]>
Commit | Line | Data |
---|---|---|
cfcf60ea | 1 | import base64 |
04b32c8f | 2 | import hashlib |
6efb0711 | 3 | import itertools |
c34f505b | 4 | import functools |
520e7533 | 5 | import re |
c34f505b | 6 | import math |
28746fbd | 7 | |
06167fbb | 8 | from .common import InfoExtractor, SearchInfoExtractor |
bd8f48c7 YCH |
9 | from ..compat import ( |
10 | compat_parse_qs, | |
11 | compat_urlparse, | |
c34f505b | 12 | compat_urllib_parse_urlparse |
bd8f48c7 | 13 | ) |
28746fbd | 14 | from ..utils import ( |
bd8f48c7 | 15 | ExtractorError, |
f5f15c99 | 16 | filter_dict, |
6461f2b7 YCH |
17 | int_or_none, |
18 | float_or_none, | |
f8580bf0 | 19 | mimetype2ext, |
bd8f48c7 | 20 | parse_iso8601, |
b4f53662 | 21 | qualities, |
e88d44c6 | 22 | traverse_obj, |
c62ecf0d | 23 | parse_count, |
bd8f48c7 | 24 | smuggle_url, |
efc947fb | 25 | srt_subtitles_timecode, |
4bc15a68 | 26 | str_or_none, |
bd8f48c7 | 27 | strip_jsonp, |
04b32c8f | 28 | unified_timestamp, |
bd8f48c7 | 29 | unsmuggle_url, |
1f85029d | 30 | urlencode_postdata, |
c62ecf0d | 31 | url_or_none, |
c34f505b | 32 | OnDemandPagedList |
28746fbd PH |
33 | ) |
34 | ||
35 | ||
36 | class BiliBiliIE(InfoExtractor): | |
b4eb08bb S |
37 | _VALID_URL = r'''(?x) |
38 | https?:// | |
39 | (?:(?:www|bangumi)\.)? | |
40 | bilibili\.(?:tv|com)/ | |
41 | (?: | |
42 | (?: | |
43 | video/[aA][vV]| | |
44 | anime/(?P<anime_id>\d+)/play\# | |
06167fbb | 45 | )(?P<id>\d+)| |
9536bc07 | 46 | (s/)?video/[bB][vV](?P<id_bv>[^/?#&]+) |
b4eb08bb | 47 | ) |
06167fbb | 48 | (?:/?\?p=(?P<page>\d+))? |
b4eb08bb | 49 | ''' |
28746fbd | 50 | |
bd8f48c7 | 51 | _TESTS = [{ |
06167fbb | 52 | 'url': 'http://www.bilibili.com/video/av1074402/', |
89fabf11 | 53 | 'md5': '7ac275ec84a99a6552c5d229659a0fe1', |
28746fbd | 54 | 'info_dict': { |
54bb3906 | 55 | 'id': '1074402_part1', |
f8580bf0 | 56 | 'ext': 'mp4', |
28746fbd | 57 | 'title': '【金坷垃】金泡沫', |
f8580bf0 | 58 | 'uploader_id': '156160', |
59 | 'uploader': '菊子桑', | |
60 | 'upload_date': '20140420', | |
6461f2b7 | 61 | 'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923', |
3526c304 | 62 | 'timestamp': 1398012678, |
89fabf11 JN |
63 | 'tags': ['顶上去报复社会', '该来的总会来的', '金克拉是检验歌曲的唯一标准', '坷垃教主', '金坷垃', '邓紫棋', '治愈系坷垃'], |
64 | 'bv_id': 'BV11x411K7CN', | |
65 | 'cid': '1554319', | |
66 | 'thumbnail': 'http://i2.hdslb.com/bfs/archive/c79a8cf0347cd7a897c53a2f756e96aead128e8c.jpg', | |
67 | 'duration': 308.36, | |
28746fbd | 68 | }, |
bd8f48c7 YCH |
69 | }, { |
70 | # Tested in BiliBiliBangumiIE | |
71 | 'url': 'http://bangumi.bilibili.com/anime/1869/play#40062', | |
72 | 'only_matching': True, | |
06167fbb | 73 | }, { |
74 | # bilibili.tv | |
75 | 'url': 'http://www.bilibili.tv/video/av1074402/', | |
76 | 'only_matching': True, | |
bd8f48c7 YCH |
77 | }, { |
78 | 'url': 'http://bangumi.bilibili.com/anime/5802/play#100643', | |
79 | 'md5': '3f721ad1e75030cc06faf73587cfec57', | |
80 | 'info_dict': { | |
54bb3906 | 81 | 'id': '100643_part1', |
bd8f48c7 YCH |
82 | 'ext': 'mp4', |
83 | 'title': 'CHAOS;CHILD', | |
84 | 'description': '如果你是神明,并且能够让妄想成为现实。那你会进行怎么样的妄想?是淫靡的世界?独裁社会?毁灭性的制裁?还是……2015年,涩谷。从6年前发生的大灾害“涩谷地震”之后复兴了的这个街区里新设立的私立高中...', | |
85 | }, | |
86 | 'skip': 'Geo-restricted to China', | |
ca270371 | 87 | }, { |
ca270371 YCH |
88 | 'url': 'http://www.bilibili.com/video/av8903802/', |
89 | 'info_dict': { | |
54bb3906 | 90 | 'id': '8903802_part1', |
f8580bf0 | 91 | 'ext': 'mp4', |
ca270371 | 92 | 'title': '阿滴英文|英文歌分享#6 "Closer', |
f8580bf0 | 93 | 'upload_date': '20170301', |
ca270371 | 94 | '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', |
f8580bf0 | 95 | 'timestamp': 1488382634, |
96 | 'uploader_id': '65880958', | |
97 | 'uploader': '阿滴英文', | |
89fabf11 JN |
98 | 'thumbnail': 'http://i2.hdslb.com/bfs/archive/49267ce20bc246be6304bf369a3ded0256854c23.jpg', |
99 | 'cid': '14694589', | |
100 | 'duration': 554.117, | |
101 | 'bv_id': 'BV13x41117TL', | |
102 | 'tags': ['人文', '英语', '文化', '公开课', '阿滴英文'], | |
f8580bf0 | 103 | }, |
104 | 'params': { | |
105 | 'skip_download': True, | |
ca270371 | 106 | }, |
b4eb08bb S |
107 | }, { |
108 | # new BV video id format | |
109 | 'url': 'https://www.bilibili.com/video/BV1JE411F741', | |
110 | 'only_matching': True, | |
adc74b3c | 111 | }, { |
112 | # Anthology | |
113 | 'url': 'https://www.bilibili.com/video/BV1bK411W797', | |
114 | 'info_dict': { | |
115 | 'id': 'BV1bK411W797', | |
7e60c069 | 116 | 'title': '物语中的人物是如何吐槽自己的OP的' |
adc74b3c | 117 | }, |
118 | 'playlist_count': 17, | |
89fabf11 JN |
119 | }, { |
120 | # Correct matching of single and double quotes in title | |
121 | 'url': 'https://www.bilibili.com/video/BV1NY411E7Rx/', | |
122 | 'info_dict': { | |
123 | 'id': '255513412_part1', | |
124 | 'ext': 'mp4', | |
125 | 'title': 'Vid"eo" Te\'st', | |
126 | 'cid': '570602418', | |
127 | 'thumbnail': 'http://i2.hdslb.com/bfs/archive/0c0de5a90b6d5b991b8dcc6cde0afbf71d564791.jpg', | |
128 | 'upload_date': '20220408', | |
129 | 'timestamp': 1649436552, | |
130 | 'description': 'Vid"eo" Te\'st', | |
131 | 'uploader_id': '1630758804', | |
132 | 'bv_id': 'BV1NY411E7Rx', | |
133 | 'duration': 60.394, | |
134 | 'uploader': 'bili_31244483705', | |
135 | 'tags': ['VLOG'], | |
136 | }, | |
137 | 'params': { | |
138 | 'skip_download': True, | |
139 | }, | |
bd8f48c7 | 140 | }] |
28746fbd | 141 | |
c9a0ea6e S |
142 | _APP_KEY = 'iVGUTjsxvpLeuDCf' |
143 | _BILIBILI_KEY = 'aHRmhWMLkdeMuILqORnYZocwMBpMEOdt' | |
6461f2b7 | 144 | |
bd8f48c7 YCH |
145 | def _report_error(self, result): |
146 | if 'message' in result: | |
147 | raise ExtractorError('%s said: %s' % (self.IE_NAME, result['message']), expected=True) | |
148 | elif 'code' in result: | |
149 | raise ExtractorError('%s returns error %d' % (self.IE_NAME, result['code']), expected=True) | |
150 | else: | |
151 | raise ExtractorError('Can\'t extract Bangumi episode ID') | |
152 | ||
520e7533 | 153 | def _real_extract(self, url): |
bd8f48c7 YCH |
154 | url, smuggled_data = unsmuggle_url(url, {}) |
155 | ||
5ad28e7f | 156 | mobj = self._match_valid_url(url) |
06167fbb | 157 | video_id = mobj.group('id_bv') or mobj.group('id') |
158 | ||
159 | av_id, bv_id = self._get_video_id_set(video_id, mobj.group('id_bv') is not None) | |
160 | video_id = av_id | |
161 | ||
f8580bf0 | 162 | info = {} |
bd8f48c7 | 163 | anime_id = mobj.group('anime_id') |
06167fbb | 164 | page_id = mobj.group('page') |
6461f2b7 YCH |
165 | webpage = self._download_webpage(url, video_id) |
166 | ||
adc74b3c | 167 | # Bilibili anthologies are similar to playlists but all videos share the same video ID as the anthology itself. |
168 | # If the video has no page argument, check to see if it's an anthology | |
169 | if page_id is None: | |
a06916d9 | 170 | if not self.get_param('noplaylist'): |
adc74b3c | 171 | r = self._extract_anthology_entries(bv_id, video_id, webpage) |
172 | if r is not None: | |
173 | self.to_screen('Downloading anthology %s - add --no-playlist to just download video' % video_id) | |
174 | return r | |
7e60c069 | 175 | else: |
176 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
adc74b3c | 177 | |
bd8f48c7 | 178 | if 'anime/' not in url: |
3526c304 | 179 | cid = self._search_regex( |
e88d44c6 | 180 | r'\bcid(?:["\']:|=)(\d+),["\']page(?:["\']:|=)' + str(page_id), webpage, 'cid', |
06167fbb | 181 | default=None |
182 | ) or self._search_regex( | |
61cb6683 | 183 | r'\bcid(?:["\']:|=)(\d+)', webpage, 'cid', |
3526c304 S |
184 | default=None |
185 | ) or compat_parse_qs(self._search_regex( | |
95a1322b S |
186 | [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)', |
187 | r'EmbedPlayer\([^)]+,\s*\\"([^"]+)\\"\)', | |
188 | r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'], | |
7be15d40 P |
189 | webpage, 'player parameters'))['cid'][0] |
190 | else: | |
bd8f48c7 | 191 | if 'no_bangumi_tip' not in smuggled_data: |
7a5c1cfe | 192 | self.to_screen('Downloading episode %s. To download all videos in anime %s, re-run yt-dlp with %s' % ( |
bd8f48c7 | 193 | video_id, anime_id, compat_urlparse.urljoin(url, '//bangumi.bilibili.com/anime/%s' % anime_id))) |
10db0d2f | 194 | headers = { |
195 | 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', | |
196 | 'Referer': url | |
197 | } | |
198 | headers.update(self.geo_verification_headers()) | |
bd8f48c7 | 199 | |
1f85029d YCH |
200 | js = self._download_json( |
201 | 'http://bangumi.bilibili.com/web_api/get_source', video_id, | |
202 | data=urlencode_postdata({'episode_id': video_id}), | |
bd8f48c7 YCH |
203 | headers=headers) |
204 | if 'result' not in js: | |
205 | self._report_error(js) | |
7be15d40 | 206 | cid = js['result']['cid'] |
04b32c8f | 207 | |
10db0d2f | 208 | headers = { |
209 | 'Accept': 'application/json', | |
210 | 'Referer': url | |
211 | } | |
212 | headers.update(self.geo_verification_headers()) | |
213 | ||
f8580bf0 | 214 | video_info = self._parse_json( |
54bb3906 | 215 | self._search_regex(r'window.__playinfo__\s*=\s*({.+?})</script>', webpage, 'video info', default=None) or '{}', |
216 | video_id, fatal=False) | |
f8580bf0 | 217 | video_info = video_info.get('data') or {} |
218 | ||
219 | durl = traverse_obj(video_info, ('dash', 'video')) | |
220 | audios = traverse_obj(video_info, ('dash', 'audio')) or [] | |
d90e4030 | 221 | entries = [] |
c4a21bc9 | 222 | |
3526c304 S |
223 | RENDITIONS = ('qn=80&quality=80&type=', 'quality=2&type=mp4') |
224 | for num, rendition in enumerate(RENDITIONS, start=1): | |
225 | payload = 'appkey=%s&cid=%s&otype=json&%s' % (self._APP_KEY, cid, rendition) | |
226 | sign = hashlib.md5((payload + self._BILIBILI_KEY).encode('utf-8')).hexdigest() | |
3526c304 | 227 | if not video_info: |
f8580bf0 | 228 | video_info = self._download_json( |
229 | 'http://interface.bilibili.com/v2/playurl?%s&sign=%s' % (payload, sign), | |
230 | video_id, note='Downloading video info page', | |
231 | headers=headers, fatal=num == len(RENDITIONS)) | |
232 | if not video_info: | |
233 | continue | |
3526c304 | 234 | |
f8580bf0 | 235 | if not durl and 'durl' not in video_info: |
3526c304 S |
236 | if num < len(RENDITIONS): |
237 | continue | |
238 | self._report_error(video_info) | |
239 | ||
f8580bf0 | 240 | formats = [] |
241 | for idx, durl in enumerate(durl or video_info['durl']): | |
242 | formats.append({ | |
243 | 'url': durl.get('baseUrl') or durl.get('base_url') or durl.get('url'), | |
244 | 'ext': mimetype2ext(durl.get('mimeType') or durl.get('mime_type')), | |
245 | 'fps': int_or_none(durl.get('frameRate') or durl.get('frame_rate')), | |
246 | 'width': int_or_none(durl.get('width')), | |
247 | 'height': int_or_none(durl.get('height')), | |
248 | 'vcodec': durl.get('codecs'), | |
249 | 'acodec': 'none' if audios else None, | |
250 | 'tbr': float_or_none(durl.get('bandwidth'), scale=1000), | |
251 | 'filesize': int_or_none(durl.get('size')), | |
252 | }) | |
253 | for backup_url in traverse_obj(durl, 'backup_url', expected_type=list) or []: | |
3526c304 S |
254 | formats.append({ |
255 | 'url': backup_url, | |
f983b875 | 256 | 'quality': -2 if 'hd.mp4' in backup_url else -3, |
3526c304 S |
257 | }) |
258 | ||
f8580bf0 | 259 | for audio in audios: |
260 | formats.append({ | |
261 | 'url': audio.get('baseUrl') or audio.get('base_url') or audio.get('url'), | |
262 | 'ext': mimetype2ext(audio.get('mimeType') or audio.get('mime_type')), | |
263 | 'fps': int_or_none(audio.get('frameRate') or audio.get('frame_rate')), | |
264 | 'width': int_or_none(audio.get('width')), | |
265 | 'height': int_or_none(audio.get('height')), | |
266 | 'acodec': audio.get('codecs'), | |
267 | 'vcodec': 'none', | |
268 | 'tbr': float_or_none(audio.get('bandwidth'), scale=1000), | |
