8 from .common
import InfoExtractor
, SearchInfoExtractor
37 class NiconicoIE(InfoExtractor
):
42 'url': 'http://www.nicovideo.jp/watch/sm22312215',
43 'md5': 'd1a75c0823e2f629128c43e1212760f9',
47 'title': 'Big Buck Bunny',
48 'thumbnail': r
're:https?://.*',
49 'uploader': 'takuya0301',
50 'uploader_id': '2698420',
51 'upload_date': '20131123',
52 'timestamp': int, # timestamp is unstable
53 'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
58 'skip': 'Requires an account',
60 # File downloaded with and without credentials are different, so omit
62 'url': 'http://www.nicovideo.jp/watch/nm14296458',
66 'title': '【鏡音リン】Dance on media【オリジナル】take2!',
67 'description': 'md5:689f066d74610b3b22e0f1739add0f58',
68 'thumbnail': r
're:https?://.*',
70 'uploader_id': '18822557',
71 'upload_date': '20110429',
72 'timestamp': 1304065916,
75 'skip': 'Requires an account',
77 # 'video exists but is marked as "deleted"
79 'url': 'http://www.nicovideo.jp/watch/sm10000',
82 'ext': 'unknown_video',
83 'description': 'deleted',
84 'title': 'ドラえもんエターナル第3話「決戦第3新東京市」<前編>',
85 'thumbnail': r
're:https?://.*',
86 'upload_date': '20071224',
87 'timestamp': int, # timestamp field has different value if logged in
91 'skip': 'Requires an account',
93 'url': 'http://www.nicovideo.jp/watch/so22543406',
97 'title': '【第1回】RADIOアニメロミックス ラブライブ!~のぞえりRadio Garden~',
98 'description': 'md5:b27d224bb0ff53d3c8269e9f8b561cf1',
99 'thumbnail': r
're:https?://.*',
100 'timestamp': 1388851200,
101 'upload_date': '20140104',
102 'uploader': 'アニメロチャンネル',
103 'uploader_id': '312',
105 'skip': 'The viewing period of the video you were searching for has expired.',
107 # video not available via `getflv`; "old" HTML5 video
108 'url': 'http://www.nicovideo.jp/watch/sm1151009',
109 'md5': '8fa81c364eb619d4085354eab075598a',
113 'title': 'マスターシステム本体内蔵のスペハリのメインテーマ(PSG版)',
114 'description': 'md5:6ee077e0581ff5019773e2e714cdd0b7',
115 'thumbnail': r
're:https?://.*',
117 'timestamp': 1190868283,
118 'upload_date': '20070927',
119 'uploader': 'denden2',
120 'uploader_id': '1392194',
122 'comment_count': int,
124 'skip': 'Requires an account',
128 'url': 'http://www.nicovideo.jp/watch/sm31464864',
132 'title': '新作TVアニメ「戦姫絶唱シンフォギアAXZ」PV 最高画質',
133 'description': 'md5:e52974af9a96e739196b2c1ca72b5feb',
134 'timestamp': 1498514060,
135 'upload_date': '20170626',
137 'uploader_id': '40826363',
138 'thumbnail': r
're:https?://.*',
141 'comment_count': int,
143 'skip': 'Requires an account',
145 # Video without owner
146 'url': 'http://www.nicovideo.jp/watch/sm18238488',
147 'md5': 'd265680a1f92bdcbbd2a507fc9e78a9e',
151 'title': '【実写版】ミュータントタートルズ',
152 'description': 'md5:15df8988e47a86f9e978af2064bf6d8e',
153 'timestamp': 1341160408,
154 'upload_date': '20120701',
157 'thumbnail': r
're:https?://.*',
160 'comment_count': int,
162 'skip': 'Requires an account',
164 'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
165 'only_matching': True,
167 'note': 'a video that is only served as an ENCRYPTED HLS.',
168 'url': 'https://www.nicovideo.jp/watch/so38016254',
169 'only_matching': True,
172 _VALID_URL
= r
'https?://(?:(?:www\.|secure\.|sp\.)?nicovideo\.jp/watch|nico\.ms)/(?P<id>(?:[a-z]{2})?[0-9]+)'
173 _NETRC_MACHINE
= 'niconico'
174 _COMMENT_API_ENDPOINTS
= (
175 'https://nvcomment.nicovideo.jp/legacy/api.json',
176 'https://nmsg.nicovideo.jp/api.json',)
178 'X-Frontend-ID': '6',
179 'X-Frontend-Version': '0',
180 'X-Niconico-Language': 'en-us',
181 'Referer': 'https://www.nicovideo.jp/',
182 'Origin': 'https://www.nicovideo.jp',
185 def _perform_login(self
, username
, password
):
188 'mail_tel': username
,
189 'password': password
,
191 self
._request
_webpage
(
192 'https://account.nicovideo.jp/login', None,
193 note
='Acquiring Login session')
194 page
= self
._download
_webpage
(
195 'https://account.nicovideo.jp/login/redirector?show_button_twitter=1&site=niconico&show_button_facebook=1', None,
196 note
='Logging in', errnote
='Unable to log in',
197 data
=urlencode_postdata(login_form_strs
),
199 'Referer': 'https://account.nicovideo.jp/login',
200 'Content-Type': 'application/x-www-form-urlencoded',
202 if 'oneTimePw' in page
:
203 post_url
= self
._search
_regex
(
204 r
'<form[^>]+action=(["\'])(?P
<url
>.+?
