mirrors/yt-dlp
1
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-01-30 01:57:54 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

[ie/bilibili] Support space video list extraction without login (#12089)

Browse Source 
Closes #12007
Authored by: grqz
This commit is contained in:
N/Ame 2025-01-26 13:56:36 +13:00 committed by GitHub
parent bb69f5dab7
commit 78912ed9c8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
yt_dlp/extractor/bilibili.py
View File

@ -4,7 +4,9 @@
import itertools import itertools
import json import json
import math import math
import random
import re import re
import string
import time import time
import urllib.parse import urllib.parse
import uuid import uuid
@ -1178,28 +1180,26 @@ def _extract_playlist(self, fetch_page, get_metadata, get_entries):
class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE): class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE):
_VALID_URL = r'https?://space\.bilibili\.com/(?P<id>\d+)(?P<video>/video)?/?(?:[?#]|$)' _VALID_URL = r'https?://space\.bilibili\.com/(?P<id>\d+)(?P<video>(?:/upload)?/video)?/?(?:[?#]|$)'
_TESTS = [{ _TESTS = [{
'url': 'https://space.bilibili.com/3985676/video', 'url': 'https://space.bilibili.com/3985676/video',
'info_dict': { 'info_dict': {
'id': '3985676', 'id': '3985676',
}, },
'playlist_mincount': 178, 'playlist_mincount': 178,
'skip': 'login required',
}, { }, {
'url': 'https://space.bilibili.com/313580179/video', 'url': 'https://space.bilibili.com/313580179/video',
'info_dict': { 'info_dict': {
'id': '313580179', 'id': '313580179',
}, },
'playlist_mincount': 92, 'playlist_mincount': 92,
'skip': 'login required',
}] }]
def _real_extract(self, url): def _real_extract(self, url):
playlist_id, is_video_url = self._match_valid_url(url).group('id', 'video') playlist_id, is_video_url = self._match_valid_url(url).group('id', 'video')
if not is_video_url: if not is_video_url:
self.to_screen('A channel URL was given. Only the channel\'s videos will be downloaded. ' self.to_screen('A channel URL was given. Only the channel\'s videos will be downloaded. '
'To download audios, add a "/audio" to the URL') 'To download audios, add a "/upload/audio" to the URL')
def fetch_page(page_idx): def fetch_page(page_idx):
query = { query = {
@ -1212,6 +1212,12 @@ def fetch_page(page_idx):
'ps': 30, 'ps': 30,
'tid': 0, 'tid': 0,
'web_location': 1550101, 'web_location': 1550101,
'dm_img_list': '[]',
'dm_img_str': base64.b64encode(
''.join(random.choices(string.printable, k=random.randint(16, 64))).encode())[:-2].decode(),
'dm_cover_img_str': base64.b64encode(
''.join(random.choices(string.printable, k=random.randint(32, 128))).encode())[:-2].decode(),
'dm_img_inter': '{"ds":[],"wh":[6093,6631,31],"of":[430,760,380]}',
} }
try: try:
@ -1222,14 +1228,14 @@ def fetch_page(page_idx):
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 412: if isinstance(e.cause, HTTPError) and e.cause.status == 412:
raise ExtractorError( raise ExtractorError(
'Request is blocked by server (412), please add cookies, wait and try later.', expected=True) 'Request is blocked by server (412), please wait and try later.', expected=True)
raise raise
status_code = response['code'] status_code = response['code']
if status_code == -401: if status_code == -401:
raise ExtractorError( raise ExtractorError(
'Request is blocked by server (401), please add cookies, wait and try later.', expected=True) 'Request is blocked by server (401), please wait and try later.', expected=True)
elif status_code == -352 and not self.is_logged_in: elif status_code == -352:
self.raise_login_required('Request is rejected, you need to login to access playlist') raise ExtractorError('Request is rejected by server (352)', expected=True)
elif status_code != 0: elif status_code != 0:
raise ExtractorError(f'Request failed ({status_code}): {response.get("message") or "Unknown error"}') raise ExtractorError(f'Request failed ({status_code}): {response.get("message") or "Unknown error"}')
return response['data'] return response['data']
@ -1251,9 +1257,9 @@ def get_entries(page_data):
class BilibiliSpaceAudioIE(BilibiliSpaceBaseIE): class BilibiliSpaceAudioIE(BilibiliSpaceBaseIE):
_VALID_URL = r'https?://space\.bilibili\.com/(?P<id>\d+)/audio' _VALID_URL = r'https?://space\.bilibili\.com/(?P<id>\d+)/(?:upload/)?audio'
_TESTS = [{ _TESTS = [{
'url': 'https://space.bilibili.com/313580179/audio', 'url': 'https://space.bilibili.com/313580179/upload/audio',
'info_dict': { 'info_dict': {
'id': '313580179', 'id': '313580179',
}, },
@ -1276,7 +1282,8 @@ def get_metadata(page_data):
} }
def get_entries(page_data): def get_entries(page_data):
for entry in page_data.get('data', []): # data is None when the playlist is empty
for entry in page_data.get('data') or []:
yield self.url_result(f'https://www.bilibili.com/audio/au{entry["id"]}', BilibiliAudioIE, entry['id']) yield self.url_result(f'https://www.bilibili.com/audio/au{entry["id"]}', BilibiliAudioIE, entry['id'])
metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries) metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries)