From 58c1f6f0a708eb2b084e773d7aa74bfe37d80c6f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 12 Dec 2014 22:10:32 +0600 Subject: [PATCH] [nbc] Fix extraction (Closes #4441) --- youtube_dl/extractor/nbc.py | 36 +++++++++++++++++++++++++----------- 1 file changed, 25 insertions(+), 11 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 @@ class NBCIE(InfoExtractor): - _VALID_URL = r'http://www\.nbc\.com/[^/]+/video/[^/]+/(?Pn?\d+)' + _VALID_URL = r'http://www\.nbc\.com/(?:[^/]+/)+(?Pn?\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.', + _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)