]>
Commit | Line | Data |
---|---|---|
1 | import base64 | |
2 | import functools | |
3 | import hashlib | |
4 | import itertools | |
5 | import json | |
6 | import math | |
7 | import re | |
8 | import time | |
9 | import urllib.parse | |
10 | import uuid | |
11 | ||
12 | from .common import InfoExtractor, SearchInfoExtractor | |
13 | from ..dependencies import Cryptodome | |
14 | from ..networking.exceptions import HTTPError | |
15 | from ..utils import ( | |
16 | ExtractorError, | |
17 | GeoRestrictedError, | |
18 | InAdvancePagedList, | |
19 | OnDemandPagedList, | |
20 | bool_or_none, | |
21 | clean_html, | |
22 | determine_ext, | |
23 | filter_dict, | |
24 | float_or_none, | |
25 | format_field, | |
26 | get_element_by_class, | |
27 | int_or_none, | |
28 | join_nonempty, | |
29 | make_archive_id, | |
30 | merge_dicts, | |
31 | mimetype2ext, | |
32 | parse_count, | |
33 | parse_qs, | |
34 | qualities, | |
35 | smuggle_url, | |
36 | srt_subtitles_timecode, | |
37 | str_or_none, | |
38 | traverse_obj, | |
39 | try_call, | |
40 | unified_timestamp, | |
41 | unsmuggle_url, | |
42 | url_or_none, | |
43 | urlencode_postdata, | |
44 | variadic, | |
45 | ) | |
46 | ||
47 | ||
48 | class BilibiliBaseIE(InfoExtractor): | |
49 | _FORMAT_ID_RE = re.compile(r'-(\d+)\.m4s\?') | |
50 | ||
51 | def extract_formats(self, play_info): | |
52 | format_names = { | |
53 | r['quality']: traverse_obj(r, 'new_description', 'display_desc') | |
54 | for r in traverse_obj(play_info, ('support_formats', lambda _, v: v['quality'])) | |
55 | } | |
56 | ||
57 | audios = traverse_obj(play_info, ('dash', (None, 'dolby'), 'audio', ..., {dict})) | |
58 | flac_audio = traverse_obj(play_info, ('dash', 'flac', 'audio')) | |
59 | if flac_audio: | |
60 | audios.append(flac_audio) | |
61 | formats = [{ | |
62 | 'url': traverse_obj(audio, 'baseUrl', 'base_url', 'url'), | |
63 | 'ext': mimetype2ext(traverse_obj(audio, 'mimeType', 'mime_type')), | |
64 | 'acodec': traverse_obj(audio, ('codecs', {str.lower})), | |
65 | 'vcodec': 'none', | |
66 | 'tbr': float_or_none(audio.get('bandwidth'), scale=1000), | |
67 | 'filesize': int_or_none(audio.get('size')), | |
68 | 'format_id': str_or_none(audio.get('id')), | |
69 | } for audio in audios] | |
70 | ||
71 | formats.extend({ | |
72 | 'url': traverse_obj(video, 'baseUrl', 'base_url', 'url'), | |
73 | 'ext': mimetype2ext(traverse_obj(video, 'mimeType', 'mime_type')), | |
74 | 'fps': float_or_none(traverse_obj(video, 'frameRate', 'frame_rate')), | |
75 | 'width': int_or_none(video.get('width')), | |
76 | 'height': int_or_none(video.get('height')), | |
77 | 'vcodec': video.get('codecs'), | |
78 | 'acodec': 'none' if audios else None, | |
79 | 'dynamic_range': {126: 'DV', 125: 'HDR10'}.get(int_or_none(video.get('id'))), | |
80 | 'tbr': float_or_none(video.get('bandwidth'), scale=1000), | |
81 | 'filesize': int_or_none(video.get('size')), | |
82 | 'quality': int_or_none(video.get('id')), | |
83 | 'format_id': traverse_obj( | |
84 | video, (('baseUrl', 'base_url'), {self._FORMAT_ID_RE.search}, 1), | |
85 | ('id', {str_or_none}), get_all=False), | |
86 | 'format': format_names.get(video.get('id')), | |
87 | } for video in traverse_obj(play_info, ('dash', 'video', ...))) | |
88 | ||
89 | missing_formats = format_names.keys() - set(traverse_obj(formats, (..., 'quality'))) | |
90 | if missing_formats: | |
91 | self.to_screen(f'Format(s) {", ".join(format_names[i] for i in missing_formats)} are missing; ' | |
92 | f'you have to login or become premium member to download them. {self._login_hint()}') | |
93 | ||
94 | return formats | |
95 | ||
96 | def _download_playinfo(self, video_id, cid, headers=None): | |
97 | return self._download_json( | |
98 | 'https://api.bilibili.com/x/player/playurl', video_id, | |
99 | query={'bvid': video_id, 'cid': cid, 'fnval': 4048}, | |
100 | note=f'Downloading video formats for cid {cid}', headers=headers)['data'] | |
101 | ||
102 | def json2srt(self, json_data): | |
103 | srt_data = '' | |
104 | for idx, line in enumerate(json_data.get('body') or []): | |
105 | srt_data += (f'{idx + 1}\n' | |
106 | f'{srt_subtitles_timecode(line["from"])} --> {srt_subtitles_timecode(line["to"])}\n' | |
107 | f'{line["content"]}\n\n') | |
108 | return srt_data | |
109 | ||
110 | def _get_subtitles(self, video_id, cid, aid=None): | |
111 | subtitles = { | |
112 | 'danmaku': [{ | |
113 | 'ext': 'xml', | |
114 | 'url': f'https://comment.bilibili.com/{cid}.xml', | |
115 | }], | |
116 | } | |
117 | ||
118 | subtitle_info = traverse_obj(self._download_json( | |
119 | 'https://api.bilibili.com/x/player/v2', video_id, | |
120 | query={'aid': aid, 'cid': cid} if aid else {'bvid': video_id, 'cid': cid}, | |
121 | note=f'Extracting subtitle info {cid}'), ('data', 'subtitle')) | |
122 | subs_list = traverse_obj(subtitle_info, ('subtitles', lambda _, v: v['subtitle_url'] and v['lan'])) | |
123 | if not subs_list and traverse_obj(subtitle_info, 'allow_submit'): | |
124 | if not self._get_cookies('https://api.bilibili.com').get('SESSDATA'): # no login session cookie | |
125 | self.report_warning(f'CC subtitles (if any) are only visible when logged in. {self._login_hint()}', only_once=True) | |
126 | for s in subs_list: | |
127 | subtitles.setdefault(s['lan'], []).append({ | |
128 | 'ext': 'srt', | |
129 | 'data': self.json2srt(self._download_json(s['subtitle_url'], video_id)), | |
130 | }) | |
131 | return subtitles | |
132 | ||
133 | def _get_chapters(self, aid, cid): | |
134 | chapters = aid and cid and self._download_json( | |
135 | 'https://api.bilibili.com/x/player/v2', aid, query={'aid': aid, 'cid': cid}, | |
136 | note='Extracting chapters', fatal=False) | |
137 | return traverse_obj(chapters, ('data', 'view_points', ..., { | |
138 | 'title': 'content', | |
139 | 'start_time': 'from', | |
140 | 'end_time': 'to', | |
141 | })) or None | |
142 | ||
143 | def _get_comments(self, aid): | |
144 | for idx in itertools.count(1): | |
145 | replies = traverse_obj( | |
146 | self._download_json( | |
147 | f'https://api.bilibili.com/x/v2/reply?pn={idx}&oid={aid}&type=1&jsonp=jsonp&sort=2&_=1567227301685', | |
148 | aid, note=f'Extracting comments from page {idx}', fatal=False), | |
149 | ('data', 'replies')) | |
150 | if not replies: | |
151 | return | |
152 | for children in map(self._get_all_children, replies): | |
153 | yield from children | |
154 | ||
155 | def _get_all_children(self, reply): | |
156 | yield { | |
157 | 'author': traverse_obj(reply, ('member', 'uname')), | |
158 | 'author_id': traverse_obj(reply, ('member', 'mid')), | |
159 | 'id': reply.get('rpid'), | |
160 | 'text': traverse_obj(reply, ('content', 'message')), | |
161 | 'timestamp': reply.get('ctime'), | |
162 | 'parent': reply.get('parent') or 'root', | |
163 | } | |
164 | for children in map(self._get_all_children, traverse_obj(reply, ('replies', ...))): | |
165 | yield from children | |
166 | ||
167 | def _get_episodes_from_season(self, ss_id, url): | |
168 | season_info = self._download_json( | |
169 | 'https://api.bilibili.com/pgc/web/season/section', ss_id, | |
170 | note='Downloading season info', query={'season_id': ss_id}, | |
171 | headers={'Referer': url, **self.geo_verification_headers()}) | |
172 | ||
173 | for entry in traverse_obj(season_info, ( | |
174 | 'result', 'main_section', 'episodes', | |
175 | lambda _, v: url_or_none(v['share_url']) and v['id'])): | |
176 | yield self.url_result(entry['share_url'], BiliBiliBangumiIE, str_or_none(entry.get('id'))) | |
177 | ||
178 | def _get_divisions(self, video_id, graph_version, edges, edge_id, cid_edges=None): | |
179 | cid_edges = cid_edges or {} | |
180 | division_data = self._download_json( | |
181 | 'https://api.bilibili.com/x/stein/edgeinfo_v2', video_id, | |
182 | query={'graph_version': graph_version, 'edge_id': edge_id, 'bvid': video_id}, | |
183 | note=f'Extracting divisions from edge {edge_id}') | |
184 | edges.setdefault(edge_id, {}).update( | |
185 | traverse_obj(division_data, ('data', 'story_list', lambda _, v: v['edge_id'] == edge_id, { | |
186 | 'title': ('title', {str}), | |
187 | 'cid': ('cid', {int_or_none}), | |
188 | }), get_all=False)) | |
189 | ||
190 | edges[edge_id].update(traverse_obj(division_data, ('data', { | |
191 | 'title': ('title', {str}), | |
192 | 'choices': ('edges', 'questions', ..., 'choices', ..., { | |
193 | 'edge_id': ('id', {int_or_none}), | |
194 | 'cid': ('cid', {int_or_none}), | |
195 | 'text': ('option', {str}), | |
196 | }), | |
197 | }))) | |
198 | # use dict to combine edges that use the same video section (same cid) | |
199 | cid_edges.setdefault(edges[edge_id]['cid'], {})[edge_id] = edges[edge_id] | |
200 | for choice in traverse_obj(edges, (edge_id, 'choices', ...)): | |
201 | if choice['edge_id'] not in edges: | |
202 | edges[choice['edge_id']] = {'cid': choice['cid']} | |
203 | self._get_divisions(video_id, graph_version, edges, choice['edge_id'], cid_edges=cid_edges) | |
204 | return cid_edges | |
205 | ||
206 | def _get_interactive_entries(self, video_id, cid, metainfo): | |
207 | graph_version = traverse_obj( | |
208 | self._download_json( | |
209 | 'https://api.bilibili.com/x/player/wbi/v2', video_id, | |
210 | 'Extracting graph version', query={'bvid': video_id, 'cid': cid}), | |
211 | ('data', 'interaction', 'graph_version', {int_or_none})) | |
212 | cid_edges = self._get_divisions(video_id, graph_version, {1: {'cid': cid}}, 1) | |
213 | for cid, edges in cid_edges.items(): | |
214 | play_info = self._download_playinfo(video_id, cid) | |
215 | yield { | |
216 | **metainfo, | |
217 | 'id': f'{video_id}_{cid}', | |
218 | 'title': f'{metainfo.get("title")} - {next(iter(edges.values())).get("title")}', | |
219 | 'formats': self.extract_formats(play_info), | |
220 | 'description': f'{json.dumps(edges, ensure_ascii=False)}\n{metainfo.get("description", "")}', | |
221 | 'duration': float_or_none(play_info.get('timelength'), scale=1000), | |
222 | 'subtitles': self.extract_subtitles(video_id, cid), | |
223 | } | |
224 | ||
225 | ||
226 | class BiliBiliIE(BilibiliBaseIE): | |
227 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:video/|festival/\w+\?(?:[^#]*&)?bvid=)[aAbB][vV](?P<id>[^/?#&]+)' | |
228 | ||
229 | _TESTS = [{ | |
230 | 'url': 'https://www.bilibili.com/video/BV13x41117TL', | |
231 | 'info_dict': { | |
232 | 'id': 'BV13x41117TL', | |
233 | 'title': '阿滴英文|英文歌分享#6 "Closer', | |
234 | 'ext': 'mp4', | |
235 | 'description': '滴妹今天唱Closer給你聽! 有史以来,被推最多次也是最久的歌曲,其实歌词跟我原本想像差蛮多的,不过还是好听! 微博@阿滴英文', | |
236 | 'uploader_id': '65880958', | |
237 | 'uploader': '阿滴英文', | |
238 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
239 | 'duration': 554.117, | |
240 | 'tags': list, | |
241 | 'comment_count': int, | |
242 | 'upload_date': '20170301', | |
243 | 'timestamp': 1488353834, | |
244 | 'like_count': int, | |
245 | 'view_count': int, | |
246 | }, | |
247 | }, { | |
248 | 'note': 'old av URL version', | |
249 | 'url': 'http://www.bilibili.com/video/av1074402/', | |
250 | 'info_dict': { | |
251 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg)$', | |
252 | 'ext': 'mp4', | |
253 | 'uploader': '菊子桑', | |
254 | 'uploader_id': '156160', | |
255 | 'id': 'BV11x411K7CN', | |
256 | 'title': '【金坷垃】金泡沫', | |
257 | 'duration': 308.36, | |
258 | 'upload_date': '20140420', | |
259 | 'timestamp': 1397983878, | |
260 | 'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923', | |
261 | 'like_count': int, | |
262 | 'comment_count': int, | |
263 | 'view_count': int, | |
264 | 'tags': list, | |
265 | }, | |
266 | 'params': {'skip_download': True}, | |
267 | }, { | |
268 | 'note': 'Anthology', | |
