]>
Commit | Line | Data |
---|---|---|
cfcf60ea | 1 | import base64 |
c34f505b | 2 | import functools |
6f10cdcf | 3 | import hashlib |
ad974876 | 4 | import itertools |
c34f505b | 5 | import math |
5336bf57 | 6 | import re |
6f10cdcf | 7 | import time |
ad974876 | 8 | import urllib.parse |
28746fbd | 9 | |
06167fbb | 10 | from .common import InfoExtractor, SearchInfoExtractor |
f6a765ce | 11 | from ..dependencies import Cryptodome |
3d2623a8 | 12 | from ..networking.exceptions import HTTPError |
28746fbd | 13 | from ..utils import ( |
bd8f48c7 | 14 | ExtractorError, |
ad974876 | 15 | GeoRestrictedError, |
2b9d0216 L |
16 | InAdvancePagedList, |
17 | OnDemandPagedList, | |
9e68747f | 18 | bool_or_none, |
f5f15c99 | 19 | filter_dict, |
6461f2b7 | 20 | float_or_none, |
ad974876 | 21 | format_field, |
2b9d0216 | 22 | int_or_none, |
bdd0b75e | 23 | join_nonempty, |
ad974876 | 24 | make_archive_id, |
d37422f1 | 25 | merge_dicts, |
f8580bf0 | 26 | mimetype2ext, |
2b9d0216 | 27 | parse_count, |
ad974876 | 28 | parse_qs, |
b4f53662 | 29 | qualities, |
26fdfc37 | 30 | smuggle_url, |
efc947fb | 31 | srt_subtitles_timecode, |
4bc15a68 | 32 | str_or_none, |
2b9d0216 | 33 | traverse_obj, |
6f10cdcf | 34 | try_call, |
b093c38c | 35 | unified_timestamp, |
26fdfc37 | 36 | unsmuggle_url, |
c62ecf0d | 37 | url_or_none, |
ad974876 | 38 | urlencode_postdata, |
9e68747f | 39 | variadic, |
28746fbd PH |
40 | ) |
41 | ||
42 | ||
ad974876 | 43 | class BilibiliBaseIE(InfoExtractor): |
5336bf57 | 44 | _FORMAT_ID_RE = re.compile(r'-(\d+)\.m4s\?') |
45 | ||
ad974876 L |
46 | def extract_formats(self, play_info): |
47 | format_names = { | |
48 | r['quality']: traverse_obj(r, 'new_description', 'display_desc') | |
49 | for r in traverse_obj(play_info, ('support_formats', lambda _, v: v['quality'])) | |
50 | } | |
51 | ||
b84fda73 | 52 | audios = traverse_obj(play_info, ('dash', (None, 'dolby'), 'audio', ..., {dict})) |
ad974876 L |
53 | flac_audio = traverse_obj(play_info, ('dash', 'flac', 'audio')) |
54 | if flac_audio: | |
55 | audios.append(flac_audio) | |
56 | formats = [{ | |
57 | 'url': traverse_obj(audio, 'baseUrl', 'base_url', 'url'), | |
58 | 'ext': mimetype2ext(traverse_obj(audio, 'mimeType', 'mime_type')), | |
b84fda73 | 59 | 'acodec': traverse_obj(audio, ('codecs', {str.lower})), |
ad974876 L |
60 | 'vcodec': 'none', |
61 | 'tbr': float_or_none(audio.get('bandwidth'), scale=1000), | |
5336bf57 | 62 | 'filesize': int_or_none(audio.get('size')), |
63 | 'format_id': str_or_none(audio.get('id')), | |
ad974876 L |
64 | } for audio in audios] |
65 | ||
66 | formats.extend({ | |
67 | 'url': traverse_obj(video, 'baseUrl', 'base_url', 'url'), | |
68 | 'ext': mimetype2ext(traverse_obj(video, 'mimeType', 'mime_type')), | |
69 | 'fps': float_or_none(traverse_obj(video, 'frameRate', 'frame_rate')), | |
70 | 'width': int_or_none(video.get('width')), | |
71 | 'height': int_or_none(video.get('height')), | |
72 | 'vcodec': video.get('codecs'), | |
73 | 'acodec': 'none' if audios else None, | |
b84fda73 | 74 | 'dynamic_range': {126: 'DV', 125: 'HDR10'}.get(int_or_none(video.get('id'))), |
ad974876 L |
75 | 'tbr': float_or_none(video.get('bandwidth'), scale=1000), |
76 | 'filesize': int_or_none(video.get('size')), | |
77 | 'quality': int_or_none(video.get('id')), | |
5336bf57 | 78 | 'format_id': traverse_obj( |
79 | video, (('baseUrl', 'base_url'), {self._FORMAT_ID_RE.search}, 1), | |
80 | ('id', {str_or_none}), get_all=False), | |
ad974876 L |
81 | 'format': format_names.get(video.get('id')), |
82 | } for video in traverse_obj(play_info, ('dash', 'video', ...))) | |
83 | ||
84 | missing_formats = format_names.keys() - set(traverse_obj(formats, (..., 'quality'))) | |
85 | if missing_formats: | |
86 | self.to_screen(f'Format(s) {", ".join(format_names[i] for i in missing_formats)} are missing; ' | |
6368e2e6 | 87 | f'you have to login or become premium member to download them. {self._login_hint()}') |
ad974876 | 88 | |
ad974876 L |
89 | return formats |
90 | ||
91 | def json2srt(self, json_data): | |
92 | srt_data = '' | |
93 | for idx, line in enumerate(json_data.get('body') or []): | |
94 | srt_data += (f'{idx + 1}\n' | |
95 | f'{srt_subtitles_timecode(line["from"])} --> {srt_subtitles_timecode(line["to"])}\n' | |
96 | f'{line["content"]}\n\n') | |
97 | return srt_data | |
98 | ||
8a83baaf | 99 | def _get_subtitles(self, video_id, aid, cid): |
ad974876 L |
100 | subtitles = { |
101 | 'danmaku': [{ | |
102 | 'ext': 'xml', | |
103 | 'url': f'https://comment.bilibili.com/{cid}.xml', | |
104 | }] | |
105 | } | |
106 | ||
8a83baaf L |
107 | video_info_json = self._download_json(f'https://api.bilibili.com/x/player/v2?aid={aid}&cid={cid}', video_id) |
108 | for s in traverse_obj(video_info_json, ('data', 'subtitle', 'subtitles', ...)): | |
ad974876 L |
109 | subtitles.setdefault(s['lan'], []).append({ |
110 | 'ext': 'srt', | |
111 | 'data': self.json2srt(self._download_json(s['subtitle_url'], video_id)) | |
112 | }) | |
113 | return subtitles | |
114 | ||
c90c5b9b | 115 | def _get_chapters(self, aid, cid): |
116 | chapters = aid and cid and self._download_json( | |
117 | 'https://api.bilibili.com/x/player/v2', aid, query={'aid': aid, 'cid': cid}, | |
118 | note='Extracting chapters', fatal=False) | |
119 | return traverse_obj(chapters, ('data', 'view_points', ..., { | |
120 | 'title': 'content', | |
121 | 'start_time': 'from', | |
122 | 'end_time': 'to', | |
123 | })) or None | |
124 | ||
ad974876 L |
125 | def _get_comments(self, aid): |
126 | for idx in itertools.count(1): | |
127 | replies = traverse_obj( | |
128 | self._download_json( | |
129 | f'https://api.bilibili.com/x/v2/reply?pn={idx}&oid={aid}&type=1&jsonp=jsonp&sort=2&_=1567227301685', | |
130 | aid, note=f'Extracting comments from page {idx}', fatal=False), | |
131 | ('data', 'replies')) | |
132 | if not replies: | |
133 | return | |
134 | for children in map(self._get_all_children, replies): | |
135 | yield from children | |
136 | ||
137 | def _get_all_children(self, reply): | |
138 | yield { | |
139 | 'author': traverse_obj(reply, ('member', 'uname')), | |
140 | 'author_id': traverse_obj(reply, ('member', 'mid')), | |
141 | 'id': reply.get('rpid'), | |
142 | 'text': traverse_obj(reply, ('content', 'message')), | |
143 | 'timestamp': reply.get('ctime'), | |
144 | 'parent': reply.get('parent') or 'root', | |
145 | } | |
146 | for children in map(self._get_all_children, traverse_obj(reply, ('replies', ...))): | |
147 | yield from children | |
148 | ||
bdd0b75e GS |
149 | def _get_episodes_from_season(self, ss_id, url): |
150 | season_info = self._download_json( | |
151 | 'https://api.bilibili.com/pgc/web/season/section', ss_id, | |
152 | note='Downloading season info', query={'season_id': ss_id}, | |
153 | headers={'Referer': url, **self.geo_verification_headers()}) | |
154 | ||
155 | for entry in traverse_obj(season_info, ( | |
156 | 'result', 'main_section', 'episodes', | |
157 | lambda _, v: url_or_none(v['share_url']) and v['id'])): | |
158 | yield self.url_result(entry['share_url'], BiliBiliBangumiIE, f'ep{entry["id"]}') | |
159 | ||
ad974876 L |
160 | |
161 | class BiliBiliIE(BilibiliBaseIE): | |
9e68747f | 162 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:video/|festival/\w+\?(?:[^#]*&)?bvid=)[aAbB][vV](?P<id>[^/?#&]+)' |
28746fbd | 163 | |
bd8f48c7 | 164 | _TESTS = [{ |
ad974876 L |
165 | 'url': 'https://www.bilibili.com/video/BV13x41117TL', |
166 | 'info_dict': { | |
167 | 'id': 'BV13x41117TL', | |
168 | 'title': '阿滴英文|英文歌分享#6 "Closer', | |
169 | 'ext': 'mp4', | |
170 | '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', | |
171 | 'uploader_id': '65880958', | |
172 | 'uploader': '阿滴英文', | |
173 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
174 | 'duration': 554.117, | |
175 | 'tags': list, | |
176 | 'comment_count': int, | |
177 | 'upload_date': '20170301', | |
178 | 'timestamp': 1488353834, | |
179 | 'like_count': int, | |
180 | 'view_count': int, | |
181 | }, | |
182 | }, { | |
183 | # old av URL version | |
06167fbb | 184 | 'url': 'http://www.bilibili.com/video/av1074402/', |
28746fbd | 185 | 'info_dict': { |
ad974876 | 186 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg)$', |
f8580bf0 | 187 | 'ext': 'mp4', |
f8580bf0 | 188 | 'uploader': '菊子桑', |
ad974876 L |
189 | 'uploader_id': '156160', |
190 | 'id': 'BV11x411K7CN', | |
191 | 'title': '【金坷垃】金泡沫', | |
192 | 'duration': 308.36, | |
f8580bf0 | 193 | 'upload_date': '20140420', |
ad974876 | 194 | 'timestamp': 1397983878, |
6461f2b7 | 195 | 'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923', |
ad974876 L |
196 | 'like_count': int, |
197 | 'comment_count': int, | |
198 | 'view_count': int, | |
199 | 'tags': list, | |
200 | }, | |
c90c5b9b | 201 | 'params': {'skip_download': True}, |
bd8f48c7 | 202 | }, { |
ad974876 L |
203 | 'note': 'Anthology', |
204 | 'url': 'https://www.bilibili.com/video/BV1bK411W797', | |
205 | 'info_dict': { | |
206 | 'id': 'BV1bK411W797', | |
207 | 'title': '物语中的人物是如何吐槽自己的OP的' | |
208 | }, | |
209 | 'playlist_count': 18, | |
210 | 'playlist': [{ | |
211 | 'info_dict': { | |
212 | 'id': 'BV1bK411W797_p1', | |
213 | 'ext': 'mp4', | |
214 | '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', | |
215 | 'tags': 'count:11', | |
216 | 'timestamp': 1589601697, | |
217 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
218 | 'uploader': '打牌还是打桩', | |
219 | 'uploader_id': '150259984', | |
220 | 'like_count': int, | |
221 | 'comment_count': int, | |
222 | 'upload_date': '20200516', | |
223 | 'view_count': int, | |
224 | 'description': 'md5:e3c401cf7bc363118d1783dd74068a68', | |
