archive
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[ie/bilibili] Support courses and interactive videos (#8343)

Browse Source 
Closes #6135, Closes #8428
Authored by: c-basalt
pull/8274/head^2
c-basalt 1 year ago committed by GitHub
parent f124fa4588
commit 9f09bdcfcb
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 463 additions and 42 deletions
Show Stats Download Patch File Download Diff File

2
yt_dlp/extractor/_extractors.py
Unescape Escape View File

@ -216,6 +216,8 @@ from .bilibili import (
BiliBiliBangumiIE,
BiliBiliBangumiSeasonIE,
BiliBiliBangumiMediaIE,
BilibiliCheeseIE,
BilibiliCheeseSeasonIE,
BiliBiliSearchIE,
BilibiliCategoryIE,
BilibiliAudioIE,

499
yt_dlp/extractor/bilibili.py
Unescape Escape View File

@ -2,6 +2,7 @@ import base64
import functools
import hashlib
import itertools
import json
import math
import re
import time
@ -16,9 +17,11 @@ from ..utils import (
InAdvancePagedList,
OnDemandPagedList,
bool_or_none,
clean_html,
filter_dict,
float_or_none,
format_field,
get_element_by_class,
int_or_none,
join_nonempty,
make_archive_id,
@ -88,6 +91,12 @@ class BilibiliBaseIE(InfoExtractor):
return formats
def _download_playinfo(self, video_id, cid):
return self._download_json(
'https://api.bilibili.com/x/player/playurl', video_id,
query={'bvid': video_id, 'cid': cid, 'fnval': 4048},
note=f'Downloading video formats for cid {cid}')['data']
def json2srt(self, json_data):
srt_data = ''
for idx, line in enumerate(json_data.get('body') or []):
@ -96,7 +105,7 @@ class BilibiliBaseIE(InfoExtractor):
f'{line["content"]}\n\n')
return srt_data
def _get_subtitles(self, video_id, aid, cid):
def _get_subtitles(self, video_id, cid, aid=None):
subtitles = {
'danmaku': [{
'ext': 'xml',
@ -104,8 +113,15 @@ class BilibiliBaseIE(InfoExtractor):
}]
}
video_info_json = self._download_json(f'https://api.bilibili.com/x/player/v2?aid={aid}&cid={cid}', video_id)
for s in traverse_obj(video_info_json, ('data', 'subtitle', 'subtitles', ...)):
subtitle_info = traverse_obj(self._download_json(
'https://api.bilibili.com/x/player/v2', video_id,
query={'aid': aid, 'cid': cid} if aid else {'bvid': video_id, 'cid': cid},
note=f'Extracting subtitle info {cid}'), ('data', 'subtitle'))
subs_list = traverse_obj(subtitle_info, ('subtitles', lambda _, v: v['subtitle_url'] and v['lan']))
if not subs_list and traverse_obj(subtitle_info, 'allow_submit'):
if not self._get_cookies('https://api.bilibili.com').get('SESSDATA'): # no login session cookie
self.report_warning(f'CC subtitles (if any) are only visible when logged in. {self._login_hint()}', only_once=True)
for s in subs_list:
subtitles.setdefault(s['lan'], []).append({
'ext': 'srt',
'data': self.json2srt(self._download_json(s['subtitle_url'], video_id))
@ -155,7 +171,54 @@ class BilibiliBaseIE(InfoExtractor):
for entry in traverse_obj(season_info, (
'result', 'main_section', 'episodes',
lambda _, v: url_or_none(v['share_url']) and v['id'])):
yield self.url_result(entry['share_url'], BiliBiliBangumiIE, f'ep{entry["id"]}')
yield self.url_result(entry['share_url'], BiliBiliBangumiIE, str_or_none(entry.get('id')))
def _get_divisions(self, video_id, graph_version, edges, edge_id, cid_edges=None):
cid_edges = cid_edges or {}
division_data = self._download_json(
'https://api.bilibili.com/x/stein/edgeinfo_v2', video_id,
query={'graph_version': graph_version, 'edge_id': edge_id, 'bvid': video_id},
note=f'Extracting divisions from edge {edge_id}')
edges.setdefault(edge_id, {}).update(
traverse_obj(division_data, ('data', 'story_list', lambda _, v: v['edge_id'] == edge_id, {
'title': ('title', {str}),
'cid': ('cid', {int_or_none}),
}), get_all=False))
edges[edge_id].update(traverse_obj(division_data, ('data', {
'title': ('title', {str}),
'choices': ('edges', 'questions', ..., 'choices', ..., {
'edge_id': ('id', {int_or_none}),
'cid': ('cid', {int_or_none}),
'text': ('option', {str}),
}),
})))
# use dict to combine edges that use the same video section (same cid)
cid_edges.setdefault(edges[edge_id]['cid'], {})[edge_id] = edges[edge_id]
for choice in traverse_obj(edges, (edge_id, 'choices', ...)):
if choice['edge_id'] not in edges:
