[cbnc] fix extraction

This commit is contained in:
gfabiano 2018-07-30 18:15:20 +02:00
parent 5484828418
commit db5fe4b1c9

View File

@ -1,13 +1,15 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import smuggle_url
class CNBCIE(InfoExtractor):
_VALID_URL = r'https?://video\.cnbc\.com/gallery/\?video=(?P<id>[0-9]+)'
_TEST = {
_VALID_URL = r'https?://(?:www|video)?\.cnbc\.com/(?:gallery|video)/(?:\?video=(?P<id>[0-9]+)|.*/(?P<display_id>[^.]+))'
_TESTS = [{
'url': 'http://video.cnbc.com/gallery/?video=3000503714',
'info_dict': {
'id': '3000503714',
@ -22,10 +24,33 @@ class CNBCIE(InfoExtractor):
# m3u8 download
'skip_download': True,
},
}
}, {
'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html',
'info_dict': {
'id': '7000033068',
'ext': 'mp4',
'title': 'Full interview with Brian Belski and Tobias Levkovich',
'description': 'md5:958012776b16f68bad3008587dd0a03a',
'timestamp': 1532908800,
'upload_date': '20180730',
'uploader': 'NBCU-CNBC',
},
'params': {
# m3u8 download
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
if not video_id:
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(
r'<a[^>]+?data-VideoID=[\'"]\s*([0-9]+)\s*',
webpage, display_id
)
return {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',