225 | 'duration': 90.314, | |
226 | } | |
227 | }] | |
06167fbb | 228 | }, { |
ad974876 L |
229 | 'note': 'Specific page of Anthology', |
230 | 'url': 'https://www.bilibili.com/video/BV1bK411W797?p=1', | |
231 | 'info_dict': { | |
232 | 'id': 'BV1bK411W797_p1', | |
233 | 'ext': 'mp4', | |
234 | 'title': '物语中的人物是如何吐槽自己的OP的 p01 Staple Stable/战场原+羽川', | |
235 | 'tags': 'count:11', | |
236 | 'timestamp': 1589601697, | |
237 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
238 | 'uploader': '打牌还是打桩', | |
239 | 'uploader_id': '150259984', | |
240 | 'like_count': int, | |
241 | 'comment_count': int, | |
242 | 'upload_date': '20200516', | |
243 | 'view_count': int, | |
244 | 'description': 'md5:e3c401cf7bc363118d1783dd74068a68', | |
245 | 'duration': 90.314, | |
246 | } | |
bd8f48c7 | 247 | }, { |
ad974876 L |
248 | 'note': 'video has subtitles', |
249 | 'url': 'https://www.bilibili.com/video/BV12N4y1M7rh', | |
bd8f48c7 | 250 | 'info_dict': { |
ad974876 | 251 | 'id': 'BV12N4y1M7rh', |
bd8f48c7 | 252 | 'ext': 'mp4', |
c90c5b9b | 253 | 'title': 'md5:96e8bb42c2b432c0d4ce3434a61479c1', |
ad974876 L |
254 | 'tags': list, |
255 | 'description': 'md5:afde2b7ba9025c01d9e3dde10de221e4', | |
256 | 'duration': 313.557, | |
257 | 'upload_date': '20220709', | |
9e68747f | 258 | 'uploader': '小夫太渴', |
ad974876 L |
259 | 'timestamp': 1657347907, |
260 | 'uploader_id': '1326814124', | |
261 | 'comment_count': int, | |
262 | 'view_count': int, | |
263 | 'like_count': int, | |
264 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
265 | 'subtitles': 'count:2' | |
bd8f48c7 | 266 | }, |
ad974876 | 267 | 'params': {'listsubtitles': True}, |
ca270371 | 268 | }, { |
ad974876 | 269 | 'url': 'https://www.bilibili.com/video/av8903802/', |
ca270371 | 270 | 'info_dict': { |
ad974876 | 271 | 'id': 'BV13x41117TL', |
f8580bf0 | 272 | 'ext': 'mp4', |
ca270371 | 273 | 'title': '阿滴英文|英文歌分享#6 "Closer', |
f8580bf0 | 274 | 'upload_date': '20170301', |
c90c5b9b | 275 | 'description': 'md5:3b1b9e25b78da4ef87e9b548b88ee76a', |
ad974876 | 276 | 'timestamp': 1488353834, |
f8580bf0 | 277 | 'uploader_id': '65880958', |
278 | 'uploader': '阿滴英文', | |
ad974876 | 279 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', |
89fabf11 | 280 | 'duration': 554.117, |
ad974876 L |
281 | 'tags': list, |
282 | 'comment_count': int, | |
283 | 'view_count': int, | |
284 | 'like_count': int, | |
89fabf11 JN |
285 | }, |
286 | 'params': { | |
287 | 'skip_download': True, | |
288 | }, | |
c90c5b9b | 289 | }, { |
290 | 'note': 'video has chapter', | |
291 | 'url': 'https://www.bilibili.com/video/BV1vL411G7N7/', | |
292 | 'info_dict': { | |
293 | 'id': 'BV1vL411G7N7', | |
294 | 'ext': 'mp4', | |
295 | 'title': '如何为你的B站视频添加进度条分段', | |
296 | 'timestamp': 1634554558, | |
297 | 'upload_date': '20211018', | |
298 | 'description': 'md5:a9a3d6702b3a94518d419b2e9c320a6d', | |
299 | 'tags': list, | |
300 | 'uploader': '爱喝咖啡的当麻', | |
301 | 'duration': 669.482, | |
302 | 'uploader_id': '1680903', | |
303 | 'chapters': 'count:6', | |
304 | 'comment_count': int, | |
305 | 'view_count': int, | |
306 | 'like_count': int, | |
307 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
308 | }, | |
309 | 'params': {'skip_download': True}, | |
ab29e470 | 310 | }, { |
311 | 'note': 'video redirects to festival page', | |
312 | 'url': 'https://www.bilibili.com/video/BV1wP4y1P72h', | |
313 | 'info_dict': { | |
314 | 'id': 'BV1wP4y1P72h', | |
315 | 'ext': 'mp4', | |
316 | 'title': '牛虎年相交之际,一首传统民族打击乐《牛斗虎》祝大家新春快乐,虎年大吉!【bilibili音乐虎闹新春】', | |
317 | 'timestamp': 1643947497, | |
318 | 'upload_date': '20220204', | |
319 | 'description': 'md5:8681a0d4d2c06b4ae27e59c8080a7fe6', | |
320 | 'uploader': '叨叨冯聊音乐', | |
321 | 'duration': 246.719, | |
322 | 'uploader_id': '528182630', | |
323 | 'view_count': int, | |
324 | 'like_count': int, | |
325 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
326 | }, | |
327 | 'params': {'skip_download': True}, | |
328 | }, { | |
329 | 'note': 'newer festival video', | |
330 | 'url': 'https://www.bilibili.com/festival/2023honkaiimpact3gala?bvid=BV1ay4y1d77f', | |
331 | 'info_dict': { | |
332 | 'id': 'BV1ay4y1d77f', | |
333 | 'ext': 'mp4', | |
334 | 'title': '【崩坏3新春剧场】为特别的你送上祝福!', | |
335 | 'timestamp': 1674273600, | |
336 | 'upload_date': '20230121', | |
337 | 'description': 'md5:58af66d15c6a0122dc30c8adfd828dd8', | |
338 | 'uploader': '果蝇轰', | |
339 | 'duration': 1111.722, | |
340 | 'uploader_id': '8469526', | |
341 | 'view_count': int, | |
342 | 'like_count': int, | |
343 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$', | |
344 | }, | |
345 | 'params': {'skip_download': True}, | |
bd8f48c7 | 346 | }] |
28746fbd | 347 | |
520e7533 | 348 | def _real_extract(self, url): |
ad974876 | 349 | video_id = self._match_id(url) |
6461f2b7 | 350 | webpage = self._download_webpage(url, video_id) |
c90c5b9b | 351 | initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id) |
ad974876 | 352 | |
ab29e470 | 353 | is_festival = 'videoData' not in initial_state |
354 | if is_festival: | |
355 | video_data = initial_state['videoInfo'] | |
356 | else: | |
357 | play_info = self._search_json(r'window\.__playinfo__\s*=', webpage, 'play info', video_id)['data'] | |
358 | video_data = initial_state['videoData'] | |
359 | ||
ad974876 | 360 | video_id, title = video_data['bvid'], video_data.get('title') |
6461f2b7 | 361 | |
adc74b3c | 362 | # Bilibili anthologies are similar to playlists but all videos share the same video ID as the anthology itself. |
ab29e470 | 363 | page_list_json = not is_festival and traverse_obj( |
ad974876 L |
364 | self._download_json( |
365 | 'https://api.bilibili.com/x/player/pagelist', video_id, | |
366 | fatal=False, query={'bvid': video_id, 'jsonp': 'jsonp'}, | |
367 | note='Extracting videos in anthology'), | |
368 | 'data', expected_type=list) or [] | |
369 | is_anthology = len(page_list_json) > 1 | |
370 | ||
371 | part_id = int_or_none(parse_qs(url).get('p', [None])[-1]) | |
372 | if is_anthology and not part_id and self._yes_playlist(video_id, video_id): | |
373 | return self.playlist_from_matches( | |
374 | page_list_json, video_id, title, ie=BiliBiliIE, | |
375 | getter=lambda entry: f'https://www.bilibili.com/video/{video_id}?p={entry["page"]}') | |
10db0d2f | 376 | |
ad974876 | 377 | if is_anthology: |
f74371a9 | 378 | part_id = part_id or 1 |
379 | title += f' p{part_id:02d} {traverse_obj(page_list_json, (part_id - 1, "part")) or ""}' | |
f8580bf0 | 380 | |
ad974876 L |
381 | aid = video_data.get('aid') |
382 | old_video_id = format_field(aid, None, f'%s_part{part_id or 1}') | |
f8580bf0 | 383 | |
c90c5b9b | 384 | cid = traverse_obj(video_data, ('pages', part_id - 1, 'cid')) if part_id else video_data.get('cid') |
385 | ||
ab29e470 | 386 | festival_info = {} |
387 | if is_festival: | |
388 | play_info = self._download_json( | |
389 | 'https://api.bilibili.com/x/player/playurl', video_id, | |
390 | query={'bvid': video_id, 'cid': cid, 'fnval': 4048}, | |
391 | note='Extracting festival video formats')['data'] | |
392 | ||
393 | festival_info = traverse_obj(initial_state, { | |
394 | 'uploader': ('videoInfo', 'upName'), | |
395 | 'uploader_id': ('videoInfo', 'upMid', {str_or_none}), | |
396 | 'like_count': ('videoStatus', 'like', {int_or_none}), | |
397 | 'thumbnail': ('sectionEpisodes', lambda _, v: v['bvid'] == video_id, 'cover'), | |
398 | }, get_all=False) | |
399 | ||
ad974876 | 400 | return { |
ab29e470 | 401 | **traverse_obj(initial_state, { |
402 | 'uploader': ('upData', 'name'), | |
403 | 'uploader_id': ('upData', 'mid', {str_or_none}), | |
404 | 'like_count': ('videoData', 'stat', 'like', {int_or_none}), | |
405 | 'tags': ('tags', ..., 'tag_name'), | |
406 | 'thumbnail': ('videoData', 'pic', {url_or_none}), | |
407 | }), | |
408 | **festival_info, | |
409 | **traverse_obj(video_data, { | |
410 | 'description': 'desc', | |
411 | 'timestamp': ('pubdate', {int_or_none}), | |
412 | 'view_count': (('viewCount', ('stat', 'view')), {int_or_none}), | |
413 | 'comment_count': ('stat', 'reply', {int_or_none}), | |
414 | }, get_all=False), | |
ad974876 L |
415 | 'id': f'{video_id}{format_field(part_id, None, "_p%d")}', |
416 | 'formats': self.extract_formats(play_info), | |
417 | '_old_archive_ids': [make_archive_id(self, old_video_id)] if old_video_id else None, | |
d90e4030 | 418 | 'title': title, |
c90c5b9b | 419 | 'duration': float_or_none(play_info.get('timelength'), scale=1000), |
420 | 'chapters': self._get_chapters(aid, cid), | |
8a83baaf | 421 | 'subtitles': self.extract_subtitles(video_id, aid, cid), |
c90c5b9b | 422 | '__post_extractor': self.extract_comments(aid), |
423 | 'http_headers': {'Referer': url}, | |
06167fbb | 424 | } |
277d6ff5 | 425 | |
06167fbb | 426 | |
ad974876 | 427 | class BiliBiliBangumiIE(BilibiliBaseIE): |
bdd0b75e | 428 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/bangumi/play/(?P<id>ep\d+)' |
e88d44c6 | 429 | |
ad974876 | 430 | _TESTS = [{ |
bdd0b75e | 431 | 'url': 'https://www.bilibili.com/bangumi/play/ep267851', |
ad974876 | 432 | 'info_dict': { |
bdd0b75e | 433 | 'id': '267851', |
ad974876 | 434 | 'ext': 'mp4', |
bdd0b75e GS |
435 | 'series': '鬼灭之刃', |
436 | 'series_id': '4358', | |
437 | 'season': '鬼灭之刃', | |
438 | 'season_id': '26801', | |
ad974876 | 439 | 'season_number': 1, |
bdd0b75e GS |
440 | 'episode': '残酷', |
441 | 'episode_id': '267851', | |
442 | 'episode_number': 1, | |
443 | 'title': '1 残酷', | |
444 | 'duration': 1425.256, | |
445 | 'timestamp': 1554566400, | |
446 | 'upload_date': '20190406', | |