269 | 'url': 'https://www.bilibili.com/video/BV1bK411W797', | |
270 | 'info_dict': { | |
271 | 'id': 'BV1bK411W797', | |
272 | 'title': '物语中的人物是如何吐槽自己的OP的', | |
273 | }, | |
274 | 'playlist_count': 18, | |
275 | 'playlist': [{ | |
276 | 'info_dict': { | |
277 | 'id': 'BV1bK411W797_p1', | |
278 | 'ext': 'mp4', | |
279 | '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', | |
280 | 'tags': 'count:10', | |
281 | 'timestamp': 1589601697, | |
282 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
283 | 'uploader': '打牌还是打桩', | |
284 | 'uploader_id': '150259984', | |
285 | 'like_count': int, | |
286 | 'comment_count': int, | |
287 | 'upload_date': '20200516', | |
288 | 'view_count': int, | |
289 | 'description': 'md5:e3c401cf7bc363118d1783dd74068a68', | |
290 | 'duration': 90.314, | |
291 | }, | |
292 | }], | |
293 | }, { | |
294 | 'note': 'Specific page of Anthology', | |
295 | 'url': 'https://www.bilibili.com/video/BV1bK411W797?p=1', | |
296 | 'info_dict': { | |
297 | 'id': 'BV1bK411W797_p1', | |
298 | 'ext': 'mp4', | |
299 | 'title': '物语中的人物是如何吐槽自己的OP的 p01 Staple Stable/战场原+羽川', | |
300 | 'tags': 'count:10', | |
301 | 'timestamp': 1589601697, | |
302 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
303 | 'uploader': '打牌还是打桩', | |
304 | 'uploader_id': '150259984', | |
305 | 'like_count': int, | |
306 | 'comment_count': int, | |
307 | 'upload_date': '20200516', | |
308 | 'view_count': int, | |
309 | 'description': 'md5:e3c401cf7bc363118d1783dd74068a68', | |
310 | 'duration': 90.314, | |
311 | }, | |
312 | }, { | |
313 | 'note': 'video has subtitles', | |
314 | 'url': 'https://www.bilibili.com/video/BV12N4y1M7rh', | |
315 | 'info_dict': { | |
316 | 'id': 'BV12N4y1M7rh', | |
317 | 'ext': 'mp4', | |
318 | 'title': 'md5:96e8bb42c2b432c0d4ce3434a61479c1', | |
319 | 'tags': list, | |
320 | 'description': 'md5:afde2b7ba9025c01d9e3dde10de221e4', | |
321 | 'duration': 313.557, | |
322 | 'upload_date': '20220709', | |
323 | 'uploader': '小夫太渴', | |
324 | 'timestamp': 1657347907, | |
325 | 'uploader_id': '1326814124', | |
326 | 'comment_count': int, | |
327 | 'view_count': int, | |
328 | 'like_count': int, | |
329 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
330 | 'subtitles': 'count:2', | |
331 | }, | |
332 | 'params': {'listsubtitles': True}, | |
333 | }, { | |
334 | 'url': 'https://www.bilibili.com/video/av8903802/', | |
335 | 'info_dict': { | |
336 | 'id': 'BV13x41117TL', | |
337 | 'ext': 'mp4', | |
338 | 'title': '阿滴英文|英文歌分享#6 "Closer', | |
339 | 'upload_date': '20170301', | |
340 | 'description': 'md5:3b1b9e25b78da4ef87e9b548b88ee76a', | |
341 | 'timestamp': 1488353834, | |
342 | 'uploader_id': '65880958', | |
343 | 'uploader': '阿滴英文', | |
344 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
345 | 'duration': 554.117, | |
346 | 'tags': list, | |
347 | 'comment_count': int, | |
348 | 'view_count': int, | |
349 | 'like_count': int, | |
350 | }, | |
351 | 'params': { | |
352 | 'skip_download': True, | |
353 | }, | |
354 | }, { | |
355 | 'note': 'video has chapter', | |
356 | 'url': 'https://www.bilibili.com/video/BV1vL411G7N7/', | |
357 | 'info_dict': { | |
358 | 'id': 'BV1vL411G7N7', | |
359 | 'ext': 'mp4', | |
360 | 'title': '如何为你的B站视频添加进度条分段', | |
361 | 'timestamp': 1634554558, | |
362 | 'upload_date': '20211018', | |
363 | 'description': 'md5:a9a3d6702b3a94518d419b2e9c320a6d', | |
364 | 'tags': list, | |
365 | 'uploader': '爱喝咖啡的当麻', | |
366 | 'duration': 669.482, | |
367 | 'uploader_id': '1680903', | |
368 | 'chapters': 'count:6', | |
369 | 'comment_count': int, | |
370 | 'view_count': int, | |
371 | 'like_count': int, | |
372 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
373 | }, | |
374 | 'params': {'skip_download': True}, | |
375 | }, { | |
376 | 'note': 'video redirects to festival page', | |
377 | 'url': 'https://www.bilibili.com/video/BV1wP4y1P72h', | |
378 | 'info_dict': { | |
379 | 'id': 'BV1wP4y1P72h', | |
380 | 'ext': 'mp4', | |
381 | 'title': '牛虎年相交之际,一首传统民族打击乐《牛斗虎》祝大家新春快乐,虎年大吉!【bilibili音乐虎闹新春】', | |
382 | 'timestamp': 1643947497, | |
383 | 'upload_date': '20220204', | |
384 | 'description': 'md5:8681a0d4d2c06b4ae27e59c8080a7fe6', | |
385 | 'uploader': '叨叨冯聊音乐', | |
386 | 'duration': 246.719, | |
387 | 'uploader_id': '528182630', | |
388 | 'view_count': int, | |
389 | 'like_count': int, | |
390 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
391 | }, | |
392 | 'params': {'skip_download': True}, | |
393 | }, { | |
394 | 'note': 'newer festival video', | |
395 | 'url': 'https://www.bilibili.com/festival/2023honkaiimpact3gala?bvid=BV1ay4y1d77f', | |
396 | 'info_dict': { | |
397 | 'id': 'BV1ay4y1d77f', | |
398 | 'ext': 'mp4', | |
399 | 'title': '【崩坏3新春剧场】为特别的你送上祝福!', | |
400 | 'timestamp': 1674273600, | |
401 | 'upload_date': '20230121', | |
402 | 'description': 'md5:58af66d15c6a0122dc30c8adfd828dd8', | |
403 | 'uploader': '果蝇轰', | |
404 | 'duration': 1111.722, | |
405 | 'uploader_id': '8469526', | |
406 | 'view_count': int, | |
407 | 'like_count': int, | |
408 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
409 | }, | |
410 | 'params': {'skip_download': True}, | |
411 | }, { | |
412 | 'note': 'interactive/split-path video', | |
413 | 'url': 'https://www.bilibili.com/video/BV1af4y1H7ga/', | |
414 | 'info_dict': { | |
415 | 'id': 'BV1af4y1H7ga', | |
416 | 'title': '【互动游戏】花了大半年时间做的自我介绍~请查收!!', | |
417 | 'timestamp': 1630500414, | |
418 | 'upload_date': '20210901', | |
419 | 'description': 'md5:01113e39ab06e28042d74ac356a08786', | |
420 | 'tags': list, | |
421 | 'uploader': '钉宫妮妮Ninico', | |
422 | 'duration': 1503, | |
423 | 'uploader_id': '8881297', | |
424 | 'comment_count': int, | |
425 | 'view_count': int, | |
426 | 'like_count': int, | |
427 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
428 | }, | |
429 | 'playlist_count': 33, | |
430 | 'playlist': [{ | |
431 | 'info_dict': { | |
432 | 'id': 'BV1af4y1H7ga_400950101', | |
433 | 'ext': 'mp4', | |
434 | '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~', | |
435 | 'timestamp': 1630500414, | |
436 | 'upload_date': '20210901', | |
437 | 'description': 'md5:db66ac7a2813a94b8291dbce990cc5b2', | |
438 | 'tags': list, | |
439 | 'uploader': '钉宫妮妮Ninico', | |
440 | 'duration': 11.605, | |
441 | 'uploader_id': '8881297', | |
442 | 'comment_count': int, | |
443 | 'view_count': int, | |
444 | 'like_count': int, | |
445 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
446 | }, | |
447 | }], | |
448 | }, { | |
449 | 'note': '301 redirect to bangumi link', | |
450 | 'url': 'https://www.bilibili.com/video/BV1TE411f7f1', | |
451 | 'info_dict': { | |
452 | 'id': '288525', | |
453 | 'title': '李永乐老师 钱学森弹道和乘波体飞行器是什么?', | |
454 | 'ext': 'mp4', | |
455 | 'series': '我和我的祖国', | |
456 | 'series_id': '4780', | |
457 | 'season': '幕后纪实', | |
458 | 'season_id': '28609', | |
459 | 'season_number': 1, | |
460 | 'episode': '钱学森弹道和乘波体飞行器是什么?', | |
461 | 'episode_id': '288525', | |
462 | 'episode_number': 105, | |
463 | 'duration': 1183.957, | |
464 | 'timestamp': 1571648124, | |
465 | 'upload_date': '20191021', | |
466 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
467 | }, | |
468 | }, { | |
469 | 'url': 'https://www.bilibili.com/video/BV1jL41167ZG/', | |
470 | 'info_dict': { | |
471 | 'id': 'BV1jL41167ZG', | |
472 | '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》!', | |
473 | 'ext': 'mp4', | |
474 | }, | |
475 | 'skip': 'supporter-only video', | |
476 | }, { | |
477 | 'url': 'https://www.bilibili.com/video/BV1Ks411f7aQ/', | |
478 | 'info_dict': { | |
479 | 'id': 'BV1Ks411f7aQ', | |
480 | 'title': '【BD1080P】狼与香辛料I【华盟】', | |
481 | 'ext': 'mp4', | |
482 | }, | |
483 | 'skip': 'login required', | |
484 | }, { | |
485 | 'url': 'https://www.bilibili.com/video/BV1GJ411x7h7/', | |
486 | 'info_dict': { | |
487 | 'id': 'BV1GJ411x7h7', | |
488 | 'title': '【官方 MV】Never Gonna Give You Up - Rick Astley', | |
489 | 'ext': 'mp4', | |
490 | }, | |
491 | 'skip': 'geo-restricted', | |
492 | }] | |
493 | ||
494 | def _real_extract(self, url): | |
495 | video_id = self._match_id(url) | |
496 | headers = self.geo_verification_headers() | |
497 | webpage, urlh = self._download_webpage_handle(url, video_id, headers=headers) | |
498 | if not self._match_valid_url(urlh.url): | |
499 | return self.url_result(urlh.url) | |
500 | ||
501 | initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id) | |
502 | ||
503 | is_festival = 'videoData' not in initial_state | |
504 | if is_festival: | |
505 | video_data = initial_state['videoInfo'] | |
506 | else: | |
507 | play_info_obj = self._search_json( | |
508 | r'window\.__playinfo__\s*=', webpage, 'play info', video_id, fatal=False) | |
509 | if not play_info_obj: | |
510 | if traverse_obj(initial_state, ('error', 'trueCode')) == -403: | |
511 | self.raise_login_required() | |
512 | if traverse_obj(initial_state, ('error', 'trueCode')) == -404: | |
513 | raise ExtractorError( | |
514 | 'This video may be deleted or geo-restricted. ' | |
515 | 'You might want to try a VPN or a proxy server (with --proxy)', expected=True) | |
516 | play_info = traverse_obj(play_info_obj, ('data', {dict})) | |
517 | if not play_info: | |
518 | if traverse_obj(play_info_obj, 'code') == 87007: | |
519 | toast = get_element_by_class('tips-toast', webpage) or '' | |
520 | msg = clean_html( | |
521 | f'{get_element_by_class("belongs-to", toast) or ""},' | |
522 | + (get_element_by_class('level', toast) or '')) | |
523 | raise ExtractorError( | |
524 | f'This is a supporter-only video: {msg}. {self._login_hint()}', expected=True) | |
525 | raise ExtractorError('Failed to extract play info') | |
526 | video_data = initial_state['videoData'] | |
527 | ||
528 | video_id, title = video_data['bvid'], video_data.get('title') | |
529 | ||
530 | # Bilibili anthologies are similar to playlists but all videos share the same video ID as the anthology itself. | |
531 | page_list_json = not is_festival and traverse_obj( | |
532 | self._download_json( | |
533 | 'https://api.bilibili.com/x/player/pagelist', video_id, | |
534 | fatal=False, query={'bvid': video_id, 'jsonp': 'jsonp'}, | |
535 | note='Extracting videos in anthology', headers=headers), | |
536 | 'data', expected_type=list) or [] | |
537 | is_anthology = len(page_list_json) > 1 | |
538 | ||
539 | part_id = int_or_none(parse_qs(url).get('p', [None])[-1]) | |
540 | if is_anthology and not part_id and self._yes_playlist(video_id, video_id): | |
541 | return self.playlist_from_matches( | |
542 | page_list_json, video_id, title, ie=BiliBiliIE, | |
543 | getter=lambda entry: f'https://www.bilibili.com/video/{video_id}?p={entry["page"]}') | |
544 | ||
545 | if is_anthology: | |
546 | part_id = part_id or 1 | |
547 | title += f' p{part_id:02d} {traverse_obj(page_list_json, (part_id - 1, "part")) or ""}' | |
548 | ||
549 | aid = video_data.get('aid') | |
550 | old_video_id = format_field(aid, None, f'%s_part{part_id or 1}') | |
551 | ||
552 | cid = traverse_obj(video_data, ('pages', part_id - 1, 'cid')) if part_id else video_data.get('cid') | |
553 | ||
554 | festival_info = {} | |
555 | if is_festival: | |
556 | play_info = self._download_playinfo(video_id, cid, headers=headers) | |
557 | ||
558 | festival_info = traverse_obj(initial_state, { | |
559 | 'uploader': ('videoInfo', 'upName'), | |
560 | 'uploader_id': ('videoInfo', 'upMid', {str_or_none}), | |
561 | 'like_count': ('videoStatus', 'like', {int_or_none}), | |
562 | 'thumbnail': ('sectionEpisodes', lambda _, v: v['bvid'] == video_id, 'cover'), | |
563 | }, get_all=False) | |
564 | ||
565 | metainfo = { | |
566 | **traverse_obj(initial_state, { | |
567 | 'uploader': ('upData', 'name'), | |
