debian/control: Rerun wrap-and-sort.

[youtubedl] / youtube_dl / extractor / cbsnews.py

diff --git a/youtube_dl/extractor/cbsnews.py b/youtube_dl/extractor/cbsnews.py
index 387537e766fc4886201285f221022181b2beeb53..91b0f5fa94c7ba919e01fd097cbdfc71fe6992b4 100644 (file)
--- a/youtube_dl/extractor/cbsnews.py
+++ b/youtube_dl/extractor/cbsnews.py
@@ -1,14 +1,15 @@
-# encoding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

-from .cbs import CBSBaseIE
+from .cbs import CBSIE

 from ..utils import (
     parse_duration,
 )
 
 
 from ..utils import (
     parse_duration,
 )
 
 

-class CBSNewsIE(CBSBaseIE):
+class CBSNewsIE(CBSIE):
+    IE_NAME = 'cbsnews'

     IE_DESC = 'CBS News'
     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
 
     IE_DESC = 'CBS News'
     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
 


@@ -26,6 +27,7 @@ class CBSNewsIE(CBSBaseIE):
                 # rtmp download
                 'skip_download': True,
             },
                 # rtmp download
                 'skip_download': True,
             },

+            'skip': 'Subscribers only',

         },
         {
             'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
         },
         {
             'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',


@@ -34,7 +36,8 @@ class CBSNewsIE(CBSBaseIE):
                 'ext': 'mp4',
                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
                 'description': 'md5:4a6983e480542d8b333a947bfc64ddc7',
                 'ext': 'mp4',
                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
                 'description': 'md5:4a6983e480542d8b333a947bfc64ddc7',

-                'upload_date': '19700101',
+                'upload_date': '20140404',
+                'timestamp': 1396650660,

                 'uploader': 'CBSI-NEW',
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'duration': 205,
                 'uploader': 'CBSI-NEW',
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'duration': 205,


@@ -62,43 +65,43 @@ class CBSNewsIE(CBSBaseIE):
 
         item = video_info['item'] if 'item' in video_info else video_info
         guid = item['mpxRefId']
 
         item = video_info['item'] if 'item' in video_info else video_info
         guid = item['mpxRefId']

-        return self._extract_video_info('byGuid=%s' % guid, guid)
+        return self._extract_video_info(guid)

 
 
 class CBSNewsLiveVideoIE(InfoExtractor):
 
 
 class CBSNewsLiveVideoIE(InfoExtractor):

+    IE_NAME = 'cbsnews:livevideo'

     IE_DESC = 'CBS News Live Videos'
     IE_DESC = 'CBS News Live Videos'

-    _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
+    _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[^/?#]+)'

 
 

+    # Live videos get deleted soon. See http://www.cbsnews.com/live/ for the latest examples

     _TEST = {
         'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
         'info_dict': {
             'id': 'clinton-sanders-prepare-to-face-off-in-nh',
     _TEST = {
         'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
         'info_dict': {
             'id': 'clinton-sanders-prepare-to-face-off-in-nh',

-            'ext': 'flv',
+            'ext': 'mp4',

             'title': 'Clinton, Sanders Prepare To Face Off In NH',
             'duration': 334,
         },
             'title': 'Clinton, Sanders Prepare To Face Off In NH',
             'duration': 334,
         },

+        'skip': 'Video gone',

     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):

-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
+        display_id = self._match_id(url)

 
 

-        video_info = self._parse_json(self._html_search_regex(
-            r'data-story-obj=\'({.+?})\'', webpage, 'video JSON info'), video_id)['story']
+        video_info = self._download_json(
+            'http://feeds.cbsn.cbsnews.com/rundown/story', display_id, query={
+                'device': 'desktop',
+                'dvr_slug': display_id,
+            })

 
 

-        hdcore_sign = 'hdcore=3.3.1'
-        f4m_formats = self._extract_f4m_formats(video_info['url'] + '&' + hdcore_sign, video_id)
-        if f4m_formats:
-            for entry in f4m_formats:
-                # URLs without the extra param induce an 404 error
-                entry.update({'extra_param_to_segment_url': hdcore_sign})
-        self._sort_formats(f4m_formats)
+        formats = self._extract_akamai_formats(video_info['url'], display_id)
+        self._sort_formats(formats)

 
         return {
 
         return {

-            'id': video_id,
+            'id': display_id,
+            'display_id': display_id,

             'title': video_info['headline'],
             'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
             'duration': parse_duration(video_info.get('segmentDur')),
             'title': video_info['headline'],
             'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
             'duration': parse_duration(video_info.get('segmentDur')),

-            'formats': f4m_formats,
+            'formats': formats,

         }
         }