diff options
| author | pukkandan <pukkandan@gmail.com> | 2020-11-20 00:52:59 +0530 |
|---|---|---|
| committer | pukkandan <pukkandan@gmail.com> | 2020-11-20 13:03:32 +0530 |
| commit | 8bdd16b4993b8d546b4cbbdbe4710db0bc2f971b (patch) | |
| tree | c5ba0d26e17bb3102c0b24886853d9a818e875c6 /youtube_dlc/extractor/cnbc.py | |
| parent | 228385340e9a976f52735078218a9b8ecfe7ae7a (diff) | |
| download | hypervideo-pre-8bdd16b4993b8d546b4cbbdbe4710db0bc2f971b.tar.lz hypervideo-pre-8bdd16b4993b8d546b4cbbdbe4710db0bc2f971b.tar.xz hypervideo-pre-8bdd16b4993b8d546b4cbbdbe4710db0bc2f971b.zip | |
Merge 'ytdl-org/youtube-dl/master' release 2020.11.19
Old Extractors left behind:
VLivePlaylistIE
YoutubeSearchURLIE
YoutubeShowIE
YoutubeFavouritesIE
If removing old extractors, make corresponding changes in
docs/supportedsites.md
youtube_dlc/extractor/extractors.py
Not merged:
.github/ISSUE_TEMPLATE/1_broken_site.md
.github/ISSUE_TEMPLATE/2_site_support_request.md
.github/ISSUE_TEMPLATE/3_site_feature_request.md
.github/ISSUE_TEMPLATE/4_bug_report.md
.github/ISSUE_TEMPLATE/5_feature_request.md
test/test_all_urls.py
youtube_dlc/version.py
Changelog
Diffstat (limited to 'youtube_dlc/extractor/cnbc.py')
| -rw-r--r-- | youtube_dlc/extractor/cnbc.py | 19 |
1 files changed, 12 insertions, 7 deletions
diff --git a/youtube_dlc/extractor/cnbc.py b/youtube_dlc/extractor/cnbc.py index 6889b0f40..7b9f4536a 100644 --- a/youtube_dlc/extractor/cnbc.py +++ b/youtube_dlc/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<id>[^./?#&]+)' + _VALID_URL = r'https?://(?:www\.)?cnbc\.com(?P<path>/video/(?:[^/]+/)+(?P<id>[^./?#&]+)\.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()) |