aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/nbc.py
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2014-12-12 22:10:32 +0600
committerSergey M․ <dstftw@gmail.com>2014-12-12 22:10:32 +0600
commit58c1f6f0a708eb2b084e773d7aa74bfe37d80c6f (patch)
tree089918dc65419de0471dcefa203de3979725330b /youtube_dl/extractor/nbc.py
parent7c7a0d395c2eb60beb6ddf2fab19b89cae6a2cdc (diff)
[nbc] Fix extraction (Closes #4441)
Diffstat (limited to 'youtube_dl/extractor/nbc.py')
-rw-r--r--youtube_dl/extractor/nbc.py38
1 files changed, 26 insertions, 12 deletions
diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py
index 7b5449031..bf5132721 100644
--- a/youtube_dl/extractor/nbc.py
+++ b/youtube_dl/extractor/nbc.py
@@ -12,23 +12,37 @@ from ..utils import (
class NBCIE(InfoExtractor):
- _VALID_URL = r'http://www\.nbc\.com/[^/]+/video/[^/]+/(?P<id>n?\d+)'
-
- _TEST = {
- 'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188',
- # md5 checksum is not stable
- 'info_dict': {
- '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.',
+ _VALID_URL = r'http://www\.nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
+
+ _TESTS = [
+ {
+ 'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188',
+ # md5 checksum is not stable
+ 'info_dict': {
+ '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.',
+ },
},
- }
+ {
+ 'url': 'http://www.nbc.com/the-tonight-show/episodes/176',
+ 'info_dict': {
+ 'id': 'XwU9KZkp98TH',
+ 'ext': 'flv',
+ 'title': 'Ricky Gervais, Steven Van Zandt, ILoveMakonnen',
+ 'description': 'A brand new episode of The Tonight Show welcomes Ricky Gervais, Steven Van Zandt and ILoveMakonnen.',
+ },
+ 'skip': 'Only works from US',
+ },
+ ]
def _real_extract(self, url):
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')
+ theplatform_url = self._search_regex(
+ '(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
+ webpage, 'theplatform url').replace('_no_endcard', '')
if theplatform_url.startswith('//'):
theplatform_url = 'http:' + theplatform_url
return self.url_result(theplatform_url)