from __future__ import unicode_literals
import re
-import json
from .common import InfoExtractor
from ..compat import (
class NBCIE(InfoExtractor):
- _VALID_URL = r'http://www\.nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
+ _VALID_URL = r'https?://www\.nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
_TESTS = [
{
- 'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188',
+ 'url': 'http://www.nbc.com/the-tonight-show/segments/112966',
# md5 checksum is not stable
'info_dict': {
- 'id': 'bTmnLCvIbaaH',
+ 'id': 'c9xnCo0YPOPH',
'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.',
+ 'title': 'Jimmy Fallon Surprises Fans at Ben & Jerry\'s',
+ 'description': 'Jimmy gives out free scoops of his new "Tonight Dough" ice cream flavor by surprising customers at the Ben & Jerry\'s scoop shop.',
},
},
{
class NBCNewsIE(InfoExtractor):
- _VALID_URL = r'''(?x)https?://www\.nbcnews\.com/
- ((video/.+?/(?P<id>\d+))|
- ((?P<program>feature|nightly-news)/[^/]+/(?P<title>.+)))
+ _VALID_URL = r'''(?x)https?://(?:www\.)?nbcnews\.com/
+ (?:video/.+?/(?P<id>\d+)|
+ (?:feature|nightly-news)/[^/]+/(?P<title>.+))
'''
_TESTS = [
# "feature" and "nightly-news" pages use theplatform.com
title = mobj.group('title')
webpage = self._download_webpage(url, title)
- program = mobj.group('program')
- if program == 'feature':
- bootstrap_json = self._search_regex(
- r'var bootstrapJson = ({.+})\s*$', webpage, 'bootstrap json',
- flags=re.MULTILINE)
- else:
- # nightly-news
- bootstrap_json = self._search_regex(
- r'var playlistData = ({.+});\s*$', webpage, 'playlist data',
- flags=re.MULTILINE)
- bootstrap = json.loads(bootstrap_json)
+ bootstrap_json = self._search_regex(
+ r'var\s+(?:bootstrapJson|playlistData)\s*=\s*({.+});?\s*$',
+ webpage, 'bootstrap json', flags=re.MULTILINE)
+ bootstrap = self._parse_json(bootstrap_json, video_id)
info = bootstrap['results'][0]['video']
mpxid = info['mpxId']