From 1737ea69b978f7ebe0f52c526d3dda5ba5c196b6 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 16 Nov 2020 15:55:07 +0100 Subject: [PATCH] [cnbc] fix extraction --- youtube_dl/extractor/cnbc.py | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/cnbc.py b/youtube_dl/extractor/cnbc.py index 6889b0f40..7b9f4536a 100644 --- a/youtube_dl/extractor/cnbc.py +++ b/youtube_dl/extractor/cnbc.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals +import re from .common import InfoExtractor from ..utils import smuggle_url @@ -38,7 +39,7 @@ class CNBCIE(InfoExtractor): class CNBCVideoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?cnbc\.com/video/(?:[^/]+/)+(?P[^./?#&]+)' + _VALID_URL = r'https?://(?:www\.)?cnbc\.com(?P/video/(?:[^/]+/)+(?P[^./?#&]+)\.html)' _TEST = { 'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html', 'info_dict': { @@ -56,11 +57,15 @@ class CNBCVideoIE(InfoExtractor): } def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - video_id = self._search_regex( - r'content_id["\']\s*:\s*["\'](\d+)', webpage, display_id, - 'video id') + path, display_id = re.match(self._VALID_URL, url).groups() + video_id = self._download_json( + 'https://webql-redesign.cnbcfm.com/graphql', display_id, query={ + 'query': '''{ + page(path: "%s") { + vcpsId + } +}''' % path, + })['data']['page']['vcpsId'] return self.url_result( - 'http://video.cnbc.com/gallery/?video=%s' % video_id, + 'http://video.cnbc.com/gallery/?video=%d' % video_id, CNBCIE.ie_key())