)\
1', page, 'post url
', group='url
')
205 page = self._download_webpage(
206 urljoin('https
://account
.nicovideo
.jp
', post_url), None,
207 note='Performing MFA
', errnote='Unable to complete MFA
',
208 data=urlencode_postdata({
209 'otp
': self._get_tfa_info('6 digits code
')
211 'Content
-Type
': 'application
/x
-www
-form
-urlencoded
',
213 if 'oneTimePw
' in page or 'formError
' in page:
214 err_msg = self._html_search_regex(
215 r'formError
["\']+>(.*?)</div>', page, 'form_error',
216 default='There\'s an error but the message can\'t be parsed.',
218 self.report_warning(f'Unable to log in: MFA challenge failed, "{err_msg}
"')
220 login_ok = 'class="notice error
"' not in page
222 self.report_warning('Unable to log in: bad username or password')
225 def _get_heartbeat_info(self, info_dict):
226 video_id, video_src_id, audio_src_id = info_dict['url'].split(':')[1].split('/')
227 dmc_protocol = info_dict['expected_protocol']
230 info_dict.get('_api_data')
232 self._html_search_regex(
233 'data-api-data="([^
"]+)"',
234 self._download_webpage('http
://www
.nicovideo
.jp
/watch
/' + video_id, video_id),
235 'API data
', default='{}'),
238 session_api_data = try_get(api_data, lambda x: x['media
']['delivery
']['movie
']['session
'])
239 session_api_endpoint = try_get(session_api_data, lambda x: x['urls
'][0])
242 tracking_id = traverse_obj(api_data, ('media
', 'delivery
', 'trackingId
'))
244 tracking_url = update_url_query('https
://nvapi
.nicovideo
.jp
/v1
/2ab0cbaa
/watch
', {'t': tracking_id})
245 watch_request_response = self._download_json(
246 tracking_url, video_id,
247 note='Acquiring permission
for downloading video
', fatal=False,
248 headers=self._API_HEADERS)
249 if traverse_obj(watch_request_response, ('meta
', 'status
')) != 200:
250 self.report_warning('Failed to acquire permission
for playing video
. Video download may fail
.')
