mirrors/yt-dlp
1
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-01-29 01:27:52 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

[ie/XiaoHongShu] Extract more formats (#12147)

Browse Source 
Authored by: seproDev
This commit is contained in:
sepro 2025-01-20 19:55:30 +01:00 committed by GitHub
parent af2c821d74
commit f9f24ae376
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 20 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
yt_dlp/extractor/xiaohongshu.py
View File

@ -5,6 +5,7 @@
int_or_none, int_or_none,
js_to_json, js_to_json,
url_or_none, url_or_none,
urlhandle_detect_ext,
) )
from ..utils.traversal import traverse_obj from ..utils.traversal import traverse_obj
@ -46,7 +47,7 @@ def _real_extract(self, url):
r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', display_id, transform_source=js_to_json) r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', display_id, transform_source=js_to_json)
note_info = traverse_obj(initial_state, ('note', 'noteDetailMap', display_id, 'note')) note_info = traverse_obj(initial_state, ('note', 'noteDetailMap', display_id, 'note'))
video_info = traverse_obj(note_info, ('video', 'media', 'stream', ('h264', 'av1', 'h265'), ...)) video_info = traverse_obj(note_info, ('video', 'media', 'stream', ..., ...))
formats = [] formats = []
for info in video_info: for info in video_info:
@ -56,18 +57,32 @@ def _real_extract(self, url):
'height': ('height', {int_or_none}), 'height': ('height', {int_or_none}),
'vcodec': ('videoCodec', {str}), 'vcodec': ('videoCodec', {str}),
'acodec': ('audioCodec', {str}), 'acodec': ('audioCodec', {str}),
'abr': ('audioBitrate', {int_or_none}), 'abr': ('audioBitrate', {int_or_none(scale=1000)}),
'vbr': ('videoBitrate', {int_or_none}), 'vbr': ('videoBitrate', {int_or_none(scale=1000)}),
'audio_channels': ('audioChannels', {int_or_none}), 'audio_channels': ('audioChannels', {int_or_none}),
'tbr': ('avgBitrate', {int_or_none}), 'tbr': ('avgBitrate', {int_or_none(scale=1000)}),
'format': ('qualityType', {str}), 'format': ('qualityType', {str}),
'filesize': ('size', {int_or_none}), 'filesize': ('size', {int_or_none}),
'duration': ('duration', {float_or_none(scale=1000)}), 'duration': ('duration', {float_or_none(scale=1000)}),
}) })
formats.extend(traverse_obj(info, (('mediaUrl', ('backupUrls', ...)), { formats.extend(traverse_obj(info, (('masterUrl', ('backupUrls', ...)), {
lambda u: url_or_none(u) and {'url': u, **format_info}}))) lambda u: url_or_none(u) and {'url': u, **format_info}})))
if origin_key := traverse_obj(note_info, ('video', 'consumer', 'originVideoKey', {str})):
# Not using a head request because of false negatives
urlh = self._request_webpage(
f'https://sns-video-bd.xhscdn.com/{origin_key}', display_id,
'Checking original video availability', 'Original video is not available', fatal=False)
if urlh:
formats.append({
'format_id': 'direct',
'ext': urlhandle_detect_ext(urlh, default='mp4'),
'filesize': int_or_none(urlh.get_header('Content-Length')),
'url': urlh.url,
'quality': 1,
})
thumbnails = [] thumbnails = []
for image_info in traverse_obj(note_info, ('imageList', ...)): for image_info in traverse_obj(note_info, ('imageList', ...)):
thumbnail_info = traverse_obj(image_info, { thumbnail_info = traverse_obj(image_info, {