269 | 'filesize': int_or_none(audio.get('size')) | |
6461f2b7 | 270 | }) |
f8580bf0 | 271 | for backup_url in traverse_obj(audio, 'backup_url', expected_type=list) or []: |
272 | formats.append({ | |
273 | 'url': backup_url, | |
274 | # backup URLs have lower priorities | |
275 | 'quality': -3, | |
276 | }) | |
277 | ||
278 | info.update({ | |
279 | 'id': video_id, | |
280 | 'duration': float_or_none(durl.get('length'), 1000), | |
281 | 'formats': formats, | |
be8d6234 DZ |
282 | 'http_headers': { |
283 | 'Referer': url, | |
284 | }, | |
f8580bf0 | 285 | }) |
3526c304 | 286 | break |
6461f2b7 | 287 | |
f8580bf0 | 288 | self._sort_formats(formats) |
289 | ||
54bb3906 | 290 | title = self._html_search_regex(( |
89fabf11 JN |
291 | r'<h1[^>]+title=(["])(?P<content>[^"]+)', |
292 | r'<h1[^>]+title=([\'])(?P<content>[^\']+)', | |
54bb3906 | 293 | r'(?s)<h1[^>]*>(?P<content>.+?)</h1>', |
294 | self._meta_regex('title') | |
295 | ), webpage, 'title', group='content', fatal=False) | |
adc74b3c | 296 | |
297 | # Get part title for anthologies | |
298 | if page_id is not None: | |
f8580bf0 | 299 | # TODO: The json is already downloaded by _extract_anthology_entries. Don't redownload for each video. |
300 | part_info = traverse_obj(self._download_json( | |
301 | f'https://api.bilibili.com/x/player/pagelist?bvid={bv_id}&jsonp=jsonp', | |
302 | video_id, note='Extracting videos in anthology'), 'data', expected_type=list) | |
303 | title = title if len(part_info) == 1 else traverse_obj(part_info, (int(page_id) - 1, 'part')) or title | |
adc74b3c | 304 | |
6461f2b7 | 305 | description = self._html_search_meta('description', webpage) |
04b32c8f | 306 | timestamp = unified_timestamp(self._html_search_regex( |
3526c304 S |
307 | r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', |
308 | default=None) or self._html_search_meta( | |
309 | 'uploadDate', webpage, 'timestamp', default=None)) | |
1f85029d | 310 | thumbnail = self._html_search_meta(['og:image', 'thumbnailUrl'], webpage) |
6461f2b7 YCH |
311 | |
312 | # TODO 'view_count' requires deobfuscating Javascript | |
f8580bf0 | 313 | info.update({ |
54bb3906 | 314 | 'id': f'{video_id}_part{page_id or 1}', |
06167fbb | 315 | 'cid': cid, |
d90e4030 | 316 | 'title': title, |
6461f2b7 YCH |
317 | 'description': description, |
318 | 'timestamp': timestamp, | |
7be15d40 | 319 | 'thumbnail': thumbnail, |
04b32c8f | 320 | 'duration': float_or_none(video_info.get('timelength'), scale=1000), |
f8580bf0 | 321 | }) |
d90e4030 | 322 | |
6461f2b7 | 323 | uploader_mobj = re.search( |
7e60c069 | 324 | r'<a[^>]+href="(?:https?:)?//space\.bilibili\.com/(?P<id>\d+)"[^>]*>\s*(?P<name>[^<]+?)\s*<', |
6461f2b7 YCH |
325 | webpage) |
326 | if uploader_mobj: | |
327 | info.update({ | |
ed807c18 | 328 | 'uploader': uploader_mobj.group('name').strip(), |
6461f2b7 YCH |
329 | 'uploader_id': uploader_mobj.group('id'), |
330 | }) | |
06167fbb | 331 | |
3526c304 S |
332 | if not info.get('uploader'): |
333 | info['uploader'] = self._html_search_meta( | |
334 | 'author', webpage, 'uploader', default=None) | |
6461f2b7 | 335 | |
06167fbb | 336 | top_level_info = { |
e88d44c6 | 337 | 'tags': traverse_obj(self._download_json( |
338 | f'https://api.bilibili.com/x/tag/archive/tags?aid={video_id}', | |
339 | video_id, fatal=False, note='Downloading tags'), ('data', ..., 'tag_name')), | |
06167fbb | 340 | } |
277d6ff5 | 341 | |
f8580bf0 | 342 | info['subtitles'] = { |
e88d44c6 | 343 | 'danmaku': [{ |
344 | 'ext': 'xml', | |
345 | 'url': f'https://comment.bilibili.com/{cid}.xml', | |
346 | }] | |
347 | } | |
06167fbb | 348 | |
e88d44c6 | 349 | r''' |
06167fbb | 350 | # Requires https://github.com/m13253/danmaku2ass which is licenced under GPL3 |
351 | # See https://github.com/animelover1984/youtube-dl | |
e88d44c6 | 352 | |
353 | raw_danmaku = self._download_webpage( | |
354 | f'https://comment.bilibili.com/{cid}.xml', video_id, fatal=False, note='Downloading danmaku comments') | |
06167fbb | 355 | danmaku = NiconicoIE.CreateDanmaku(raw_danmaku, commentType='Bilibili', x=1024, y=576) |
356 | entries[0]['subtitles'] = { | |
357 | 'danmaku': [{ | |
358 | 'ext': 'ass', | |
359 | 'data': danmaku | |
360 | }] | |
361 | } | |
362 | ''' | |
363 | ||
e88d44c6 | 364 | top_level_info['__post_extractor'] = self.extract_comments(video_id) |
365 | ||
6461f2b7 YCH |
366 | for entry in entries: |
367 | entry.update(info) | |
368 | ||
d90e4030 | 369 | if len(entries) == 1: |
06167fbb | 370 | entries[0].update(top_level_info) |
d90e4030 | 371 | return entries[0] |
bd8f48c7 | 372 | |
e88d44c6 | 373 | for idx, entry in enumerate(entries): |
374 | entry['id'] = '%s_part%d' % (video_id, (idx + 1)) | |
06167fbb | 375 | |
e88d44c6 | 376 | return { |
e88d44c6 | 377 | 'id': str(video_id), |
378 | 'bv_id': bv_id, | |
379 | 'title': title, | |
380 | 'description': description, | |
e88d44c6 | 381 | **info, **top_level_info |
382 | } | |
06167fbb | 383 | |
adc74b3c | 384 | def _extract_anthology_entries(self, bv_id, video_id, webpage): |
385 | title = self._html_search_regex( | |
386 | (r'<h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1', | |
ac0efabf | 387 | r'(?s)<h1[^>]*>(?P<title>.+?)</h1>', |
388 | r'<title>(?P<title>.+?)</title>'), webpage, 'title', | |
adc74b3c | 389 | group='title') |
390 | json_data = self._download_json( | |
e88d44c6 | 391 | f'https://api.bilibili.com/x/player/pagelist?bvid={bv_id}&jsonp=jsonp', |
adc74b3c | 392 | video_id, note='Extracting videos in anthology') |
393 | ||
e88d44c6 | 394 | if json_data['data']: |
adc74b3c | 395 | return self.playlist_from_matches( |
396 | json_data['data'], bv_id, title, ie=BiliBiliIE.ie_key(), | |
397 | getter=lambda entry: 'https://www.bilibili.com/video/%s?p=%d' % (bv_id, entry['page'])) | |
398 | ||
06167fbb | 399 | def _get_video_id_set(self, id, is_bv): |