447 | 'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$' | |
ad974876 | 448 | }, |
bdd0b75e | 449 | 'skip': 'According to the copyright owner\'s request, you may only watch the video after you are premium member.' |
ad974876 | 450 | }] |
06167fbb | 451 | |
ad974876 L |
452 | def _real_extract(self, url): |
453 | video_id = self._match_id(url) | |
bdd0b75e | 454 | episode_id = video_id[2:] |
ad974876 | 455 | webpage = self._download_webpage(url, video_id) |
e88d44c6 | 456 | |
ad974876 L |
457 | if '您所在的地区无法观看本片' in webpage: |
458 | raise GeoRestrictedError('This video is restricted') | |
bdd0b75e | 459 | elif '正在观看预览,大会员免费看全片' in webpage: |
ad974876 | 460 | self.raise_login_required('This video is for premium members only') |
6461f2b7 | 461 | |
bdd0b75e GS |
462 | headers = {'Referer': url, **self.geo_verification_headers()} |
463 | play_info = self._download_json( | |
464 | 'https://api.bilibili.com/pgc/player/web/v2/playurl', video_id, | |
465 | 'Extracting episode', query={'fnval': '4048', 'ep_id': episode_id}, | |
466 | headers=headers) | |
467 | premium_only = play_info.get('code') == -10403 | |
468 | play_info = traverse_obj(play_info, ('result', 'video_info', {dict})) or {} | |
469 | ||
ad974876 | 470 | formats = self.extract_formats(play_info) |
bdd0b75e | 471 | 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): |
ad974876 | 472 | self.raise_login_required('This video is for premium members only') |
bd8f48c7 | 473 | |
bdd0b75e GS |
474 | bangumi_info = self._download_json( |
475 | 'https://api.bilibili.com/pgc/view/web/season', video_id, 'Get episode details', | |
476 | query={'ep_id': episode_id}, headers=headers)['result'] | |
477 | ||
478 | episode_number, episode_info = next(( | |
479 | (idx, ep) for idx, ep in enumerate(traverse_obj( | |
480 | bangumi_info, ('episodes', ..., {dict})), 1) | |
481 | if str_or_none(ep.get('id')) == episode_id), (1, {})) | |
c90c5b9b | 482 | |
bdd0b75e | 483 | season_id = bangumi_info.get('season_id') |
c90c5b9b | 484 | season_number = season_id and next(( |
485 | idx + 1 for idx, e in enumerate( | |
bdd0b75e | 486 | traverse_obj(bangumi_info, ('seasons', ...))) |
c90c5b9b | 487 | if e.get('season_id') == season_id |
488 | ), None) | |
06167fbb | 489 | |
bdd0b75e GS |
490 | aid = episode_info.get('aid') |
491 | ||
e88d44c6 | 492 | return { |
ad974876 L |
493 | 'id': video_id, |
494 | 'formats': formats, | |
bdd0b75e GS |
495 | **traverse_obj(bangumi_info, { |
496 | 'series': ('series', 'series_title', {str}), | |
497 | 'series_id': ('series', 'series_id', {str_or_none}), | |
498 | 'thumbnail': ('square_cover', {url_or_none}), | |
499 | }), | |
500 | 'title': join_nonempty('title', 'long_title', delim=' ', from_dict=episode_info), | |
501 | 'episode': episode_info.get('long_title'), | |
502 | 'episode_id': episode_id, | |
503 | 'episode_number': int_or_none(episode_info.get('title')) or episode_number, | |
504 | 'season_id': str_or_none(season_id), | |
c90c5b9b | 505 | 'season_number': season_number, |
bdd0b75e | 506 | 'timestamp': int_or_none(episode_info.get('pub_time')), |
c90c5b9b | 507 | 'duration': float_or_none(play_info.get('timelength'), scale=1000), |
bdd0b75e GS |
508 | 'subtitles': self.extract_subtitles(video_id, aid, episode_info.get('cid')), |
509 | '__post_extractor': self.extract_comments(aid), | |
510 | 'http_headers': headers, | |
e88d44c6 | 511 | } |
bd8f48c7 | 512 | |
bd8f48c7 | 513 | |
bdd0b75e | 514 | class BiliBiliBangumiMediaIE(BilibiliBaseIE): |
9e68747f | 515 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/bangumi/media/md(?P<id>\d+)' |
bd8f48c7 | 516 | _TESTS = [{ |
ad974876 | 517 | 'url': 'https://www.bilibili.com/bangumi/media/md24097891', |
bd8f48c7 | 518 | 'info_dict': { |
ad974876 | 519 | 'id': '24097891', |
bd8f48c7 | 520 | }, |
ad974876 | 521 | 'playlist_mincount': 25, |
bd8f48c7 YCH |
522 | }] |
523 | ||
bd8f48c7 | 524 | def _real_extract(self, url): |
ad974876 L |
525 | media_id = self._match_id(url) |
526 | webpage = self._download_webpage(url, media_id) | |
bdd0b75e GS |
527 | ss_id = self._search_json( |
528 | r'window\.__INITIAL_STATE__\s*=', webpage, 'initial_state', media_id)['mediaInfo']['season_id'] | |
529 | ||
530 | return self.playlist_result(self._get_episodes_from_season(ss_id, url), media_id) | |
531 | ||
bd8f48c7 | 532 | |
bdd0b75e | 533 | class BiliBiliBangumiSeasonIE(BilibiliBaseIE): |
9e68747f | 534 | _VALID_URL = r'(?x)https?://(?:www\.)?bilibili\.com/bangumi/play/ss(?P<id>\d+)' |
bdd0b75e GS |
535 | _TESTS = [{ |
536 | 'url': 'https://www.bilibili.com/bangumi/play/ss26801', | |
537 | 'info_dict': { | |
538 | 'id': '26801' | |
539 | }, | |
540 | 'playlist_mincount': 26 | |
541 | }] | |
542 | ||
543 | def _real_extract(self, url): | |
544 | ss_id = self._match_id(url) | |
bd8f48c7 | 545 | |
bdd0b75e | 546 | return self.playlist_result(self._get_episodes_from_season(ss_id, url), ss_id) |
4bc15a68 RA |
547 | |
548 | ||
2b9d0216 L |
549 | class BilibiliSpaceBaseIE(InfoExtractor): |
550 | def _extract_playlist(self, fetch_page, get_metadata, get_entries): | |
12f153a8 | 551 | first_page = fetch_page(0) |
2b9d0216 L |
552 | metadata = get_metadata(first_page) |
553 | ||
554 | paged_list = InAdvancePagedList( | |
12f153a8 | 555 | lambda idx: get_entries(fetch_page(idx) if idx else first_page), |
2b9d0216 L |
556 | metadata['page_count'], metadata['page_size']) |
557 | ||
558 | return metadata, paged_list | |
559 | ||
560 | ||
561 | class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE): | |
562 | _VALID_URL = r'https?://space\.bilibili\.com/(?P<id>\d+)(?P<video>/video)?/?(?:[?#]|$)' | |
6efb0711 | 563 | _TESTS = [{ |
564 | 'url': 'https://space.bilibili.com/3985676/video', | |
2b9d0216 L |
565 | 'info_dict': { |
566 | 'id': '3985676', | |
567 | }, | |
568 | 'playlist_mincount': 178, | |
6f10cdcf E |
569 | }, { |
570 | 'url': 'https://space.bilibili.com/313580179/video', | |
571 | 'info_dict': { | |
572 | 'id': '313580179', | |
573 | }, | |
574 | 'playlist_mincount': 92, | |
6efb0711 | 575 | }] |
576 | ||
6f10cdcf E |
577 | def _extract_signature(self, playlist_id): |
578 | session_data = self._download_json('https://api.bilibili.com/x/web-interface/nav', playlist_id, fatal=False) | |
579 | ||
580 | key_from_url = lambda x: x[x.rfind('/') + 1:].split('.')[0] | |
581 | img_key = traverse_obj( | |
582 | session_data, ('data', 'wbi_img', 'img_url', {key_from_url})) or '34478ba821254d9d93542680e3b86100' | |
583 | sub_key = traverse_obj( | |
584 | session_data, ('data', 'wbi_img', 'sub_url', {key_from_url})) or '7e16a90d190a4355a78fd00b32a38de6' | |
585 | ||
586 | session_key = img_key + sub_key | |
587 | ||
588 | signature_values = [] | |
589 | for position in ( | |
590 | 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, | |
591 | 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, | |
592 | 57, 62, 11, 36, 20, 34, 44, 52 | |
593 | ): | |
594 | char_at_position = try_call(lambda: session_key[position]) | |
595 | if char_at_position: | |
596 | signature_values.append(char_at_position) | |
597 | ||
598 | return ''.join(signature_values)[:32] | |
599 | ||
2b9d0216 L |
600 | def _real_extract(self, url): |
601 | playlist_id, is_video_url = self._match_valid_url(url).group('id', 'video') | |
602 | if not is_video_url: | |
603 | self.to_screen('A channel URL was given. Only the channel\'s videos will be downloaded. ' | |
604 | 'To download audios, add a "/audio" to the URL') | |
605 | ||
6f10cdcf E |
606 | signature = self._extract_signature(playlist_id) |
607 | ||
2b9d0216 | 608 | def fetch_page(page_idx): |
6f10cdcf E |
609 | query = { |
610 | 'keyword': '', | |
611 | 'mid': playlist_id, | |
612 | 'order': 'pubdate', | |
613 | 'order_avoided': 'true', | |
614 | 'platform': 'web', | |
615 | 'pn': page_idx + 1, | |
616 | 'ps': 30, | |
617 | 'tid': 0, | |
618 | 'web_location': 1550101, | |
619 | 'wts': int(time.time()), | |
620 | } | |
621 | query['w_rid'] = hashlib.md5(f'{urllib.parse.urlencode(query)}{signature}'.encode()).hexdigest() | |
622 | ||
12f153a8 | 623 | try: |
6f10cdcf E |
624 | response = self._download_json('https://api.bilibili.com/x/space/wbi/arc/search', |
625 | playlist_id, note=f'Downloading page {page_idx}', query=query) | |
12f153a8 | 626 | except ExtractorError as e: |
3d2623a8 | 627 | if isinstance(e.cause, HTTPError) and e.cause.status == 412: |
12f153a8 L |
628 | raise ExtractorError( |
629 | 'Request is blocked by server (412), please add cookies, wait and try later.', expected=True) | |
630 | raise | |
631 | if response['code'] == -401: | |
632 | raise ExtractorError( | |
633 | 'Request is blocked by server (401), please add cookies, wait and try later.', expected=True) | |
634 | return response['data'] | |
2b9d0216 L |
635 | |
636 | def get_metadata(page_data): | |
637 | page_size = page_data['page']['ps'] | |
638 | entry_count = page_data['page']['count'] | |
639 | return { | |
640 | 'page_count': math.ceil(entry_count / page_size), | |
641 | 'page_size': page_size, | |
642 | } | |
6efb0711 | 643 | |
2b9d0216 L |
644 | def get_entries(page_data): |
645 | for entry in traverse_obj(page_data, ('list', 'vlist')) or []: | |
646 | yield self.url_result(f'https://www.bilibili.com/video/{entry["bvid"]}', BiliBiliIE, entry['bvid']) | |
6efb0711 | 647 | |
2b9d0216 L |
648 | metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries) |
649 | return self.playlist_result(paged_list, playlist_id) | |
6efb0711 | 650 | |
6efb0711 | 651 | |
2b9d0216 L |
652 | class BilibiliSpaceAudioIE(BilibiliSpaceBaseIE): |
653 | _VALID_URL = r'https?://space\.bilibili\.com/(?P<id>\d+)/audio' | |
