[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 981de430d98f02c18f8909b02bb3dfc7f8936719..acd4090fa351c56147245983b3b1b7dd0c1e5495 100644 (file)
--- a/youtube_dl/extractor/extremetube.py
+++ b/youtube_dl/extractor/extremetube.py
@@ -1,52 +1,50 @@
-import os
-import re
-
-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]+))(?:[/?&]|$)'
-    _TEST = {
-        u'url': u'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
-        u'file': u'652431.mp4',
-        u'md5': u'1fb9228f5e3332ec8c057d6ac36f33e0',
-        u'info_dict': {
-            u"title": u"Music Video 14 british euro brit european cumshots swallow",
-            u"uploader": u"unknown",
-            u"age_limit": 18,
+from __future__ import unicode_literals
+
+from ..utils import str_to_int
+from .keezmovies import KeezMoviesIE
+
+
+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': '92feaafa4b58e82f261e5419f39c60cb',
+        'info_dict': {
+            'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
+            'ext': 'mp4',
+            'title': 'Music Video 14 british euro brit european cumshots swallow',
+            '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')
-
-        req = compat_urllib_request.Request(url)
-        req.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(req, video_id)
-
-        video_title = self._html_search_regex(r'<h1 [^>]*?title="([^"]+)"[^>]*>\1<', webpage, u'title')
-        uploader = self._html_search_regex(r'>Posted by:(?=<)(\s|<[^>]*>)*(.+?)\|', webpage, u'uploader', fatal=False)
-        video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, u'video_url'))
-        path = compat_urllib_parse_urlparse( video_url ).path
-        extension = os.path.splitext( path )[1][1:]
-        format = path.split('/')[5].split('_')[:2]
-        format = "-".join( format )
-
-        age_limit = self._rta_search(webpage)
-
-        return {
-            'id': video_id,
-            'title': video_title,
+        webpage, info = self._extract_info(url)
+
+        if not info['title']:
+            info['title'] = self._search_regex(
+                r'<h1[^>]+title="([^"]+)"[^>]*>', webpage, 'title')
+
+        uploader = self._html_search_regex(
+            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,
-            'ext': extension,
-            'format': format,
-            'format_id': format,
-            'age_limit': age_limit,
-        }
+            'view_count': view_count,
+        })
+
+        return info