400 | query = {'bvid': id} if is_bv else {'aid': id} | |
401 | response = self._download_json( | |
402 | "http://api.bilibili.cn/x/web-interface/view", | |
403 | id, query=query, | |
404 | note='Grabbing original ID via API') | |
405 | ||
406 | if response['code'] == -400: | |
407 | raise ExtractorError('Video ID does not exist', expected=True, video_id=id) | |
408 | elif response['code'] != 0: | |
e88d44c6 | 409 | raise ExtractorError(f'Unknown error occurred during API check (code {response["code"]})', |
410 | expected=True, video_id=id) | |
411 | return response['data']['aid'], response['data']['bvid'] | |
06167fbb | 412 | |
e88d44c6 | 413 | def _get_comments(self, video_id, commentPageNumber=0): |
414 | for idx in itertools.count(1): | |
415 | replies = traverse_obj( | |
416 | self._download_json( | |
417 | f'https://api.bilibili.com/x/v2/reply?pn={idx}&oid={video_id}&type=1&jsonp=jsonp&sort=2&_=1567227301685', | |
8e7ab2cf | 418 | video_id, note=f'Extracting comments from page {idx}', fatal=False), |
419 | ('data', 'replies')) | |
420 | if not replies: | |
421 | return | |
e88d44c6 | 422 | for children in map(self._get_all_children, replies): |
423 | yield from children | |
424 | ||
425 | def _get_all_children(self, reply): | |
426 | yield { | |
427 | 'author': traverse_obj(reply, ('member', 'uname')), | |
428 | 'author_id': traverse_obj(reply, ('member', 'mid')), | |
429 | 'id': reply.get('rpid'), | |
430 | 'text': traverse_obj(reply, ('content', 'message')), | |
431 | 'timestamp': reply.get('ctime'), | |
432 | 'parent': reply.get('parent') or 'root', | |
433 | } | |
434 | for children in map(self._get_all_children, reply.get('replies') or []): | |
435 | yield from children | |
06167fbb | 436 | |
bd8f48c7 YCH |
437 | |
438 | class BiliBiliBangumiIE(InfoExtractor): | |
439 | _VALID_URL = r'https?://bangumi\.bilibili\.com/anime/(?P<id>\d+)' | |
440 | ||
441 | IE_NAME = 'bangumi.bilibili.com' | |
442 | IE_DESC = 'BiliBili番剧' | |
443 | ||
444 | _TESTS = [{ | |
445 | 'url': 'http://bangumi.bilibili.com/anime/1869', | |
446 | 'info_dict': { | |
447 | 'id': '1869', | |
448 | 'title': '混沌武士', | |
449 | 'description': 'md5:6a9622b911565794c11f25f81d6a97d2', | |
450 | }, | |
451 | 'playlist_count': 26, | |
452 | }, { | |
453 | 'url': 'http://bangumi.bilibili.com/anime/1869', | |
454 | 'info_dict': { | |
455 | 'id': '1869', | |
456 | 'title': '混沌武士', | |
457 | 'description': 'md5:6a9622b911565794c11f25f81d6a97d2', | |
458 | }, | |
459 | 'playlist': [{ | |
460 | 'md5': '91da8621454dd58316851c27c68b0c13', | |
461 | 'info_dict': { | |
462 | 'id': '40062', | |
463 | 'ext': 'mp4', | |
464 | 'title': '混沌武士', | |
465 | 'description': '故事发生在日本的江户时代。风是一个小酒馆的打工女。一日,酒馆里来了一群恶霸,虽然他们的举动令风十分不满,但是毕竟风只是一届女流,无法对他们采取什么行动,只能在心里嘟哝。这时,酒家里又进来了个“不良份子...', | |
466 | 'timestamp': 1414538739, | |
467 | 'upload_date': '20141028', | |
468 | 'episode': '疾风怒涛 Tempestuous Temperaments', | |
469 | 'episode_number': 1, | |
470 | }, | |
471 | }], | |
472 | 'params': { | |
473 | 'playlist_items': '1', | |
474 | }, | |
475 | }] | |
476 | ||
477 | @classmethod | |
478 | def suitable(cls, url): | |
479 | return False if BiliBiliIE.suitable(url) else super(BiliBiliBangumiIE, cls).suitable(url) | |
480 | ||
481 | def _real_extract(self, url): | |
482 | bangumi_id = self._match_id(url) | |
483 | ||
484 | # Sometimes this API returns a JSONP response | |
485 | season_info = self._download_json( | |
486 | 'http://bangumi.bilibili.com/jsonp/seasoninfo/%s.ver' % bangumi_id, | |
487 | bangumi_id, transform_source=strip_jsonp)['result'] | |
488 | ||
489 | entries = [{ | |
490 | '_type': 'url_transparent', | |
491 | 'url': smuggle_url(episode['webplay_url'], {'no_bangumi_tip': 1}), | |
492 | 'ie_key': BiliBiliIE.ie_key(), | |
493 | 'timestamp': parse_iso8601(episode.get('update_time'), delimiter=' '), | |
494 | 'episode': episode.get('index_title'), | |
495 | 'episode_number': int_or_none(episode.get('index')), | |
496 | } for episode in season_info['episodes']] | |
497 | ||
498 | entries = sorted(entries, key=lambda entry: entry.get('episode_number')) | |
499 | ||
500 | return self.playlist_result( | |
501 | entries, bangumi_id, | |
502 | season_info.get('bangumi_title'), season_info.get('evaluate')) | |
4bc15a68 RA |
503 | |
504 | ||
06167fbb | 505 | class BilibiliChannelIE(InfoExtractor): |
506 | _VALID_URL = r'https?://space.bilibili\.com/(?P<id>\d+)' | |
6efb0711 | 507 | _API_URL = "https://api.bilibili.com/x/space/arc/search?mid=%s&pn=%d&jsonp=jsonp" |
508 | _TESTS = [{ | |
509 | 'url': 'https://space.bilibili.com/3985676/video', | |
510 | 'info_dict': {}, | |
511 | 'playlist_mincount': 112, | |
512 | }] | |
513 | ||
514 | def _entries(self, list_id): | |
515 | count, max_count = 0, None | |
516 | ||
517 | for page_num in itertools.count(1): | |
e88d44c6 | 518 | data = self._download_json( |
519 | self._API_URL % (list_id, page_num), list_id, note=f'Downloading page {page_num}')['data'] | |
6efb0711 | 520 | |
f8580bf0 | 521 | max_count = max_count or traverse_obj(data, ('page', 'count')) |
6efb0711 | 522 | |
f8580bf0 | 523 | entries = traverse_obj(data, ('list', 'vlist')) |
6efb0711 | 524 | if not entries: |
525 | return | |
526 | for entry in entries: | |
527 | yield self.url_result( | |
528 | 'https://www.bilibili.com/video/%s' % entry['bvid'], | |
529 | BiliBiliIE.ie_key(), entry['bvid']) | |
530 | ||
531 | count += len(entries) | |
532 | if max_count and count >= max_count: | |
533 | return | |
06167fbb | 534 | |
535 | def _real_extract(self, url): | |
536 | list_id = self._match_id(url) | |
6efb0711 | 537 | return self.playlist_result(self._entries(list_id), list_id) |
06167fbb | 538 | |
539 | ||
c34f505b | 540 | class BilibiliCategoryIE(InfoExtractor): |
541 | IE_NAME = 'Bilibili category extractor' | |
542 | _MAX_RESULTS = 1000000 | |
