diff options
| author | Tom-Oliver Heidel <github@tom-oliver.eu> | 2020-11-30 02:51:41 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2020-11-30 02:51:41 +0100 |
| commit | b662fc8d2033c615ffbdd3b51123b446c03255e8 (patch) | |
| tree | 3d32dc25a663f4e61fc28860acda67c7a425cb7a /youtube_dlc/extractor/nbc.py | |
| parent | 8924ddc3eec4c03c6776673d0d5e823dc5445549 (diff) | |
| parent | 929576bb9e4aa31f0516f1437d2ae762afdd9f2c (diff) | |
Merge branch 'master' into gedi
Diffstat (limited to 'youtube_dlc/extractor/nbc.py')
| -rw-r--r-- | youtube_dlc/extractor/nbc.py | 5 |
1 files changed, 2 insertions, 3 deletions
diff --git a/youtube_dlc/extractor/nbc.py b/youtube_dlc/extractor/nbc.py index 6f3cb3003..ea5f5a315 100644 --- a/youtube_dlc/extractor/nbc.py +++ b/youtube_dlc/extractor/nbc.py @@ -10,7 +10,6 @@ from .adobepass import AdobePassIE from ..compat import compat_urllib_parse_unquote from ..utils import ( int_or_none, - js_to_json, parse_duration, smuggle_url, try_get, @@ -394,8 +393,8 @@ class NBCNewsIE(ThePlatformIE): webpage = self._download_webpage(url, video_id) data = self._parse_json(self._search_regex( - r'window\.__data\s*=\s*({.+});', webpage, - 'bootstrap json'), video_id, js_to_json) + r'<script[^>]+id="__NEXT_DATA__"[^>]*>({.+?})</script>', + webpage, 'bootstrap json'), video_id)['props']['initialState'] video_data = try_get(data, lambda x: x['video']['current'], dict) if not video_data: video_data = data['article']['content'][0]['primaryMedia']['video'] |