github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-14 20:38:11 -05:00
Code Issues Projects Releases Packages Wiki Activity

[ie/Bandcamp:user] Fix extraction (#10328)

Browse source 
Authored by: quad, bashonly

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>
This commit is contained in:
Scott Robinson 2024-09-14 09:02:54 +10:00 committed by GitHub
parent 409f8e9e3b
commit 5d0176547f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 17 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
yt_dlp/extractor/bandcamp.py
View file

@ -1,3 +1,5 @@
import functools
import json
import random
import re
import time
@ -6,7 +8,9 @@
from ..utils import (
KNOWN_EXTENSIONS,
ExtractorError,
extract_attributes,
float_or_none,
get_element_html_by_id,
int_or_none,
parse_filesize,
str_or_none,
@ -17,6 +21,7 @@
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj
class BandcampIE(InfoExtractor):
@ -459,7 +464,7 @@ class BandcampUserIE(InfoExtractor):
},
}, {
'url': 'https://coldworldofficial.bandcamp.com/music',
'playlist_mincount': 10,
'playlist_mincount': 7,
'info_dict': {
'id': 'coldworldofficial',
'title': 'Discography of coldworldofficial',
@ -473,12 +478,19 @@ class BandcampUserIE(InfoExtractor):
},
}]
def _yield_items(self, webpage):
yield from (
re.findall(r'<li data-item-id=["\'][^>]+>\s*<a href=["\'](?![^"\'/]*?/merch)([^"\']+)', webpage)
or re.findall(r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage))
yield from traverse_obj(webpage, (
{functools.partial(get_element_html_by_id, 'music-grid')}, {extract_attributes},
'data-client-items', {json.loads}, ..., 'page_url', {str}))
def _real_extract(self, url):
uploader = self._match_id(url)
webpage = self._download_webpage(url, uploader)
discography_data = (re.findall(r'<li data-item-id=["\'][^>]+>\s*<a href=["\'](?![^"\'/]*?/merch)([^"\']+)', webpage)
or re.findall(r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage))
return self.playlist_from_matches(
discography_data, uploader, f'Discography of {uploader}', getter=lambda x: urljoin(url, x))
self._yield_items(webpage), uploader, f'Discography of {uploader}',
getter=functools.partial(urljoin, url))