543 | _VALID_URL = r'https?://www\.bilibili\.com/v/[a-zA-Z]+\/[a-zA-Z]+' | |
544 | _TESTS = [{ | |
545 | 'url': 'https://www.bilibili.com/v/kichiku/mad', | |
546 | 'info_dict': { | |
547 | 'id': 'kichiku: mad', | |
548 | 'title': 'kichiku: mad' | |
549 | }, | |
550 | 'playlist_mincount': 45, | |
551 | 'params': { | |
552 | 'playlistend': 45 | |
553 | } | |
554 | }] | |
555 | ||
556 | def _fetch_page(self, api_url, num_pages, query, page_num): | |
557 | parsed_json = self._download_json( | |
558 | api_url, query, query={'Search_key': query, 'pn': page_num}, | |
559 | note='Extracting results from page %s of %s' % (page_num, num_pages)) | |
560 | ||
f8580bf0 | 561 | video_list = traverse_obj(parsed_json, ('data', 'archives'), expected_type=list) |
c34f505b | 562 | if not video_list: |
563 | raise ExtractorError('Failed to retrieve video list for page %d' % page_num) | |
564 | ||
565 | for video in video_list: | |
566 | yield self.url_result( | |
567 | 'https://www.bilibili.com/video/%s' % video['bvid'], 'BiliBili', video['bvid']) | |
568 | ||
569 | def _entries(self, category, subcategory, query): | |
570 | # map of categories : subcategories : RIDs | |
571 | rid_map = { | |
572 | 'kichiku': { | |
573 | 'mad': 26, | |
574 | 'manual_vocaloid': 126, | |
575 | 'guide': 22, | |
576 | 'theatre': 216, | |
577 | 'course': 127 | |
578 | }, | |
579 | } | |
580 | ||
581 | if category not in rid_map: | |
e88d44c6 | 582 | raise ExtractorError( |
583 | f'The category {category} isn\'t supported. Supported categories: {list(rid_map.keys())}') | |
c34f505b | 584 | if subcategory not in rid_map[category]: |
e88d44c6 | 585 | raise ExtractorError( |
586 | f'The subcategory {subcategory} isn\'t supported for this category. Supported subcategories: {list(rid_map[category].keys())}') | |
c34f505b | 587 | rid_value = rid_map[category][subcategory] |
588 | ||
589 | api_url = 'https://api.bilibili.com/x/web-interface/newlist?rid=%d&type=1&ps=20&jsonp=jsonp' % rid_value | |
590 | page_json = self._download_json(api_url, query, query={'Search_key': query, 'pn': '1'}) | |
f8580bf0 | 591 | page_data = traverse_obj(page_json, ('data', 'page'), expected_type=dict) |
c34f505b | 592 | count, size = int_or_none(page_data.get('count')), int_or_none(page_data.get('size')) |
593 | if count is None or not size: | |
594 | raise ExtractorError('Failed to calculate either page count or size') | |
595 | ||
596 | num_pages = math.ceil(count / size) | |
597 | ||
598 | return OnDemandPagedList(functools.partial( | |
599 | self._fetch_page, api_url, num_pages, query), size) | |
600 | ||
601 | def _real_extract(self, url): | |
602 | u = compat_urllib_parse_urlparse(url) | |
603 | category, subcategory = u.path.split('/')[2:4] | |
604 | query = '%s: %s' % (category, subcategory) | |
605 | ||
606 | return self.playlist_result(self._entries(category, subcategory, query), query, query) | |
607 | ||
608 | ||
06167fbb | 609 | class BiliBiliSearchIE(SearchInfoExtractor): |
96565c7e | 610 | IE_DESC = 'Bilibili video search' |
06167fbb | 611 | _MAX_RESULTS = 100000 |
612 | _SEARCH_KEY = 'bilisearch' | |
06167fbb | 613 | |
e88d44c6 | 614 | def _search_results(self, query): |
615 | for page_num in itertools.count(1): | |
616 | videos = self._download_json( | |
617 | 'https://api.bilibili.com/x/web-interface/search/type', query, | |
618 | note=f'Extracting results from page {page_num}', query={ | |
619 | 'Search_key': query, | |
620 | 'keyword': query, | |
621 | 'page': page_num, | |
622 | 'context': '', | |
623 | 'order': 'pubdate', | |
624 | 'duration': 0, | |
625 | 'tids_2': '', | |
626 | '__refresh__': 'true', | |
627 | 'search_type': 'video', | |
628 | 'tids': 0, | |
629 | 'highlight': 1, | |
630 | })['data'].get('result') or [] | |
06167fbb | 631 | for video in videos: |
e88d44c6 | 632 | yield self.url_result(video['arcurl'], 'BiliBili', str(video['aid'])) |
06167fbb | 633 | |
634 | ||
4bc15a68 RA |
635 | class BilibiliAudioBaseIE(InfoExtractor): |
636 | def _call_api(self, path, sid, query=None): | |
637 | if not query: | |
638 | query = {'sid': sid} | |
639 | return self._download_json( | |
640 | 'https://www.bilibili.com/audio/music-service-c/web/' + path, | |
641 | sid, query=query)['data'] | |
642 | ||
643 | ||
644 | class BilibiliAudioIE(BilibiliAudioBaseIE): | |
645 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/audio/au(?P<id>\d+)' | |
646 | _TEST = { | |
647 | 'url': 'https://www.bilibili.com/audio/au1003142', | |
648 | 'md5': 'fec4987014ec94ef9e666d4d158ad03b', | |
649 | 'info_dict': { | |
650 | 'id': '1003142', | |
651 | 'ext': 'm4a', | |
652 | 'title': '【tsukimi】YELLOW / 神山羊', | |
653 | 'artist': 'tsukimi', | |
654 | 'comment_count': int, | |
655 | 'description': 'YELLOW的mp3版!', | |
656 | 'duration': 183, | |
657 | 'subtitles': { | |
658 | 'origin': [{ | |
659 | 'ext': 'lrc', | |
660 | }], | |
661 | }, | |
662 | 'thumbnail': r're:^https?://.+\.jpg', | |
663 | 'timestamp': 1564836614, | |
664 | 'upload_date': '20190803', | |
665 | 'uploader': 'tsukimi-つきみぐー', | |
666 | 'view_count': int, | |
667 | }, | |
668 | } | |
669 | ||
670 | def _real_extract(self, url): | |
671 | au_id = self._match_id(url) | |
672 | ||
673 | play_data = self._call_api('url', au_id) | |
674 | formats = [{ | |
675 | 'url': play_data['cdns'][0], | |
676 | 'filesize': int_or_none(play_data.get('size')), | |
f0884c8b | 677 | 'vcodec': 'none' |
4bc15a68 RA |
678 | }] |
679 | ||
6d1b3489 | 680 | for a_format in formats: |
681 | a_format.setdefault('http_headers', {}).update({ | |
682 | 'Referer': url, | |
683 | }) | |
684 | ||
4bc15a68 RA |
685 | song = self._call_api('song/info', au_id) |
686 | title = song['title'] | |
687 | statistic = song.get('statistic') or {} | |
688 | ||
689 | subtitles = None | |
690 | lyric = song.get('lyric') | |
691 | if lyric: | |
692 | subtitles = { | |
