Tidy up cleanup rule and keep lintian happy.

[youtubedl] / youtube_dl / extractor / ustream.py

diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py
index 7fa2b9e159ed1a60c056140f05f51851663830e9..54605d863027968a4a15c5358b9f98539c69c4b3 100644 (file)
--- a/youtube_dl/extractor/ustream.py
+++ b/youtube_dl/extractor/ustream.py
@@ -1,74 +1,154 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import json

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

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

     compat_urlparse,
     compat_urlparse,

-    get_meta_content,
+)
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    float_or_none,

 )
 
 
 class UstreamIE(InfoExtractor):
 )
 
 
 class UstreamIE(InfoExtractor):

-    _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)'
+    _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed|embed/recorded)/(?P<id>\d+)'

     IE_NAME = 'ustream'
     IE_NAME = 'ustream'

-    _TEST = {
+    _TESTS = [{

         'url': 'http://www.ustream.tv/recorded/20274954',
         'url': 'http://www.ustream.tv/recorded/20274954',

-        'file': '20274954.flv',

         'md5': '088f151799e8f572f84eb62f17d73e5c',
         'info_dict': {
         'md5': '088f151799e8f572f84eb62f17d73e5c',
         'info_dict': {

-            "uploader": "Young Americans for Liberty",
-            "title": "Young Americans for Liberty February 7, 2012 2:28 AM",
+            'id': '20274954',
+            'ext': 'flv',
+            '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
+        # Title and uploader available only from params JSON
+        'url': 'http://www.ustream.tv/embed/recorded/59307601?ub=ff0000&lc=ff0000&oc=ffffff&uc=ffffff&v=3&wmode=direct',
+        'md5': '5a2abf40babeac9812ed20ae12d34e10',
+        'info_dict': {
+            'id': '59307601',
+            '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.',
+    }, {
+        'url': 'http://www.ustream.tv/embed/10299409',
+        'info_dict': {
+            'id': '10299409',
+        },
+        'playlist_count': 3,
+    }]

 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)

-        video_id = m.group('videoID')
-
-        video_url = 'http://tcdn.ustream.tv/video/%s' % video_id
-        webpage = self._download_webpage(url, video_id)
-
-        self.report_extraction(video_id)
+        video_id = m.group('id')
+
+        # some sites use this embed format (see: https://github.com/rg3/youtube-dl/issues/2990)
+        if m.group('type') == 'embed/recorded':
+            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('id')
+            webpage = self._download_webpage(url, video_id)
+            content_video_ids = self._parse_json(self._search_regex(
+                r'ustream\.vars\.offAirContentVideoIds=([^;]+);', webpage,
+                'content video IDs'), video_id)
+            return self.playlist_result(
+                map(lambda u: self.url_result('http://www.ustream.tv/recorded/' + u, 'Ustream'), content_video_ids),
+                video_id)
+
+        params = self._download_json(
+            'https://api.ustream.tv/videos/%s.json' % video_id, video_id)
+
+        error = params.get('error')
+        if error:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, error), expected=True)
+
+        video = params['video']
+
+        title = video['title']
+        filesize = float_or_none(video.get('file_size'))
+
+        formats = [{
+            '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)

 
 

-        video_title = self._html_search_regex(r'data-title="(?P<title>.+)"',
-            webpage, 'title')
+        description = video.get('description')
+        timestamp = int_or_none(video.get('created_at'))
+        duration = float_or_none(video.get('length'))
+        view_count = int_or_none(video.get('views'))

 
 

-        uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>',
-            webpage, 'uploader', fatal=False, flags=re.DOTALL)
+        uploader = video.get('owner', {}).get('username')
+        uploader_id = video.get('owner', {}).get('id')

 
 

-        thumbnail = self._html_search_regex(r'<link rel="image_src" href="(?P<thumb>.*?)"',
-            webpage, 'thumbnail', fatal=False)
+        thumbnails = [{
+            'id': thumbnail_id,
+            'url': thumbnail_url,
+        } for thumbnail_id, thumbnail_url in video.get('thumbnail', {}).items()]

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,

-            'url': video_url,
-            'ext': 'flv',
-            'title': video_title,
+            'title': title,
+            'description': description,
+            'thumbnails': thumbnails,
+            'timestamp': timestamp,
+            'duration': duration,
+            'view_count': view_count,

             'uploader': uploader,
             'uploader': uploader,

-            'thumbnail': thumbnail,
+            'uploader_id': uploader_id,
+            'formats': formats,

         }
 
 
 class UstreamChannelIE(InfoExtractor):
     _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)'
     IE_NAME = 'ustream:channel'
         }
 
 
 class UstreamChannelIE(InfoExtractor):
     _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)'
     IE_NAME = 'ustream:channel'

+    _TEST = {
+        'url': 'http://www.ustream.tv/channel/channeljapan',
+        'info_dict': {
+            'id': '10874166',
+        },
+        'playlist_mincount': 17,
+    }

 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)

-        slug = m.group('slug')
-        webpage = self._download_webpage(url, slug)
-        channel_id = get_meta_content('ustream:channel_id', webpage)
+        display_id = m.group('slug')
+        webpage = self._download_webpage(url, display_id)
+        channel_id = self._html_search_meta('ustream:channel_id', webpage)

 
         BASE = 'http://www.ustream.tv'
         next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id
         video_ids = []
         while next_url:
 
         BASE = 'http://www.ustream.tv'
         next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id
         video_ids = []
         while next_url:

-            reply = json.loads(self._download_webpage(compat_urlparse.urljoin(BASE, next_url), channel_id))
+            reply = self._download_json(
+                compat_urlparse.urljoin(BASE, next_url), display_id,
+                note='Downloading video information (next: %d)' % (len(video_ids) + 1))

             video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data']))
             next_url = reply['nextUrl']
 
             video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data']))
             next_url = reply['nextUrl']
 

-        urls = ['http://www.ustream.tv/recorded/' + vid for vid in video_ids]
-        url_entries = [self.url_result(eurl, 'Ustream') for eurl in urls]
-        return self.playlist_result(url_entries, channel_id)
+        entries = [
+            self.url_result('http://www.ustream.tv/recorded/' + vid, 'Ustream')
+            for vid in video_ids]
+        return {
+            '_type': 'playlist',
+            'id': channel_id,
+            'display_id': display_id,
+            'entries': entries,
+        }