252 yesno = lambda x: 'yes
' if x else 'no
'
254 if dmc_protocol == 'http
':
256 protocol_parameters = {
257 'http_output_download_parameters
': {
258 'use_ssl
': yesno(session_api_data['urls
'][0]['isSsl
']),
259 'use_well_known_port
': yesno(session_api_data['urls
'][0]['isWellKnownPort
']),
262 elif dmc_protocol == 'hls
':
264 segment_duration = try_get(self._configuration_arg('segment_duration
'), lambda x: int(x[0])) or 6000
265 parsed_token = self._parse_json(session_api_data['token
'], video_id)
266 encryption = traverse_obj(api_data, ('media
', 'delivery
', 'encryption
'))
267 protocol_parameters = {
269 'segment_duration
': segment_duration,
270 'transfer_preset
': '',
271 'use_ssl
': yesno(session_api_data['urls
'][0]['isSsl
']),
272 'use_well_known_port
': yesno(session_api_data['urls
'][0]['isWellKnownPort
']),
275 if 'hls_encryption
' in parsed_token and encryption:
276 protocol_parameters['hls_parameters
']['encryption
'] = {
277 parsed_token['hls_encryption
']: {
278 'encrypted_key
': encryption['encryptedKey
'],
279 'key_uri
': encryption['keyUri
'],
283 protocol = 'm3u8_native
'
285 raise ExtractorError(f'Unsupported DMC protocol
: {dmc_protocol}
')
287 session_response = self._download_json(
288 session_api_endpoint['url
'], video_id,
289 query={'_format': 'json'},
290 headers={'Content-Type': 'application/json'},
291 note='Downloading JSON metadata
for %s' % info_dict['format_id
'],
295 'player_id
': session_api_data.get('playerId
'),
298 'auth_type
': try_get(session_api_data, lambda x: x['authTypes
'][session_api_data['protocols
'][0]]),
299 'content_key_timeout
': session_api_data.get('contentKeyTimeout
'),
300 'service_id
': 'nicovideo
',
301 'service_user_id
': session_api_data.get('serviceUserId
')
303 'content_id
': session_api_data.get('contentId
'),
304 'content_src_id_sets
': [{
305 'content_src_ids
': [{
307 'audio_src_ids
': [audio_src_id],
308 'video_src_ids
': [video_src_id],
312 'content_type
': 'movie
',
316 'lifetime
': session_api_data.get('heartbeatLifetime
')
319 'priority
': session_api_data['priority
'],
324 'parameters
': protocol_parameters
328 'recipe_id
': session_api_data.get('recipeId
'),
329 'session_operation_auth
': {
330 'session_operation_auth_by_signature
': {
331 'signature
': session_api_data.get('signature
'),
332 'token
': session_api_data.get('token
'),
335 'timing_constraint
': 'unlimited
'
339 info_dict['url
'] = session_response['data
']['session
']['content_uri
']
340 info_dict['protocol
'] = protocol
343 heartbeat_info_dict = {
344 'url
': session_api_endpoint['url
'] + '/' + session_response['data
']['session
']['id'] + '?_format
=json
&_method
=PUT
',
345 'data
': json.dumps(session_response['data
']),
346 # interval, convert milliseconds to seconds, then halve to make a buffer.
347 'interval
': float_or_none(session_api_data.get('heartbeatLifetime
'), scale=3000),
351 return info_dict, heartbeat_info_dict
353 def _extract_format_for_quality(self, video_id, audio_quality, video_quality, dmc_protocol):
355 if not audio_quality.get('isAvailable
') or not video_quality.get('isAvailable
'):
358 def extract_video_quality(video_quality):
359 return parse_filesize('%sB
' % self._search_regex(
360 r'\|
([0-9]*\
.?
[0-9]*[MK
])', video_quality, 'vbr
', default=''))
362 format_id = '-'.join(
363 [remove_start(s['id'], 'archive_
') for s in (video_quality, audio_quality)] + [dmc_protocol])
365 vid_qual_label = traverse_obj(video_quality, ('metadata
', 'label
'))
366 vid_quality = traverse_obj(video_quality, ('metadata
', 'bitrate
'))
369 'url
': 'niconico_dmc
:%s/%s/%s' % (video_id, video_quality['id'], audio_quality['id']),
370 'format_id
': format_id,
371 'format_note
': join_nonempty('DMC
', vid_qual_label, dmc_protocol.upper(), delim=' '),
372 'ext
': 'mp4
', # Session API are used in HTML5, which always serves mp4
375 'abr
': float_or_none(traverse_obj(audio_quality, ('metadata
', 'bitrate
')), 1000),
376 'vbr
': float_or_none(vid_quality if vid_quality > 0 else extract_video_quality(vid_qual_label), 1000),
377 'height
': traverse_obj(video_quality, ('metadata
', 'resolution
', 'height
')),
378 'width
': traverse_obj(video_quality, ('metadata
', 'resolution
', 'width
')),
379 'quality
': -2 if 'low
' in video_quality['id'] else None,
380 'protocol
': 'niconico_dmc
',
381 'expected_protocol
': dmc_protocol, # XXX: This is not a documented field
383 'Origin
': 'https
://www
.nicovideo
.jp
',
384 'Referer
': 'https
://www
.nicovideo
.jp
/watch
/' + video_id,
388 def _real_extract(self, url):
389 video_id = self._match_id(url)
392 webpage, handle = self._download_webpage_handle(
393 'http
://www
.nicovideo
.jp
/watch
/' + video_id, video_id)
394 if video_id.startswith('so
'):
395 video_id = self._match_id(handle.geturl())
397 api_data = self._parse_json(self._html_search_regex(
398 'data
-api
-data
="([^"]+)"', webpage,
399 'API data', default='{}'), video_id)
400 except ExtractorError as e:
402 api_data = self._download_json(
403 'https://www.nicovideo.jp/api/watch/v3/%s?_frontendId=6&_frontendVersion=0&actionTrackId=AAAAAAAAAA_%d' % (video_id, round(time.time() * 1000)), video_id,
404 note='Downloading API JSON', errnote='Unable to fetch data')['data']
405 except ExtractorError:
406 if not isinstance(e.cause, compat_HTTPError):
408 webpage = e.cause.read().decode('utf-8', 'replace')
409 error_msg = self._html_search_regex(
410 r'(?s)<section\s+class="(?