693 | 'origin': [{ | |
694 | 'url': lyric, | |
695 | }] | |
696 | } | |
697 | ||
698 | return { | |
699 | 'id': au_id, | |
700 | 'title': title, | |
701 | 'formats': formats, | |
702 | 'artist': song.get('author'), | |
703 | 'comment_count': int_or_none(statistic.get('comment')), | |
704 | 'description': song.get('intro'), | |
705 | 'duration': int_or_none(song.get('duration')), | |
706 | 'subtitles': subtitles, | |
707 | 'thumbnail': song.get('cover'), | |
708 | 'timestamp': int_or_none(song.get('passtime')), | |
709 | 'uploader': song.get('uname'), | |
710 | 'view_count': int_or_none(statistic.get('play')), | |
711 | } | |
712 | ||
713 | ||
714 | class BilibiliAudioAlbumIE(BilibiliAudioBaseIE): | |
715 | _VALID_URL = r'https?://(?:www\.)?bilibili\.com/audio/am(?P<id>\d+)' | |
716 | _TEST = { | |
717 | 'url': 'https://www.bilibili.com/audio/am10624', | |
718 | 'info_dict': { | |
719 | 'id': '10624', | |
720 | 'title': '每日新曲推荐(每日11:00更新)', | |
721 | 'description': '每天11:00更新,为你推送最新音乐', | |
722 | }, | |
723 | 'playlist_count': 19, | |
724 | } | |
725 | ||
726 | def _real_extract(self, url): | |
727 | am_id = self._match_id(url) | |
728 | ||
729 | songs = self._call_api( | |
730 | 'song/of-menu', am_id, {'sid': am_id, 'pn': 1, 'ps': 100})['data'] | |
731 | ||
732 | entries = [] | |
733 | for song in songs: | |
734 | sid = str_or_none(song.get('id')) | |
735 | if not sid: | |
736 | continue | |
737 | entries.append(self.url_result( | |
738 | 'https://www.bilibili.com/audio/au' + sid, | |
739 | BilibiliAudioIE.ie_key(), sid)) | |
740 | ||
741 | if entries: | |
742 | album_data = self._call_api('menu/info', am_id) or {} | |
743 | album_title = album_data.get('title') | |
744 | if album_title: | |
745 | for entry in entries: | |
746 | entry['album'] = album_title | |
747 | return self.playlist_result( | |
748 | entries, am_id, album_title, album_data.get('intro')) | |
749 | ||
750 | return self.playlist_result(entries, am_id) | |
63dce309 S |
751 | |
752 | ||
753 | class BiliBiliPlayerIE(InfoExtractor): | |
754 | _VALID_URL = r'https?://player\.bilibili\.com/player\.html\?.*?\baid=(?P<id>\d+)' | |
755 | _TEST = { | |
756 | 'url': 'http://player.bilibili.com/player.html?aid=92494333&cid=157926707&page=1', | |
757 | 'only_matching': True, | |
758 | } | |
759 | ||
760 | def _real_extract(self, url): | |
761 | video_id = self._match_id(url) | |
762 | return self.url_result( | |
763 | 'http://www.bilibili.tv/video/av%s/' % video_id, | |
764 | ie=BiliBiliIE.ie_key(), video_id=video_id) | |
16f7e6be AG |
765 | |
766 | ||
767 | class BiliIntlBaseIE(InfoExtractor): | |
c62ecf0d | 768 | _API_URL = 'https://api.bilibili.tv/intl/gateway' |
cfcf60ea | 769 | _NETRC_MACHINE = 'biliintl' |
16f7e6be | 770 | |
c62ecf0d | 771 | def _call_api(self, endpoint, *args, **kwargs): |
cfcf60ea M |
772 | json = self._download_json(self._API_URL + endpoint, *args, **kwargs) |
773 | if json.get('code'): | |
774 | if json['code'] in (10004004, 10004005, 10023006): | |
775 | self.raise_login_required() | |
776 | elif json['code'] == 10004001: | |
777 | self.raise_geo_restricted() | |
778 | else: | |
779 | if json.get('message') and str(json['code']) != json['message']: | |
780 | errmsg = f'{kwargs.get("errnote", "Unable to download JSON metadata")}: {self.IE_NAME} said: {json["message"]}' | |
781 | else: | |
782 | errmsg = kwargs.get('errnote', 'Unable to download JSON metadata') | |
783 | if kwargs.get('fatal'): | |
784 | raise ExtractorError(errmsg) | |
785 | else: | |
786 | self.report_warning(errmsg) | |
787 | return json.get('data') | |
16f7e6be | 788 | |
efc947fb | 789 | def json2srt(self, json): |
790 | data = '\n\n'.join( | |
791 | f'{i + 1}\n{srt_subtitles_timecode(line["from"])} --> {srt_subtitles_timecode(line["to"])}\n{line["content"]}' | |
cfcf60ea | 792 | for i, line in enumerate(json['body']) if line.get('content')) |
efc947fb | 793 | return data |
794 | ||
f5f15c99 LR |
795 | def _get_subtitles(self, *, ep_id=None, aid=None): |
796 | sub_json = self._call_api( | |
797 | '/web/v2/subtitle', ep_id or aid, note='Downloading subtitles list', | |
798 | errnote='Unable to download subtitles list', query=filter_dict({ | |
799 | 'platform': 'web', | |
800 | 'episode_id': ep_id, | |
801 | 'aid': aid, | |
802 | })) | |
16f7e6be | 803 | subtitles = {} |
c62ecf0d | 804 | for sub in sub_json.get('subtitles') or []: |
16f7e6be AG |
805 | sub_url = sub.get('url') |
806 | if not sub_url: | |
807 | continue | |
c62ecf0d | 808 | sub_data = self._download_json( |
f5f15c99 | 809 | sub_url, ep_id or aid, errnote='Unable to download subtitles', fatal=False, |
c62ecf0d | 810 | note='Downloading subtitles%s' % f' for {sub["lang"]}' if sub.get('lang') else '') |
efc947fb | 811 | if not sub_data: |
812 | continue | |
c62ecf0d | 813 | subtitles.setdefault(sub.get('lang_key', 'en'), []).append({ |
efc947fb | 814 | 'ext': 'srt', |
815 | 'data': self.json2srt(sub_data) | |
16f7e6be AG |
816 | }) |
817 | return subtitles | |
818 | ||
f5f15c99 LR |
819 | def _get_formats(self, *, ep_id=None, aid=None): |
820 | video_json = self._call_api( | |
821 | '/web/playurl', ep_id or aid, note='Downloading video formats', | |
822 | errnote='Unable to download video formats', query=filter_dict({ | |
823 | 'platform': 'web', | |
824 | 'ep_id': ep_id, | |
825 | 'aid': aid, | |
826 | })) | |
16f7e6be AG |
827 | video_json = video_json['playurl'] |
828 | formats = [] | |
c62ecf0d | 829 | for vid in video_json.get('video') or []: |
16f7e6be AG |
830 | video_res = vid.get('video_resource') or {} |
831 | video_info = vid.get('stream_info') or {} | |
832 | if not video_res.get('url'): | |
833 | continue | |
834 | formats.append({ | |
835 | 'url': video_res['url'], | |
836 | 'ext': 'mp4', | |
837 | 'format_note': video_info.get('desc_words'), | |
838 | 'width': video_res.get('width'), | |
