github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[Instagram] Improve thumbnail extraction (#1496)

Browse source 
Authored by: u-spec-png
This commit is contained in:
u-spec-png 2021-11-04 03:22:10 +00:00 committed by GitHub
parent a4211baff5
commit 22cd06c452
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
yt_dlp/extractor/instagram.py
View file

@ -234,7 +234,9 @@ def _real_extract(self, url):
media, lambda x: x['edge_media_to_caption']['edges'][0]['node']['text'], media, lambda x: x['edge_media_to_caption']['edges'][0]['node']['text'],
compat_str) or media.get('caption') compat_str) or media.get('caption')
title = media.get('title') title = media.get('title')
thumbnail = media.get('display_src') or media.get('display_url') display_resources = media.get('display_resources')
if not display_resources:
display_resources = [{'src': media.get('display_src')}, {'src': media.get('display_url')}]
duration = float_or_none(media.get('video_duration')) duration = float_or_none(media.get('video_duration'))
timestamp = int_or_none(media.get('taken_at_timestamp') or media.get('date')) timestamp = int_or_none(media.get('taken_at_timestamp') or media.get('date'))
uploader = try_get(media, lambda x: x['owner']['full_name']) uploader = try_get(media, lambda x: x['owner']['full_name'])
@ -252,6 +254,12 @@ def get_count(keys, kind):
comment_count = get_count( comment_count = get_count(
('preview_comment', 'to_comment', 'to_parent_comment'), 'comment') ('preview_comment', 'to_comment', 'to_parent_comment'), 'comment')
thumbnails = [{
'url': thumbnail['src'],
'width': thumbnail.get('config_width'),
'height': thumbnail.get('config_height'),
} for thumbnail in display_resources if thumbnail.get('src')]
comments = [] comments = []
for comment in try_get(media, lambda x: x['edge_media_to_parent_comment']['edges']): for comment in try_get(media, lambda x: x['edge_media_to_parent_comment']['edges']):
comment_dict = comment.get('node', {}) comment_dict = comment.get('node', {})
@ -326,7 +334,7 @@ def get_count(keys, kind):
'title': title or 'Video by %s' % uploader_id, 'title': title or 'Video by %s' % uploader_id,
'description': description, 'description': description,
'duration': duration, 'duration': duration,
'thumbnail': thumbnail, 'thumbnails': thumbnails,
'timestamp': timestamp, 'timestamp': timestamp,
'uploader_id': uploader_id, 'uploader_id': uploader_id,
'uploader': uploader, 'uploader': uploader,