github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[extractor/substack] Fix extraction (#7218)

Browse source 
Closes #7155
Authored by: bashonly
This commit is contained in:
bashonly 2023-06-04 06:10:30 -05:00 committed by GitHub
parent c91ac833ea
commit 12037d8b0a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
yt_dlp/extractor/substack.py
View file

@ -2,7 +2,7 @@
import urllib.parse import urllib.parse
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import str_or_none, traverse_obj from ..utils import js_to_json, str_or_none, traverse_obj
class SubstackIE(InfoExtractor): class SubstackIE(InfoExtractor):
@ -14,7 +14,7 @@ class SubstackIE(InfoExtractor):
'id': '47660949', 'id': '47660949',
'ext': 'mp4', 'ext': 'mp4',
'title': 'I MADE A VLOG', 'title': 'I MADE A VLOG',
'description': 'md5:10c01ff93439a62e70ce963b2aa0b7f6', 'description': 'md5:9248af9a759321e1027226f988f54d96',
'thumbnail': 'md5:bec758a34d8ee9142d43bcebdf33af18', 'thumbnail': 'md5:bec758a34d8ee9142d43bcebdf33af18',
'uploader': 'Maybe Baby', 'uploader': 'Maybe Baby',
'uploader_id': '33628', 'uploader_id': '33628',
@ -77,7 +77,9 @@ def _real_extract(self, url):
display_id, username = self._match_valid_url(url).group('id', 'username') display_id, username = self._match_valid_url(url).group('id', 'username')
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
webpage_info = self._search_json(r'<script[^>]*>\s*window\._preloads\s*=', webpage, 'preloads', display_id) webpage_info = self._parse_json(self._search_json(
r'window\._preloads\s*=\s*JSON\.parse\(', webpage, 'json string',
display_id, transform_source=js_to_json, contains_pattern=r'"{(?s:.+)}"'), display_id)
post_type = webpage_info['post']['type'] post_type = webpage_info['post']['type']
formats, subtitles = [], {} formats, subtitles = [], {}