568 | 'uploader_id': ('upData', 'mid', {str_or_none}), | |
569 | 'like_count': ('videoData', 'stat', 'like', {int_or_none}), | |
570 | 'tags': ('tags', ..., 'tag_name'), | |
571 | 'thumbnail': ('videoData', 'pic', {url_or_none}), | |
572 | }), | |
573 | **festival_info, | |
574 | **traverse_obj(video_data, { | |
575 | 'description': 'desc', | |
576 | 'timestamp': ('pubdate', {int_or_none}), | |
577 | 'view_count': (('viewCount', ('stat', 'view')), {int_or_none}), | |
578 | 'comment_count': ('stat', 'reply', {int_or_none}), | |
579 | }, get_all=False), | |
580 | 'id': f'{video_id}{format_field(part_id, None, "_p%d")}', | |
581 | '_old_archive_ids': [make_archive_id(self, old_video_id)] if old_video_id else None, | |
582 | 'title': title, | |
583 | 'http_headers': {'Referer': url}, | |
584 | } | |
585 | ||
586 | is_interactive = traverse_obj(video_data, ('rights', 'is_stein_gate')) | |
587 | if is_interactive: | |
588 | return self.playlist_result( | |
589 | self._get_interactive_entries(video_id, cid, metainfo), **metainfo, | |
590 | duration=traverse_obj(initial_state, ('videoData', 'duration', {int_or_none})), | |
591 | __post_extractor=self.extract_comments(aid)) | |
592 | else: | |
593 | return { | |
594 | **metainfo, | |
595 | 'duration': float_or_none(play_info.get('timelength'), scale=1000), | |
596 | 'chapters': self._get_chapters(aid, cid), | |
597 | 'subtitles': self.extract_subtitles(video_id, cid), | |
598 | 'formats': self.extract_formats(play_info), | |
599 | '__post_extractor': self.extract_comments(aid), | |
600 | } | |
601 | ||
602 | ||
603 | class BiliBiliBangumiIE(BilibiliBaseIE): | |
604 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/bangumi/play/ep(?P<id>\d+)' | |
605 | ||
606 | _TESTS = [{ | |
607 | 'url': 'https://www.bilibili.com/bangumi/play/ep21495/', | |
608 | 'info_dict': { | |
609 | 'id': '21495', | |
610 | 'ext': 'mp4', | |
611 | 'series': '悠久之翼', | |
612 | 'series_id': '774', | |
613 | 'season': '第二季', | |
614 | 'season_id': '1182', | |
615 | 'season_number': 2, | |
616 | 'episode': 'forever/ef', | |
617 | 'episode_id': '21495', | |
618 | 'episode_number': 12, | |
619 | 'title': '12 forever/ef', | |
620 | 'duration': 1420.791, | |
621 | 'timestamp': 1320412200, | |
622 | 'upload_date': '20111104', | |
623 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
624 | }, | |
625 | }, { | |
626 | 'url': 'https://www.bilibili.com/bangumi/play/ep267851', | |
627 | 'info_dict': { | |
628 | 'id': '267851', | |
629 | 'ext': 'mp4', | |
630 | 'series': '鬼灭之刃', | |
631 | 'series_id': '4358', | |
632 | 'season': '立志篇', | |
633 | 'season_id': '26801', | |
634 | 'season_number': 1, | |
635 | 'episode': '残酷', | |
636 | 'episode_id': '267851', | |
637 | 'episode_number': 1, | |
638 | 'title': '1 残酷', | |
639 | 'duration': 1425.256, | |
640 | 'timestamp': 1554566400, | |
641 | 'upload_date': '20190406', | |
642 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
643 | }, | |
644 | 'skip': 'Geo-restricted', | |
645 | }, { | |
646 | 'note': 'a making-of which falls outside main section', | |
647 | 'url': 'https://www.bilibili.com/bangumi/play/ep345120', | |
648 | 'info_dict': { | |
649 | 'id': '345120', | |
650 | 'ext': 'mp4', | |
651 | 'series': '鬼灭之刃', | |
652 | 'series_id': '4358', | |
653 | 'season': '立志篇', | |
654 | 'season_id': '26801', | |
655 | 'season_number': 1, | |
656 | 'episode': '炭治郎篇', | |
657 | 'episode_id': '345120', | |
658 | 'episode_number': 27, | |
659 | 'title': '#1 炭治郎篇', | |
660 | 'duration': 1922.129, | |
661 | 'timestamp': 1602853860, | |
662 | 'upload_date': '20201016', | |
663 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
664 | }, | |
665 | }] | |
666 | ||
667 | def _real_extract(self, url): | |
668 | episode_id = self._match_id(url) | |
669 | headers = self.geo_verification_headers() | |
670 | webpage = self._download_webpage(url, episode_id, headers=headers) | |
671 | ||
672 | if '您所在的地区无法观看本片' in webpage: | |
673 | raise GeoRestrictedError('This video is restricted') | |
674 | elif '正在观看预览,大会员免费看全片' in webpage: | |
675 | self.raise_login_required('This video is for premium members only') | |
676 | ||
677 | headers['Referer'] = url | |
678 | play_info = self._download_json( | |
679 | 'https://api.bilibili.com/pgc/player/web/v2/playurl', episode_id, | |
680 | 'Extracting episode', query={'fnval': '4048', 'ep_id': episode_id}, | |
681 | headers=headers) | |
682 | premium_only = play_info.get('code') == -10403 | |
683 | play_info = traverse_obj(play_info, ('result', 'video_info', {dict})) or {} | |
684 | ||
685 | formats = self.extract_formats(play_info) | |
686 | if not formats and (premium_only or '成为大会员抢先看' in webpage or '开通大会员观看' in webpage): | |
687 | self.raise_login_required('This video is for premium members only') | |
688 | ||
689 | bangumi_info = self._download_json( | |
690 | 'https://api.bilibili.com/pgc/view/web/season', episode_id, 'Get episode details', | |
691 | query={'ep_id': episode_id}, headers=headers)['result'] | |
692 | ||
693 | episode_number, episode_info = next(( | |
694 | (idx, ep) for idx, ep in enumerate(traverse_obj( | |
695 | bangumi_info, (('episodes', ('section', ..., 'episodes')), ..., {dict})), 1) | |
696 | if str_or_none(ep.get('id')) == episode_id), (1, {})) | |
697 | ||
698 | season_id = bangumi_info.get('season_id') | |
699 | season_number, season_title = season_id and next(( | |
700 | (idx + 1, e.get('season_title')) for idx, e in enumerate( | |
701 | traverse_obj(bangumi_info, ('seasons', ...))) | |
702 | if e.get('season_id') == season_id | |
703 | ), (None, None)) | |
704 | ||
705 | aid = episode_info.get('aid') | |
706 | ||
707 | return { | |
708 | 'id': episode_id, | |
709 | 'formats': formats, | |
710 | **traverse_obj(bangumi_info, { | |
711 | 'series': ('series', 'series_title', {str}), | |
712 | 'series_id': ('series', 'series_id', {str_or_none}), | |
713 | 'thumbnail': ('square_cover', {url_or_none}), | |
714 | }), | |
715 | **traverse_obj(episode_info, { | |
716 | 'episode': ('long_title', {str}), | |
717 | 'episode_number': ('title', {int_or_none}, {lambda x: x or episode_number}), | |
718 | 'timestamp': ('pub_time', {int_or_none}), | |
719 | 'title': {lambda v: v and join_nonempty('title', 'long_title', delim=' ', from_dict=v)}, | |
720 | }), | |
721 | 'episode_id': episode_id, | |
722 | 'season': str_or_none(season_title), | |
723 | 'season_id': str_or_none(season_id), | |
724 | 'season_number': season_number, | |
725 | 'duration': float_or_none(play_info.get('timelength'), scale=1000), | |
726 | 'subtitles': self.extract_subtitles(episode_id, episode_info.get('cid'), aid=aid), | |
727 | '__post_extractor': self.extract_comments(aid), | |
728 | 'http_headers': {'Referer': url}, | |
729 | } | |
730 | ||
731 | ||
732 | class BiliBiliBangumiMediaIE(BilibiliBaseIE): | |
733 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/bangumi/media/md(?P<id>\d+)' | |
734 | _TESTS = [{ | |
735 | 'url': 'https://www.bilibili.com/bangumi/media/md24097891', | |
736 | 'info_dict': { | |
737 | 'id': '24097891', | |
738 | 'title': 'CAROLE & TUESDAY', | |
739 | 'description': 'md5:42417ad33d1eaa1c93bfd2dd1626b829', | |
740 | }, | |
741 | 'playlist_mincount': 25, | |
742 | }, { | |
743 | 'url': 'https://www.bilibili.com/bangumi/media/md1565/', | |
744 | 'info_dict': { | |
745 | 'id': '1565', | |
746 | 'title': '攻壳机动队 S.A.C. 2nd GIG', | |
747 | 'description': 'md5:46cac00bafd645b97f4d6df616fc576d', | |
748 | }, | |
749 | 'playlist_count': 26, | |
750 | 'playlist': [{ | |
751 | 'info_dict': { | |
752 | 'id': '68540', | |
753 | 'ext': 'mp4', | |
754 | 'series': '攻壳机动队', | |
755 | 'series_id': '1077', | |
756 | 'season': '第二季', | |
757 | 'season_id': '1565', | |
758 | 'season_number': 2, | |
759 | 'episode': '再启动 REEMBODY', | |
760 | 'episode_id': '68540', | |
761 | 'episode_number': 1, | |
762 | 'title': '1 再启动 REEMBODY', | |
763 | 'duration': 1525.777, | |
764 | 'timestamp': 1425074413, | |
765 | 'upload_date': '20150227', | |
766 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
767 | }, | |
768 | }], | |
769 | }] | |
770 | ||
771 | def _real_extract(self, url): | |
772 | media_id = self._match_id(url) | |
773 | webpage = self._download_webpage(url, media_id) | |
774 | ||
775 | initial_state = self._search_json( | |
776 | r'window\.__INITIAL_STATE__\s*=', webpage, 'initial_state', media_id) | |
777 | ss_id = initial_state['mediaInfo']['season_id'] | |
778 | ||
779 | return self.playlist_result( | |
780 | self._get_episodes_from_season(ss_id, url), media_id, | |
781 | **traverse_obj(initial_state, ('mediaInfo', { | |
782 | 'title': ('title', {str}), | |
783 | 'description': ('evaluate', {str}), | |
784 | }))) | |
785 | ||
786 | ||
787 | class BiliBiliBangumiSeasonIE(BilibiliBaseIE): | |
788 | _VALID_URL = r'(?x)https?://(?:www\.)?bilibili\.com/bangumi/play/ss(?P<id>\d+)' | |
789 | _TESTS = [{ | |
790 | 'url': 'https://www.bilibili.com/bangumi/play/ss26801', | |
791 | 'info_dict': { | |
792 | 'id': '26801', | |
793 | 'title': '鬼灭之刃', | |
794 | 'description': 'md5:e2cc9848b6f69be6db79fc2a82d9661b', | |
795 | }, | |
796 | 'playlist_mincount': 26, | |
797 | }, { | |
798 | 'url': 'https://www.bilibili.com/bangumi/play/ss2251', | |
799 | 'info_dict': { | |
800 | 'id': '2251', | |
801 | 'title': '玲音', | |
802 | 'description': 'md5:1fd40e3df4c08d4d9d89a6a34844bdc4', | |
803 | }, | |
804 | 'playlist_count': 13, | |
805 | 'playlist': [{ | |
806 | 'info_dict': { | |
807 | 'id': '50188', | |
808 | 'ext': 'mp4', | |
809 | 'series': '玲音', | |
810 | 'series_id': '1526', | |
811 | 'season': 'TV', | |
812 | 'season_id': '2251', | |
813 | 'season_number': 1, | |
814 | 'episode': 'WEIRD', | |
815 | 'episode_id': '50188', | |
816 | 'episode_number': 1, | |
817 | 'title': '1 WEIRD', | |
818 | 'duration': 1436.992, | |
819 | 'timestamp': 1343185080, | |
820 | 'upload_date': '20120725', | |
821 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
822 | }, | |
823 | }], | |
824 | }] | |
825 | ||
826 | def _real_extract(self, url): | |
827 | ss_id = self._match_id(url) | |
828 | webpage = self._download_webpage(url, ss_id) | |
829 | metainfo = traverse_obj( | |
830 | self._search_json(r'<script[^>]+type="application/ld\+json"[^>]*>', webpage, 'info', ss_id), | |
831 | ('itemListElement', ..., { | |
832 | 'title': ('name', {str}), | |
833 | 'description': ('description', {str}), | |
834 | }), get_all=False) | |
835 | ||
836 | return self.playlist_result(self._get_episodes_from_season(ss_id, url), ss_id, **metainfo) | |
837 | ||
838 | ||
839 | class BilibiliCheeseBaseIE(BilibiliBaseIE): | |
840 | _HEADERS = {'Referer': 'https://www.bilibili.com/'} | |
841 | ||
842 | def _extract_episode(self, season_info, ep_id): | |
843 | episode_info = traverse_obj(season_info, ( | |
844 | 'episodes', lambda _, v: v['id'] == int(ep_id)), get_all=False) | |
845 | aid, cid = episode_info['aid'], episode_info['cid'] | |
846 | ||
847 | if traverse_obj(episode_info, 'ep_status') == -1: | |
848 | raise ExtractorError('This course episode is not yet available.', expected=True) | |
849 | if not traverse_obj(episode_info, 'playable'): | |
850 | self.raise_login_required('You need to purchase the course to download this episode') | |
851 | ||
852 | play_info = self._download_json( | |
853 | 'https://api.bilibili.com/pugv/player/web/playurl', ep_id, | |
854 | query={'avid': aid, 'cid': cid, 'ep_id': ep_id, 'fnval': 16, 'fourk': 1}, | |
855 | headers=self._HEADERS, note='Downloading playinfo')['data'] | |
856 | ||
857 | return { | |
858 | 'id': str_or_none(ep_id), | |
859 | 'episode_id': str_or_none(ep_id), | |
860 | 'formats': self.extract_formats(play_info), | |