654 | _TESTS = [{ | |
6f10cdcf | 655 | 'url': 'https://space.bilibili.com/313580179/audio', |
2b9d0216 | 656 | 'info_dict': { |
6f10cdcf | 657 | 'id': '313580179', |
2b9d0216 L |
658 | }, |
659 | 'playlist_mincount': 1, | |
660 | }] | |
661 | ||
662 | def _real_extract(self, url): | |
663 | playlist_id = self._match_id(url) | |
664 | ||
665 | def fetch_page(page_idx): | |
666 | return self._download_json( | |
667 | 'https://api.bilibili.com/audio/music-service/web/song/upper', playlist_id, | |
668 | note=f'Downloading page {page_idx}', | |
12f153a8 | 669 | query={'uid': playlist_id, 'pn': page_idx + 1, 'ps': 30, 'order': 1, 'jsonp': 'jsonp'})['data'] |
2b9d0216 L |
670 | |
671 | def get_metadata(page_data): | |
672 | return { | |
673 | 'page_count': page_data['pageCount'], | |
674 | 'page_size': page_data['pageSize'], | |
675 | } | |
676 | ||
677 | def get_entries(page_data): | |
678 | for entry in page_data.get('data', []): | |
679 | yield self.url_result(f'https://www.bilibili.com/audio/au{entry["id"]}', BilibiliAudioIE, entry['id']) | |
680 | ||
681 | metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries) | |
682 | return self.playlist_result(paged_list, playlist_id) | |
683 | ||
684 | ||
9e68747f | 685 | class BilibiliSpaceListBaseIE(BilibiliSpaceBaseIE): |
686 | def _get_entries(self, page_data, bvid_keys, ending_key='bvid'): | |
687 | for bvid in traverse_obj(page_data, (*variadic(bvid_keys, (str, bytes, dict, set)), ..., ending_key, {str})): | |
688 | yield self.url_result(f'https://www.bilibili.com/video/{bvid}', BiliBiliIE, bvid) | |
689 | ||
690 | def _get_uploader(self, uid, playlist_id): | |
691 | webpage = self._download_webpage(f'https://space.bilibili.com/{uid}', playlist_id, fatal=False) | |
692 | return self._search_regex(r'(?s)<title\b[^>]*>([^<]+)的个人空间-', webpage, 'uploader', fatal=False) | |
693 | ||
694 | def _extract_playlist(self, fetch_page, get_metadata, get_entries): | |
695 | metadata, page_list = super()._extract_playlist(fetch_page, get_metadata, get_entries) | |
696 | metadata.pop('page_count', None) | |
697 | metadata.pop('page_size', None) | |
698 | return metadata, page_list | |
699 | ||
700 | ||
701 | class BilibiliCollectionListIE(BilibiliSpaceListBaseIE): | |
702 | _VALID_URL = r'https?://space\.bilibili\.com/(?P<mid>\d+)/channel/collectiondetail/?\?sid=(?P<sid>\d+)' | |
2b9d0216 L |
703 | _TESTS = [{ |
704 | 'url': 'https://space.bilibili.com/2142762/channel/collectiondetail?sid=57445', | |
705 | 'info_dict': { | |
706 | 'id': '2142762_57445', | |
9e68747f | 707 | 'title': '【完结】《底特律 变人》全结局流程解说', |
708 | 'description': '', | |
709 | 'uploader': '老戴在此', | |
710 | 'uploader_id': '2142762', | |
711 | 'timestamp': int, | |
712 | 'upload_date': str, | |
713 | 'thumbnail': 'https://archive.biliimg.com/bfs/archive/e0e543ae35ad3df863ea7dea526bc32e70f4c091.jpg', | |
2b9d0216 L |
714 | }, |
715 | 'playlist_mincount': 31, | |
716 | }] | |
06167fbb | 717 | |
718 | def _real_extract(self, url): | |
2b9d0216 L |
719 | mid, sid = self._match_valid_url(url).group('mid', 'sid') |
720 | playlist_id = f'{mid}_{sid}' | |
721 | ||
722 | def fetch_page(page_idx): | |
723 | return self._download_json( | |
724 | 'https://api.bilibili.com/x/polymer/space/seasons_archives_list', | |
725 | playlist_id, note=f'Downloading page {page_idx}', | |
12f153a8 | 726 | query={'mid': mid, 'season_id': sid, 'page_num': page_idx + 1, 'page_size': 30})['data'] |
2b9d0216 L |
727 | |
728 | def get_metadata(page_data): | |
729 | page_size = page_data['page']['page_size'] | |
730 | entry_count = page_data['page']['total'] | |
731 | return { | |
732 | 'page_count': math.ceil(entry_count / page_size), | |
733 | 'page_size': page_size, | |
9e68747f | 734 | 'uploader': self._get_uploader(mid, playlist_id), |
735 | **traverse_obj(page_data, { | |
736 | 'title': ('meta', 'name', {str}), | |
737 | 'description': ('meta', 'description', {str}), | |
738 | 'uploader_id': ('meta', 'mid', {str_or_none}), | |
739 | 'timestamp': ('meta', 'ptime', {int_or_none}), | |
740 | 'thumbnail': ('meta', 'cover', {url_or_none}), | |
741 | }) | |
2b9d0216 L |
742 | } |
743 | ||
744 | def get_entries(page_data): | |
9e68747f | 745 | return self._get_entries(page_data, 'archives') |
2b9d0216 L |
746 | |
747 | metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries) | |
9e68747f | 748 | return self.playlist_result(paged_list, playlist_id, **metadata) |
749 | ||
750 | ||
751 | class BilibiliSeriesListIE(BilibiliSpaceListBaseIE): | |
752 | _VALID_URL = r'https?://space\.bilibili\.com/(?P<mid>\d+)/channel/seriesdetail/?\?\bsid=(?P<sid>\d+)' | |
753 | _TESTS = [{ | |
754 | 'url': 'https://space.bilibili.com/1958703906/channel/seriesdetail?sid=547718&ctype=0', | |
755 | 'info_dict': { | |
756 | 'id': '1958703906_547718', | |
757 | 'title': '直播回放', | |
758 | 'description': '直播回放', | |
759 | 'uploader': '靡烟miya', | |
760 | 'uploader_id': '1958703906', | |
761 | 'timestamp': 1637985853, | |
762 | 'upload_date': '20211127', | |
763 | 'modified_timestamp': int, | |
764 | 'modified_date': str, | |
765 | }, | |
766 | 'playlist_mincount': 513, | |
767 | }] | |
768 | ||
769 | def _real_extract(self, url): | |
770 | mid, sid = self._match_valid_url(url).group('mid', 'sid') | |
771 | playlist_id = f'{mid}_{sid}' | |
772 | playlist_meta = traverse_obj(self._download_json( | |
773 | f'https://api.bilibili.com/x/series/series?series_id={sid}', playlist_id, fatal=False | |
774 | ), { | |
775 | 'title': ('data', 'meta', 'name', {str}), | |
776 | 'description': ('data', 'meta', 'description', {str}), | |
777 | 'uploader_id': ('data', 'meta', 'mid', {str_or_none}), | |
778 | 'timestamp': ('data', 'meta', 'ctime', {int_or_none}), | |
779 | 'modified_timestamp': ('data', 'meta', 'mtime', {int_or_none}), | |
780 | }) | |
781 | ||
782 | def fetch_page(page_idx): | |
783 | return self._download_json( | |
784 | 'https://api.bilibili.com/x/series/archives', | |
785 | playlist_id, note=f'Downloading page {page_idx}', | |
786 | query={'mid': mid, 'series_id': sid, 'pn': page_idx + 1, 'ps': 30})['data'] | |
787 | ||
788 | def get_metadata(page_data): | |
789 | page_size = page_data['page']['size'] | |
790 | entry_count = page_data['page']['total'] | |
791 | return { | |
792 | 'page_count': math.ceil(entry_count / page_size), | |
793 | 'page_size': page_size, | |
794 | 'uploader': self._get_uploader(mid, playlist_id), | |
795 | **playlist_meta | |
796 | } | |
797 | ||
798 | def get_entries(page_data): | |
799 | return self._get_entries(page_data, 'archives') | |
800 | ||
801 | metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries) | |
802 | return self.playlist_result(paged_list, playlist_id, **metadata) | |
803 | ||
804 | ||
805 | class BilibiliFavoritesListIE(BilibiliSpaceListBaseIE): | |
806 | _VALID_URL = r'https?://(?:space\.bilibili\.com/\d+/favlist/?\?fid=|(?:www\.)?bilibili\.com/medialist/detail/ml)(?P<id>\d+)' | |
807 | _TESTS = [{ | |
808 | 'url': 'https://space.bilibili.com/84912/favlist?fid=1103407912&ftype=create', | |
809 | 'info_dict': { | |
810 | 'id': '1103407912', | |
811 | 'title': '【V2】(旧)', | |
812 | 'description': '', | |
813 | 'uploader': '晓月春日', | |
814 | 'uploader_id': '84912', | |
815 | 'timestamp': 1604905176, | |
816 | 'upload_date': '20201109', | |
817 | 'modified_timestamp': int, | |
818 | 'modified_date': str, | |
819 | 'thumbnail': r"re:http://i\d\.hdslb\.com/bfs/archive/14b83c62aa8871b79083df1e9ab4fbc699ad16fe\.jpg", | |
820 | 'view_count': int, | |
821 | 'like_count': int, | |
822 | }, | |
823 | 'playlist_mincount': 22, | |
824 | }, { | |
825 | 'url': 'https://www.bilibili.com/medialist/detail/ml1103407912', | |
826 | 'only_matching': True, | |
827 | }] | |
828 | ||
829 | def _real_extract(self, url): | |
830 | fid = self._match_id(url) | |
831 | ||
832 | list_info = self._download_json( | |
833 | f'https://api.bilibili.com/x/v3/fav/resource/list?media_id={fid}&pn=1&ps=20', | |
834 | fid, note='Downloading favlist metadata') | |
835 | if list_info['code'] == -403: | |
836 | self.raise_login_required(msg='This is a private favorites list. You need to log in as its owner') | |
837 | ||
838 | entries = self._get_entries(self._download_json( | |
839 | f'https://api.bilibili.com/x/v3/fav/resource/ids?media_id={fid}', | |
840 | fid, note='Download favlist entries'), 'data') | |
841 | ||
842 | return self.playlist_result(entries, fid, **traverse_obj(list_info, ('data', 'info', { | |
843 | 'title': ('title', {str}), | |
844 | 'description': ('intro', {str}), | |
845 | 'uploader': ('upper', 'name', {str}), | |
846 | 'uploader_id': ('upper', 'mid', {str_or_none}), | |
847 | 'timestamp': ('ctime', {int_or_none}), | |
848 | 'modified_timestamp': ('mtime', {int_or_none}), | |
849 | 'thumbnail': ('cover', {url_or_none}), | |
850 | 'view_count': ('cnt_info', 'play', {int_or_none}), | |
851 | 'like_count': ('cnt_info', 'thumb_up', {int_or_none}), | |
852 | }))) | |
853 | ||
854 | ||
855 | class BilibiliWatchlaterIE(BilibiliSpaceListBaseIE): | |
856 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/watchlater/?(?:[?#]|$)' | |
857 | _TESTS = [{ | |
858 | 'url': 'https://www.bilibili.com/watchlater/#/list', | |
859 | 'info_dict': {'id': 'watchlater'}, | |
860 | 'playlist_mincount': 0, | |
861 | 'skip': 'login required', | |
862 | }] | |
863 | ||
864 | def _real_extract(self, url): | |
865 | list_id = getattr(self._get_cookies(url).get('DedeUserID'), 'value', 'watchlater') | |
866 | watchlater_info = self._download_json( | |
867 | 'https://api.bilibili.com/x/v2/history/toview/web?jsonp=jsonp', list_id) | |
