etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-25 02:45:12 +00:00
Code Issues Projects Releases Wiki Activity

[ie/tiktok:collection] Add extractor (#9986)

Browse source 
Closes #9984
Authored by: imanoreotwe, bashonly
This commit is contained in:
imanoreotwe 2024-05-26 15:26:30 -06:00 committed by GitHub
parent 347f13dd9b
commit 119d41f270
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 59 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
yt_dlp/extractor/_extractors.py
View file

@ -2074,6 +2074,7 @@
)
from .tiktok import (
DouyinIE,
TikTokCollectionIE,
TikTokEffectIE,
TikTokIE,
TikTokLiveIE,

58
yt_dlp/extractor/tiktok.py
View file

@ -1117,6 +1117,64 @@ def _real_extract(self, url):
return self.playlist_result(self._entries(tag_id, display_id), tag_id, display_id)
class TikTokCollectionIE(TikTokBaseIE):
IE_NAME = 'tiktok:collection'
_VALID_URL = r'https?://www\.tiktok\.com/@(?P<user_id>[\w.-]+)/collection/(?P<title>[^/?#]+)-(?P<id>\d+)/?(?:[?#]|$)'
_TESTS = [{
# playlist should have exactly 9 videos
'url': 'https://www.tiktok.com/@imanoreotwe/collection/count-test-7371330159376370462',
'info_dict': {
'id': '7371330159376370462',
'title': 'imanoreotwe-count-test'
},
'playlist_count': 9
}, {
# tests returning multiple pages of a large collection
'url': 'https://www.tiktok.com/@imanoreotwe/collection/%F0%9F%98%82-7111887189571160875',
'info_dict': {
'id': '7111887189571160875',
'title': 'imanoreotwe-%F0%9F%98%82'
},
'playlist_mincount': 100
}]
_API_BASE_URL = 'https://www.tiktok.com/api/collection/item_list/'
_PAGE_COUNT = 30
def _build_web_query(self, collection_id, cursor):
return {
'aid': '1988',
'collectionId': collection_id,
'count': self._PAGE_COUNT,
'cursor': cursor,
'sourceType': '113',
}
def _entries(self, collection_id):
cursor = 0
for page in itertools.count(1):
response = self._download_json(
self._API_BASE_URL, collection_id, f'Downloading page {page}',
query=self._build_web_query(collection_id, cursor))
for video in traverse_obj(response, ('itemList', lambda _, v: v['id'])):
video_id = video['id']
author = traverse_obj(video, ('author', ('uniqueId', 'secUid', 'id'), {str}, any)) or '_'
webpage_url = self._create_url(author, video_id)
yield self.url_result(
webpage_url, TikTokIE,
**self._parse_aweme_video_web(video, webpage_url, video_id, extract_flat=True))
if not traverse_obj(response, 'hasMore'):
break
cursor += self._PAGE_COUNT
def _real_extract(self, url):
collection_id, title, user_name = self._match_valid_url(url).group('id', 'title', 'user_id')
return self.playlist_result(
self._entries(collection_id), collection_id, '-'.join((user_name, title)))
class DouyinIE(TikTokBaseIE):
_VALID_URL = r'https?://(?:www\.)?douyin\.com/video/(?P<id>[0-9]+)'
_TESTS = [{