861 | 'extractor_key': BilibiliCheeseIE.ie_key(), | |
862 | 'extractor': BilibiliCheeseIE.IE_NAME, | |
863 | 'webpage_url': f'https://www.bilibili.com/cheese/play/ep{ep_id}', | |
864 | **traverse_obj(episode_info, { | |
865 | 'episode': ('title', {str}), | |
866 | 'title': {lambda v: v and join_nonempty('index', 'title', delim=' - ', from_dict=v)}, | |
867 | 'alt_title': ('subtitle', {str}), | |
868 | 'duration': ('duration', {int_or_none}), | |
869 | 'episode_number': ('index', {int_or_none}), | |
870 | 'thumbnail': ('cover', {url_or_none}), | |
871 | 'timestamp': ('release_date', {int_or_none}), | |
872 | 'view_count': ('play', {int_or_none}), | |
873 | }), | |
874 | **traverse_obj(season_info, { | |
875 | 'uploader': ('up_info', 'uname', {str}), | |
876 | 'uploader_id': ('up_info', 'mid', {str_or_none}), | |
877 | }), | |
878 | 'subtitles': self.extract_subtitles(ep_id, cid, aid=aid), | |
879 | '__post_extractor': self.extract_comments(aid), | |
880 | 'http_headers': self._HEADERS, | |
881 | } | |
882 | ||
883 | def _download_season_info(self, query_key, video_id): | |
884 | return self._download_json( | |
885 | f'https://api.bilibili.com/pugv/view/web/season?{query_key}={video_id}', video_id, | |
886 | headers=self._HEADERS, note='Downloading season info')['data'] | |
887 | ||
888 | ||
889 | class BilibiliCheeseIE(BilibiliCheeseBaseIE): | |
890 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/cheese/play/ep(?P<id>\d+)' | |
891 | _TESTS = [{ | |
892 | 'url': 'https://www.bilibili.com/cheese/play/ep229832', | |
893 | 'info_dict': { | |
894 | 'id': '229832', | |
895 | 'ext': 'mp4', | |
896 | 'title': '1 - 课程先导片', | |
897 | 'alt_title': '视频课 · 3分41秒', | |
898 | 'uploader': '马督工', | |
899 | 'uploader_id': '316568752', | |
900 | 'episode': '课程先导片', | |
901 | 'episode_id': '229832', | |
902 | 'episode_number': 1, | |
903 | 'duration': 221, | |
904 | 'timestamp': 1695549606, | |
905 | 'upload_date': '20230924', | |
906 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
907 | 'view_count': int, | |
908 | }, | |
909 | }] | |
910 | ||
911 | def _real_extract(self, url): | |
912 | ep_id = self._match_id(url) | |
913 | return self._extract_episode(self._download_season_info('ep_id', ep_id), ep_id) | |
914 | ||
915 | ||
916 | class BilibiliCheeseSeasonIE(BilibiliCheeseBaseIE): | |
917 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/cheese/play/ss(?P<id>\d+)' | |
918 | _TESTS = [{ | |
919 | 'url': 'https://www.bilibili.com/cheese/play/ss5918', | |
920 | 'info_dict': { | |
921 | 'id': '5918', | |
922 | 'title': '【限时五折】新闻系学不到:马督工教你做自媒体', | |
923 | 'description': '帮普通人建立世界模型,降低人与人的沟通门槛', | |
924 | }, | |
925 | 'playlist': [{ | |
926 | 'info_dict': { | |
927 | 'id': '229832', | |
928 | 'ext': 'mp4', | |
929 | 'title': '1 - 课程先导片', | |
930 | 'alt_title': '视频课 · 3分41秒', | |
931 | 'uploader': '马督工', | |
932 | 'uploader_id': '316568752', | |
933 | 'episode': '课程先导片', | |
934 | 'episode_id': '229832', | |
935 | 'episode_number': 1, | |
936 | 'duration': 221, | |
937 | 'timestamp': 1695549606, | |
938 | 'upload_date': '20230924', | |
939 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
940 | 'view_count': int, | |
941 | }, | |
942 | }], | |
943 | 'params': {'playlist_items': '1'}, | |
944 | }, { | |
945 | 'url': 'https://www.bilibili.com/cheese/play/ss5918', | |
946 | 'info_dict': { | |
947 | 'id': '5918', | |
948 | 'title': '【限时五折】新闻系学不到:马督工教你做自媒体', | |
949 | 'description': '帮普通人建立世界模型,降低人与人的沟通门槛', | |
950 | }, | |
951 | 'playlist_mincount': 5, | |
952 | 'skip': 'paid video in list', | |
953 | }] | |
954 | ||
955 | def _get_cheese_entries(self, season_info): | |
956 | for ep_id in traverse_obj(season_info, ('episodes', lambda _, v: v['episode_can_view'], 'id')): | |
957 | yield self._extract_episode(season_info, ep_id) | |
958 | ||
959 | def _real_extract(self, url): | |
960 | season_id = self._match_id(url) | |
961 | season_info = self._download_season_info('season_id', season_id) | |
962 | ||
963 | return self.playlist_result( | |
964 | self._get_cheese_entries(season_info), season_id, | |
965 | **traverse_obj(season_info, { | |
966 | 'title': ('title', {str}), | |
967 | 'description': ('subtitle', {str}), | |
968 | })) | |
969 | ||
970 | ||
971 | class BilibiliSpaceBaseIE(InfoExtractor): | |
972 | def _extract_playlist(self, fetch_page, get_metadata, get_entries): | |
973 | first_page = fetch_page(0) | |
974 | metadata = get_metadata(first_page) | |
975 | ||
976 | paged_list = InAdvancePagedList( | |
977 | lambda idx: get_entries(fetch_page(idx) if idx else first_page), | |
978 | metadata['page_count'], metadata['page_size']) | |
979 | ||
980 | return metadata, paged_list | |
981 | ||
982 | ||
983 | class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE): | |
984 | _VALID_URL = r'https?://space\.bilibili\.com/(?P<id>\d+)(?P<video>/video)?/?(?:[?#]|$)' | |
985 | _TESTS = [{ | |
986 | 'url': 'https://space.bilibili.com/3985676/video', | |
987 | 'info_dict': { | |
988 | 'id': '3985676', | |
989 | }, | |
990 | 'playlist_mincount': 178, | |
991 | }, { | |
992 | 'url': 'https://space.bilibili.com/313580179/video', | |
993 | 'info_dict': { | |
994 | 'id': '313580179', | |
995 | }, | |
996 | 'playlist_mincount': 92, | |
997 | }] | |
998 | ||
999 | def _extract_signature(self, playlist_id): | |
1000 | session_data = self._download_json('https://api.bilibili.com/x/web-interface/nav', playlist_id, fatal=False) | |
1001 | ||
1002 | key_from_url = lambda x: x[x.rfind('/') + 1:].split('.')[0] | |
1003 | img_key = traverse_obj( | |
1004 | session_data, ('data', 'wbi_img', 'img_url', {key_from_url})) or '34478ba821254d9d93542680e3b86100' | |
1005 | sub_key = traverse_obj( | |
1006 | session_data, ('data', 'wbi_img', 'sub_url', {key_from_url})) or '7e16a90d190a4355a78fd00b32a38de6' | |
1007 | ||
1008 | session_key = img_key + sub_key | |
1009 | ||
1010 | signature_values = [] | |
1011 | for position in ( | |
1012 | 46, 47, 18, 2, 53, 8, 23, 32, 15, 50, 10, 31, 58, 3, 45, 35, 27, 43, 5, 49, 33, 9, 42, 19, 29, 28, 14, 39, | |
1013 | 12, 38, 41, 13, 37, 48, 7, 16, 24, 55, 40, 61, 26, 17, 0, 1, 60, 51, 30, 4, 22, 25, 54, 21, 56, 59, 6, 63, | |
1014 | 57, 62, 11, 36, 20, 34, 44, 52, | |
1015 | ): | |
1016 | char_at_position = try_call(lambda: session_key[position]) | |
1017 | if char_at_position: | |
1018 | signature_values.append(char_at_position) | |
1019 | ||
1020 | return ''.join(signature_values)[:32] | |
1021 | ||
1022 | def _real_extract(self, url): | |
1023 | playlist_id, is_video_url = self._match_valid_url(url).group('id', 'video') | |
1024 | if not is_video_url: | |
1025 | self.to_screen('A channel URL was given. Only the channel\'s videos will be downloaded. ' | |
1026 | 'To download audios, add a "/audio" to the URL') | |
1027 | ||
1028 | signature = self._extract_signature(playlist_id) | |
1029 | ||
1030 | def fetch_page(page_idx): | |
1031 | query = { | |
1032 | 'keyword': '', | |
1033 | 'mid': playlist_id, | |
1034 | 'order': 'pubdate', | |
1035 | 'order_avoided': 'true', | |
1036 | 'platform': 'web', | |
1037 | 'pn': page_idx + 1, | |
1038 | 'ps': 30, | |
1039 | 'tid': 0, | |
1040 | 'web_location': 1550101, | |
1041 | 'wts': int(time.time()), | |
1042 | } | |
1043 | query['w_rid'] = hashlib.md5(f'{urllib.parse.urlencode(query)}{signature}'.encode()).hexdigest() | |
1044 | ||
1045 | try: | |
1046 | response = self._download_json('https://api.bilibili.com/x/space/wbi/arc/search', | |
1047 | playlist_id, note=f'Downloading page {page_idx}', query=query, | |
1048 | headers={'referer': url}) | |
1049 | except ExtractorError as e: | |
1050 | if isinstance(e.cause, HTTPError) and e.cause.status == 412: | |
1051 | raise ExtractorError( | |
1052 | 'Request is blocked by server (412), please add cookies, wait and try later.', expected=True) | |
1053 | raise | |
1054 | if response['code'] in (-352, -401): | |
1055 | raise ExtractorError( | |
1056 | f'Request is blocked by server ({-response["code"]}), ' | |
1057 | 'please add cookies, wait and try later.', expected=True) | |
1058 | return response['data'] | |
1059 | ||
1060 | def get_metadata(page_data): | |
1061 | page_size = page_data['page']['ps'] | |
1062 | entry_count = page_data['page']['count'] | |
1063 | return { | |
1064 | 'page_count': math.ceil(entry_count / page_size), | |
1065 | 'page_size': page_size, | |
1066 | } | |
1067 | ||
1068 | def get_entries(page_data): | |
1069 | for entry in traverse_obj(page_data, ('list', 'vlist')) or []: | |
1070 | yield self.url_result(f'https://www.bilibili.com/video/{entry["bvid"]}', BiliBiliIE, entry['bvid']) | |
1071 | ||
1072 | metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries) | |
1073 | return self.playlist_result(paged_list, playlist_id) | |
1074 | ||
1075 | ||
1076 | class BilibiliSpaceAudioIE(BilibiliSpaceBaseIE): | |
1077 | _VALID_URL = r'https?://space\.bilibili\.com/(?P<id>\d+)/audio' | |
1078 | _TESTS = [{ | |
1079 | 'url': 'https://space.bilibili.com/313580179/audio', | |
1080 | 'info_dict': { | |
1081 | 'id': '313580179', | |
1082 | }, | |
1083 | 'playlist_mincount': 1, | |
1084 | }] | |
1085 | ||
1086 | def _real_extract(self, url): | |
1087 | playlist_id = self._match_id(url) | |
1088 | ||
1089 | def fetch_page(page_idx): | |
1090 | return self._download_json( | |
1091 | 'https://api.bilibili.com/audio/music-service/web/song/upper', playlist_id, | |
1092 | note=f'Downloading page {page_idx}', | |
1093 | query={'uid': playlist_id, 'pn': page_idx + 1, 'ps': 30, 'order': 1, 'jsonp': 'jsonp'})['data'] | |
1094 | ||
1095 | def get_metadata(page_data): | |
1096 | return { | |
1097 | 'page_count': page_data['pageCount'], | |
1098 | 'page_size': page_data['pageSize'], | |
1099 | } | |
1100 | ||
1101 | def get_entries(page_data): | |
1102 | for entry in page_data.get('data', []): | |
1103 | yield self.url_result(f'https://www.bilibili.com/audio/au{entry["id"]}', BilibiliAudioIE, entry['id']) | |
1104 | ||
1105 | metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries) | |
1106 | return self.playlist_result(paged_list, playlist_id) | |
1107 | ||
1108 | ||
1109 | class BilibiliSpaceListBaseIE(BilibiliSpaceBaseIE): | |
1110 | def _get_entries(self, page_data, bvid_keys, ending_key='bvid'): | |
1111 | for bvid in traverse_obj(page_data, (*variadic(bvid_keys, (str, bytes, dict, set)), ..., ending_key, {str})): | |
1112 | yield self.url_result(f'https://www.bilibili.com/video/{bvid}', BiliBiliIE, bvid) | |
1113 | ||
1114 | def _get_uploader(self, uid, playlist_id): | |
1115 | webpage = self._download_webpage(f'https://space.bilibili.com/{uid}', playlist_id, fatal=False) | |
1116 | return self._search_regex(r'(?s)<title\b[^>]*>([^<]+)的个人空间-', webpage, 'uploader', fatal=False) | |
1117 | ||
1118 | def _extract_playlist(self, fetch_page, get_metadata, get_entries): | |
1119 | metadata, page_list = super()._extract_playlist(fetch_page, get_metadata, get_entries) | |
1120 | metadata.pop('page_count', None) | |
1121 | metadata.pop('page_size', None) | |
1122 | return metadata, page_list | |
1123 | ||
1124 | ||
1125 | class BilibiliCollectionListIE(BilibiliSpaceListBaseIE): | |
1126 | _VALID_URL = r'https?://space\.bilibili\.com/(?P<mid>\d+)/channel/collectiondetail/?\?sid=(?P<sid>\d+)' | |
1127 | _TESTS = [{ | |
1128 | 'url': 'https://space.bilibili.com/2142762/channel/collectiondetail?sid=57445', | |
1129 | 'info_dict': { | |
1130 | 'id': '2142762_57445', | |
1131 | 'title': '【完结】《底特律 变人》全结局流程解说', | |
1132 | 'description': '', | |
1133 | 'uploader': '老戴在此', | |
1134 | 'uploader_id': '2142762', | |
1135 | 'timestamp': int, | |
1136 | 'upload_date': str, | |