868 | if watchlater_info['code'] == -101: | |
869 | self.raise_login_required(msg='You need to login to access your watchlater list') | |
870 | entries = self._get_entries(watchlater_info, ('data', 'list')) | |
871 | return self.playlist_result(entries, id=list_id, title='稍后再看') | |
872 | ||
873 | ||
874 | class BilibiliPlaylistIE(BilibiliSpaceListBaseIE): | |
875 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:medialist/play|list)/(?P<id>\w+)' | |
876 | _TESTS = [{ | |
877 | 'url': 'https://www.bilibili.com/list/1958703906?sid=547718', | |
878 | 'info_dict': { | |
879 | 'id': '5_547718', | |
880 | 'title': '直播回放', | |
881 | 'uploader': '靡烟miya', | |
882 | 'uploader_id': '1958703906', | |
883 | 'timestamp': 1637985853, | |
884 | 'upload_date': '20211127', | |
885 | }, | |
886 | 'playlist_mincount': 513, | |
887 | }, { | |
888 | 'url': 'https://www.bilibili.com/medialist/play/1958703906?business=space_series&business_id=547718&desc=1', | |
889 | 'info_dict': { | |
890 | 'id': '5_547718', | |
891 | }, | |
892 | 'playlist_mincount': 513, | |
893 | 'skip': 'redirect url', | |
894 | }, { | |
895 | 'url': 'https://www.bilibili.com/list/ml1103407912', | |
896 | 'info_dict': { | |
897 | 'id': '3_1103407912', | |
898 | 'title': '【V2】(旧)', | |
899 | 'uploader': '晓月春日', | |
900 | 'uploader_id': '84912', | |
901 | 'timestamp': 1604905176, | |
902 | 'upload_date': '20201109', | |
903 | 'thumbnail': r"re:http://i\d\.hdslb\.com/bfs/archive/14b83c62aa8871b79083df1e9ab4fbc699ad16fe\.jpg", | |
904 | }, | |
905 | 'playlist_mincount': 22, | |
906 | }, { | |
907 | 'url': 'https://www.bilibili.com/medialist/play/ml1103407912', | |
908 | 'info_dict': { | |
909 | 'id': '3_1103407912', | |
910 | }, | |
911 | 'playlist_mincount': 22, | |
912 | 'skip': 'redirect url', | |
913 | }, { | |
914 | 'url': 'https://www.bilibili.com/list/watchlater', | |
915 | 'info_dict': {'id': 'watchlater'}, | |
916 | 'playlist_mincount': 0, | |
917 | 'skip': 'login required', | |
918 | }, { | |
919 | 'url': 'https://www.bilibili.com/medialist/play/watchlater', | |
920 | 'info_dict': {'id': 'watchlater'}, | |
921 | 'playlist_mincount': 0, | |
922 | 'skip': 'login required', | |
923 | }] | |
924 | ||
925 | def _extract_medialist(self, query, list_id): | |
926 | for page_num in itertools.count(1): | |
927 | page_data = self._download_json( | |
928 | 'https://api.bilibili.com/x/v2/medialist/resource/list', | |
929 | list_id, query=query, note=f'getting playlist {query["biz_id"]} page {page_num}' | |
930 | )['data'] | |
931 | yield from self._get_entries(page_data, 'media_list', ending_key='bv_id') | |
932 | query['oid'] = traverse_obj(page_data, ('media_list', -1, 'id')) | |
933 | if not page_data.get('has_more', False): | |
934 | break | |
935 | ||
936 | def _real_extract(self, url): | |
937 | list_id = self._match_id(url) | |
938 | webpage = self._download_webpage(url, list_id) | |
939 | initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', list_id) | |
940 | if traverse_obj(initial_state, ('error', 'code', {int_or_none})) != 200: | |
941 | error_code = traverse_obj(initial_state, ('error', 'trueCode', {int_or_none})) | |
942 | error_message = traverse_obj(initial_state, ('error', 'message', {str_or_none})) | |
943 | if error_code == -400 and list_id == 'watchlater': | |
944 | self.raise_login_required('You need to login to access your watchlater playlist') | |
945 | elif error_code == -403: | |
946 | self.raise_login_required('This is a private playlist. You need to login as its owner') | |
947 | elif error_code == 11010: | |
948 | raise ExtractorError('Playlist is no longer available', expected=True) | |
949 | raise ExtractorError(f'Could not access playlist: {error_code} {error_message}') | |
950 | ||
951 | query = { | |
952 | 'ps': 20, | |
953 | 'with_current': False, | |
954 | **traverse_obj(initial_state, { | |
955 | 'type': ('playlist', 'type', {int_or_none}), | |
956 | 'biz_id': ('playlist', 'id', {int_or_none}), | |
957 | 'tid': ('tid', {int_or_none}), | |
958 | 'sort_field': ('sortFiled', {int_or_none}), | |
959 | 'desc': ('desc', {bool_or_none}, {str_or_none}, {str.lower}), | |
960 | }) | |
961 | } | |
962 | metadata = { | |
963 | 'id': f'{query["type"]}_{query["biz_id"]}', | |
964 | **traverse_obj(initial_state, ('mediaListInfo', { | |
965 | 'title': ('title', {str}), | |
966 | 'uploader': ('upper', 'name', {str}), | |
967 | 'uploader_id': ('upper', 'mid', {str_or_none}), | |
968 | 'timestamp': ('ctime', {int_or_none}), | |
969 | 'thumbnail': ('cover', {url_or_none}), | |
970 | })), | |
971 | } | |
972 | return self.playlist_result(self._extract_medialist(query, list_id), **metadata) | |
06167fbb | 973 | |
974 | ||
c34f505b | 975 | class BilibiliCategoryIE(InfoExtractor): |
976 | IE_NAME = 'Bilibili category extractor' | |
977 | _MAX_RESULTS = 1000000 | |
9e68747f | 978 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/v/[a-zA-Z]+\/[a-zA-Z]+' |
c34f505b | 979 | _TESTS = [{ |
980 | 'url': 'https://www.bilibili.com/v/kichiku/mad', | |
981 | 'info_dict': { | |
982 | 'id': 'kichiku: mad', | |
983 | 'title': 'kichiku: mad' | |
984 | }, | |
985 | 'playlist_mincount': 45, | |
986 | 'params': { | |
987 | 'playlistend': 45 | |
988 | } | |
989 | }] | |
990 | ||
991 | def _fetch_page(self, api_url, num_pages, query, page_num): | |
992 | parsed_json = self._download_json( | |
993 | api_url, query, query={'Search_key': query, 'pn': page_num}, | |
994 | note='Extracting results from page %s of %s' % (page_num, num_pages)) | |
995 | ||
f8580bf0 | 996 | video_list = traverse_obj(parsed_json, ('data', 'archives'), expected_type=list) |
c34f505b | 997 | if not video_list: |
998 | raise ExtractorError('Failed to retrieve video list for page %d' % page_num) | |
999 | ||
1000 | for video in video_list: | |
1001 | yield self.url_result( | |
1002 | 'https://www.bilibili.com/video/%s' % video['bvid'], 'BiliBili', video['bvid']) | |
1003 | ||
1004 | def _entries(self, category, subcategory, query): | |
1005 | # map of categories : subcategories : RIDs | |
1006 | rid_map = { | |
1007 | 'kichiku': { | |
1008 | 'mad': 26, | |
1009 | 'manual_vocaloid': 126, | |
1010 | 'guide': 22, | |
1011 | 'theatre': 216, | |
1012 | 'course': 127 | |
1013 | }, | |
1014 | } | |
1015 | ||
1016 | if category not in rid_map: | |
e88d44c6 | 1017 | raise ExtractorError( |
1018 | f'The category {category} isn\'t supported. Supported categories: {list(rid_map.keys())}') | |
c34f505b | 1019 | if subcategory not in rid_map[category]: |
e88d44c6 | 1020 | raise ExtractorError( |
1021 | f'The subcategory {subcategory} isn\'t supported for this category. Supported subcategories: {list(rid_map[category].keys())}') | |
c34f505b | 1022 | rid_value = rid_map[category][subcategory] |
1023 | ||
1024 | api_url = 'https://api.bilibili.com/x/web-interface/newlist?rid=%d&type=1&ps=20&jsonp=jsonp' % rid_value | |
1025 | page_json = self._download_json(api_url, query, query={'Search_key': query, 'pn': '1'}) | |
f8580bf0 | 1026 | page_data = traverse_obj(page_json, ('data', 'page'), expected_type=dict) |
c34f505b | 1027 | count, size = int_or_none(page_data.get('count')), int_or_none(page_data.get('size')) |
1028 | if count is None or not size: | |
1029 | raise ExtractorError('Failed to calculate either page count or size') | |
1030 | ||
1031 | num_pages = math.ceil(count / size) | |
1032 | ||
1033 | return OnDemandPagedList(functools.partial( | |
1034 | self._fetch_page, api_url, num_pages, query), size) | |
1035 | ||
1036 | def _real_extract(self, url): | |
ad974876 | 1037 | category, subcategory = urllib.parse.urlparse(url).path.split('/')[2:4] |
c34f505b | 1038 | query = '%s: %s' % (category, subcategory) |
1039 | ||
1040 | return self.playlist_result(self._entries(category, subcategory, query), query, query) | |
1041 | ||
1042 | ||
06167fbb | 1043 | class BiliBiliSearchIE(SearchInfoExtractor): |
96565c7e | 1044 | IE_DESC = 'Bilibili video search' |
06167fbb | 1045 | _MAX_RESULTS = 100000 |
1046 | _SEARCH_KEY = 'bilisearch' | |
06167fbb | 1047 | |
e88d44c6 | 1048 | def _search_results(self, query): |
1049 | for page_num in itertools.count(1): | |
1050 | videos = self._download_json( | |
1051 | 'https://api.bilibili.com/x/web-interface/search/type', query, | |
1052 | note=f'Extracting results from page {page_num}', query={ | |
1053 | 'Search_key': query, | |
1054 | 'keyword': query, | |
1055 | 'page': page_num, | |
1056 | 'context': '', | |
e88d44c6 | 1057 | 'duration': 0, |
1058 | 'tids_2': '', | |
1059 | '__refresh__': 'true', | |
1060 | 'search_type': 'video', | |
1061 | 'tids': 0, | |
1062 | 'highlight': 1, | |
2d101954 | 1063 | })['data'].get('result') |
1064 | if not videos: | |
1065 | break | |
06167fbb | 1066 | for video in videos: |
e88d44c6 | 1067 | yield self.url_result(video['arcurl'], 'BiliBili', str(video['aid'])) |
06167fbb | 1068 | |
1069 | ||
4bc15a68 RA |
1070 | class BilibiliAudioBaseIE(InfoExtractor): |
1071 | def _call_api(self, path, sid, query=None): | |
1072 | if not query: | |
1073 | query = {'sid': sid} | |
1074 | return self._download_json( | |
1075 | 'https://www.bilibili.com/audio/music-service-c/web/' + path, | |
1076 | sid, query=query)['data'] | |
1077 | ||
1078 | ||
1079 | class BilibiliAudioIE(BilibiliAudioBaseIE): | |
1080 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/audio/au(?P<id>\d+)' | |
1081 | _TEST = { | |
1082 | 'url': 'https://www.bilibili.com/audio/au1003142', | |
1083 | 'md5': 'fec4987014ec94ef9e666d4d158ad03b', | |
1084 | 'info_dict': { | |
1085 | 'id': '1003142', | |
1086 | 'ext': 'm4a', | |
1087 | 'title': '【tsukimi】YELLOW / 神山羊', | |