:(?
:ErrorMessage|WatchExceptionPage
-message
)\s
*)+">(.+?)</section>',
411 webpage, 'error reason', default=None)
414 raise ExtractorError(re.sub(r'\s+', ' ', error_msg), expected=True)
418 def get_video_info(*items, get_first=True, **kwargs):
419 return traverse_obj(api_data, ('video', *items), get_all=not get_first, **kwargs)
421 quality_info = api_data['media']['delivery']['movie']
422 session_api_data = quality_info['session']
423 for (audio_quality, video_quality, protocol) in itertools.product(quality_info['audios'], quality_info['videos'], session_api_data['protocols']):
424 fmt = self._extract_format_for_quality(video_id, audio_quality, video_quality, protocol)
428 self._sort_formats(formats)
430 # Start extracting information
433 # use og:video:tag (not logged in)
434 og_video_tags = re.finditer(r'<meta\s+property="og
:video
:tag
"\s*content="(.*?
)">', webpage)
435 tags = list(filter(None, (clean_html(x.group(1)) for x in og_video_tags)))
437 # use keywords and split with comma (not logged in)
438 kwds = self._html_search_meta('keywords', webpage, default=None)
440 tags = [x for x in kwds.split(',') if x]
442 # find in json (logged in)
443 tags = traverse_obj(api_data, ('tag', 'items', ..., 'name'))
445 thumb_prefs = qualities(['url', 'middleUrl', 'largeUrl', 'player', 'ogp'])
449 '_api_data': api_data,
450 'title': get_video_info(('originalTitle', 'title')) or self._og_search_title(webpage, default=None),
456 'preference': thumb_prefs(key),
457 **parse_resolution(url, lenient=True),
458 } for key, url in (get_video_info('thumbnail') or {}).items() if url],
459 'description': clean_html(get_video_info('description')),
460 'uploader': traverse_obj(api_data, ('owner', 'nickname'), ('channel', 'name'), ('community', 'name')),
461 'uploader_id': str_or_none(traverse_obj(api_data, ('owner', 'id'), ('channel', 'id'), ('community', 'id'))),
462 'timestamp': parse_iso8601(get_video_info('registeredAt')) or parse_iso8601(
463 self._html_search_meta('video:release_date', webpage, 'date published', default=None)),
464 'channel': traverse_obj(api_data, ('channel', 'name'), ('community', 'name')),
465 'channel_id': traverse_obj(api_data, ('channel', 'id'), ('community', 'id')),
466 'view_count': int_or_none(get_video_info('count', 'view')),
468 'genre': traverse_obj(api_data, ('genre', 'label'), ('genre', 'key')),
469 'comment_count': get_video_info('count', 'comment', expected_type=int),
471 parse_duration(self._html_search_meta('video:duration', webpage, 'video duration', default=None))
472 or get_video_info('duration')),
473 'webpage_url': url_or_none(url) or f'https://www.nicovideo.jp/watch/{video_id}',
474 'subtitles': self.extract_subtitles(video_id, api_data, session_api_data),
477 def _get_subtitles(self, video_id, api_data, session_api_data):
478 comment_user_key = traverse_obj(api_data, ('comment', 'keys', 'userKey'))
479 user_id_str = session_api_data.get('serviceUserId')
481 thread_ids = traverse_obj(api_data, ('comment', 'threads', lambda _, v: v['isActive']))
482 raw_danmaku = self._extract_all_comments(video_id, thread_ids, user_id_str, comment_user_key)
484 self.report_warning(f'Failed to get comments. {bug_reports_message()}')
489 'data': json.dumps(raw_danmaku),
493 def _extract_all_comments(self, video_id, threads, user_id, user_key):
497 } if user_id and user_key else {'user_id': ''}
500 post_data = [{'ping': {'content': 'rs:0'}}]
501 for i, thread in enumerate(threads):
502 thread_id = thread['id']
503 thread_fork = thread['fork']