1137 | 'thumbnail': 'https://archive.biliimg.com/bfs/archive/e0e543ae35ad3df863ea7dea526bc32e70f4c091.jpg', | |
1138 | }, | |
1139 | 'playlist_mincount': 31, | |
1140 | }] | |
1141 | ||
1142 | def _real_extract(self, url): | |
1143 | mid, sid = self._match_valid_url(url).group('mid', 'sid') | |
1144 | playlist_id = f'{mid}_{sid}' | |
1145 | ||
1146 | def fetch_page(page_idx): | |
1147 | return self._download_json( | |
1148 | 'https://api.bilibili.com/x/polymer/space/seasons_archives_list', | |
1149 | playlist_id, note=f'Downloading page {page_idx}', | |
1150 | query={'mid': mid, 'season_id': sid, 'page_num': page_idx + 1, 'page_size': 30})['data'] | |
1151 | ||
1152 | def get_metadata(page_data): | |
1153 | page_size = page_data['page']['page_size'] | |
1154 | entry_count = page_data['page']['total'] | |
1155 | return { | |
1156 | 'page_count': math.ceil(entry_count / page_size), | |
1157 | 'page_size': page_size, | |
1158 | 'uploader': self._get_uploader(mid, playlist_id), | |
1159 | **traverse_obj(page_data, { | |
1160 | 'title': ('meta', 'name', {str}), | |
1161 | 'description': ('meta', 'description', {str}), | |
1162 | 'uploader_id': ('meta', 'mid', {str_or_none}), | |
1163 | 'timestamp': ('meta', 'ptime', {int_or_none}), | |
1164 | 'thumbnail': ('meta', 'cover', {url_or_none}), | |
1165 | }), | |
1166 | } | |
1167 | ||
1168 | def get_entries(page_data): | |
1169 | return self._get_entries(page_data, 'archives') | |
1170 | ||
1171 | metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries) | |
1172 | return self.playlist_result(paged_list, playlist_id, **metadata) | |
1173 | ||
1174 | ||
1175 | class BilibiliSeriesListIE(BilibiliSpaceListBaseIE): | |
1176 | _VALID_URL = r'https?://space\.bilibili\.com/(?P<mid>\d+)/channel/seriesdetail/?\?\bsid=(?P<sid>\d+)' | |
1177 | _TESTS = [{ | |
1178 | 'url': 'https://space.bilibili.com/1958703906/channel/seriesdetail?sid=547718&ctype=0', | |
1179 | 'info_dict': { | |
1180 | 'id': '1958703906_547718', | |
1181 | 'title': '直播回放', | |
1182 | 'description': '直播回放', | |
1183 | 'uploader': '靡烟miya', | |
1184 | 'uploader_id': '1958703906', | |
1185 | 'timestamp': 1637985853, | |
1186 | 'upload_date': '20211127', | |
1187 | 'modified_timestamp': int, | |
1188 | 'modified_date': str, | |
1189 | }, | |
1190 | 'playlist_mincount': 513, | |
1191 | }] | |
1192 | ||
1193 | def _real_extract(self, url): | |
1194 | mid, sid = self._match_valid_url(url).group('mid', 'sid') | |
1195 | playlist_id = f'{mid}_{sid}' | |
1196 | playlist_meta = traverse_obj(self._download_json( | |
1197 | f'https://api.bilibili.com/x/series/series?series_id={sid}', playlist_id, fatal=False, | |
1198 | ), { | |
1199 | 'title': ('data', 'meta', 'name', {str}), | |
1200 | 'description': ('data', 'meta', 'description', {str}), | |
1201 | 'uploader_id': ('data', 'meta', 'mid', {str_or_none}), | |
1202 | 'timestamp': ('data', 'meta', 'ctime', {int_or_none}), | |
1203 | 'modified_timestamp': ('data', 'meta', 'mtime', {int_or_none}), | |
1204 | }) | |
1205 | ||
1206 | def fetch_page(page_idx): | |
1207 | return self._download_json( | |
1208 | 'https://api.bilibili.com/x/series/archives', | |
1209 | playlist_id, note=f'Downloading page {page_idx}', | |
1210 | query={'mid': mid, 'series_id': sid, 'pn': page_idx + 1, 'ps': 30})['data'] | |
1211 | ||
1212 | def get_metadata(page_data): | |
1213 | page_size = page_data['page']['size'] | |
1214 | entry_count = page_data['page']['total'] | |
1215 | return { | |
1216 | 'page_count': math.ceil(entry_count / page_size), | |
1217 | 'page_size': page_size, | |
1218 | 'uploader': self._get_uploader(mid, playlist_id), | |
1219 | **playlist_meta, | |
1220 | } | |
1221 | ||
1222 | def get_entries(page_data): | |
1223 | return self._get_entries(page_data, 'archives') | |
1224 | ||
1225 | metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries) | |
1226 | return self.playlist_result(paged_list, playlist_id, **metadata) | |
1227 | ||
1228 | ||
1229 | class BilibiliFavoritesListIE(BilibiliSpaceListBaseIE): | |
1230 | _VALID_URL = r'https?://(?:space\.bilibili\.com/\d+/favlist/?\?fid=|(?:www\.)?bilibili\.com/medialist/detail/ml)(?P<id>\d+)' | |
1231 | _TESTS = [{ | |
1232 | 'url': 'https://space.bilibili.com/84912/favlist?fid=1103407912&ftype=create', | |
1233 | 'info_dict': { | |
1234 | 'id': '1103407912', | |
1235 | 'title': '【V2】(旧)', | |
1236 | 'description': '', | |
1237 | 'uploader': '晓月春日', | |
1238 | 'uploader_id': '84912', | |
1239 | 'timestamp': 1604905176, | |
1240 | 'upload_date': '20201109', | |
1241 | 'modified_timestamp': int, | |
1242 | 'modified_date': str, | |
1243 | 'thumbnail': r're:http://i\d\.hdslb\.com/bfs/archive/14b83c62aa8871b79083df1e9ab4fbc699ad16fe\.jpg', | |
1244 | 'view_count': int, | |
1245 | 'like_count': int, | |
1246 | }, | |
1247 | 'playlist_mincount': 22, | |
1248 | }, { | |
1249 | 'url': 'https://www.bilibili.com/medialist/detail/ml1103407912', | |
1250 | 'only_matching': True, | |
1251 | }] | |
1252 | ||
1253 | def _real_extract(self, url): | |
1254 | fid = self._match_id(url) | |
1255 | ||
1256 | list_info = self._download_json( | |
1257 | f'https://api.bilibili.com/x/v3/fav/resource/list?media_id={fid}&pn=1&ps=20', | |
1258 | fid, note='Downloading favlist metadata') | |
1259 | if list_info['code'] == -403: | |
1260 | self.raise_login_required(msg='This is a private favorites list. You need to log in as its owner') | |
1261 | ||
1262 | entries = self._get_entries(self._download_json( | |
1263 | f'https://api.bilibili.com/x/v3/fav/resource/ids?media_id={fid}', | |
1264 | fid, note='Download favlist entries'), 'data') | |
1265 | ||
1266 | return self.playlist_result(entries, fid, **traverse_obj(list_info, ('data', 'info', { | |
1267 | 'title': ('title', {str}), | |
1268 | 'description': ('intro', {str}), | |
1269 | 'uploader': ('upper', 'name', {str}), | |
1270 | 'uploader_id': ('upper', 'mid', {str_or_none}), | |
1271 | 'timestamp': ('ctime', {int_or_none}), | |
1272 | 'modified_timestamp': ('mtime', {int_or_none}), | |
1273 | 'thumbnail': ('cover', {url_or_none}), | |
1274 | 'view_count': ('cnt_info', 'play', {int_or_none}), | |
1275 | 'like_count': ('cnt_info', 'thumb_up', {int_or_none}), | |
1276 | }))) | |
1277 | ||
1278 | ||
1279 | class BilibiliWatchlaterIE(BilibiliSpaceListBaseIE): | |
1280 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/watchlater/?(?:[?#]|$)' | |
1281 | _TESTS = [{ | |
1282 | 'url': 'https://www.bilibili.com/watchlater/#/list', | |
1283 | 'info_dict': {'id': 'watchlater'}, | |
1284 | 'playlist_mincount': 0, | |
1285 | 'skip': 'login required', | |
1286 | }] | |
1287 | ||
1288 | def _real_extract(self, url): | |
1289 | list_id = getattr(self._get_cookies(url).get('DedeUserID'), 'value', 'watchlater') | |
1290 | watchlater_info = self._download_json( | |
1291 | 'https://api.bilibili.com/x/v2/history/toview/web?jsonp=jsonp', list_id) | |
1292 | if watchlater_info['code'] == -101: | |
1293 | self.raise_login_required(msg='You need to login to access your watchlater list') | |
1294 | entries = self._get_entries(watchlater_info, ('data', 'list')) | |
1295 | return self.playlist_result(entries, id=list_id, title='稍后再看') | |
1296 | ||
1297 | ||
1298 | class BilibiliPlaylistIE(BilibiliSpaceListBaseIE): | |
1299 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:medialist/play|list)/(?P<id>\w+)' | |
1300 | _TESTS = [{ | |
1301 | 'url': 'https://www.bilibili.com/list/1958703906?sid=547718', | |
1302 | 'info_dict': { | |
1303 | 'id': '5_547718', | |
1304 | 'title': '直播回放', | |
1305 | 'uploader': '靡烟miya', | |
1306 | 'uploader_id': '1958703906', | |
1307 | 'timestamp': 1637985853, | |
1308 | 'upload_date': '20211127', | |
1309 | }, | |
1310 | 'playlist_mincount': 513, | |
1311 | }, { | |
1312 | 'url': 'https://www.bilibili.com/list/1958703906?sid=547718&oid=687146339&bvid=BV1DU4y1r7tz', | |
1313 | 'info_dict': { | |
1314 | 'id': 'BV1DU4y1r7tz', | |
1315 | 'ext': 'mp4', | |
1316 | 'title': '【直播回放】8.20晚9:30 3d发布喵 2022年8月20日21点场', | |
1317 | 'upload_date': '20220820', | |
1318 | 'description': '', | |
1319 | 'timestamp': 1661016330, | |
1320 | 'uploader_id': '1958703906', | |
1321 | 'uploader': '靡烟miya', | |
1322 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
1323 | 'duration': 9552.903, | |
1324 | 'tags': list, | |
1325 | 'comment_count': int, | |
1326 | 'view_count': int, | |
1327 | 'like_count': int, | |
1328 | '_old_archive_ids': ['bilibili 687146339_part1'], | |
1329 | }, | |
1330 | 'params': {'noplaylist': True}, | |
1331 | }, { | |
1332 | 'url': 'https://www.bilibili.com/medialist/play/1958703906?business=space_series&business_id=547718&desc=1', | |
1333 | 'info_dict': { | |
1334 | 'id': '5_547718', | |
1335 | }, | |
1336 | 'playlist_mincount': 513, | |
1337 | 'skip': 'redirect url', | |
1338 | }, { | |
1339 | 'url': 'https://www.bilibili.com/list/ml1103407912', | |
1340 | 'info_dict': { | |
1341 | 'id': '3_1103407912', | |
1342 | 'title': '【V2】(旧)', | |
1343 | 'uploader': '晓月春日', | |
1344 | 'uploader_id': '84912', | |
1345 | 'timestamp': 1604905176, | |
1346 | 'upload_date': '20201109', | |
1347 | 'thumbnail': r're:http://i\d\.hdslb\.com/bfs/archive/14b83c62aa8871b79083df1e9ab4fbc699ad16fe\.jpg', | |
1348 | }, | |
1349 | 'playlist_mincount': 22, | |
1350 | }, { | |
1351 | 'url': 'https://www.bilibili.com/medialist/play/ml1103407912', | |
1352 | 'info_dict': { | |
1353 | 'id': '3_1103407912', | |
1354 | }, | |
1355 | 'playlist_mincount': 22, | |
1356 | 'skip': 'redirect url', | |
1357 | }, { | |
1358 | 'url': 'https://www.bilibili.com/list/watchlater', | |
1359 | 'info_dict': {'id': 'watchlater'}, | |
1360 | 'playlist_mincount': 0, | |
1361 | 'skip': 'login required', | |
1362 | }, { | |
1363 | 'url': 'https://www.bilibili.com/medialist/play/watchlater', | |
1364 | 'info_dict': {'id': 'watchlater'}, | |
1365 | 'playlist_mincount': 0, | |
1366 | 'skip': 'login required', | |
1367 | }] | |
1368 | ||
1369 | def _extract_medialist(self, query, list_id): | |
1370 | for page_num in itertools.count(1): | |
1371 | page_data = self._download_json( | |
1372 | 'https://api.bilibili.com/x/v2/medialist/resource/list', | |
1373 | list_id, query=query, note=f'getting playlist {query["biz_id"]} page {page_num}', | |
1374 | )['data'] | |
1375 | yield from self._get_entries(page_data, 'media_list', ending_key='bv_id') | |
1376 | query['oid'] = traverse_obj(page_data, ('media_list', -1, 'id')) | |
1377 | if not page_data.get('has_more', False): | |
1378 | break | |
1379 | ||
1380 | def _real_extract(self, url): | |
1381 | list_id = self._match_id(url) | |
1382 | ||
1383 | bvid = traverse_obj(parse_qs(url), ('bvid', 0)) | |
1384 | if not self._yes_playlist(list_id, bvid): | |
1385 | return self.url_result(f'https://www.bilibili.com/video/{bvid}', BiliBiliIE) | |
1386 | ||
1387 | webpage = self._download_webpage(url, list_id) | |
1388 | initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', list_id) | |
1389 | if traverse_obj(initial_state, ('error', 'code', {int_or_none})) != 200: | |
1390 | error_code = traverse_obj(initial_state, ('error', 'trueCode', {int_or_none})) | |
1391 | error_message = traverse_obj(initial_state, ('error', 'message', {str_or_none})) | |
1392 | if error_code == -400 and list_id == 'watchlater': | |
1393 | self.raise_login_required('You need to login to access your watchlater playlist') | |
1394 | elif error_code == -403: | |
1395 | self.raise_login_required('This is a private playlist. You need to login as its owner') | |
1396 | elif error_code == 11010: | |
1397 | raise ExtractorError('Playlist is no longer available', expected=True) | |
1398 | raise ExtractorError(f'Could not access playlist: {error_code} {error_message}') | |
