X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fextremetube.py;h=aacbf14141f6d5109d265b8e4dfa37883cee81ab;hb=71069d215791a85dc627ec3dcfa0a87f3d5643eb;hp=981de430d98f02c18f8909b02bb3dfc7f8936719;hpb=32a35e441874ad9daba10c29a6a33f13a4953fbb;p=youtube-dl

diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py
index 981de430d..aacbf1414 100644
--- a/youtube_dl/extractor/extremetube.py
+++ b/youtube_dl/extractor/extremetube.py
@@ -1,4 +1,5 @@
-import os
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -6,20 +7,27 @@ from ..utils import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,
+    str_to_int,
 )
 
+
 class ExtremeTubeIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
-    _TEST = {
-        u'url': u'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
-        u'file': u'652431.mp4',
-        u'md5': u'1fb9228f5e3332ec8c057d6ac36f33e0',
-        u'info_dict': {
-            u"title": u"Music Video 14 british euro brit european cumshots swallow",
-            u"uploader": u"unknown",
-            u"age_limit": 18,
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
+    _TESTS = [{
+        'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
+        'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
+        'info_dict': {
+            'id': '652431',
+            'ext': 'mp4',
+            'title': 'Music Video 14 british euro brit european cumshots swallow',
+            'uploader': 'unknown',
+            'view_count': int,
+            'age_limit': 18,
         }
-    }
+    }, {
+        'url': 'http://www.extremetube.com/gay/video/abcde-1234',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -30,23 +38,28 @@ class ExtremeTubeIE(InfoExtractor):
         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 )
+        video_title = self._html_search_regex(
+            r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
+        uploader = self._html_search_regex(
+            r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
+            webpage, 'uploader', fatal=False)
+        view_count = str_to_int(self._html_search_regex(
+            r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
+            webpage, 'view count', fatal=False))
 
-        age_limit = self._rta_search(webpage)
+        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,
             'uploader': uploader,
+            'view_count': view_count,
             'url': video_url,
-            'ext': extension,
             'format': format,
             'format_id': format,
-            'age_limit': age_limit,
+            'age_limit': 18,
         }