edges[choice['edge_id']] = {'cid': choice['cid']}
self._get_divisions(video_id, graph_version, edges, choice['edge_id'], cid_edges=cid_edges)
return cid_edges
def _get_interactive_entries(self, video_id, cid, metainfo):
graph_version = traverse_obj(
self._download_json(
'https://api.bilibili.com/x/player/wbi/v2', video_id,
'Extracting graph version', query={'bvid': video_id, 'cid': cid}),
('data', 'interaction', 'graph_version', {int_or_none}))
cid_edges = self._get_divisions(video_id, graph_version, {1: {'cid': cid}}, 1)
for cid, edges in cid_edges.items():
play_info = self._download_playinfo(video_id, cid)
yield {
**metainfo,
'id': f'{video_id}_{cid}',
'title': f'{metainfo.get("title")} - {list(edges.values())[0].get("title")}',
'formats': self.extract_formats(play_info),
'description': f'{json.dumps(edges, ensure_ascii=False)}\n{metainfo.get("description", "")}',
'duration': float_or_none(play_info.get('timelength'), scale=1000),
'subtitles': self.extract_subtitles(video_id, cid),
}
class BiliBiliIE(BilibiliBaseIE):
@ -180,7 +243,7 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
},
}, {
# old av URL version
'note': 'old av URL version',
'url': 'http://www.bilibili.com/video/av1074402/',
'info_dict': {
'thumbnail': r're:^https?://.*\.(jpg|jpeg)$',
@ -212,7 +275,7 @@ class BiliBiliIE(BilibiliBaseIE):
'id': 'BV1bK411W797_p1',
'ext': 'mp4',
'title': '物语中的人物是如何吐槽自己的OP的 p01 Staple Stable/战场原+羽川',
'tags': 'count:11',
'tags': 'count:10',
'timestamp': 1589601697,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'uploader': '打牌还是打桩',
@ -232,7 +295,7 @@ class BiliBiliIE(BilibiliBaseIE):
'id': 'BV1bK411W797_p1',
'ext': 'mp4',
'title': '物语中的人物是如何吐槽自己的OP的 p01 Staple Stable/战场原+羽川',
'tags': 'count:11',
'tags': 'count:10',
'timestamp': 1589601697,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'uploader': '打牌还是打桩',
@ -343,18 +406,120 @@ class BiliBiliIE(BilibiliBaseIE):
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
'params': {'skip_download': True},
}, {
'note': 'interactive/split-path video',
'url': 'https://www.bilibili.com/video/BV1af4y1H7ga/',
'info_dict': {
'id': 'BV1af4y1H7ga',
'title': '【互动游戏】花了大半年时间做的自我介绍~请查收！！',
'timestamp': 1630500414,
'upload_date': '20210901',
'description': 'md5:01113e39ab06e28042d74ac356a08786',
'tags': list,
'uploader': '钉宫妮妮Ninico',
'duration': 1503,
'uploader_id': '8881297',
'comment_count': int,
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
'playlist_count': 33,
'playlist': [{
'info_dict': {
'id': 'BV1af4y1H7ga_400950101',
'ext': 'mp4',
'title': '【互动游戏】花了大半年时间做的自我介绍~请查收！！ - 听见猫猫叫~',
'timestamp': 1630500414,
'upload_date': '20210901',
'description': 'md5:db66ac7a2813a94b8291dbce990cc5b2',
'tags': list,
'uploader': '钉宫妮妮Ninico',
'duration': 11.605,
'uploader_id': '8881297',
'comment_count': int,
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}],
}, {
'note': '301 redirect to bangumi link',
'url': 'https://www.bilibili.com/video/BV1TE411f7f1',
'info_dict': {
'id': '288525',
'title': '李永乐老师 钱学森弹道和乘波体飞行器是什么？',
'ext': 'mp4',
'series': '我和我的祖国',
'series_id': '4780',
'season': '幕后纪实',
'season_id': '28609',
'season_number': 1,
'episode': '钱学森弹道和乘波体飞行器是什么？',
'episode_id': '288525',
'episode_number': 105,
'duration': 1183.957,
'timestamp': 1571648124,
'upload_date': '20191021',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}, {
'url': 'https://www.bilibili.com/video/BV1jL41167ZG/',
'info_dict': {
'id': 'BV1jL41167ZG',
'title': '一场大火引发的离奇死亡！古典推理经典短篇集《不可能犯罪诊断书》！',
'ext': 'mp4',
},
'skip': 'supporter-only video',
}, {
'url': 'https://www.bilibili.com/video/BV1Ks411f7aQ/',
'info_dict': {
'id': 'BV1Ks411f7aQ',
'title': '【BD1080P】狼与香辛料I【华盟】',
'ext': 'mp4',
},
'skip': 'login required',
}, {
'url': 'https://www.bilibili.com/video/BV1GJ411x7h7/',
'info_dict': {
'id': 'BV1GJ411x7h7',
'title': '【官方 MV】Never Gonna Give You Up - Rick Astley',
'ext': 'mp4',
},
'skip': 'geo-restricted',
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
webpage, urlh = self._download_webpage_handle(url, video_id)
if not self._match_valid_url(urlh.url):
return self.url_result(urlh.url)
initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)