839 | 'height': video_res.get('height'), | |
840 | 'vbr': video_res.get('bandwidth'), | |
841 | 'acodec': 'none', | |
842 | 'vcodec': video_res.get('codecs'), | |
843 | 'filesize': video_res.get('size'), | |
844 | }) | |
c62ecf0d | 845 | for aud in video_json.get('audio_resource') or []: |
16f7e6be AG |
846 | if not aud.get('url'): |
847 | continue | |
848 | formats.append({ | |
849 | 'url': aud['url'], | |
850 | 'ext': 'mp4', | |
851 | 'abr': aud.get('bandwidth'), | |
852 | 'acodec': aud.get('codecs'), | |
853 | 'vcodec': 'none', | |
854 | 'filesize': aud.get('size'), | |
855 | }) | |
856 | ||
857 | self._sort_formats(formats) | |
858 | return formats | |
859 | ||
f5f15c99 | 860 | def _extract_video_info(self, video_data, *, ep_id=None, aid=None): |
16f7e6be | 861 | return { |
f5f15c99 LR |
862 | 'id': ep_id or aid, |
863 | 'title': video_data.get('title_display') or video_data.get('title'), | |
864 | 'thumbnail': video_data.get('cover'), | |
c62ecf0d | 865 | 'episode_number': int_or_none(self._search_regex( |
f5f15c99 LR |
866 | r'^E(\d+)(?:$| - )', video_data.get('title_display') or '', 'episode number', default=None)), |
867 | 'formats': self._get_formats(ep_id=ep_id, aid=aid), | |
868 | 'subtitles': self._get_subtitles(ep_id=ep_id, aid=aid), | |
16f7e6be AG |
869 | 'extractor_key': BiliIntlIE.ie_key(), |
870 | } | |
871 | ||
52efa4b3 | 872 | def _perform_login(self, username, password): |
cfcf60ea M |
873 | try: |
874 | from Cryptodome.PublicKey import RSA | |
875 | from Cryptodome.Cipher import PKCS1_v1_5 | |
876 | except ImportError: | |
877 | try: | |
878 | from Crypto.PublicKey import RSA | |
879 | from Crypto.Cipher import PKCS1_v1_5 | |
880 | except ImportError: | |
881 | raise ExtractorError('pycryptodomex not found. Please install', expected=True) | |
882 | ||
883 | key_data = self._download_json( | |
884 | 'https://passport.bilibili.tv/x/intl/passport-login/web/key?lang=en-US', None, | |
885 | note='Downloading login key', errnote='Unable to download login key')['data'] | |
886 | ||
887 | public_key = RSA.importKey(key_data['key']) | |
888 | password_hash = PKCS1_v1_5.new(public_key).encrypt((key_data['hash'] + password).encode('utf-8')) | |
889 | login_post = self._download_json( | |
890 | 'https://passport.bilibili.tv/x/intl/passport-login/web/login/password?lang=en-US', None, data=urlencode_postdata({ | |
891 | 'username': username, | |
892 | 'password': base64.b64encode(password_hash).decode('ascii'), | |
893 | 'keep_me': 'true', | |
894 | 's_locale': 'en_US', | |
895 | 'isTrusted': 'true' | |
896 | }), note='Logging in', errnote='Unable to log in') | |
897 | if login_post.get('code'): | |
898 | if login_post.get('message'): | |
899 | raise ExtractorError(f'Unable to log in: {self.IE_NAME} said: {login_post["message"]}', expected=True) | |
900 | else: | |
901 | raise ExtractorError('Unable to log in') | |
902 | ||
16f7e6be AG |
903 | |
904 | class BiliIntlIE(BiliIntlBaseIE): | |
f5f15c99 | 905 | _VALID_URL = r'https?://(?:www\.)?bili(?:bili\.tv|intl\.com)/(?:[a-z]{2}/)?(play/(?P<season_id>\d+)/(?P<ep_id>\d+)|video/(?P<aid>\d+))' |
16f7e6be | 906 | _TESTS = [{ |
cfcf60ea | 907 | # Bstation page |
16f7e6be AG |
908 | 'url': 'https://www.bilibili.tv/en/play/34613/341736', |
909 | 'info_dict': { | |
910 | 'id': '341736', | |
911 | 'ext': 'mp4', | |
c62ecf0d M |
912 | 'title': 'E2 - The First Night', |
913 | 'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.png$', | |
16f7e6be | 914 | 'episode_number': 2, |
c62ecf0d | 915 | } |
16f7e6be | 916 | }, { |
cfcf60ea | 917 | # Non-Bstation page |
c62ecf0d | 918 | 'url': 'https://www.bilibili.tv/en/play/1033760/11005006', |
16f7e6be | 919 | 'info_dict': { |
c62ecf0d | 920 | 'id': '11005006', |
16f7e6be | 921 | 'ext': 'mp4', |
c62ecf0d M |
922 | 'title': 'E3 - Who?', |
923 | 'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.png$', | |
924 | 'episode_number': 3, | |
925 | } | |
cfcf60ea M |
926 | }, { |
927 | # Subtitle with empty content | |
928 | 'url': 'https://www.bilibili.tv/en/play/1005144/10131790', | |
929 | 'info_dict': { | |
930 | 'id': '10131790', | |
931 | 'ext': 'mp4', | |
932 | 'title': 'E140 - Two Heartbeats: Kabuto\'s Trap', | |
933 | 'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.png$', | |
934 | 'episode_number': 140, | |
935 | }, | |
936 | 'skip': 'According to the copyright owner\'s request, you may only watch the video after you log in.' | |
c62ecf0d M |
937 | }, { |
938 | 'url': 'https://www.biliintl.com/en/play/34613/341736', | |
939 | 'only_matching': True, | |
f5f15c99 LR |
940 | }, { |
941 | # User-generated content (as opposed to a series licensed from a studio) | |
942 | 'url': 'https://bilibili.tv/en/video/2019955076', | |
943 | 'only_matching': True, | |
944 | }, { | |
945 | # No language in URL | |
946 | 'url': 'https://www.bilibili.tv/video/2019955076', | |
947 | 'only_matching': True, | |
16f7e6be AG |
948 | }] |
949 | ||
950 | def _real_extract(self, url): | |
f5f15c99 LR |
951 | season_id, ep_id, aid = self._match_valid_url(url).group('season_id', 'ep_id', 'aid') |
952 | video_id = ep_id or aid | |
c62ecf0d M |
953 | webpage = self._download_webpage(url, video_id) |
954 | # Bstation layout | |
8072ef2b | 955 | initial_data = ( |
956 | self._search_json(r'window\.__INITIAL_(?:DATA|STATE)__\s*=', webpage, 'preload state', video_id, default={}) | |
957 | or self._search_nuxt_data(webpage, video_id, '__initialState', fatal=False, traverse=None)) | |
958 | video_data = traverse_obj( | |
959 | initial_data, ('OgvVideo', 'epDetail'), ('UgcVideo', 'videoData'), ('ugc', 'archive'), expected_type=dict) | |
c62ecf0d | 960 | |
f5f15c99 | 961 | if season_id and not video_data: |
c62ecf0d M |
962 | # Non-Bstation layout, read through episode list |
