[nbc] add support for today.com(closes #2909)

This commit is contained in:
remitamine 2016-04-22 18:07:40 +01:00
parent c80037918b
commit cb7d4d0efd

View file

@ -172,7 +172,7 @@ def _real_extract(self, url):
class NBCNewsIE(ThePlatformIE):
_VALID_URL = r'''(?x)https?://(?:www\.)?nbcnews\.com/
_VALID_URL = r'''(?x)https?://(?:www\.)?(?:nbcnews|today)\.com/
(?:video/.+?/(?P<id>\d+)|
([^/]+/)*(?P<display_id>[^/?]+))
'''
@ -230,6 +230,18 @@ class NBCNewsIE(ThePlatformIE):
},
'expected_warnings': ['http-6000 is not available']
},
{
'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
'md5': '118d7ca3f0bea6534f119c68ef539f71',
'info_dict': {
'id': '669831235788',
'ext': 'mp4',
'title': 'See the aurora borealis from space in stunning new NASA video',
'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
'upload_date': '20160420',
'timestamp': 1461152093,
},
},
{
'url': 'http://www.nbcnews.com/watch/dateline/full-episode--deadly-betrayal-386250819952',
'only_matching': True,
@ -264,7 +276,10 @@ def _real_extract(self, url):
info = bootstrap['results'][0]['video']
else:
player_instance_json = self._search_regex(
r'videoObj\s*:\s*({.+})', webpage, 'player instance')
r'videoObj\s*:\s*({.+})', webpage, 'player instance', default=None)
if not player_instance_json:
player_instance_json = self._html_search_regex(
r'data-video="([^"]+)"', webpage, 'video json')
info = self._parse_json(player_instance_json, display_id)
video_id = info['mpxId']
title = info['title']
@ -295,7 +310,7 @@ def _real_extract(self, url):
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
else:
tbr = int_or_none(video_asset.get('bitRate'), 1000)
tbr = int_or_none(video_asset.get('bitRate') or video_asset.get('bitrate'), 1000)
format_id = 'http%s' % ('-%d' % tbr if tbr else '')
video_url = update_url_query(
video_url, {'format': 'redirect'})
@ -321,10 +336,9 @@ def _real_extract(self, url):
'id': video_id,
'title': title,
'description': info.get('description'),
'thumbnail': info.get('description'),
'thumbnail': info.get('thumbnail'),
'duration': int_or_none(info.get('duration')),
'timestamp': parse_iso8601(info.get('pubDate')),
'timestamp': parse_iso8601(info.get('pubDate') or info.get('pub_date')),
'formats': formats,
'subtitles': subtitles,
}