is_festival = 'videoData' not in initial_state
if is_festival:
video_data = initial_state['videoInfo']
else:
play_info = self._search_json(r'window\.__playinfo__\s*=', webpage, 'play info', video_id)['data']
play_info_obj = self._search_json(
r'window\.__playinfo__\s*=', webpage, 'play info', video_id, fatal=False)
if not play_info_obj:
if traverse_obj(initial_state, ('error', 'trueCode')) == -403:
self.raise_login_required()
if traverse_obj(initial_state, ('error', 'trueCode')) == -404:
raise ExtractorError(
'This video may be deleted or geo-restricted. '
'You might want to try a VPN or a proxy server (with --proxy)', expected=True)
play_info = traverse_obj(play_info_obj, ('data', {dict}))
if not play_info:
if traverse_obj(play_info_obj, 'code') == 87007:
toast = get_element_by_class('tips-toast', webpage) or ''
msg = clean_html(
f'{get_element_by_class("belongs-to", toast) or ""}，'
+ (get_element_by_class('level', toast) or ''))
raise ExtractorError(
f'This is a supporter-only video: {msg}. {self._login_hint()}', expected=True)
raise ExtractorError('Failed to extract play info')
video_data = initial_state['videoData']
video_id, title = video_data['bvid'], video_data.get('title')
@ -385,10 +550,7 @@ class BiliBiliIE(BilibiliBaseIE):
festival_info = {}
if is_festival:
play_info = self._download_json(
'https://api.bilibili.com/x/player/playurl', video_id,
query={'bvid': video_id, 'cid': cid, 'fnval': 4048},
note='Extracting festival video formats')['data']
play_info = self._download_playinfo(video_id, cid)
festival_info = traverse_obj(initial_state, {
'uploader': ('videoInfo', 'upName'),
@ -397,7 +559,7 @@ class BiliBiliIE(BilibiliBaseIE):
'thumbnail': ('sectionEpisodes', lambda _, v: v['bvid'] == video_id, 'cover'),
}, get_all=False)
return {
metainfo = {
**traverse_obj(initial_state, {
'uploader': ('upData', 'name'),
'uploader_id': ('upData', 'mid', {str_or_none}),
@ -413,28 +575,59 @@ class BiliBiliIE(BilibiliBaseIE):
'comment_count': ('stat', 'reply', {int_or_none}),
}, get_all=False),
'id': f'{video_id}{format_field(part_id, None, "_p%d")}',
'formats': self.extract_formats(play_info),
'_old_archive_ids': [make_archive_id(self, old_video_id)] if old_video_id else None,
'title': title,
'http_headers': {'Referer': url},
}
is_interactive = traverse_obj(video_data, ('rights', 'is_stein_gate'))
if is_interactive:
return self.playlist_result(
self._get_interactive_entries(video_id, cid, metainfo), **metainfo, **{
'duration': traverse_obj(initial_state, ('videoData', 'duration', {int_or_none})),
'__post_extractor': self.extract_comments(aid),
})
else:
return {
**metainfo,
'duration': float_or_none(play_info.get('timelength'), scale=1000),
'chapters': self._get_chapters(aid, cid),
'subtitles': self.extract_subtitles(video_id, aid, cid),
'subtitles': self.extract_subtitles(video_id, cid),
'formats': self.extract_formats(play_info),
'__post_extractor': self.extract_comments(aid),
'http_headers': {'Referer': url},
}
class BiliBiliBangumiIE(BilibiliBaseIE):
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/bangumi/play/(?P<id>ep\d+)'
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/bangumi/play/ep(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.bilibili.com/bangumi/play/ep21495/',
'info_dict': {
'id': '21495',
'ext': 'mp4',
'series': '悠久之翼',
'series_id': '774',
'season': '第二季',
'season_id': '1182',
'season_number': 2,
'episode': 'forever／ef',
'episode_id': '21495',
'episode_number': 12,
'title': '12 forever／ef',
'duration': 1420.791,
'timestamp': 1320412200,
'upload_date': '20111104',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}, {
'url': 'https://www.bilibili.com/bangumi/play/ep267851',
'info_dict': {
'id': '267851',
'ext': 'mp4',
'series': '鬼灭之刃',
'series_id': '4358',
'season': '鬼灭之刃',
'season': '立志篇',
'season_id': '26801',
'season_number': 1,
'episode': '残酷',
@ -446,13 +639,32 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
'upload_date': '20190406',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$'
},
'skip': 'According to the copyright owner\'s request, you may only watch the video after you are premium member.'
