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

Bugfix for bae4834245

Browse source 
Authored by: bashonly
This commit is contained in:
bashonly 2023-09-04 11:18:59 -05:00
parent 2301b5c1b7
commit 69dbfe01c4
No known key found for this signature in database
GPG key ID: 783F096F253D15B0
1 changed files with 21 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
yt_dlp/extractor/noodlemagazine.py
View file

@ -1,7 +1,5 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
extract_attributes,
get_element_html_by_id,
int_or_none, int_or_none,
parse_count, parse_count,
parse_duration, parse_duration,
@ -42,17 +40,26 @@ def _real_extract(self, url):
like_count = parse_count(self._html_search_meta('ya:ovs:likes', webpage, default=None)) like_count = parse_count(self._html_search_meta('ya:ovs:likes', webpage, default=None))
upload_date = unified_strdate(self._html_search_meta('ya:ovs:upload_date', webpage, default='')) upload_date = unified_strdate(self._html_search_meta('ya:ovs:upload_date', webpage, default=''))
player_path = extract_attributes(get_element_html_by_id('iplayer', webpage) or '')['src'] def build_url(url_or_path):
return urljoin('https://adult.noodlemagazine.com', url_or_path)
headers = {'Referer': url}
player_path = self._html_search_regex(
r'<iframe[^>]+\bid="iplayer"[^>]+\bsrc="([^"]+)"', webpage, 'player path')
player_iframe = self._download_webpage( player_iframe = self._download_webpage(
urljoin('https://adult.noodlemagazine.com', player_path), video_id, 'Downloading iframe page') build_url(player_path), video_id, 'Downloading iframe page', headers=headers)
playlist_url = self._search_regex( playlist_url = self._search_regex(
r'window\.playlistUrl\s*=\s*["\']([^"\']+)["\']', player_iframe, 'playlist url') r'window\.playlistUrl\s*=\s*["\']([^"\']+)["\']', player_iframe, 'playlist url')
playlist_info = self._download_json( playlist_info = self._download_json(build_url(playlist_url), video_id, headers=headers)
urljoin('https://adult.noodlemagazine.com', playlist_url), video_id, headers={'Referer': url})
thumbnail = self._og_search_property('image', webpage, default=None) or playlist_info.get('image') formats = []
formats = traverse_obj(playlist_info, ('sources', lambda _, v: v['file'], { for source in traverse_obj(playlist_info, ('sources', lambda _, v: v['file'])):
'url': 'file', if source.get('type') == 'hls':
formats.extend(self._extract_m3u8_formats(
build_url(source['file']), video_id, 'mp4', fatal=False, m3u8_id='hls'))
else:
formats.append(traverse_obj(source, {
'url': ('file', {build_url}),
'format_id': 'label', 'format_id': 'label',
'height': ('label', {int_or_none}), 'height': ('label', {int_or_none}),
'ext': 'type', 'ext': 'type',
@ -62,7 +69,7 @@ def _real_extract(self, url):
'id': video_id, 'id': video_id,
'formats': formats, 'formats': formats,
'title': title, 'title': title,
'thumbnail': thumbnail, 'thumbnail': self._og_search_property('image', webpage, default=None) or playlist_info.get('image'),
'duration': duration, 'duration': duration,
'description': description, 'description': description,
'tags': tags, 'tags': tags,