1399 | ||
1400 | query = { | |
1401 | 'ps': 20, | |
1402 | 'with_current': False, | |
1403 | **traverse_obj(initial_state, { | |
1404 | 'type': ('playlist', 'type', {int_or_none}), | |
1405 | 'biz_id': ('playlist', 'id', {int_or_none}), | |
1406 | 'tid': ('tid', {int_or_none}), | |
1407 | 'sort_field': ('sortFiled', {int_or_none}), | |
1408 | 'desc': ('desc', {bool_or_none}, {str_or_none}, {str.lower}), | |
1409 | }), | |
1410 | } | |
1411 | metadata = { | |
1412 | 'id': f'{query["type"]}_{query["biz_id"]}', | |
1413 | **traverse_obj(initial_state, ('mediaListInfo', { | |
1414 | 'title': ('title', {str}), | |
1415 | 'uploader': ('upper', 'name', {str}), | |
1416 | 'uploader_id': ('upper', 'mid', {str_or_none}), | |
1417 | 'timestamp': ('ctime', {int_or_none}), | |
1418 | 'thumbnail': ('cover', {url_or_none}), | |
1419 | })), | |
1420 | } | |
1421 | return self.playlist_result(self._extract_medialist(query, list_id), **metadata) | |
1422 | ||
1423 | ||
1424 | class BilibiliCategoryIE(InfoExtractor): | |
1425 | IE_NAME = 'Bilibili category extractor' | |
1426 | _MAX_RESULTS = 1000000 | |
1427 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/v/[a-zA-Z]+\/[a-zA-Z]+' | |
1428 | _TESTS = [{ | |
1429 | 'url': 'https://www.bilibili.com/v/kichiku/mad', | |
1430 | 'info_dict': { | |
1431 | 'id': 'kichiku: mad', | |
1432 | 'title': 'kichiku: mad', | |
1433 | }, | |
1434 | 'playlist_mincount': 45, | |
1435 | 'params': { | |
1436 | 'playlistend': 45, | |
1437 | }, | |
1438 | }] | |
1439 | ||
1440 | def _fetch_page(self, api_url, num_pages, query, page_num): | |
1441 | parsed_json = self._download_json( | |
1442 | api_url, query, query={'Search_key': query, 'pn': page_num}, | |
1443 | note=f'Extracting results from page {page_num} of {num_pages}') | |
1444 | ||
1445 | video_list = traverse_obj(parsed_json, ('data', 'archives'), expected_type=list) | |
1446 | if not video_list: | |
1447 | raise ExtractorError(f'Failed to retrieve video list for page {page_num}') | |
1448 | ||
1449 | for video in video_list: | |
1450 | yield self.url_result( | |
1451 | 'https://www.bilibili.com/video/{}'.format(video['bvid']), 'BiliBili', video['bvid']) | |
1452 | ||
1453 | def _entries(self, category, subcategory, query): | |
1454 | # map of categories : subcategories : RIDs | |
1455 | rid_map = { | |
1456 | 'kichiku': { | |
1457 | 'mad': 26, | |
1458 | 'manual_vocaloid': 126, | |
1459 | 'guide': 22, | |
1460 | 'theatre': 216, | |
1461 | 'course': 127, | |
1462 | }, | |
1463 | } | |
1464 | ||
1465 | if category not in rid_map: | |
1466 | raise ExtractorError( | |
1467 | f'The category {category} isn\'t supported. Supported categories: {list(rid_map.keys())}') | |
1468 | if subcategory not in rid_map[category]: | |
1469 | raise ExtractorError( | |
1470 | f'The subcategory {subcategory} isn\'t supported for this category. Supported subcategories: {list(rid_map[category].keys())}') | |
1471 | rid_value = rid_map[category][subcategory] | |
1472 | ||
1473 | api_url = 'https://api.bilibili.com/x/web-interface/newlist?rid=%d&type=1&ps=20&jsonp=jsonp' % rid_value | |
1474 | page_json = self._download_json(api_url, query, query={'Search_key': query, 'pn': '1'}) | |
1475 | page_data = traverse_obj(page_json, ('data', 'page'), expected_type=dict) | |
1476 | count, size = int_or_none(page_data.get('count')), int_or_none(page_data.get('size')) | |
1477 | if count is None or not size: | |
1478 | raise ExtractorError('Failed to calculate either page count or size') | |
1479 | ||
1480 | num_pages = math.ceil(count / size) | |
1481 | ||
1482 | return OnDemandPagedList(functools.partial( | |
1483 | self._fetch_page, api_url, num_pages, query), size) | |
1484 | ||
1485 | def _real_extract(self, url): | |
1486 | category, subcategory = urllib.parse.urlparse(url).path.split('/')[2:4] | |
1487 | query = f'{category}: {subcategory}' | |
1488 | ||
1489 | return self.playlist_result(self._entries(category, subcategory, query), query, query) | |
1490 | ||
1491 | ||
1492 | class BiliBiliSearchIE(SearchInfoExtractor): | |
1493 | IE_DESC = 'Bilibili video search' | |
1494 | _MAX_RESULTS = 100000 | |
1495 | _SEARCH_KEY = 'bilisearch' | |
1496 | _TESTS = [{ | |
1497 | 'url': 'bilisearch3:靡烟 出道一年,我怎么还在等你单推的女人睡觉后开播啊', | |
1498 | 'playlist_count': 3, | |
1499 | 'info_dict': { | |
1500 | 'id': '靡烟 出道一年,我怎么还在等你单推的女人睡觉后开播啊', | |
1501 | 'title': '靡烟 出道一年,我怎么还在等你单推的女人睡觉后开播啊', | |
1502 | }, | |
1503 | 'playlist': [{ | |
1504 | 'info_dict': { | |
1505 | 'id': 'BV1n44y1Q7sc', | |
1506 | 'ext': 'mp4', | |
1507 | 'title': '“出道一年,我怎么还在等你单推的女人睡觉后开播啊?”【一分钟了解靡烟miya】', | |
1508 | 'timestamp': 1669889987, | |
1509 | 'upload_date': '20221201', | |
1510 | 'description': 'md5:43343c0973defff527b5a4b403b4abf9', | |
1511 | 'tags': list, | |
1512 | 'uploader': '靡烟miya', | |
1513 | 'duration': 123.156, | |
1514 | 'uploader_id': '1958703906', | |
1515 | 'comment_count': int, | |
1516 | 'view_count': int, | |
1517 | 'like_count': int, | |
1518 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
1519 | '_old_archive_ids': ['bilibili 988222410_part1'], | |
1520 | }, | |
1521 | }], | |
1522 | }] | |
1523 | ||
1524 | def _search_results(self, query): | |
1525 | if not self._get_cookies('https://api.bilibili.com').get('buvid3'): | |
1526 | self._set_cookie('.bilibili.com', 'buvid3', f'{uuid.uuid4()}infoc') | |
1527 | for page_num in itertools.count(1): | |
1528 | videos = self._download_json( | |
1529 | 'https://api.bilibili.com/x/web-interface/search/type', query, | |
1530 | note=f'Extracting results from page {page_num}', query={ | |
1531 | 'Search_key': query, | |
1532 | 'keyword': query, | |
1533 | 'page': page_num, | |
1534 | 'context': '', | |
1535 | 'duration': 0, | |
1536 | 'tids_2': '', | |
1537 | '__refresh__': 'true', | |
1538 | 'search_type': 'video', | |
1539 | 'tids': 0, | |
1540 | 'highlight': 1, | |
1541 | })['data'].get('result') | |
1542 | if not videos: | |
1543 | break | |
1544 | for video in videos: | |
1545 | yield self.url_result(video['arcurl'], 'BiliBili', str(video['aid'])) | |
1546 | ||
1547 | ||
1548 | class BilibiliAudioBaseIE(InfoExtractor): | |
1549 | def _call_api(self, path, sid, query=None): | |
1550 | if not query: | |
1551 | query = {'sid': sid} | |
1552 | return self._download_json( | |
1553 | 'https://www.bilibili.com/audio/music-service-c/web/' + path, | |
1554 | sid, query=query)['data'] | |
1555 | ||
1556 | ||
1557 | class BilibiliAudioIE(BilibiliAudioBaseIE): | |
1558 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/audio/au(?P<id>\d+)' | |
1559 | _TEST = { | |
1560 | 'url': 'https://www.bilibili.com/audio/au1003142', | |
1561 | 'md5': 'fec4987014ec94ef9e666d4d158ad03b', | |
1562 | 'info_dict': { | |
1563 | 'id': '1003142', | |
1564 | 'ext': 'm4a', | |
1565 | 'title': '【tsukimi】YELLOW / 神山羊', | |
1566 | 'artist': 'tsukimi', | |
1567 | 'comment_count': int, | |
1568 | 'description': 'YELLOW的mp3版!', | |
1569 | 'duration': 183, | |
1570 | 'subtitles': { | |
1571 | 'origin': [{ | |
1572 | 'ext': 'lrc', | |
1573 | }], | |
1574 | }, | |
1575 | 'thumbnail': r're:^https?://.+\.jpg', | |
1576 | 'timestamp': 1564836614, | |
1577 | 'upload_date': '20190803', | |
1578 | 'uploader': 'tsukimi-つきみぐー', | |
1579 | 'view_count': int, | |
1580 | }, | |
1581 | } | |
1582 | ||
1583 | def _real_extract(self, url): | |
1584 | au_id = self._match_id(url) | |
1585 | ||
1586 | play_data = self._call_api('url', au_id) | |
1587 | formats = [{ | |
1588 | 'url': play_data['cdns'][0], | |
1589 | 'filesize': int_or_none(play_data.get('size')), | |
1590 | 'vcodec': 'none', | |
1591 | }] | |
1592 | ||
1593 | for a_format in formats: | |
1594 | a_format.setdefault('http_headers', {}).update({ | |
1595 | 'Referer': url, | |
1596 | }) | |
1597 | ||
1598 | song = self._call_api('song/info', au_id) | |
1599 | title = song['title'] | |
1600 | statistic = song.get('statistic') or {} | |
1601 | ||
1602 | subtitles = None | |
1603 | lyric = song.get('lyric') | |
1604 | if lyric: | |
1605 | subtitles = { | |
1606 | 'origin': [{ | |
1607 | 'url': lyric, | |
1608 | }], | |
1609 | } | |
1610 | ||
1611 | return { | |
1612 | 'id': au_id, | |
1613 | 'title': title, | |
1614 | 'formats': formats, | |
1615 | 'artist': song.get('author'), | |
1616 | 'comment_count': int_or_none(statistic.get('comment')), | |
1617 | 'description': song.get('intro'), | |
1618 | 'duration': int_or_none(song.get('duration')), | |
1619 | 'subtitles': subtitles, | |
1620 | 'thumbnail': song.get('cover'), | |
1621 | 'timestamp': int_or_none(song.get('passtime')), | |
1622 | 'uploader': song.get('uname'), | |
1623 | 'view_count': int_or_none(statistic.get('play')), | |
1624 | } | |
1625 | ||
1626 | ||
1627 | class BilibiliAudioAlbumIE(BilibiliAudioBaseIE): | |
1628 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/audio/am(?P<id>\d+)' | |
1629 | _TEST = { | |
1630 | 'url': 'https://www.bilibili.com/audio/am10624', | |
1631 | 'info_dict': { | |
1632 | 'id': '10624', | |
1633 | 'title': '每日新曲推荐(每日11:00更新)', | |
1634 | 'description': '每天11:00更新,为你推送最新音乐', | |
1635 | }, | |
1636 | 'playlist_count': 19, | |
1637 | } | |
1638 | ||
1639 | def _real_extract(self, url): | |
1640 | am_id = self._match_id(url) | |
1641 | ||
1642 | songs = self._call_api( | |
1643 | 'song/of-menu', am_id, {'sid': am_id, 'pn': 1, 'ps': 100})['data'] | |
1644 | ||
1645 | entries = [] | |
1646 | for song in songs: | |
1647 | sid = str_or_none(song.get('id')) | |
1648 | if not sid: | |
1649 | continue | |
1650 | entries.append(self.url_result( | |
1651 | 'https://www.bilibili.com/audio/au' + sid, | |
1652 | BilibiliAudioIE.ie_key(), sid)) | |
1653 | ||
1654 | if entries: | |
1655 | album_data = self._call_api('menu/info', am_id) or {} | |
1656 | album_title = album_data.get('title') | |
1657 | if album_title: | |
1658 | for entry in entries: | |
1659 | entry['album'] = album_title | |
1660 | return self.playlist_result( | |
1661 | entries, am_id, album_title, album_data.get('intro')) | |
1662 | ||
1663 | return self.playlist_result(entries, am_id) | |
1664 | ||
1665 | ||
1666 | class BiliBiliPlayerIE(InfoExtractor): | |
1667 | _VALID_URL = r'https?://player\.bilibili\.com/player\.html\?.*?\baid=(?P<id>\d+)' | |
1668 | _TEST = { | |
1669 | 'url': 'http://player.bilibili.com/player.html?aid=92494333&cid=157926707&page=1', | |
1670 | 'only_matching': True, | |
1671 | } | |
1672 | ||
1673 | def _real_extract(self, url): | |
1674 | video_id = self._match_id(url) | |
1675 | return self.url_result( | |
1676 | f'http://www.bilibili.tv/video/av{video_id}/', | |
1677 | ie=BiliBiliIE.ie_key(), video_id=video_id) | |
1678 | ||
1679 | ||
1680 | class BiliIntlBaseIE(InfoExtractor): | |
1681 | _API_URL = 'https://api.bilibili.tv/intl/gateway' | |
1682 | _NETRC_MACHINE = 'biliintl' | |
1683 | _HEADERS = {'Referer': 'https://www.bilibili.com/'} | |
1684 | ||
1685 | def _call_api(self, endpoint, *args, **kwargs): | |
1686 | json = self._download_json(self._API_URL + endpoint, *args, **kwargs) | |
1687 | if json.get('code'): | |
1688 | if json['code'] in (10004004, 10004005, 10023006): | |
1689 | self.raise_login_required() | |
1690 | elif json['code'] == 10004001: | |
1691 | self.raise_geo_restricted() | |
1692 | else: | |
1693 | if json.get('message') and str(json['code']) != json['message']: | |
1694 | errmsg = f'{kwargs.get("errnote", "Unable to download JSON metadata")}: {self.IE_NAME} said: {json["message"]}' | |
1695 | else: | |
1696 | errmsg = kwargs.get('errnote', 'Unable to download JSON metadata') | |
1697 | if kwargs.get('fatal'): | |
1698 | raise ExtractorError(errmsg) | |
1699 | else: | |