1088 | 'artist': 'tsukimi', | |
1089 | 'comment_count': int, | |
1090 | 'description': 'YELLOW的mp3版!', | |
1091 | 'duration': 183, | |
1092 | 'subtitles': { | |
1093 | 'origin': [{ | |
1094 | 'ext': 'lrc', | |
1095 | }], | |
1096 | }, | |
1097 | 'thumbnail': r're:^https?://.+\.jpg', | |
1098 | 'timestamp': 1564836614, | |
1099 | 'upload_date': '20190803', | |
1100 | 'uploader': 'tsukimi-つきみぐー', | |
1101 | 'view_count': int, | |
1102 | }, | |
1103 | } | |
1104 | ||
1105 | def _real_extract(self, url): | |
1106 | au_id = self._match_id(url) | |
1107 | ||
1108 | play_data = self._call_api('url', au_id) | |
1109 | formats = [{ | |
1110 | 'url': play_data['cdns'][0], | |
1111 | 'filesize': int_or_none(play_data.get('size')), | |
f0884c8b | 1112 | 'vcodec': 'none' |
4bc15a68 RA |
1113 | }] |
1114 | ||
6d1b3489 | 1115 | for a_format in formats: |
1116 | a_format.setdefault('http_headers', {}).update({ | |
1117 | 'Referer': url, | |
1118 | }) | |
1119 | ||
4bc15a68 RA |
1120 | song = self._call_api('song/info', au_id) |
1121 | title = song['title'] | |
1122 | statistic = song.get('statistic') or {} | |
1123 | ||
1124 | subtitles = None | |
1125 | lyric = song.get('lyric') | |
1126 | if lyric: | |
1127 | subtitles = { | |
1128 | 'origin': [{ | |
1129 | 'url': lyric, | |
1130 | }] | |
1131 | } | |
1132 | ||
1133 | return { | |
1134 | 'id': au_id, | |
1135 | 'title': title, | |
1136 | 'formats': formats, | |
1137 | 'artist': song.get('author'), | |
1138 | 'comment_count': int_or_none(statistic.get('comment')), | |
1139 | 'description': song.get('intro'), | |
1140 | 'duration': int_or_none(song.get('duration')), | |
1141 | 'subtitles': subtitles, | |
1142 | 'thumbnail': song.get('cover'), | |
1143 | 'timestamp': int_or_none(song.get('passtime')), | |
1144 | 'uploader': song.get('uname'), | |
1145 | 'view_count': int_or_none(statistic.get('play')), | |
1146 | } | |
1147 | ||
1148 | ||
1149 | class BilibiliAudioAlbumIE(BilibiliAudioBaseIE): | |
1150 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/audio/am(?P<id>\d+)' | |
1151 | _TEST = { | |
1152 | 'url': 'https://www.bilibili.com/audio/am10624', | |
1153 | 'info_dict': { | |
1154 | 'id': '10624', | |
1155 | 'title': '每日新曲推荐(每日11:00更新)', | |
1156 | 'description': '每天11:00更新,为你推送最新音乐', | |
1157 | }, | |
1158 | 'playlist_count': 19, | |
1159 | } | |
1160 | ||
1161 | def _real_extract(self, url): | |
1162 | am_id = self._match_id(url) | |
1163 | ||
1164 | songs = self._call_api( | |
1165 | 'song/of-menu', am_id, {'sid': am_id, 'pn': 1, 'ps': 100})['data'] | |
1166 | ||
1167 | entries = [] | |
1168 | for song in songs: | |
1169 | sid = str_or_none(song.get('id')) | |
1170 | if not sid: | |
1171 | continue | |
1172 | entries.append(self.url_result( | |
1173 | 'https://www.bilibili.com/audio/au' + sid, | |
1174 | BilibiliAudioIE.ie_key(), sid)) | |
1175 | ||
1176 | if entries: | |
1177 | album_data = self._call_api('menu/info', am_id) or {} | |
1178 | album_title = album_data.get('title') | |
1179 | if album_title: | |
1180 | for entry in entries: | |
1181 | entry['album'] = album_title | |
1182 | return self.playlist_result( | |
1183 | entries, am_id, album_title, album_data.get('intro')) | |
1184 | ||
1185 | return self.playlist_result(entries, am_id) | |
63dce309 S |
1186 | |
1187 | ||
1188 | class BiliBiliPlayerIE(InfoExtractor): | |
1189 | _VALID_URL = r'https?://player\.bilibili\.com/player\.html\?.*?\baid=(?P<id>\d+)' | |
1190 | _TEST = { | |
1191 | 'url': 'http://player.bilibili.com/player.html?aid=92494333&cid=157926707&page=1', | |
1192 | 'only_matching': True, | |
1193 | } | |
1194 | ||
1195 | def _real_extract(self, url): | |
1196 | video_id = self._match_id(url) | |
1197 | return self.url_result( | |
1198 | 'http://www.bilibili.tv/video/av%s/' % video_id, | |
1199 | ie=BiliBiliIE.ie_key(), video_id=video_id) | |
16f7e6be AG |
1200 | |
1201 | ||
1202 | class BiliIntlBaseIE(InfoExtractor): | |
c62ecf0d | 1203 | _API_URL = 'https://api.bilibili.tv/intl/gateway' |
cfcf60ea | 1204 | _NETRC_MACHINE = 'biliintl' |
16f7e6be | 1205 | |
c62ecf0d | 1206 | def _call_api(self, endpoint, *args, **kwargs): |
cfcf60ea M |
1207 | json = self._download_json(self._API_URL + endpoint, *args, **kwargs) |
1208 | if json.get('code'): | |
1209 | if json['code'] in (10004004, 10004005, 10023006): | |
1210 | self.raise_login_required() | |
1211 | elif json['code'] == 10004001: | |
1212 | self.raise_geo_restricted() | |
1213 | else: | |
1214 | if json.get('message') and str(json['code']) != json['message']: | |
1215 | errmsg = f'{kwargs.get("errnote", "Unable to download JSON metadata")}: {self.IE_NAME} said: {json["message"]}' | |
1216 | else: | |
1217 | errmsg = kwargs.get('errnote', 'Unable to download JSON metadata') | |
1218 | if kwargs.get('fatal'): | |
1219 | raise ExtractorError(errmsg) | |
1220 | else: | |
1221 | self.report_warning(errmsg) | |
1222 | return json.get('data') | |
16f7e6be | 1223 | |
efc947fb | 1224 | def json2srt(self, json): |
1225 | data = '\n\n'.join( | |
1226 | f'{i + 1}\n{srt_subtitles_timecode(line["from"])} --> {srt_subtitles_timecode(line["to"])}\n{line["content"]}' | |
dfb855b4 | 1227 | for i, line in enumerate(traverse_obj(json, ( |
1228 | 'body', lambda _, l: l['content'] and l['from'] and l['to'])))) | |
efc947fb | 1229 | return data |
1230 | ||
f5f15c99 LR |
1231 | def _get_subtitles(self, *, ep_id=None, aid=None): |
1232 | sub_json = self._call_api( | |
fbb888a3 | 1233 | '/web/v2/subtitle', ep_id or aid, fatal=False, |
1234 | note='Downloading subtitles list', errnote='Unable to download subtitles list', | |
1235 | query=filter_dict({ | |
f5f15c99 | 1236 | 'platform': 'web', |
fbb888a3 | 1237 | 's_locale': 'en_US', |
f5f15c99 LR |
1238 | 'episode_id': ep_id, |
1239 | 'aid': aid, | |
fbb888a3 | 1240 | })) or {} |
16f7e6be | 1241 | subtitles = {} |
c62ecf0d | 1242 | for sub in sub_json.get('subtitles') or []: |
16f7e6be AG |
1243 | sub_url = sub.get('url') |
1244 | if not sub_url: | |
1245 | continue | |
c62ecf0d | 1246 | sub_data = self._download_json( |
f5f15c99 | 1247 | sub_url, ep_id or aid, errnote='Unable to download subtitles', fatal=False, |
c62ecf0d | 1248 | note='Downloading subtitles%s' % f' for {sub["lang"]}' if sub.get('lang') else '') |
efc947fb | 1249 | if not sub_data: |
1250 | continue | |
c62ecf0d | 1251 | subtitles.setdefault(sub.get('lang_key', 'en'), []).append({ |
efc947fb | 1252 | 'ext': 'srt', |
1253 | 'data': self.json2srt(sub_data) | |
16f7e6be AG |
1254 | }) |
1255 | return subtitles | |
1256 | ||
f5f15c99 LR |
1257 | def _get_formats(self, *, ep_id=None, aid=None): |
1258 | video_json = self._call_api( | |
1259 | '/web/playurl', ep_id or aid, note='Downloading video formats', | |
1260 | errnote='Unable to download video formats', query=filter_dict({ | |
1261 | 'platform': 'web', | |
1262 | 'ep_id': ep_id, | |
1263 | 'aid': aid, | |
1264 | })) | |
16f7e6be AG |
1265 | video_json = video_json['playurl'] |
1266 | formats = [] | |
c62ecf0d | 1267 | for vid in video_json.get('video') or []: |
16f7e6be AG |
1268 | video_res = vid.get('video_resource') or {} |
1269 | video_info = vid.get('stream_info') or {} | |
1270 | if not video_res.get('url'): | |
1271 | continue | |
1272 | formats.append({ | |
1273 | 'url': video_res['url'], | |
1274 | 'ext': 'mp4', | |
1275 | 'format_note': video_info.get('desc_words'), | |
1276 | 'width': video_res.get('width'), | |
1277 | 'height': video_res.get('height'), | |
1278 | 'vbr': video_res.get('bandwidth'), | |
1279 | 'acodec': 'none', | |
1280 | 'vcodec': video_res.get('codecs'), | |
1281 | 'filesize': video_res.get('size'), | |
1282 | }) | |
c62ecf0d | 1283 | for aud in video_json.get('audio_resource') or []: |
16f7e6be AG |
1284 | if not aud.get('url'): |
1285 | continue | |
1286 | formats.append({ | |
1287 | 'url': aud['url'], | |
1288 | 'ext': 'mp4', | |
1289 | 'abr': aud.get('bandwidth'), | |
1290 | 'acodec': aud.get('codecs'), | |
1291 | 'vcodec': 'none', | |
1292 | 'filesize': aud.get('size'), | |
1293 | }) | |
1294 | ||
16f7e6be AG |
1295 | return formats |
1296 | ||
26fdfc37 | 1297 | def _parse_video_metadata(self, video_data): |
16f7e6be | 1298 | return { |
f5f15c99 LR |
1299 | 'title': video_data.get('title_display') or video_data.get('title'), |
1300 | 'thumbnail': video_data.get('cover'), | |
c62ecf0d | 1301 | 'episode_number': int_or_none(self._search_regex( |
f5f15c99 | 1302 | r'^E(\d+)(?:$| - )', video_data.get('title_display') or '', 'episode number', default=None)), |
16f7e6be AG |
1303 | } |
1304 | ||
52efa4b3 | 1305 | def _perform_login(self, username, password): |
65f6e807 | 1306 | if not Cryptodome.RSA: |
f6a765ce | 1307 | raise ExtractorError('pycryptodomex not found. Please install', expected=True) |
cfcf60ea M |
1308 | |
1309 | key_data = self._download_json( | |
1310 | 'https://passport.bilibili.tv/x/intl/passport-login/web/key?lang=en-US', None, | |
1311 | note='Downloading login key', errnote='Unable to download login key')['data'] | |
1312 | ||
65f6e807 | 1313 | public_key = Cryptodome.RSA.importKey(key_data['key']) |
1314 | password_hash = Cryptodome.PKCS1_v1_5.new(public_key).encrypt((key_data['hash'] + password).encode('utf-8')) | |
cfcf60ea M |
1315 | login_post = self._download_json( |
1316 | 'https://passport.bilibili.tv/x/intl/passport-login/web/login/password?lang=en-US', None, data=urlencode_postdata({ | |
1317 | 'username': username, | |
1318 | 'password': base64.b64encode(password_hash).decode('ascii'), | |
1319 | 'keep_me': 'true', | |
1320 | 's_locale': 'en_US', | |
1321 | 'isTrusted': 'true' | |
