Merge tag 'upstream/2015.11.27.1'

[youtubedl] / youtube_dl / extractor / cnet.py

diff --git a/youtube_dl/extractor/cnet.py b/youtube_dl/extractor/cnet.py
index 710d5009b71aafe0da901771048b8c0ba68def04..5dd69bff7ac73bcc0adc4d91c614045ddf116a9c 100644 (file)
--- a/youtube_dl/extractor/cnet.py
+++ b/youtube_dl/extractor/cnet.py
@@ -2,36 +2,48 @@
 from __future__ import unicode_literals
 
 import json
 from __future__ import unicode_literals
 
 import json

-import re

 
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
 
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,

-    int_or_none,

 )
 
 
 class CNETIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
 )
 
 
 class CNETIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'

-    _TEST = {
+    _TESTS = [{

         'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
         'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',

-        'md5': '041233212a0d06b179c87cbcca1577b8',

         'info_dict': {
             'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
         'info_dict': {
             'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',

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

             'title': 'Hands-on with Microsoft Windows 8.1 Update',
             'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
             'thumbnail': 're:^http://.*/flmswindows8.jpg$',
             'title': 'Hands-on with Microsoft Windows 8.1 Update',
             'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
             'thumbnail': 're:^http://.*/flmswindows8.jpg$',

-            'uploader_id': 'sarah.mitroff@cbsinteractive.com',
+            'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',

             'uploader': 'Sarah Mitroff',
             'uploader': 'Sarah Mitroff',

+        },
+        'params': {
+            'skip_download': 'requires rtmpdump',

         }
         }

-    }
+    }, {
+        'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
+        'info_dict': {
+            'id': '56527b93-d25d-44e3-b738-f989ce2e49ba',
+            'ext': 'flv',
+            'description': 'Khail and Ashley wonder what other civic woes can be solved by self-tweeting objects, investigate a new kind of VR camera and watch an origami robot self-assemble, walk, climb, dig and dissolve. #TDPothole',
+            'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
+            'uploader': 'Ashley Esqueda',
+            'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
+        },
+        'params': {
+            'skip_download': True,  # requires rtmpdump
+        },
+    }]

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

-        mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('id')
-
+        display_id = self._match_id(url)

         webpage = self._download_webpage(url, display_id)
         webpage = self._download_webpage(url, display_id)

+

         data_json = self._html_search_regex(
             r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'",
             webpage, 'data json')
         data_json = self._html_search_regex(
             r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'",
             webpage, 'data json')


@@ -42,37 +54,31 @@ class CNETIE(InfoExtractor):
         if not vdata:
             raise ExtractorError('Cannot find video data')
 
         if not vdata:
             raise ExtractorError('Cannot find video data')
 

+        mpx_account = data['config']['players']['default']['mpx_account']
+        vid = vdata['files'].get('rtmp', vdata['files']['hds'])
+        tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid)
+

         video_id = vdata['id']
         title = vdata.get('headline')
         if title is None:
             title = vdata.get('title')
         if title is None:
             raise ExtractorError('Cannot find title!')
         video_id = vdata['id']
         title = vdata.get('headline')
         if title is None:
             title = vdata.get('title')
         if title is None:
             raise ExtractorError('Cannot find title!')

-        description = vdata.get('dek')

         thumbnail = vdata.get('image', {}).get('path')
         author = vdata.get('author')
         if author:
             uploader = '%s %s' % (author['firstName'], author['lastName'])
         thumbnail = vdata.get('image', {}).get('path')
         author = vdata.get('author')
         if author:
             uploader = '%s %s' % (author['firstName'], author['lastName'])

-            uploader_id = author.get('email')
+            uploader_id = author.get('id')

         else:
             uploader = None
             uploader_id = None
 
         else:
             uploader = None
             uploader_id = None
 

-        formats = [{
-            'format_id': '%s-%s-%s' % (
-                f['type'], f['format'],
-                int_or_none(f.get('bitrate'), 1000, default='')),
-            'url': f['uri'],
-            'tbr': int_or_none(f.get('bitrate'), 1000),
-        } for f in vdata['files']['data']]
-        self._sort_formats(formats)
-

         return {
         return {

+            '_type': 'url_transparent',
+            'url': tp_link,

             'id': video_id,
             'display_id': display_id,
             'title': title,
             'id': video_id,
             'display_id': display_id,
             'title': title,

-            'formats': formats,
-            'description': description,

             'uploader': uploader,
             'uploader_id': uploader_id,
             'thumbnail': thumbnail,
             'uploader': uploader,
             'uploader_id': uploader_id,
             'thumbnail': thumbnail,