'skip': 'Geo-restricted',
}, {
'note': 'a making-of which falls outside main section',
'url': 'https://www.bilibili.com/bangumi/play/ep345120',
'info_dict': {
'id': '345120',
'ext': 'mp4',
'series': '鬼灭之刃',
'series_id': '4358',
'season': '立志篇',
'season_id': '26801',
'season_number': 1,
'episode': '炭治郎篇',
'episode_id': '345120',
'episode_number': 27,
'title': '#1 炭治郎篇',
'duration': 1922.129,
'timestamp': 1602853860,
'upload_date': '20201016',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$'
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
episode_id = video_id[2:]
webpage = self._download_webpage(url, video_id)
episode_id = self._match_id(url)
webpage = self._download_webpage(url, episode_id)
if '您所在的地区无法观看本片' in webpage:
raise GeoRestrictedError('This video is restricted')
@ -461,7 +673,7 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
headers = {'Referer': url, **self.geo_verification_headers()}
play_info = self._download_json(
'https://api.bilibili.com/pgc/player/web/v2/playurl', video_id,
'https://api.bilibili.com/pgc/player/web/v2/playurl', episode_id,
'Extracting episode', query={'fnval': '4048', 'ep_id': episode_id},
headers=headers)
premium_only = play_info.get('code') == -10403
@ -472,40 +684,43 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
self.raise_login_required('This video is for premium members only')
bangumi_info = self._download_json(
'https://api.bilibili.com/pgc/view/web/season', video_id, 'Get episode details',
'https://api.bilibili.com/pgc/view/web/season', episode_id, 'Get episode details',
query={'ep_id': episode_id}, headers=headers)['result']
episode_number, episode_info = next((
(idx, ep) for idx, ep in enumerate(traverse_obj(
bangumi_info, ('episodes', ..., {dict})), 1)
bangumi_info, (('episodes', ('section', ..., 'episodes')), ..., {dict})), 1)
if str_or_none(ep.get('id')) == episode_id), (1, {}))
season_id = bangumi_info.get('season_id')
season_number = season_id and next((
idx + 1 for idx, e in enumerate(
season_number, season_title = season_id and next((
(idx + 1, e.get('season_title')) for idx, e in enumerate(
traverse_obj(bangumi_info, ('seasons', ...)))
