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

[bitchute] Fix extraction (closes #18567)

Browse source
This commit is contained in:
Sergey M․ 2019-01-01 18:12:44 +07:00
parent 9d9daed464
commit 6b688b8942
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 12 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
youtube_dl/extractor/bitchute.py
View file

@ -5,7 +5,10 @@
import re
from .common import InfoExtractor
from ..utils import urlencode_postdata
from ..utils import (
orderedSet,
urlencode_postdata,
)
class BitChuteIE(InfoExtractor):
@ -43,10 +46,15 @@ def _real_extract(self, url):
'description', webpage, 'title',
default=None) or self._og_search_description(webpage)
format_urls = []
for mobj in re.finditer(
r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage):
format_urls.append(mobj.group('url'))
format_urls.extend(re.findall(r'as=(https?://[^&"\']+)', webpage))
formats = [
{'url': mobj.group('url')}
for mobj in re.finditer(
r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage)]
{'url': format_url}
for format_url in orderedSet(format_urls)]
self._sort_formats(formats)
description = self._html_search_regex(