505 post_data.append({'ping': {'content': f'ps:{i * 2}'}})
506 post_data.append({'thread': {
512 'version': '20090904',
517 post_data.append({'ping': {'content': f'pf:{i * 2}'}})
520 post_data.append({'ping': {'content': f'ps:{i * 2 + 1}'}})
521 post_data.append({'thread_leaves': {
522 # format is '<bottom of minute range>-<top of minute range>:<comments per minute>,<total last comments'
523 # unfortunately NND limits (deletes?) comment returns this way, so you're only able to grab the last 1000 per language
524 'content': '0-999999:999999,999999,nicoru:999999',
533 post_data.append({'ping': {'content': f'pf:{i * 2 + 1}'}})
535 post_data.append({'ping': {'content': 'rf:0'}})
537 for api_url in self._COMMENT_API_ENDPOINTS:
538 comments = self._download_json(
539 api_url, video_id, data=json.dumps(post_data).encode(), fatal=False,
541 'Referer': 'https://www.nicovideo.jp/watch/%s' % video_id,
542 'Origin': 'https://www.nicovideo.jp',
543 'Content-Type': 'text/plain;charset=UTF-8',
545 note='Downloading comments', errnote=f'Failed to access endpoint {api_url}')
550 class NiconicoPlaylistBaseIE(InfoExtractor):
554 'X-Frontend-ID': '6',
555 'X-Frontend-Version': '0',
556 'X-Niconico-Language': 'en-us'
559 def _call_api(self, list_id, resource, query):
560 raise NotImplementedError('Must be implemented in subclasses')
563 def _parse_owner(item):
565 'uploader': traverse_obj(item, ('owner', 'name')),
566 'uploader_id': traverse_obj(item, ('owner', 'id')),
569 def _fetch_page(self, list_id, page):
571 resp = self._call_api(list_id, 'page %d' % page, {
573 'pageSize': self._PAGE_SIZE,
575 # this is needed to support both mylist and user
576 for video in traverse_obj(resp, ('items', ..., ('video', None))) or []:
577 video_id = video.get('id')
579 # skip {"video": {"id": "blablabla", ...}}
581 count = video.get('count') or {}
582 get_count = lambda x: int_or_none(count.get(x))
586 'title': video.get('title'),
587 'url': f'https://www.nicovideo.jp/watch/{video_id}',
588 'description': video.get('shortDescription'),
589 'duration': int_or_none(video.get('duration')),
590 'view_count': get_count('view'),
591 'comment_count': get_count('comment'),
592 'thumbnail': traverse_obj(video, ('thumbnail', ('nHdUrl', 'largeUrl', 'listingUrl', 'url'))),
593 'ie_key': NiconicoIE.ie_key(),
594 **self._parse_owner(video),
597 def _entries(self, list_id):
598 return OnDemandPagedList(functools.partial(self._fetch_page, list_id), self._PAGE_SIZE)
601 class NiconicoPlaylistIE(NiconicoPlaylistBaseIE):
602 IE_NAME = 'niconico:playlist'
603 _VALID_URL = r'https?://(?:(?:www\.|sp\.)?nicovideo\.jp|nico\.ms)/(?:user/\d+/)?(?:my/)?mylist/(?:#/)?(?P<id>\d+)'
606 'url': 'http://www.nicovideo.jp/mylist/27411728',
609 'title': 'AKB48のオールナイトニッポン',
610 'description': 'md5:d89694c5ded4b6c693dea2db6e41aa08',
612 'uploader_id': '805442',
614 'playlist_mincount': 291,
616 'url': 'https://www.nicovideo.jp/user/805442/mylist/27411728',
617 'only_matching': True,
619 'url': 'https://www.nicovideo.jp/my/mylist/#/68048635',
620 'only_matching': True,
623 def _call_api(self, list_id, resource, query):
624 return self._download_json(
625 f'https://nvapi.nicovideo.jp/v2/mylists/{list_id}', list_id,
626 f'Downloading {resource}', query=query,
627 headers=self._API_HEADERS)['data']['mylist']
629 def _real_extract(self, url):
630 list_id = self._match_id(url)
631 mylist = self._call_api(list_id, 'list', {
634 return self.playlist_result(
635 self._entries(list_id), list_id,
