pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2025-01-10 13:30:09 +09:00
Code Issues Projects Releases Wiki Activity

Merge 05f85f886b into c5098961b0

Browse Source
This commit is contained in:
Deleted user 2024-08-21 22:21:51 -04:00 committed by GitHub
commit b17f440484
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 47 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
youtube_dl/extractor/weibo.py
View File

@ -14,6 +14,7 @@ from ..compat import (
from ..utils import ( from ..utils import (
js_to_json, js_to_json,
strip_jsonp, strip_jsonp,
url_or_none,
urlencode_postdata, urlencode_postdata,
) )
@ -26,6 +27,7 @@ class WeiboIE(InfoExtractor):
'id': 'Fp6RGfbff', 'id': 'Fp6RGfbff',
'ext': 'mp4', 'ext': 'mp4',
'title': 'You should have servants to massage you,... 来自Hosico_猫 - 微博', 'title': 'You should have servants to massage you,... 来自Hosico_猫 - 微博',
'uploader': 'Hosico_猫',
} }
} }
@ -74,13 +76,34 @@ class WeiboIE(InfoExtractor):
url, video_id, note='Revisiting webpage') url, video_id, note='Revisiting webpage')
title = self._html_search_regex( title = self._html_search_regex(
r'<title>(.+?)</title>', webpage, 'title') r'<title>(.+?)</title>', webpage, 'title', default=None, flags=re.DOTALL) or \
self._search_regex(
r'CONFIG\[\'title_value\'\]=\'(.+?)\';', webpage, 'title')
video_formats = compat_parse_qs(self._search_regex( video_formats = compat_parse_qs(self._search_regex(
r'video-sources=\\\"(.+?)\"', webpage, 'video_sources')) r'video-sources=\\\"(.+?)\"', webpage, 'video_sources'))
formats = [] formats = []
supported_resolutions = (480, 720) supported_resolutions = ('360p', '480p', '720p', '1080p', '1080p+')
quality_list = video_formats.get('quality_label_list')
if quality_list and isinstance(quality_list, list):
quality_list = self._parse_json(quality_list[0], video_id, fatal=False)
if quality_list:
for res in supported_resolutions:
vid_urls = [q.get('url') for q in quality_list
if q.get('quality_label', '').lower() == res]
if not vid_urls:
continue
vid_url = url_or_none(vid_urls[0])
if not vid_url:
continue
formats.append({
'url': vid_url,
'resolution': res,
})
if not formats:
supported_resolutions = (480, 720, 1080)
for res in supported_resolutions: for res in supported_resolutions:
vid_urls = video_formats.get(compat_str(res)) vid_urls = video_formats.get(compat_str(res))
if not vid_urls or not isinstance(vid_urls, list): if not vid_urls or not isinstance(vid_urls, list):
@ -94,14 +117,24 @@ class WeiboIE(InfoExtractor):
self._sort_formats(formats) self._sort_formats(formats)
uploader = self._og_search_property( uploader = self._search_regex(
'nick-name', webpage, 'uploader', default=None) [r'nick-name=\\\"(.+?)\\\"', r'CONFIG\[\'onick\'\]=\'(.+?)\';'],
webpage, 'uploader', default=None)
thumbnail = None
action_data = compat_parse_qs(self._search_regex(
r'action-data=\\\"([^"]+?cover_img=[^"]+?)\\\"', webpage, 'thumbnail', default=''))
if action_data:
cover_imgs = action_data.get('cover_img')
if cover_imgs and isinstance(cover_imgs, list):
thumbnail = url_or_none(cover_imgs[0])
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'uploader': uploader, 'uploader': uploader,
'formats': formats 'formats': formats,
'thumbnail': thumbnail,
} }