Merge tag 'upstream/2015.02.06'

[youtubedl] / youtube_dl / extractor / extremetube.py

diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py
index 1c20e43644b917d5b73b712d1630740f1a7e7e81..36ba331285b434136b8d3c10e6a8a16bef18e7b7 100644 (file)
--- a/youtube_dl/extractor/extremetube.py
+++ b/youtube_dl/extractor/extremetube.py
@@ -1,40 +1,57 @@
-import os
+from __future__ import unicode_literals
+

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

-from ..utils import (
+from ..compat import (

     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,
 )
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,
 )

+from ..utils import (
+    str_to_int,
+)
+

 
 class ExtremeTubeIE(InfoExtractor):
 
 class ExtremeTubeIE(InfoExtractor):

-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
-    _TEST = {
-        u'url': u'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
-        u'file': u'652431.mp4',
-        u'md5': u'1fb9228f5e3332ec8c057d6ac36f33e0',
-        u'info_dict': {
-            u"title": u"Music Video 14 british euro brit european cumshots swallow",
-            u"uploader": u"unknown",
-            u"age_limit": 18,
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)'
+    _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)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

-        video_id = mobj.group('videoid')
+        video_id = mobj.group('id')

         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)
 
         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'))
+        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))
+
+        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
         path = compat_urllib_parse_urlparse(video_url).path

-        extension = os.path.splitext(path)[1][1:]

         format = path.split('/')[5].split('_')[:2]
         format = "-".join(format)
 
         format = path.split('/')[5].split('_')[:2]
         format = "-".join(format)
 


@@ -42,8 +59,8 @@ class ExtremeTubeIE(InfoExtractor):
             'id': video_id,
             'title': video_title,
             'uploader': uploader,
             'id': video_id,
             'title': video_title,
             'uploader': uploader,

+            'view_count': view_count,

             'url': video_url,
             'url': video_url,

-            'ext': extension,

             'format': format,
             'format_id': format,
             'age_limit': 18,
             'format': format,
             'format_id': format,
             'age_limit': 18,