if e.get('season_id') == season_id
), None)
), (None, None))
aid = episode_info.get('aid')
return {
'id': video_id,
'id': episode_id,
'formats': formats,
**traverse_obj(bangumi_info, {
'series': ('series', 'series_title', {str}),
'series_id': ('series', 'series_id', {str_or_none}),
'thumbnail': ('square_cover', {url_or_none}),
}),
'title': join_nonempty('title', 'long_title', delim=' ', from_dict=episode_info),
'episode': episode_info.get('long_title'),
**traverse_obj(episode_info, {
'episode': ('long_title', {str}),
'episode_number': ('title', {int_or_none}, {lambda x: x or episode_number}),
'timestamp': ('pub_time', {int_or_none}),
'title': {lambda v: v and join_nonempty('title', 'long_title', delim=' ', from_dict=v)},
}),
'episode_id': episode_id,
'episode_number': int_or_none(episode_info.get('title')) or episode_number,
'season': str_or_none(season_title),
'season_id': str_or_none(season_id),
'season_number': season_number,
'timestamp': int_or_none(episode_info.get('pub_time')),
'duration': float_or_none(play_info.get('timelength'), scale=1000),
'subtitles': self.extract_subtitles(video_id, aid, episode_info.get('cid')),
'subtitles': self.extract_subtitles(episode_id, episode_info.get('cid'), aid=aid),
'__post_extractor': self.extract_comments(aid),
'http_headers': headers,
}
@ -517,17 +732,53 @@ class BiliBiliBangumiMediaIE(BilibiliBaseIE):
'url': 'https://www.bilibili.com/bangumi/media/md24097891',
'info_dict': {
'id': '24097891',
'title': 'CAROLE & TUESDAY',
'description': 'md5:42417ad33d1eaa1c93bfd2dd1626b829',
},
'playlist_mincount': 25,
}, {
'url': 'https://www.bilibili.com/bangumi/media/md1565/',
'info_dict': {
'id': '1565',
'title': '攻壳机动队 S.A.C. 2nd GIG',
'description': 'md5:46cac00bafd645b97f4d6df616fc576d',
},
'playlist_count': 26,
'playlist': [{
'info_dict': {
'id': '68540',
'ext': 'mp4',
'series': '攻壳机动队',
'series_id': '1077',
'season': '第二季',
'season_id': '1565',
'season_number': 2,
'episode': '再启动 REEMBODY',
'episode_id': '68540',
'episode_number': 1,
'title': '1 再启动 REEMBODY',
'duration': 1525.777,
'timestamp': 1425074413,
'upload_date': '20150227',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$'
},
}],
}]
def _real_extract(self, url):
media_id = self._match_id(url)
webpage = self._download_webpage(url, media_id)
ss_id = self._search_json(
r'window\.__INITIAL_STATE__\s*=', webpage, 'initial_state', media_id)['mediaInfo']['season_id']
return self.playlist_result(self._get_episodes_from_season(ss_id, url), media_id)
initial_state = self._search_json(
r'window\.__INITIAL_STATE__\s*=', webpage, 'initial_state', media_id)
ss_id = initial_state['mediaInfo']['season_id']
return self.playlist_result(
self._get_episodes_from_season(ss_id, url), media_id,
**traverse_obj(initial_state, ('mediaInfo', {
'title': ('title', {str}),
'description': ('evaluate', {str}),
})))
class BiliBiliBangumiSeasonIE(BilibiliBaseIE):
@ -535,15 +786,183 @@ class BiliBiliBangumiSeasonIE(BilibiliBaseIE):
_TESTS = [{
'url': 'https://www.bilibili.com/bangumi/play/ss26801',
'info_dict': {
'id': '26801'
'id': '26801',
'title': '鬼灭之刃',
'description': 'md5:e2cc9848b6f69be6db79fc2a82d9661b',
},
'playlist_mincount': 26
}, {
'url': 'https://www.bilibili.com/bangumi/play/ss2251',
'info_dict': {
'id': '2251',
'title': '玲音',
'description': 'md5:1fd40e3df4c08d4d9d89a6a34844bdc4',
},
'playlist_count': 13,
'playlist': [{
'info_dict': {
'id': '50188',
'ext': 'mp4',
'series': '玲音',
'series_id': '1526',
'season': 'TV',
'season_id': '2251',
'season_number': 1,
'episode': 'WEIRD',
'episode_id': '50188',
'episode_number': 1,
'title': '1 WEIRD',
'duration': 1436.992,
'timestamp': 1343185080,
'upload_date': '20120725',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$'
},
}],
}]
def _real_extract(self, url):
ss_id = self._match_id(url)
webpage = self._download_webpage(url, ss_id)
metainfo = traverse_obj(
self._search_json(r'<script[^>]+type="application/ld\+json"[^>]*>', webpage, 'info', ss_id),
('itemListElement', ..., {
'title': ('name', {str}),
'description': ('description', {str}),
}), get_all=False)
return self.playlist_result(self._get_episodes_from_season(ss_id, url), ss_id, **metainfo)
