Imported Upstream version 2014.11.21

[youtubedl] / youtube_dl / extractor / nbc.py

diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py
index d2e4acbada5b99c5c3eac4fe6b966ce77dab1ef9..7b5449031ebd2b7245d452c04ae50dfaf970d6ca 100644 (file)
--- a/youtube_dl/extractor/nbc.py
+++ b/youtube_dl/extractor/nbc.py
@@ -16,9 +16,9 @@ class NBCIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188',
 
     _TEST = {
         'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188',

-        'md5': '54d0fbc33e0b853a65d7b4de5c06d64e',
+        # md5 checksum is not stable

         'info_dict': {
         'info_dict': {

-            'id': 'u1RInQZRN7QJ',
+            'id': 'bTmnLCvIbaaH',

             'ext': 'flv',
             'title': 'I Am a Firefighter',
             'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.',
             'ext': 'flv',
             'title': 'I Am a Firefighter',
             'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.',


@@ -26,8 +26,7 @@ class NBCIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):

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

         webpage = self._download_webpage(url, video_id)
         theplatform_url = self._search_regex('class="video-player video-player-full" data-mpx-url="(.*?)"', webpage, 'theplatform url')
         if theplatform_url.startswith('//'):
         webpage = self._download_webpage(url, video_id)
         theplatform_url = self._search_regex('class="video-player video-player-full" data-mpx-url="(.*?)"', webpage, 'theplatform url')
         if theplatform_url.startswith('//'):


@@ -57,7 +56,7 @@ class NBCNewsIE(InfoExtractor):
             'md5': 'b2421750c9f260783721d898f4c42063',
             'info_dict': {
                 'id': 'I1wpAI_zmhsQ',
             'md5': 'b2421750c9f260783721d898f4c42063',
             'info_dict': {
                 'id': 'I1wpAI_zmhsQ',

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

                 'title': 'How Twitter Reacted To The Snowden Interview',
                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
             },
                 'title': 'How Twitter Reacted To The Snowden Interview',
                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
             },


@@ -97,6 +96,8 @@ class NBCNewsIE(InfoExtractor):
             ]
 
             for base_url in base_urls:
             ]
 
             for base_url in base_urls:

+                if not base_url:
+                    continue

                 playlist_url = base_url + '?form=MPXNBCNewsAPI'
                 all_videos = self._download_json(playlist_url, title)['videos']
 
                 playlist_url = base_url + '?form=MPXNBCNewsAPI'
                 all_videos = self._download_json(playlist_url, title)['videos']