Merge pull request #7045 from remitamine/ign

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

diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py
index 3065c9f31c6e88496967a6a9c70774e498b753b6..73b05ecab82a10a6c80360b0b980f285dfbb9c45 100644 (file)
--- a/youtube_dl/extractor/ustream.py
+++ b/youtube_dl/extractor/ustream.py
@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
@@ -15,7 +14,7 @@ from ..utils import (
 
 
 class UstreamIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed|embed/recorded)/(?P<videoID>\d+)'
+    _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed|embed/recorded)/(?P<id>\d+)'
     IE_NAME = 'ustream'
     _TESTS = [{
         'url': 'http://www.ustream.tv/recorded/20274954',
@@ -23,8 +22,12 @@ class UstreamIE(InfoExtractor):
         'info_dict': {
             'id': '20274954',
             'ext': 'flv',
-            'uploader': 'Young Americans for Liberty',
             'title': 'Young Americans for Liberty February 7, 2012 2:28 AM',
+            'description': 'Young Americans for Liberty February 7, 2012 2:28 AM',
+            'timestamp': 1328577035,
+            'upload_date': '20120207',
+            'uploader': 'yaliberty',
+            'uploader_id': '6780869',
         },
     }, {
         # From http://sportscanada.tv/canadagames/index.php/week2/figure-skating/444
@@ -36,27 +39,29 @@ class UstreamIE(InfoExtractor):
             'ext': 'flv',
             'title': '-CG11- Canada Games Figure Skating',
             'uploader': 'sportscanadatv',
-        }
+        },
+        'skip': 'This Pro Broadcaster has chosen to remove this video from the ustream.tv site.',
     }]
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
-        video_id = m.group('videoID')
+        video_id = m.group('id')
 
         # some sites use this embed format (see: http://github.com/rg3/youtube-dl/issues/2990)
         if m.group('type') == 'embed/recorded':
-            video_id = m.group('videoID')
+            video_id = m.group('id')
             desktop_url = 'http://www.ustream.tv/recorded/' + video_id
             return self.url_result(desktop_url, 'Ustream')
         if m.group('type') == 'embed':
-            video_id = m.group('videoID')
+            video_id = m.group('id')
             webpage = self._download_webpage(url, video_id)
             desktop_video_id = self._html_search_regex(
                 r'ContentVideoIds=\["([^"]*?)"\]', webpage, 'desktop_video_id')
             desktop_url = 'http://www.ustream.tv/recorded/' + desktop_video_id
             return self.url_result(desktop_url, 'Ustream')
 
-        params = self._download_json('https://api.ustream.tv/videos/' + video_id + '.json', video_id)
+        params = self._download_json(
+            'https://api.ustream.tv/videos/%s.json' % video_id, video_id)
 
         error = params.get('error')
         if error:
@@ -65,18 +70,20 @@ class UstreamIE(InfoExtractor):
 
         video = params['video']
 
+        title = video['title']
+        filesize = float_or_none(video.get('file_size'))
+
         formats = [{
-            'id': format_id,
+            'id': video_id,
             'url': video_url,
             'ext': format_id,
+            'filesize': filesize,
         } for format_id, video_url in video['media_urls'].items()]
         self._sort_formats(formats)
 
-        title = video['title']
         description = video.get('description')
         timestamp = int_or_none(video.get('created_at'))
         duration = float_or_none(video.get('length'))
-        filesize = float_or_none(video.get('file_size'))
         view_count = int_or_none(video.get('views'))
 
         uploader = video.get('owner', {}).get('username')
@@ -94,7 +101,6 @@ class UstreamIE(InfoExtractor):
             'thumbnails': thumbnails,
             'timestamp': timestamp,
             'duration': duration,
-            'filesize': filesize,
             'view_count': view_count,
             'uploader': uploader,
             'uploader_id': uploader_id,