963 | season_json = self._call_api(f'/web/v2/ogv/play/episodes?season_id={season_id}&platform=web', video_id) | |
a44ca5a4 | 964 | video_data = traverse_obj(season_json, |
965 | ('sections', ..., 'episodes', lambda _, v: str(v['episode_id']) == ep_id), | |
966 | expected_type=dict, get_all=False) | |
8072ef2b | 967 | return self._extract_video_info(video_data or {}, ep_id=ep_id, aid=aid) |
16f7e6be AG |
968 | |
969 | ||
970 | class BiliIntlSeriesIE(BiliIntlBaseIE): | |
c62ecf0d | 971 | _VALID_URL = r'https?://(?:www\.)?bili(?:bili\.tv|intl\.com)/(?:[a-z]{2}/)?play/(?P<id>\d+)$' |
16f7e6be AG |
972 | _TESTS = [{ |
973 | 'url': 'https://www.bilibili.tv/en/play/34613', | |
974 | 'playlist_mincount': 15, | |
975 | 'info_dict': { | |
976 | 'id': '34613', | |
c62ecf0d M |
977 | 'title': 'Fly Me to the Moon', |
978 | 'description': 'md5:a861ee1c4dc0acfad85f557cc42ac627', | |
979 | 'categories': ['Romance', 'Comedy', 'Slice of life'], | |
980 | 'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.png$', | |
981 | 'view_count': int, | |
16f7e6be AG |
982 | }, |
983 | 'params': { | |
984 | 'skip_download': True, | |
16f7e6be AG |
985 | }, |
986 | }, { | |
987 | 'url': 'https://www.biliintl.com/en/play/34613', | |
c62ecf0d | 988 | 'only_matching': True, |
16f7e6be AG |
989 | }] |
990 | ||
c62ecf0d M |
991 | def _entries(self, series_id): |
992 | series_json = self._call_api(f'/web/v2/ogv/play/episodes?season_id={series_id}&platform=web', series_id) | |
993 | for episode in traverse_obj(series_json, ('sections', ..., 'episodes', ...), expected_type=dict, default=[]): | |
994 | episode_id = str(episode.get('episode_id')) | |
f5f15c99 | 995 | yield self._extract_video_info(episode, ep_id=episode_id) |
16f7e6be AG |
996 | |
997 | def _real_extract(self, url): | |
c62ecf0d M |
998 | series_id = self._match_id(url) |
999 | series_info = self._call_api(f'/web/v2/ogv/play/season_info?season_id={series_id}&platform=web', series_id).get('season') or {} | |
1000 | return self.playlist_result( | |
1001 | self._entries(series_id), series_id, series_info.get('title'), series_info.get('description'), | |
1002 | categories=traverse_obj(series_info, ('styles', ..., 'title'), expected_type=str_or_none), | |
1003 | thumbnail=url_or_none(series_info.get('horizontal_cover')), view_count=parse_count(series_info.get('view'))) | |
b4f53662 H |
1004 | |
1005 | ||
1006 | class BiliLiveIE(InfoExtractor): | |
1007 | _VALID_URL = r'https?://live.bilibili.com/(?P<id>\d+)' | |
1008 | ||
1009 | _TESTS = [{ | |
1010 | 'url': 'https://live.bilibili.com/196', | |
1011 | 'info_dict': { | |
1012 | 'id': '33989', | |
1013 | '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)", | |
1014 | 'ext': 'flv', | |
1015 | 'title': "太空狼人杀联动,不被爆杀就算赢", | |
1016 | 'thumbnail': "https://i0.hdslb.com/bfs/live/new_room_cover/e607bc1529057ef4b332e1026e62cf46984c314d.jpg", | |
1017 | 'timestamp': 1650802769, | |
1018 | }, | |
1019 | 'skip': 'not live' | |
1020 | }, { | |
1021 | 'url': 'https://live.bilibili.com/196?broadcast_type=0&is_room_feed=1?spm_id_from=333.999.space_home.strengthen_live_card.click', | |
1022 | 'only_matching': True | |
1023 | }] | |
1024 | ||
1025 | _FORMATS = { | |
1026 | 80: {'format_id': 'low', 'format_note': '流畅'}, | |
1027 | 150: {'format_id': 'high_res', 'format_note': '高清'}, | |
1028 | 250: {'format_id': 'ultra_high_res', 'format_note': '超清'}, | |
1029 | 400: {'format_id': 'blue_ray', 'format_note': '蓝光'}, | |
1030 | 10000: {'format_id': 'source', 'format_note': '原画'}, | |
1031 | 20000: {'format_id': '4K', 'format_note': '4K'}, | |
1032 | 30000: {'format_id': 'dolby', 'format_note': '杜比'}, | |
1033 | } | |
1034 | ||
1035 | _quality = staticmethod(qualities(list(_FORMATS))) | |
1036 | ||
1037 | def _call_api(self, path, room_id, query): | |
1038 | api_result = self._download_json(f'https://api.live.bilibili.com/{path}', room_id, query=query) | |
1039 | if api_result.get('code') != 0: | |
1040 | raise ExtractorError(api_result.get('message') or 'Unable to download JSON metadata') | |
1041 | return api_result.get('data') or {} | |
1042 | ||
1043 | def _parse_formats(self, qn, fmt): | |
1044 | for codec in fmt.get('codec') or []: | |
1045 | if codec.get('current_qn') != qn: | |
1046 | continue | |
1047 | for url_info in codec['url_info']: | |
1048 | yield { | |
1049 | 'url': f'{url_info["host"]}{codec["base_url"]}{url_info["extra"]}', | |
1050 | 'ext': fmt.get('format_name'), | |
1051 | 'vcodec': codec.get('codec_name'), | |
1052 | 'quality': self._quality(qn), | |
1053 | **self._FORMATS[qn], | |
1054 | } | |
1055 | ||
1056 | def _real_extract(self, url): | |
1057 | room_id = self._match_id(url) | |
1058 | room_data = self._call_api('room/v1/Room/get_info', room_id, {'id': room_id}) | |
1059 | if room_data.get('live_status') == 0: | |
1060 | raise ExtractorError('Streamer is not live', expected=True) | |
1061 | ||
1062 | formats = [] | |
1063 | for qn in self._FORMATS.keys(): | |
1064 | stream_data = self._call_api('xlive/web-room/v2/index/getRoomPlayInfo', room_id, { | |
1065 | 'room_id': room_id, | |
1066 | 'qn': qn, | |
1067 | 'codec': '0,1', | |
1068 | 'format': '0,2', | |
1069 | 'mask': '0', | |
1070 | 'no_playurl': '0', | |
1071 | 'platform': 'web', | |
1072 | 'protocol': '0,1', | |
1073 | }) | |
1074 | for fmt in traverse_obj(stream_data, ('playurl_info', 'playurl', 'stream', ..., 'format', ...)) or []: | |
1075 | formats.extend(self._parse_formats(qn, fmt)) | |
1076 | self._sort_formats(formats) | |
1077 | ||
1078 | return { | |
1079 | 'id': room_id, | |
1080 | 'title': room_data.get('title'), | |
1081 | 'description': room_data.get('description'), | |
1082 | 'thumbnail': room_data.get('user_cover'), | |
1083 | 'timestamp': stream_data.get('live_time'), | |
1084 | 'formats': formats, | |
1085 | 'http_headers': { | |
1086 | 'Referer': url, | |
1087 | }, | |
1088 | } |