1700 | self.report_warning(errmsg) | |
1701 | return json.get('data') | |
1702 | ||
1703 | def json2srt(self, json): | |
1704 | return '\n\n'.join( | |
1705 | f'{i + 1}\n{srt_subtitles_timecode(line["from"])} --> {srt_subtitles_timecode(line["to"])}\n{line["content"]}' | |
1706 | for i, line in enumerate(traverse_obj(json, ( | |
1707 | 'body', lambda _, l: l['content'] and l['from'] and l['to'])))) | |
1708 | ||
1709 | def _get_subtitles(self, *, ep_id=None, aid=None): | |
1710 | sub_json = self._call_api( | |
1711 | '/web/v2/subtitle', ep_id or aid, fatal=False, | |
1712 | note='Downloading subtitles list', errnote='Unable to download subtitles list', | |
1713 | query=filter_dict({ | |
1714 | 'platform': 'web', | |
1715 | 's_locale': 'en_US', | |
1716 | 'episode_id': ep_id, | |
1717 | 'aid': aid, | |
1718 | })) or {} | |
1719 | subtitles = {} | |
1720 | fetched_urls = set() | |
1721 | for sub in traverse_obj(sub_json, (('subtitles', 'video_subtitle'), ..., {dict})): | |
1722 | for url in traverse_obj(sub, ((None, 'ass', 'srt'), 'url', {url_or_none})): | |
1723 | if url in fetched_urls: | |
1724 | continue | |
1725 | fetched_urls.add(url) | |
1726 | sub_ext = determine_ext(url) | |
1727 | sub_lang = sub.get('lang_key') or 'en' | |
1728 | ||
1729 | if sub_ext == 'ass': | |
1730 | subtitles.setdefault(sub_lang, []).append({ | |
1731 | 'ext': 'ass', | |
1732 | 'url': url, | |
1733 | }) | |
1734 | elif sub_ext == 'json': | |
1735 | sub_data = self._download_json( | |
1736 | url, ep_id or aid, fatal=False, | |
1737 | note=f'Downloading subtitles{format_field(sub, "lang", " for %s")} ({sub_lang})', | |
1738 | errnote='Unable to download subtitles') | |
1739 | ||
1740 | if sub_data: | |
1741 | subtitles.setdefault(sub_lang, []).append({ | |
1742 | 'ext': 'srt', | |
1743 | 'data': self.json2srt(sub_data), | |
1744 | }) | |
1745 | else: | |
1746 | self.report_warning('Unexpected subtitle extension', ep_id or aid) | |
1747 | ||
1748 | return subtitles | |
1749 | ||
1750 | def _get_formats(self, *, ep_id=None, aid=None): | |
1751 | video_json = self._call_api( | |
1752 | '/web/playurl', ep_id or aid, note='Downloading video formats', | |
1753 | errnote='Unable to download video formats', query=filter_dict({ | |
1754 | 'platform': 'web', | |
1755 | 'ep_id': ep_id, | |
1756 | 'aid': aid, | |
1757 | })) | |
1758 | video_json = video_json['playurl'] | |
1759 | formats = [] | |
1760 | for vid in video_json.get('video') or []: | |
1761 | video_res = vid.get('video_resource') or {} | |
1762 | video_info = vid.get('stream_info') or {} | |
1763 | if not video_res.get('url'): | |
1764 | continue | |
1765 | formats.append({ | |
1766 | 'url': video_res['url'], | |
1767 | 'ext': 'mp4', | |
1768 | 'format_note': video_info.get('desc_words'), | |
1769 | 'width': video_res.get('width'), | |
1770 | 'height': video_res.get('height'), | |
1771 | 'vbr': video_res.get('bandwidth'), | |
1772 | 'acodec': 'none', | |
1773 | 'vcodec': video_res.get('codecs'), | |
1774 | 'filesize': video_res.get('size'), | |
1775 | }) | |
1776 | for aud in video_json.get('audio_resource') or []: | |
1777 | if not aud.get('url'): | |
1778 | continue | |
1779 | formats.append({ | |
1780 | 'url': aud['url'], | |
1781 | 'ext': 'mp4', | |
1782 | 'abr': aud.get('bandwidth'), | |
1783 | 'acodec': aud.get('codecs'), | |
1784 | 'vcodec': 'none', | |
1785 | 'filesize': aud.get('size'), | |
1786 | }) | |
1787 | ||
1788 | return formats | |
1789 | ||
1790 | def _parse_video_metadata(self, video_data): | |
1791 | return { | |
1792 | 'title': video_data.get('title_display') or video_data.get('title'), | |
1793 | 'description': video_data.get('desc'), | |
1794 | 'thumbnail': video_data.get('cover'), | |
1795 | 'timestamp': unified_timestamp(video_data.get('formatted_pub_date')), | |
1796 | 'episode_number': int_or_none(self._search_regex( | |
1797 | r'^E(\d+)(?:$| - )', video_data.get('title_display') or '', 'episode number', default=None)), | |
1798 | } | |
1799 | ||
1800 | def _perform_login(self, username, password): | |
1801 | if not Cryptodome.RSA: | |
1802 | raise ExtractorError('pycryptodomex not found. Please install', expected=True) | |
1803 | ||
1804 | key_data = self._download_json( | |
1805 | 'https://passport.bilibili.tv/x/intl/passport-login/web/key?lang=en-US', None, | |
1806 | note='Downloading login key', errnote='Unable to download login key')['data'] | |
1807 | ||
1808 | public_key = Cryptodome.RSA.importKey(key_data['key']) | |
1809 | password_hash = Cryptodome.PKCS1_v1_5.new(public_key).encrypt((key_data['hash'] + password).encode()) | |
1810 | login_post = self._download_json( | |
1811 | 'https://passport.bilibili.tv/x/intl/passport-login/web/login/password?lang=en-US', None, data=urlencode_postdata({ | |
1812 | 'username': username, | |
1813 | 'password': base64.b64encode(password_hash).decode('ascii'), | |
1814 | 'keep_me': 'true', | |
1815 | 's_locale': 'en_US', | |
1816 | 'isTrusted': 'true', | |
1817 | }), note='Logging in', errnote='Unable to log in') | |
1818 | if login_post.get('code'): | |
1819 | if login_post.get('message'): | |
1820 | raise ExtractorError(f'Unable to log in: {self.IE_NAME} said: {login_post["message"]}', expected=True) | |
1821 | else: | |
1822 | raise ExtractorError('Unable to log in') | |
1823 | ||
1824 | ||
1825 | class BiliIntlIE(BiliIntlBaseIE): | |
1826 | _VALID_URL = r'https?://(?:www\.)?bili(?:bili\.tv|intl\.com)/(?:[a-zA-Z]{2}/)?(play/(?P<season_id>\d+)/(?P<ep_id>\d+)|video/(?P<aid>\d+))' | |
1827 | _TESTS = [{ | |
1828 | # Bstation page | |
1829 | 'url': 'https://www.bilibili.tv/en/play/34613/341736', | |
1830 | 'info_dict': { | |
1831 | 'id': '341736', | |
1832 | 'ext': 'mp4', | |
1833 | 'title': 'E2 - The First Night', | |
1834 | 'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.png$', | |
1835 | 'episode_number': 2, | |
1836 | 'upload_date': '20201009', | |
1837 | 'episode': 'Episode 2', | |
1838 | 'timestamp': 1602259500, | |
1839 | 'description': 'md5:297b5a17155eb645e14a14b385ab547e', | |
1840 | 'chapters': [{ | |
1841 | 'start_time': 0, | |
1842 | 'end_time': 76.242, | |
1843 | 'title': '<Untitled Chapter 1>', | |
1844 | }, { | |
1845 | 'start_time': 76.242, | |
1846 | 'end_time': 161.161, | |
1847 | 'title': 'Intro', | |
1848 | }, { | |
1849 | 'start_time': 1325.742, | |
1850 | 'end_time': 1403.903, | |
1851 | 'title': 'Outro', | |
1852 | }], | |
1853 | }, | |
1854 | }, { | |
1855 | # Non-Bstation page | |
1856 | 'url': 'https://www.bilibili.tv/en/play/1033760/11005006', | |
1857 | 'info_dict': { | |
1858 | 'id': '11005006', | |
1859 | 'ext': 'mp4', | |
1860 | 'title': 'E3 - Who?', | |
1861 | 'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.png$', | |
1862 | 'episode_number': 3, | |
1863 | 'description': 'md5:e1a775e71a35c43f141484715470ad09', | |
1864 | 'episode': 'Episode 3', | |
1865 | 'upload_date': '20211219', | |
1866 | 'timestamp': 1639928700, | |
1867 | 'chapters': [{ | |
1868 | 'start_time': 0, | |
1869 | 'end_time': 88.0, | |
1870 | 'title': '<Untitled Chapter 1>', | |
1871 | }, { | |
1872 | 'start_time': 88.0, | |
1873 | 'end_time': 156.0, | |
1874 | 'title': 'Intro', | |
1875 | }, { | |
1876 | 'start_time': 1173.0, | |
1877 | 'end_time': 1259.535, | |
1878 | 'title': 'Outro', | |
1879 | }], | |
1880 | }, | |
1881 | }, { | |
1882 | # Subtitle with empty content | |
1883 | 'url': 'https://www.bilibili.tv/en/play/1005144/10131790', | |
1884 | 'info_dict': { | |
1885 | 'id': '10131790', | |
1886 | 'ext': 'mp4', | |
1887 | 'title': 'E140 - Two Heartbeats: Kabuto\'s Trap', | |
1888 | 'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.png$', | |
1889 | 'episode_number': 140, | |
1890 | }, | |
1891 | 'skip': 'According to the copyright owner\'s request, you may only watch the video after you log in.', | |
1892 | }, { | |
1893 | # episode comment extraction | |
1894 | 'url': 'https://www.bilibili.tv/en/play/34580/340317', | |
1895 | 'info_dict': { | |
1896 | 'id': '340317', | |
1897 | 'ext': 'mp4', | |
1898 | 'timestamp': 1604057820, | |
1899 | 'upload_date': '20201030', | |
1900 | 'episode_number': 5, | |
1901 | 'title': 'E5 - My Own Steel', | |
1902 | 'description': 'md5:2b17ab10aebb33e3c2a54da9e8e487e2', | |
1903 | 'thumbnail': r're:https?://pic\.bstarstatic\.com/ogv/.+\.png$', | |
1904 | 'episode': 'Episode 5', | |
1905 | 'comment_count': int, | |
1906 | 'chapters': [{ | |
1907 | 'start_time': 0, | |
1908 | 'end_time': 61.0, | |
1909 | 'title': '<Untitled Chapter 1>', | |
1910 | }, { | |
1911 | 'start_time': 61.0, | |
1912 | 'end_time': 134.0, | |
1913 | 'title': 'Intro', | |
1914 | }, { | |
1915 | 'start_time': 1290.0, | |
1916 | 'end_time': 1379.0, | |
1917 | 'title': 'Outro', | |
1918 | }], | |
1919 | }, | |
1920 | 'params': { | |
1921 | 'getcomments': True, | |
1922 | }, | |
1923 | }, { | |
1924 | # user generated content comment extraction | |
1925 | 'url': 'https://www.bilibili.tv/en/video/2045730385', | |
1926 | 'info_dict': { | |
1927 | 'id': '2045730385', | |
1928 | 'ext': 'mp4', | |
1929 | 'description': 'md5:693b6f3967fb4e7e7764ea817857c33a', | |
1930 | 'timestamp': 1667891924, | |
1931 | 'upload_date': '20221108', | |
1932 | 'title': 'That Time I Got Reincarnated as a Slime: Scarlet Bond - Official Trailer 3| AnimeStan', | |
1933 | 'comment_count': int, | |
1934 | 'thumbnail': r're:https://pic\.bstarstatic\.(?:com|net)/ugc/f6c363659efd2eabe5683fbb906b1582\.jpg', | |
1935 | }, | |
1936 | 'params': { | |
1937 | 'getcomments': True, | |
1938 | }, | |
1939 | }, { | |
1940 | # episode id without intro and outro | |
1941 | 'url': 'https://www.bilibili.tv/en/play/1048837/11246489', | |
1942 | 'info_dict': { | |
1943 | 'id': '11246489', | |
1944 | 'ext': 'mp4', | |
1945 | 'title': 'E1 - Operation \'Strix\' <Owl>', | |
1946 | 'description': 'md5:b4434eb1a9a97ad2bccb779514b89f17', | |
1947 | 'timestamp': 1649516400, | |
1948 | 'thumbnail': 'https://pic.bstarstatic.com/ogv/62cb1de23ada17fb70fbe7bdd6ff29c29da02a64.png', | |
1949 | 'episode': 'Episode 1', | |
1950 | 'episode_number': 1, | |
1951 | 'upload_date': '20220409', | |
1952 | }, | |
1953 | }, { | |
1954 | 'url': 'https://www.biliintl.com/en/play/34613/341736', | |
1955 | 'only_matching': True, | |
1956 | }, { | |
1957 | # User-generated content (as opposed to a series licensed from a studio) | |
1958 | 'url': 'https://bilibili.tv/en/video/2019955076', | |
1959 | 'only_matching': True, | |
1960 | }, { | |
1961 | # No language in URL | |
1962 | 'url': 'https://www.bilibili.tv/video/2019955076', | |
1963 | 'only_matching': True, | |
1964 | }, { | |
1965 | # Uppercase language in URL | |
1966 | 'url': 'https://www.bilibili.tv/EN/video/2019955076', | |
1967 | 'only_matching': True, | |
1968 | }] | |
1969 | ||
1970 | @staticmethod | |
1971 | def _make_url(video_id, series_id=None): | |
1972 | if series_id: | |
1973 | return f'https://www.bilibili.tv/en/play/{series_id}/{video_id}' | |
1974 | return f'https://www.bilibili.tv/en/video/{video_id}' | |
1975 | ||
1976 | def _extract_video_metadata(self, url, video_id, season_id): | |
1977 | url, smuggled_data = unsmuggle_url(url, {}) | |
1978 | if smuggled_data.get('title'): | |
1979 | return smuggled_data | |
1980 | ||
1981 | webpage = self._download_webpage(url, video_id) | |
1982 | # Bstation layout | |
1983 | initial_data = ( | |
1984 | self._search_json(r'window\.__INITIAL_(?:DATA|STATE)__\s*=', webpage, 'preload state', video_id, default={}) | |
1985 | or self._search_nuxt_data(webpage, video_id, '__initialState', fatal=False, traverse=None)) | |
1986 | video_data = traverse_obj( | |
1987 | initial_data, ('OgvVideo', 'epDetail'), ('UgcVideo', 'videoData'), ('ugc', 'archive'), expected_type=dict) or {} | |