return self.playlist_result(self._get_episodes_from_season(ss_id, url), ss_id)
class BilibiliCheeseBaseIE(BilibiliBaseIE):
_HEADERS = {'Referer': 'https://www.bilibili.com/'}
def _extract_episode(self, season_info, ep_id):
episode_info = traverse_obj(season_info, (
'episodes', lambda _, v: v['id'] == int(ep_id)), get_all=False)
aid, cid = episode_info['aid'], episode_info['cid']
if traverse_obj(episode_info, 'ep_status') == -1:
raise ExtractorError('This course episode is not yet available.', expected=True)
if not traverse_obj(episode_info, 'playable'):
self.raise_login_required('You need to purchase the course to download this episode')
play_info = self._download_json(
'https://api.bilibili.com/pugv/player/web/playurl', ep_id,
query={'avid': aid, 'cid': cid, 'ep_id': ep_id, 'fnval': 16, 'fourk': 1},
headers=self._HEADERS, note='Downloading playinfo')['data']
return {
'id': str_or_none(ep_id),
'episode_id': str_or_none(ep_id),
'formats': self.extract_formats(play_info),
'extractor_key': BilibiliCheeseIE.ie_key(),
'extractor': BilibiliCheeseIE.IE_NAME,
'webpage_url': f'https://www.bilibili.com/cheese/play/ep{ep_id}',
**traverse_obj(episode_info, {
'episode': ('title', {str}),
'title': {lambda v: v and join_nonempty('index', 'title', delim=' - ', from_dict=v)},
'alt_title': ('subtitle', {str}),
'duration': ('duration', {int_or_none}),
'episode_number': ('index', {int_or_none}),
'thumbnail': ('cover', {url_or_none}),
'timestamp': ('release_date', {int_or_none}),
'view_count': ('play', {int_or_none}),
}),
**traverse_obj(season_info, {
'uploader': ('up_info', 'uname', {str}),
'uploader_id': ('up_info', 'mid', {str_or_none}),
}),
'subtitles': self.extract_subtitles(ep_id, cid, aid=aid),
'__post_extractor': self.extract_comments(aid),
'http_headers': self._HEADERS,
}
def _download_season_info(self, query_key, video_id):
return self._download_json(
f'https://api.bilibili.com/pugv/view/web/season?{query_key}={video_id}', video_id,
headers=self._HEADERS, note='Downloading season info')['data']
class BilibiliCheeseIE(BilibiliCheeseBaseIE):
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/cheese/play/ep(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.bilibili.com/cheese/play/ep229832',
'info_dict': {
'id': '229832',
'ext': 'mp4',
'title': '1 - 课程先导片',
'alt_title': '视频课 · 3分41秒',
'uploader': '马督工',
'uploader_id': '316568752',
'episode': '课程先导片',
'episode_id': '229832',
'episode_number': 1,
'duration': 221,
'timestamp': 1695549606,
'upload_date': '20230924',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'view_count': int,
}
}]
def _real_extract(self, url):
ep_id = self._match_id(url)
return self._extract_episode(self._download_season_info('ep_id', ep_id), ep_id)
class BilibiliCheeseSeasonIE(BilibiliCheeseBaseIE):
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/cheese/play/ss(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.bilibili.com/cheese/play/ss5918',
'info_dict': {
'id': '5918',
'title': '【限时五折】新闻系学不到：马督工教你做自媒体',
'description': '帮普通人建立世界模型，降低人与人的沟通门槛',
},
'playlist': [{
'info_dict': {
'id': '229832',
'ext': 'mp4',
'title': '1 - 课程先导片',
'alt_title': '视频课 · 3分41秒',
'uploader': '马督工',
'uploader_id': '316568752',
'episode': '课程先导片',
'episode_id': '229832',
'episode_number': 1,
'duration': 221,
'timestamp': 1695549606,
'upload_date': '20230924',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'view_count': int,
}
}],
'params': {'playlist_items': '1'},
}, {
'url': 'https://www.bilibili.com/cheese/play/ss5918',
'info_dict': {
'id': '5918',
'title': '【限时五折】新闻系学不到：马督工教你做自媒体',
'description': '帮普通人建立世界模型，降低人与人的沟通门槛',
},
'playlist_mincount': 5,
'skip': 'paid video in list',
}]
def _get_cheese_entries(self, season_info):
for ep_id in traverse_obj(season_info, ('episodes', lambda _, v: v['episode_can_view'], 'id')):
yield self._extract_episode(season_info, ep_id)
def _real_extract(self, url):
season_id = self._match_id(url)
season_info = self._download_season_info('season_id', season_id)
return self.playlist_result(
self._get_cheese_entries(season_info), season_id,
**traverse_obj(season_info, {
'title': ('title', {str}),
'description': ('subtitle', {str}),
}))
class BilibiliSpaceBaseIE(InfoExtractor):

Write Preview
Loading…
Cancel
Save