636 mylist.get('name'), mylist.get('description'), **self._parse_owner(mylist))
639 class NiconicoSeriesIE(InfoExtractor):
640 IE_NAME = 'niconico:series'
641 _VALID_URL = r'https?://(?:(?:www\.|sp\.)?nicovideo\.jp|nico\.ms)/series/(?P<id>\d+)'
644 'url': 'https://www.nicovideo.jp/series/110226',
647 'title': 'ご立派ァ!のシリーズ',
649 'playlist_mincount': 10,
651 'url': 'https://www.nicovideo.jp/series/12312/',
654 'title': 'バトルスピリッツ お勧めカード紹介(調整中)',
656 'playlist_mincount': 103,
658 'url': 'https://nico.ms/series/203559',
659 'only_matching': True,
662 def _real_extract(self, url):
663 list_id = self._match_id(url)
664 webpage = self._download_webpage(f'https://www.nicovideo.jp/series/{list_id}', list_id)
666 title = self._search_regex(
668 r'<div class="TwitterShareButton
"\s+data-text="(.+)\s
+https
:'),
669 webpage, 'title
', fatal=False)
671 title = unescapeHTML(title)
673 self.url_result(f'https
://www
.nicovideo
.jp
/watch
/{v_id}
', video_id=v_id)
674 for v_id in re.findall(r'data
-href
=[\'"](?:https://www\.nicovideo\.jp)?/watch/([a-z0-9]+)', webpage)]
675 return self.playlist_result(playlist, list_id, title)
678 class NiconicoHistoryIE(NiconicoPlaylistBaseIE):
679 IE_NAME = 'niconico:history'
680 IE_DESC = 'NicoNico user history. Requires cookies.'
681 _VALID_URL = r'https?://(?:www\.|sp\.)?nicovideo\.jp/my/history'
684 'note': 'PC page, with /video',
685 'url': 'https://www.nicovideo.jp/my/history/video',
686 'only_matching': True,
688 'note': 'PC page, without /video',
689 'url': 'https://www.nicovideo.jp/my/history',
690 'only_matching': True,
692 'note': 'mobile page, with /video',
693 'url': 'https://sp.nicovideo.jp/my/history/video',
694 'only_matching': True,
696 'note': 'mobile page, without /video',
697 'url': 'https://sp.nicovideo.jp/my/history',
698 'only_matching': True,
701 def _call_api(self, list_id, resource, query):
702 return self._download_json(
703 'https://nvapi.nicovideo.jp/v1/users/me/watch/history', 'history',
704 f'Downloading {resource}', query=query,
705 headers=self._API_HEADERS)['data']
707 def _real_extract(self, url):
710 mylist = self._call_api(list_id, 'list', {
713 except ExtractorError as e:
714 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
715 self.raise_login_required('You have to be logged in to get your watch history')
717 return self.playlist_result(self._entries(list_id), list_id, **self._parse_owner(mylist))
720 class NicovideoSearchBaseIE(InfoExtractor):
721 _SEARCH_TYPE = 'search'
723 def _entries(self, url, item_id, query=None, note='Downloading page %(page)s'):
725 pages = [query['page']] if 'page' in query else itertools.count(1)
726 for page_num in pages:
727 query['page'] = str(page_num)
728 webpage = self._download_webpage(url, item_id, query=query, note=note % {'page': page_num})
729 results = re.findall(r'(?<=data-video-id=)["\']?
(?P
<videoid
>.*?
)(?
=["\'])', webpage)
731 yield self.url_result(f'http://www.nicovideo.jp/watch/{item}', 'Niconico', item)
735 def _search_results(self, query):
736 return self._entries(
737 self._proto_relative_url(f'//www.nicovideo.jp/{self._SEARCH_TYPE}/{query}'), query)
740 class NicovideoSearchIE(NicovideoSearchBaseIE, SearchInfoExtractor):
741 IE_DESC = 'Nico video search'
742 IE_NAME = 'nicovideo:search'
743 _SEARCH_KEY = 'nicosearch'
746 class NicovideoSearchURLIE(NicovideoSearchBaseIE):
747 IE_NAME = f'{NicovideoSearchIE.IE_NAME}_url'
748 IE_DESC = 'Nico video search URLs'
749 _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/search/(?P<id>[^?#&]+)?'