1988 | ||
1989 | if season_id and not video_data: | |
1990 | # Non-Bstation layout, read through episode list | |
1991 | season_json = self._call_api(f'/web/v2/ogv/play/episodes?season_id={season_id}&platform=web', video_id) | |
1992 | video_data = traverse_obj(season_json, ( | |
1993 | 'sections', ..., 'episodes', lambda _, v: str(v['episode_id']) == video_id, | |
1994 | ), expected_type=dict, get_all=False) | |
1995 | ||
1996 | # XXX: webpage metadata may not accurate, it just used to not crash when video_data not found | |
1997 | return merge_dicts( | |
1998 | self._parse_video_metadata(video_data), { | |
1999 | 'title': get_element_by_class( | |
2000 | 'bstar-meta__title', webpage) or self._html_search_meta('og:title', webpage), | |
2001 | 'description': get_element_by_class( | |
2002 | 'bstar-meta__desc', webpage) or self._html_search_meta('og:description', webpage), | |
2003 | }, self._search_json_ld(webpage, video_id, default={})) | |
2004 | ||
2005 | def _get_comments_reply(self, root_id, next_id=0, display_id=None): | |
2006 | comment_api_raw_data = self._download_json( | |
2007 | 'https://api.bilibili.tv/reply/web/detail', display_id, | |
2008 | note=f'Downloading reply comment of {root_id} - {next_id}', | |
2009 | query={ | |
2010 | 'platform': 'web', | |
2011 | 'ps': 20, # comment's reply per page (default: 3) | |
2012 | 'root': root_id, | |
2013 | 'next': next_id, | |
2014 | }) | |
2015 | ||
2016 | for replies in traverse_obj(comment_api_raw_data, ('data', 'replies', ...)): | |
2017 | yield { | |
2018 | 'author': traverse_obj(replies, ('member', 'name')), | |
2019 | 'author_id': traverse_obj(replies, ('member', 'mid')), | |
2020 | 'author_thumbnail': traverse_obj(replies, ('member', 'face')), | |
2021 | 'text': traverse_obj(replies, ('content', 'message')), | |
2022 | 'id': replies.get('rpid'), | |
2023 | 'like_count': int_or_none(replies.get('like_count')), | |
2024 | 'parent': replies.get('parent'), | |
2025 | 'timestamp': unified_timestamp(replies.get('ctime_text')), | |
2026 | } | |
2027 | ||
2028 | if not traverse_obj(comment_api_raw_data, ('data', 'cursor', 'is_end')): | |
2029 | yield from self._get_comments_reply( | |
2030 | root_id, comment_api_raw_data['data']['cursor']['next'], display_id) | |
2031 | ||
2032 | def _get_comments(self, video_id, ep_id): | |
2033 | for i in itertools.count(0): | |
2034 | comment_api_raw_data = self._download_json( | |
2035 | 'https://api.bilibili.tv/reply/web/root', video_id, | |
2036 | note=f'Downloading comment page {i + 1}', | |
2037 | query={ | |
2038 | 'platform': 'web', | |
2039 | 'pn': i, # page number | |
2040 | 'ps': 20, # comment per page (default: 20) | |
2041 | 'oid': video_id, | |
2042 | 'type': 3 if ep_id else 1, # 1: user generated content, 3: series content | |
2043 | 'sort_type': 1, # 1: best, 2: recent | |
2044 | }) | |
2045 | ||
2046 | for replies in traverse_obj(comment_api_raw_data, ('data', 'replies', ...)): | |
2047 | yield { | |
2048 | 'author': traverse_obj(replies, ('member', 'name')), | |
2049 | 'author_id': traverse_obj(replies, ('member', 'mid')), | |
2050 | 'author_thumbnail': traverse_obj(replies, ('member', 'face')), | |
2051 | 'text': traverse_obj(replies, ('content', 'message')), | |
2052 | 'id': replies.get('rpid'), | |
2053 | 'like_count': int_or_none(replies.get('like_count')), | |
2054 | 'timestamp': unified_timestamp(replies.get('ctime_text')), | |
2055 | 'author_is_uploader': bool(traverse_obj(replies, ('member', 'type'))), | |
2056 | } | |
2057 | if replies.get('count'): | |
2058 | yield from self._get_comments_reply(replies.get('rpid'), display_id=video_id) | |
2059 | ||
2060 | if traverse_obj(comment_api_raw_data, ('data', 'cursor', 'is_end')): | |
2061 | break | |
2062 | ||
2063 | def _real_extract(self, url): | |
2064 | season_id, ep_id, aid = self._match_valid_url(url).group('season_id', 'ep_id', 'aid') | |
2065 | video_id = ep_id or aid | |
2066 | chapters = None | |
2067 | ||
2068 | if ep_id: | |
2069 | intro_ending_json = self._call_api( | |
2070 | f'/web/v2/ogv/play/episode?episode_id={ep_id}&platform=web', | |
2071 | video_id, fatal=False) or {} | |
2072 | if intro_ending_json.get('skip'): | |
2073 | # FIXME: start time and end time seems a bit off a few second even it corrext based on ogv.*.js | |
2074 | # ref: https://p.bstarstatic.com/fe-static/bstar-web-new/assets/ogv.2b147442.js | |
2075 | chapters = [{ | |
2076 | 'start_time': float_or_none(traverse_obj(intro_ending_json, ('skip', 'opening_start_time')), 1000), | |
2077 | 'end_time': float_or_none(traverse_obj(intro_ending_json, ('skip', 'opening_end_time')), 1000), | |
2078 | 'title': 'Intro', | |
2079 | }, { | |
2080 | 'start_time': float_or_none(traverse_obj(intro_ending_json, ('skip', 'ending_start_time')), 1000), | |
2081 | 'end_time': float_or_none(traverse_obj(intro_ending_json, ('skip', 'ending_end_time')), 1000), | |
2082 | 'title': 'Outro', | |
2083 | }] | |
2084 | ||
2085 | return { | |
2086 | 'id': video_id, | |
2087 | **self._extract_video_metadata(url, video_id, season_id), | |
2088 | 'formats': self._get_formats(ep_id=ep_id, aid=aid), | |
2089 | 'subtitles': self.extract_subtitles(ep_id=ep_id, aid=aid), | |
2090 | 'chapters': chapters, | |
2091 | '__post_extractor': self.extract_comments(video_id, ep_id), | |
2092 | 'http_headers': self._HEADERS, | |
2093 | } | |
2094 | ||
2095 | ||
2096 | class BiliIntlSeriesIE(BiliIntlBaseIE): | |
2097 | IE_NAME = 'biliIntl:series' | |
2098 | _VALID_URL = r'https?://(?:www\.)?bili(?:bili\.tv|intl\.com)/(?:[a-zA-Z]{2}/)?(?:play|media)/(?P<id>\d+)/?(?:[?#]|$)' | |
2099 | _TESTS = [{ | |
2100 | 'url': 'https://www.bilibili.tv/en/play/34613', | |
2101 | 'playlist_mincount': 15, | |
2102 | 'info_dict': { | |
2103 | 'id': '34613', | |
2104 | 'title': 'TONIKAWA: Over the Moon For You', | |
2105 | 'description': 'md5:297b5a17155eb645e14a14b385ab547e', | |
2106 | 'categories': ['Slice of life', 'Comedy', 'Romance'], | |
2107 | 'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.png$', | |
2108 | 'view_count': int, | |
2109 | }, | |
2110 | 'params': { | |
2111 | 'skip_download': True, | |
2112 | }, | |
2113 | }, { | |
2114 | 'url': 'https://www.bilibili.tv/en/media/1048837', | |
2115 | 'info_dict': { | |
2116 | 'id': '1048837', | |
2117 | 'title': 'SPY×FAMILY', | |
2118 | 'description': 'md5:b4434eb1a9a97ad2bccb779514b89f17', | |
2119 | 'categories': ['Adventure', 'Action', 'Comedy'], | |
2120 | 'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.jpg$', | |
2121 | 'view_count': int, | |
2122 | }, | |
2123 | 'playlist_mincount': 25, | |
2124 | }, { | |
2125 | 'url': 'https://www.biliintl.com/en/play/34613', | |
2126 | 'only_matching': True, | |
2127 | }, { | |
2128 | 'url': 'https://www.biliintl.com/EN/play/34613', | |
2129 | 'only_matching': True, | |
2130 | }] | |
2131 | ||
2132 | def _entries(self, series_id): | |
2133 | series_json = self._call_api(f'/web/v2/ogv/play/episodes?season_id={series_id}&platform=web', series_id) | |
2134 | for episode in traverse_obj(series_json, ('sections', ..., 'episodes', ...), expected_type=dict): | |
2135 | episode_id = str(episode['episode_id']) | |
2136 | yield self.url_result(smuggle_url( | |
2137 | BiliIntlIE._make_url(episode_id, series_id), | |
2138 | self._parse_video_metadata(episode), | |
2139 | ), BiliIntlIE, episode_id) | |
2140 | ||
2141 | def _real_extract(self, url): | |
2142 | series_id = self._match_id(url) | |
2143 | series_info = self._call_api(f'/web/v2/ogv/play/season_info?season_id={series_id}&platform=web', series_id).get('season') or {} | |
2144 | return self.playlist_result( | |
2145 | self._entries(series_id), series_id, series_info.get('title'), series_info.get('description'), | |
2146 | categories=traverse_obj(series_info, ('styles', ..., 'title'), expected_type=str_or_none), | |
2147 | thumbnail=url_or_none(series_info.get('horizontal_cover')), view_count=parse_count(series_info.get('view'))) | |
2148 | ||
2149 | ||
2150 | class BiliLiveIE(InfoExtractor): | |
2151 | _VALID_URL = r'https?://live\.bilibili\.com/(?:blanc/)?(?P<id>\d+)' | |
2152 | ||
2153 | _TESTS = [{ | |
2154 | 'url': 'https://live.bilibili.com/196', | |
2155 | 'info_dict': { | |
2156 | 'id': '33989', | |
2157 | 'description': '周六杂谈回,其他时候随机游戏。 | \n录播:@下播型泛式录播组。 | \n直播通知群(全员禁言):666906670,902092584,59971⑧481 (功能一样,别多加)', | |
2158 | 'ext': 'flv', | |
2159 | 'title': '太空狼人杀联动,不被爆杀就算赢', | |
2160 | 'thumbnail': 'https://i0.hdslb.com/bfs/live/new_room_cover/e607bc1529057ef4b332e1026e62cf46984c314d.jpg', | |
2161 | 'timestamp': 1650802769, | |
2162 | }, | |
2163 | 'skip': 'not live', | |
2164 | }, { | |
2165 | 'url': 'https://live.bilibili.com/196?broadcast_type=0&is_room_feed=1?spm_id_from=333.999.space_home.strengthen_live_card.click', | |
2166 | 'only_matching': True, | |
2167 | }, { | |
2168 | 'url': 'https://live.bilibili.com/blanc/196', | |
2169 | 'only_matching': True, | |
2170 | }] | |
2171 | ||
2172 | _FORMATS = { | |
2173 | 80: {'format_id': 'low', 'format_note': '流畅'}, | |
2174 | 150: {'format_id': 'high_res', 'format_note': '高清'}, | |
2175 | 250: {'format_id': 'ultra_high_res', 'format_note': '超清'}, | |
2176 | 400: {'format_id': 'blue_ray', 'format_note': '蓝光'}, | |
2177 | 10000: {'format_id': 'source', 'format_note': '原画'}, | |
2178 | 20000: {'format_id': '4K', 'format_note': '4K'}, | |
2179 | 30000: {'format_id': 'dolby', 'format_note': '杜比'}, | |
2180 | } | |
2181 | ||
2182 | _quality = staticmethod(qualities(list(_FORMATS))) | |
2183 | ||
2184 | def _call_api(self, path, room_id, query): | |
2185 | api_result = self._download_json(f'https://api.live.bilibili.com/{path}', room_id, query=query) | |
2186 | if api_result.get('code') != 0: | |
2187 | raise ExtractorError(api_result.get('message') or 'Unable to download JSON metadata') | |
2188 | return api_result.get('data') or {} | |
2189 | ||
2190 | def _parse_formats(self, qn, fmt): | |
2191 | for codec in fmt.get('codec') or []: | |
2192 | if codec.get('current_qn') != qn: | |
2193 | continue | |
2194 | for url_info in codec['url_info']: | |
2195 | yield { | |
2196 | 'url': f'{url_info["host"]}{codec["base_url"]}{url_info["extra"]}', | |
2197 | 'ext': fmt.get('format_name'), | |
2198 | 'vcodec': codec.get('codec_name'), | |
2199 | 'quality': self._quality(qn), | |
2200 | **self._FORMATS[qn], | |
2201 | } | |
2202 | ||
2203 | def _real_extract(self, url): | |
2204 | room_id = self._match_id(url) | |
2205 | room_data = self._call_api('room/v1/Room/get_info', room_id, {'id': room_id}) | |
2206 | if room_data.get('live_status') == 0: | |
2207 | raise ExtractorError('Streamer is not live', expected=True) | |
2208 | ||
2209 | formats = [] | |
2210 | for qn in self._FORMATS: | |
2211 | stream_data = self._call_api('xlive/web-room/v2/index/getRoomPlayInfo', room_id, { | |
2212 | 'room_id': room_id, | |
2213 | 'qn': qn, | |
2214 | 'codec': '0,1', | |
2215 | 'format': '0,2', | |
2216 | 'mask': '0', | |
2217 | 'no_playurl': '0', | |
2218 | 'platform': 'web', | |
2219 | 'protocol': '0,1', | |
2220 | }) | |
2221 | for fmt in traverse_obj(stream_data, ('playurl_info', 'playurl', 'stream', ..., 'format', ...)) or []: | |
2222 | formats.extend(self._parse_formats(qn, fmt)) | |
2223 | ||
2224 | return { | |
2225 | 'id': room_id, | |
2226 | 'title': room_data.get('title'), | |
2227 | 'description': room_data.get('description'), | |
2228 | 'thumbnail': room_data.get('user_cover'), | |
2229 | 'timestamp': stream_data.get('live_time'), | |
2230 | 'formats': formats, | |
2231 | 'is_live': True, | |
2232 | 'http_headers': { | |
2233 | 'Referer': url, | |
2234 | }, | |
2235 | } |