1322 | }), note='Logging in', errnote='Unable to log in') | |
1323 | if login_post.get('code'): | |
1324 | if login_post.get('message'): | |
1325 | raise ExtractorError(f'Unable to log in: {self.IE_NAME} said: {login_post["message"]}', expected=True) | |
1326 | else: | |
1327 | raise ExtractorError('Unable to log in') | |
1328 | ||
16f7e6be AG |
1329 | |
1330 | class BiliIntlIE(BiliIntlBaseIE): | |
0831d95c | 1331 | _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+))' |
16f7e6be | 1332 | _TESTS = [{ |
cfcf60ea | 1333 | # Bstation page |
16f7e6be AG |
1334 | 'url': 'https://www.bilibili.tv/en/play/34613/341736', |
1335 | 'info_dict': { | |
1336 | 'id': '341736', | |
1337 | 'ext': 'mp4', | |
c62ecf0d M |
1338 | 'title': 'E2 - The First Night', |
1339 | 'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.png$', | |
16f7e6be | 1340 | 'episode_number': 2, |
d37422f1 H |
1341 | 'upload_date': '20201009', |
1342 | 'episode': 'Episode 2', | |
1343 | 'timestamp': 1602259500, | |
1344 | 'description': 'md5:297b5a17155eb645e14a14b385ab547e', | |
0ba87dd2 H |
1345 | 'chapters': [{ |
1346 | 'start_time': 0, | |
1347 | 'end_time': 76.242, | |
1348 | 'title': '<Untitled Chapter 1>' | |
1349 | }, { | |
1350 | 'start_time': 76.242, | |
1351 | 'end_time': 161.161, | |
1352 | 'title': 'Intro' | |
1353 | }, { | |
1354 | 'start_time': 1325.742, | |
1355 | 'end_time': 1403.903, | |
1356 | 'title': 'Outro' | |
1357 | }], | |
c62ecf0d | 1358 | } |
16f7e6be | 1359 | }, { |
cfcf60ea | 1360 | # Non-Bstation page |
c62ecf0d | 1361 | 'url': 'https://www.bilibili.tv/en/play/1033760/11005006', |
16f7e6be | 1362 | 'info_dict': { |
c62ecf0d | 1363 | 'id': '11005006', |
16f7e6be | 1364 | 'ext': 'mp4', |
c62ecf0d M |
1365 | 'title': 'E3 - Who?', |
1366 | 'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.png$', | |
1367 | 'episode_number': 3, | |
d37422f1 H |
1368 | 'description': 'md5:e1a775e71a35c43f141484715470ad09', |
1369 | 'episode': 'Episode 3', | |
1370 | 'upload_date': '20211219', | |
1371 | 'timestamp': 1639928700, | |
0ba87dd2 H |
1372 | 'chapters': [{ |
1373 | 'start_time': 0, | |
1374 | 'end_time': 88.0, | |
1375 | 'title': '<Untitled Chapter 1>' | |
1376 | }, { | |
1377 | 'start_time': 88.0, | |
1378 | 'end_time': 156.0, | |
1379 | 'title': 'Intro' | |
1380 | }, { | |
1381 | 'start_time': 1173.0, | |
1382 | 'end_time': 1259.535, | |
1383 | 'title': 'Outro' | |
1384 | }], | |
c62ecf0d | 1385 | } |
cfcf60ea M |
1386 | }, { |
1387 | # Subtitle with empty content | |
1388 | 'url': 'https://www.bilibili.tv/en/play/1005144/10131790', | |
1389 | 'info_dict': { | |
1390 | 'id': '10131790', | |
1391 | 'ext': 'mp4', | |
1392 | 'title': 'E140 - Two Heartbeats: Kabuto\'s Trap', | |
1393 | 'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.png$', | |
1394 | 'episode_number': 140, | |
1395 | }, | |
1396 | 'skip': 'According to the copyright owner\'s request, you may only watch the video after you log in.' | |
d37422f1 H |
1397 | }, { |
1398 | 'url': 'https://www.bilibili.tv/en/video/2041863208', | |
1399 | 'info_dict': { | |
1400 | 'id': '2041863208', | |
1401 | 'ext': 'mp4', | |
1402 | 'timestamp': 1670874843, | |
1403 | 'description': 'Scheduled for April 2023.\nStudio: ufotable', | |
1404 | 'thumbnail': r're:https?://pic[-\.]bstarstatic.+/ugc/.+\.jpg$', | |
1405 | 'upload_date': '20221212', | |
1406 | 'title': 'Kimetsu no Yaiba Season 3 Official Trailer - Bstation', | |
b093c38c H |
1407 | }, |
1408 | }, { | |
1409 | # episode comment extraction | |
1410 | 'url': 'https://www.bilibili.tv/en/play/34580/340317', | |
1411 | 'info_dict': { | |
1412 | 'id': '340317', | |
1413 | 'ext': 'mp4', | |
1414 | 'timestamp': 1604057820, | |
1415 | 'upload_date': '20201030', | |
1416 | 'episode_number': 5, | |
1417 | 'title': 'E5 - My Own Steel', | |
1418 | 'description': 'md5:2b17ab10aebb33e3c2a54da9e8e487e2', | |
1419 | 'thumbnail': r're:https?://pic\.bstarstatic\.com/ogv/.+\.png$', | |
1420 | 'episode': 'Episode 5', | |
1421 | 'comment_count': int, | |
1422 | 'chapters': [{ | |
1423 | 'start_time': 0, | |
1424 | 'end_time': 61.0, | |
1425 | 'title': '<Untitled Chapter 1>' | |
1426 | }, { | |
1427 | 'start_time': 61.0, | |
1428 | 'end_time': 134.0, | |
1429 | 'title': 'Intro' | |
1430 | }, { | |
1431 | 'start_time': 1290.0, | |
1432 | 'end_time': 1379.0, | |
1433 | 'title': 'Outro' | |
1434 | }], | |
1435 | }, | |
1436 | 'params': { | |
1437 | 'getcomments': True | |
1438 | } | |
1439 | }, { | |
1440 | # user generated content comment extraction | |
1441 | 'url': 'https://www.bilibili.tv/en/video/2045730385', | |
1442 | 'info_dict': { | |
1443 | 'id': '2045730385', | |
1444 | 'ext': 'mp4', | |
1445 | 'description': 'md5:693b6f3967fb4e7e7764ea817857c33a', | |
1446 | 'timestamp': 1667891924, | |
1447 | 'upload_date': '20221108', | |
1448 | 'title': 'That Time I Got Reincarnated as a Slime: Scarlet Bond - Official Trailer 3| AnimeStan - Bstation', | |
1449 | 'comment_count': int, | |
1450 | 'thumbnail': 'https://pic.bstarstatic.com/ugc/f6c363659efd2eabe5683fbb906b1582.jpg', | |
1451 | }, | |
1452 | 'params': { | |
1453 | 'getcomments': True | |
d37422f1 | 1454 | } |
0ba87dd2 H |
1455 | }, { |
1456 | # episode id without intro and outro | |
1457 | 'url': 'https://www.bilibili.tv/en/play/1048837/11246489', | |
1458 | 'info_dict': { | |
1459 | 'id': '11246489', | |
1460 | 'ext': 'mp4', | |
1461 | 'title': 'E1 - Operation \'Strix\' <Owl>', | |
1462 | 'description': 'md5:b4434eb1a9a97ad2bccb779514b89f17', | |
1463 | 'timestamp': 1649516400, | |
1464 | 'thumbnail': 'https://pic.bstarstatic.com/ogv/62cb1de23ada17fb70fbe7bdd6ff29c29da02a64.png', | |
1465 | 'episode': 'Episode 1', | |
1466 | 'episode_number': 1, | |
1467 | 'upload_date': '20220409', | |
1468 | }, | |
c62ecf0d M |
1469 | }, { |
1470 | 'url': 'https://www.biliintl.com/en/play/34613/341736', | |
1471 | 'only_matching': True, | |
f5f15c99 LR |
1472 | }, { |
1473 | # User-generated content (as opposed to a series licensed from a studio) | |
1474 | 'url': 'https://bilibili.tv/en/video/2019955076', | |
1475 | 'only_matching': True, | |
1476 | }, { | |
1477 | # No language in URL | |
1478 | 'url': 'https://www.bilibili.tv/video/2019955076', | |
1479 | 'only_matching': True, | |
0831d95c | 1480 | }, { |
1481 | # Uppercase language in URL | |
1482 | 'url': 'https://www.bilibili.tv/EN/video/2019955076', | |
1483 | 'only_matching': True, | |
16f7e6be AG |
1484 | }] |
1485 | ||
26fdfc37 | 1486 | def _make_url(video_id, series_id=None): |
1487 | if series_id: | |
1488 | return f'https://www.bilibili.tv/en/play/{series_id}/{video_id}' | |
1489 | return f'https://www.bilibili.tv/en/video/{video_id}' | |
1490 | ||
1491 | def _extract_video_metadata(self, url, video_id, season_id): | |
1492 | url, smuggled_data = unsmuggle_url(url, {}) | |
1493 | if smuggled_data.get('title'): | |
1494 | return smuggled_data | |
1495 | ||
c62ecf0d M |
1496 | webpage = self._download_webpage(url, video_id) |
1497 | # Bstation layout | |
8072ef2b | 1498 | initial_data = ( |
1499 | self._search_json(r'window\.__INITIAL_(?:DATA|STATE)__\s*=', webpage, 'preload state', video_id, default={}) | |
1500 | or self._search_nuxt_data(webpage, video_id, '__initialState', fatal=False, traverse=None)) | |
1501 | video_data = traverse_obj( | |
d37422f1 | 1502 | initial_data, ('OgvVideo', 'epDetail'), ('UgcVideo', 'videoData'), ('ugc', 'archive'), expected_type=dict) or {} |
c62ecf0d | 1503 | |
f5f15c99 | 1504 | if season_id and not video_data: |
c62ecf0d M |
1505 | # Non-Bstation layout, read through episode list |
1506 | season_json = self._call_api(f'/web/v2/ogv/play/episodes?season_id={season_id}&platform=web', video_id) | |
26fdfc37 | 1507 | video_data = traverse_obj(season_json, ( |
1508 | 'sections', ..., 'episodes', lambda _, v: str(v['episode_id']) == video_id | |
1509 | ), expected_type=dict, get_all=False) | |
1510 | ||
d37422f1 H |
1511 | # XXX: webpage metadata may not accurate, it just used to not crash when video_data not found |
1512 | return merge_dicts( | |
b093c38c | 1513 | self._parse_video_metadata(video_data), self._search_json_ld(webpage, video_id, fatal=False), { |
d37422f1 H |
1514 | 'title': self._html_search_meta('og:title', webpage), |
1515 | 'description': self._html_search_meta('og:description', webpage) | |
1516 | }) | |
26fdfc37 | 1517 | |
b093c38c H |
1518 | def _get_comments_reply(self, root_id, next_id=0, display_id=None): |
1519 | comment_api_raw_data = self._download_json( | |
1520 | 'https://api.bilibili.tv/reply/web/detail', display_id, | |
1521 | note=f'Downloading reply comment of {root_id} - {next_id}', | |
1522 | query={ | |
1523 | 'platform': 'web', | |
1524 | 'ps': 20, # comment's reply per page (default: 3) | |
1525 | 'root': root_id, | |
1526 | 'next': next_id, | |
1527 | }) | |
1528 | ||
1529 | for replies in traverse_obj(comment_api_raw_data, ('data', 'replies', ...)): | |
1530 | yield { | |
1531 | 'author': traverse_obj(replies, ('member', 'name')), | |
1532 | 'author_id': traverse_obj(replies, ('member', 'mid')), | |
1533 | 'author_thumbnail': traverse_obj(replies, ('member', 'face')), | |
1534 | 'text': traverse_obj(replies, ('content', 'message')), | |
1535 | 'id': replies.get('rpid'), | |
1536 | 'like_count': int_or_none(replies.get('like_count')), | |
1537 | 'parent': replies.get('parent'), | |
1538 | 'timestamp': unified_timestamp(replies.get('ctime_text')) | |
1539 | } | |
1540 | ||
1541 | if not traverse_obj(comment_api_raw_data, ('data', 'cursor', 'is_end')): | |
1542 | yield from self._get_comments_reply( | |
1543 | root_id, comment_api_raw_data['data']['cursor']['next'], display_id) | |