751 'url': 'http://www.nicovideo.jp/search/sm9',
756 'playlist_mincount': 40,
758 'url': 'https://www.nicovideo.jp/search/sm9?sort=h&order=d&end=2020-12-31&start=2020-01-01',
763 'playlist_count': 31,
766 def _real_extract(self, url):
767 query = self._match_id(url)
768 return self.playlist_result(self._entries(url, query), query, query)
771 class NicovideoSearchDateIE(NicovideoSearchBaseIE, SearchInfoExtractor):
772 IE_DESC = 'Nico video search, newest first'
773 IE_NAME = f'{NicovideoSearchIE.IE_NAME}:date'
774 _SEARCH_KEY = 'nicosearchdate'
776 'url': 'nicosearchdateall:a',
781 'playlist_mincount': 1610,
784 _START_DATE = datetime.date(2007, 1, 1)
785 _RESULTS_PER_PAGE = 32
788 def _entries(self, url, item_id, start_date=None, end_date=None):
789 start_date, end_date = start_date or self._START_DATE, end_date or datetime.datetime.now().date()
791 # If the last page has a full page of videos, we need to break down the query interval further
792 last_page_len = len(list(self._get_entries_for_date(
793 url, item_id, start_date, end_date, self._MAX_PAGES,
794 note=f'Checking number of videos from {start_date} to {end_date}')))
795 if (last_page_len == self._RESULTS_PER_PAGE and start_date != end_date):
796 midpoint = start_date + ((end_date - start_date) // 2)
797 yield from self._entries(url, item_id, midpoint, end_date)
798 yield from self._entries(url, item_id, start_date, midpoint)
800 self.to_screen(f'{item_id}: Downloading results from {start_date} to {end_date}')
801 yield from self._get_entries_for_date(
802 url, item_id, start_date, end_date, note=' Downloading page %(page)s')
804 def _get_entries_for_date(self, url, item_id, start_date, end_date=None, page_num=None, note=None):
806 'start': str(start_date),
807 'end': str(end_date or start_date),
812 query['page'] = str(page_num)
814 yield from super()._entries(url, item_id, query=query, note=note)
817 class NicovideoTagURLIE(NicovideoSearchBaseIE):
818 IE_NAME = 'niconico:tag'
819 IE_DESC = 'NicoNico video tag URLs'
821 _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/tag/(?P<id>[^?#&]+)?'
823 'url': 'https://www.nicovideo.jp/tag/ドキュメンタリー淫夢',
826 'title': 'ドキュメンタリー淫夢'
828 'playlist_mincount': 400,
831 def _real_extract(self, url):
832 query = self._match_id(url)
833 return self.playlist_result(self._entries(url, query), query, query)
836 class NiconicoUserIE(InfoExtractor):
837 _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/user/(?P<id>\d+)/?(?:$|[#?])'
839 'url': 'https://www.nicovideo.jp/user/419948',
843 'playlist_mincount': 101,
845 _API_URL = "https
://nvapi
.nicovideo
.jp
/v1
/users
/%s/videos?sortKey
=registeredAt
&sortOrder
=desc
&pageSize
=%s&page
=%s"
849 'X-Frontend-ID': '6',
850 'X-Frontend-Version': '0'
853 def _entries(self, list_id):
856 while count < total_count:
857 json_parsed = self._download_json(
858 self._API_URL % (list_id, self._PAGE_SIZE, page_num + 1), list_id,
859 headers=self._API_HEADERS,
860 note='Downloading JSON metadata%s' % (' page %d' % page_num if page_num else ''))
862 total_count = int_or_none(json_parsed['data'].get('totalCount'))
863 for entry in json_parsed["data
"]["items
"]:
865 yield self.url_result('https://www.nicovideo.jp/watch/%s' % entry['id'])
868 def _real_extract(self, url):
869 list_id = self._match_id(url)
870 return self.playlist_result(self._entries(list_id), list_id, ie=NiconicoIE.ie_key())