ext': 'mp4',
             'title': 'Music Video 14 british euro brit european cumshots swallow',
-            'uploader': 'unknown',
+            'uploader': 'anonim',
+            'view_count': int,
             'age_limit': 18,
         }
     }, {
         'url': 'http://www.extremetube.com/gay/video/abcde-1234',
         'only_matching': True,
+    }, {
+        'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.extremetube.com/video/652431',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
-        url = 'http://www.' + mobj.group('url')
+        webpage, info = self._extract_info(url)
 
-        req = compat_urllib_request.Request(url)
-        req.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(req, video_id)
+        if not info['title']:
+            info['title'] = self._search_regex(
+                r'<h1[^>]+title="([^"]+)"[^>]*>', webpage, 'title')
 
-        video_title = self._html_search_regex(
-            r'<h1 [^>]*?title="([^"]+)"[^>]*>\1<', webpage, 'title')
         uploader = self._html_search_regex(
-            r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader',
-            fatal=False)
-        video_url = compat_urllib_parse.unquote(self._html_search_regex(
-            r'video_url=(.+?)&amp;', webpage, 'video_url'))
-        path = compat_urllib_parse_urlparse(video_url).path
-        format = path.split('/')[5].split('_')[:2]
-        format = "-".join(format)
-
-        return {
-            'id': video_id,
-            'title': video_title,
+            r'Uploaded by:\s*</[^>]+>\s*<a[^>]+>(.+?)</a>',
+            webpage, 'uploader', fatal=False)
+        view_count = str_to_int(self._search_regex(
+            r'Views:\s*</[^>]+>\s*<[^>]+>([\d,\.]+)</',
+            webpage, 'view count', fatal=False))
+
+        info.update({
             'uploader': uploader,
-            'url': video_url,
-            'format': format,
-            'format_id': format,
-            'age_limit': 18,
-        }
+            'view_count': view_count,
+        })
+
+        return info