1544 | ||
1545 | def _get_comments(self, video_id, ep_id): | |
1546 | for i in itertools.count(0): | |
1547 | comment_api_raw_data = self._download_json( | |
1548 | 'https://api.bilibili.tv/reply/web/root', video_id, | |
1549 | note=f'Downloading comment page {i + 1}', | |
1550 | query={ | |
1551 | 'platform': 'web', | |
1552 | 'pn': i, # page number | |
1553 | 'ps': 20, # comment per page (default: 20) | |
1554 | 'oid': video_id, | |
1555 | 'type': 3 if ep_id else 1, # 1: user generated content, 3: series content | |
1556 | 'sort_type': 1, # 1: best, 2: recent | |
1557 | }) | |
1558 | ||
1559 | for replies in traverse_obj(comment_api_raw_data, ('data', 'replies', ...)): | |
1560 | yield { | |
1561 | 'author': traverse_obj(replies, ('member', 'name')), | |
1562 | 'author_id': traverse_obj(replies, ('member', 'mid')), | |
1563 | 'author_thumbnail': traverse_obj(replies, ('member', 'face')), | |
1564 | 'text': traverse_obj(replies, ('content', 'message')), | |
1565 | 'id': replies.get('rpid'), | |
1566 | 'like_count': int_or_none(replies.get('like_count')), | |
1567 | 'timestamp': unified_timestamp(replies.get('ctime_text')), | |
1568 | 'author_is_uploader': bool(traverse_obj(replies, ('member', 'type'))), | |
1569 | } | |
1570 | if replies.get('count'): | |
1571 | yield from self._get_comments_reply(replies.get('rpid'), display_id=video_id) | |
1572 | ||
1573 | if traverse_obj(comment_api_raw_data, ('data', 'cursor', 'is_end')): | |
1574 | break | |
1575 | ||
26fdfc37 | 1576 | def _real_extract(self, url): |
1577 | season_id, ep_id, aid = self._match_valid_url(url).group('season_id', 'ep_id', 'aid') | |
1578 | video_id = ep_id or aid | |
0ba87dd2 H |
1579 | chapters = None |
1580 | ||
1581 | if ep_id: | |
1582 | intro_ending_json = self._call_api( | |
1583 | f'/web/v2/ogv/play/episode?episode_id={ep_id}&platform=web', | |
1584 | video_id, fatal=False) or {} | |
1585 | if intro_ending_json.get('skip'): | |
1586 | # FIXME: start time and end time seems a bit off a few second even it corrext based on ogv.*.js | |
1587 | # ref: https://p.bstarstatic.com/fe-static/bstar-web-new/assets/ogv.2b147442.js | |
1588 | chapters = [{ | |
1589 | 'start_time': float_or_none(traverse_obj(intro_ending_json, ('skip', 'opening_start_time')), 1000), | |
1590 | 'end_time': float_or_none(traverse_obj(intro_ending_json, ('skip', 'opening_end_time')), 1000), | |
1591 | 'title': 'Intro' | |
1592 | }, { | |
1593 | 'start_time': float_or_none(traverse_obj(intro_ending_json, ('skip', 'ending_start_time')), 1000), | |
1594 | 'end_time': float_or_none(traverse_obj(intro_ending_json, ('skip', 'ending_end_time')), 1000), | |
1595 | 'title': 'Outro' | |
1596 | }] | |
26fdfc37 | 1597 | |
1598 | return { | |
1599 | 'id': video_id, | |
1600 | **self._extract_video_metadata(url, video_id, season_id), | |
1601 | 'formats': self._get_formats(ep_id=ep_id, aid=aid), | |
1602 | 'subtitles': self.extract_subtitles(ep_id=ep_id, aid=aid), | |
b093c38c H |
1603 | 'chapters': chapters, |
1604 | '__post_extractor': self.extract_comments(video_id, ep_id) | |
26fdfc37 | 1605 | } |
16f7e6be AG |
1606 | |
1607 | ||
1608 | class BiliIntlSeriesIE(BiliIntlBaseIE): | |
08e29b9f | 1609 | IE_NAME = 'biliIntl:series' |
76c3cecc | 1610 | _VALID_URL = r'https?://(?:www\.)?bili(?:bili\.tv|intl\.com)/(?:[a-zA-Z]{2}/)?(?:play|media)/(?P<id>\d+)/?(?:[?#]|$)' |
16f7e6be AG |
1611 | _TESTS = [{ |
1612 | 'url': 'https://www.bilibili.tv/en/play/34613', | |
1613 | 'playlist_mincount': 15, | |
1614 | 'info_dict': { | |
1615 | 'id': '34613', | |
76c3cecc H |
1616 | 'title': 'TONIKAWA: Over the Moon For You', |
1617 | 'description': 'md5:297b5a17155eb645e14a14b385ab547e', | |
1618 | 'categories': ['Slice of life', 'Comedy', 'Romance'], | |
c62ecf0d M |
1619 | 'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.png$', |
1620 | 'view_count': int, | |
16f7e6be AG |
1621 | }, |
1622 | 'params': { | |
1623 | 'skip_download': True, | |
16f7e6be | 1624 | }, |
76c3cecc H |
1625 | }, { |
1626 | 'url': 'https://www.bilibili.tv/en/media/1048837', | |
1627 | 'info_dict': { | |
1628 | 'id': '1048837', | |
1629 | 'title': 'SPY×FAMILY', | |
1630 | 'description': 'md5:b4434eb1a9a97ad2bccb779514b89f17', | |
1631 | 'categories': ['Adventure', 'Action', 'Comedy'], | |
1632 | 'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.jpg$', | |
1633 | 'view_count': int, | |
1634 | }, | |
1635 | 'playlist_mincount': 25, | |
16f7e6be AG |
1636 | }, { |
1637 | 'url': 'https://www.biliintl.com/en/play/34613', | |
c62ecf0d | 1638 | 'only_matching': True, |
0831d95c | 1639 | }, { |
1640 | 'url': 'https://www.biliintl.com/EN/play/34613', | |
1641 | 'only_matching': True, | |
16f7e6be AG |
1642 | }] |
1643 | ||
c62ecf0d M |
1644 | def _entries(self, series_id): |
1645 | series_json = self._call_api(f'/web/v2/ogv/play/episodes?season_id={series_id}&platform=web', series_id) | |
26fdfc37 | 1646 | for episode in traverse_obj(series_json, ('sections', ..., 'episodes', ...), expected_type=dict): |
1647 | episode_id = str(episode['episode_id']) | |
1648 | yield self.url_result(smuggle_url( | |
1649 | BiliIntlIE._make_url(episode_id, series_id), | |
1650 | self._parse_video_metadata(episode) | |
1651 | ), BiliIntlIE, episode_id) | |
16f7e6be AG |
1652 | |
1653 | def _real_extract(self, url): | |
c62ecf0d M |
1654 | series_id = self._match_id(url) |
1655 | series_info = self._call_api(f'/web/v2/ogv/play/season_info?season_id={series_id}&platform=web', series_id).get('season') or {} | |
1656 | return self.playlist_result( | |
1657 | self._entries(series_id), series_id, series_info.get('title'), series_info.get('description'), | |
1658 | categories=traverse_obj(series_info, ('styles', ..., 'title'), expected_type=str_or_none), | |
1659 | thumbnail=url_or_none(series_info.get('horizontal_cover')), view_count=parse_count(series_info.get('view'))) | |
b4f53662 H |
1660 | |
1661 | ||
1662 | class BiliLiveIE(InfoExtractor): | |
9e68747f | 1663 | _VALID_URL = r'https?://live\.bilibili\.com/(?:blanc/)?(?P<id>\d+)' |
b4f53662 H |
1664 | |
1665 | _TESTS = [{ | |
1666 | 'url': 'https://live.bilibili.com/196', | |
1667 | 'info_dict': { | |
1668 | 'id': '33989', | |
1669 | '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)", | |
1670 | 'ext': 'flv', | |
1671 | 'title': "太空狼人杀联动,不被爆杀就算赢", | |
1672 | 'thumbnail': "https://i0.hdslb.com/bfs/live/new_room_cover/e607bc1529057ef4b332e1026e62cf46984c314d.jpg", | |
1673 | 'timestamp': 1650802769, | |
1674 | }, | |
1675 | 'skip': 'not live' | |
1676 | }, { | |
1677 | 'url': 'https://live.bilibili.com/196?broadcast_type=0&is_room_feed=1?spm_id_from=333.999.space_home.strengthen_live_card.click', | |
1678 | 'only_matching': True | |
1c226ccd | 1679 | }, { |
1680 | 'url': 'https://live.bilibili.com/blanc/196', | |
1681 | 'only_matching': True | |
b4f53662 H |
1682 | }] |
1683 | ||
1684 | _FORMATS = { | |
1685 | 80: {'format_id': 'low', 'format_note': '流畅'}, | |
1686 | 150: {'format_id': 'high_res', 'format_note': '高清'}, | |
1687 | 250: {'format_id': 'ultra_high_res', 'format_note': '超清'}, | |
1688 | 400: {'format_id': 'blue_ray', 'format_note': '蓝光'}, | |
1689 | 10000: {'format_id': 'source', 'format_note': '原画'}, | |
1690 | 20000: {'format_id': '4K', 'format_note': '4K'}, | |
1691 | 30000: {'format_id': 'dolby', 'format_note': '杜比'}, | |
1692 | } | |
1693 | ||
1694 | _quality = staticmethod(qualities(list(_FORMATS))) | |
1695 | ||
1696 | def _call_api(self, path, room_id, query): | |
1697 | api_result = self._download_json(f'https://api.live.bilibili.com/{path}', room_id, query=query) | |
1698 | if api_result.get('code') != 0: | |
1699 | raise ExtractorError(api_result.get('message') or 'Unable to download JSON metadata') | |
1700 | return api_result.get('data') or {} | |
1701 | ||
1702 | def _parse_formats(self, qn, fmt): | |
1703 | for codec in fmt.get('codec') or []: | |
1704 | if codec.get('current_qn') != qn: | |
1705 | continue | |
1706 | for url_info in codec['url_info']: | |
1707 | yield { | |
1708 | 'url': f'{url_info["host"]}{codec["base_url"]}{url_info["extra"]}', | |
1709 | 'ext': fmt.get('format_name'), | |
1710 | 'vcodec': codec.get('codec_name'), | |
1711 | 'quality': self._quality(qn), | |
1712 | **self._FORMATS[qn], | |
1713 | } | |
1714 | ||
1715 | def _real_extract(self, url): | |
1716 | room_id = self._match_id(url) | |
1717 | room_data = self._call_api('room/v1/Room/get_info', room_id, {'id': room_id}) | |
1718 | if room_data.get('live_status') == 0: | |
1719 | raise ExtractorError('Streamer is not live', expected=True) | |
1720 | ||
1721 | formats = [] | |
1722 | for qn in self._FORMATS.keys(): | |
1723 | stream_data = self._call_api('xlive/web-room/v2/index/getRoomPlayInfo', room_id, { | |
1724 | 'room_id': room_id, | |
1725 | 'qn': qn, | |
1726 | 'codec': '0,1', | |
1727 | 'format': '0,2', | |
1728 | 'mask': '0', | |
1729 | 'no_playurl': '0', | |
1730 | 'platform': 'web', | |
1731 | 'protocol': '0,1', | |
1732 | }) | |
1733 | for fmt in traverse_obj(stream_data, ('playurl_info', 'playurl', 'stream', ..., 'format', ...)) or []: | |
1734 | formats.extend(self._parse_formats(qn, fmt)) | |
b4f53662 H |
1735 | |
1736 | return { | |
1737 | 'id': room_id, | |
1738 | 'title': room_data.get('title'), | |
1739 | 'description': room_data.get('description'), | |
1740 | 'thumbnail': room_data.get('user_cover'), | |
1741 | 'timestamp': stream_data.get('live_time'), | |
1742 | 'formats': formats, | |
ca2f6e14 | 1743 | 'is_live': True, |
b4f53662 H |
1744 | 'http_headers': { |
1745 | 'Referer': url, | |
1746 | }, | |
1747 | } |