2 from __future__
import unicode_literals
11 from .common
import InfoExtractor
, SearchInfoExtractor
12 from ..compat
import (
14 compat_urllib_parse_urlparse
,
38 class NiconicoIE(InfoExtractor
):
43 'url': 'http://www.nicovideo.jp/watch/sm22312215',
44 'md5': 'd1a75c0823e2f629128c43e1212760f9',
48 'title': 'Big Buck Bunny',
49 'thumbnail': r
're:https?://.*',
50 'uploader': 'takuya0301',
51 'uploader_id': '2698420',
52 'upload_date': '20131123',
53 'timestamp': int, # timestamp is unstable
54 'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
59 'skip': 'Requires an account',
61 # File downloaded with and without credentials are different, so omit
63 'url': 'http://www.nicovideo.jp/watch/nm14296458',
67 'title': '【鏡音リン】Dance on media【オリジナル】take2!',
68 'description': 'md5:689f066d74610b3b22e0f1739add0f58',
69 'thumbnail': r
're:https?://.*',
71 'uploader_id': '18822557',
72 'upload_date': '20110429',
73 'timestamp': 1304065916,
76 'skip': 'Requires an account',
78 # 'video exists but is marked as "deleted"
80 'url': 'http://www.nicovideo.jp/watch/sm10000',
83 'ext': 'unknown_video',
84 'description': 'deleted',
85 'title': 'ドラえもんエターナル第3話「決戦第3新東京市」<前編>',
86 'thumbnail': r
're:https?://.*',
87 'upload_date': '20071224',
88 'timestamp': int, # timestamp field has different value if logged in
92 'skip': 'Requires an account',
94 'url': 'http://www.nicovideo.jp/watch/so22543406',
98 'title': '【第1回】RADIOアニメロミックス ラブライブ!~のぞえりRadio Garden~',
99 'description': 'md5:b27d224bb0ff53d3c8269e9f8b561cf1',
100 'thumbnail': r
're:https?://.*',
101 'timestamp': 1388851200,
102 'upload_date': '20140104',
103 'uploader': 'アニメロチャンネル',
104 'uploader_id': '312',
106 'skip': 'The viewing period of the video you were searching for has expired.',
108 # video not available via `getflv`; "old" HTML5 video
109 'url': 'http://www.nicovideo.jp/watch/sm1151009',
110 'md5': '8fa81c364eb619d4085354eab075598a',
114 '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)',
115 'description': 'md5:6ee077e0581ff5019773e2e714cdd0b7',
116 'thumbnail': r
're:https?://.*',
118 'timestamp': 1190868283,
119 'upload_date': '20070927',
120 'uploader': 'denden2',
121 'uploader_id': '1392194',
123 'comment_count': int,
125 'skip': 'Requires an account',
129 'url': 'http://www.nicovideo.jp/watch/sm31464864',
133 'title': '新作TVアニメ「戦姫絶唱シンフォギアAXZ」PV 最高画質',
134 'description': 'md5:e52974af9a96e739196b2c1ca72b5feb',
135 'timestamp': 1498514060,
136 'upload_date': '20170626',
138 'uploader_id': '40826363',
139 'thumbnail': r
're:https?://.*',
142 'comment_count': int,
144 'skip': 'Requires an account',
146 # Video without owner
147 'url': 'http://www.nicovideo.jp/watch/sm18238488',
148 'md5': 'd265680a1f92bdcbbd2a507fc9e78a9e',
152 'title': '【実写版】ミュータントタートルズ',
153 'description': 'md5:15df8988e47a86f9e978af2064bf6d8e',
154 'timestamp': 1341160408,
155 'upload_date': '20120701',
158 'thumbnail': r
're:https?://.*',
161 'comment_count': int,
163 'skip': 'Requires an account',
165 'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
166 'only_matching': True,
168 'note': 'a video that is only served as an ENCRYPTED HLS.',
169 'url': 'https://www.nicovideo.jp/watch/so38016254',
170 'only_matching': True,
173 _VALID_URL
= r
'https?://(?:(?:www\.|secure\.|sp\.)?nicovideo\.jp/watch|nico\.ms)/(?P<id>(?:[a-z]{2})?[0-9]+)'
174 _NETRC_MACHINE
= 'niconico'
175 _COMMENT_API_ENDPOINTS
= (
176 'https://nvcomment.nicovideo.jp/legacy/api.json',
177 'https://nmsg.nicovideo.jp/api.json',)
179 'X-Frontend-ID': '6',
180 'X-Frontend-Version': '0',
181 'X-Niconico-Language': 'en-us',
182 'Referer': 'https://www.nicovideo.jp/',
183 'Origin': 'https://www.nicovideo.jp',
186 def _perform_login(self
, username
, password
):
189 'mail_tel': username
,
190 'password': password
,
192 self
._request
_webpage
(
193 'https://account.nicovideo.jp/login', None,
194 note
='Acquiring Login session')
195 urlh
= self
._request
_webpage
(
196 'https://account.nicovideo.jp/login/redirector?show_button_twitter=1&site=niconico&show_button_facebook=1', None,
197 note
='Logging in', errnote
='Unable to log in',
198 data
=urlencode_postdata(login_form_strs
),
200 'Referer': 'https://account.nicovideo.jp/login',
201 'Content-Type': 'application/x-www-form-urlencoded',
206 parts
= compat_urllib_parse_urlparse(urlh
.geturl())
207 if compat_parse_qs(parts
.query
).get('message', [None])[0] == 'cant_login':
210 self
.report_warning('unable to log in: bad username or password')
213 def _get_heartbeat_info(self
, info_dict
):
214 video_id
, video_src_id
, audio_src_id
= info_dict
['url'].split(':')[1].split('/')
215 dmc_protocol
= info_dict
['_expected_protocol']
218 info_dict
.get('_api_data')
220 self
._html
_search
_regex
(
221 'data-api-data="([^"]+)"',
222 self
._download
_webpage
('http://www.nicovideo.jp/watch/' + video_id
, video_id
),
223 'API data', default
='{}'),
226 session_api_data
= try_get(api_data
, lambda x
: x
['media']['delivery']['movie']['session'])
227 session_api_endpoint
= try_get(session_api_data
, lambda x
: x
['urls'][0])
230 tracking_id
= traverse_obj(api_data
, ('media', 'delivery', 'trackingId'))
232 tracking_url
= update_url_query('https://nvapi.nicovideo.jp/v1/2ab0cbaa/watch', {'t': tracking_id}
)
233 watch_request_response
= self
._download
_json
(
234 tracking_url
, video_id
,
235 note
='Acquiring permission for downloading video', fatal
=False,
236 headers
=self
._API
_HEADERS
)
237 if traverse_obj(watch_request_response
, ('meta', 'status')) != 200:
238 self
.report_warning('Failed to acquire permission for playing video. Video download may fail.')
240 yesno
= lambda x
: 'yes' if x
else 'no'
242 if dmc_protocol
== 'http':
244 protocol_parameters
= {
245 'http_output_download_parameters': {
246 'use_ssl': yesno(session_api_data
['urls'][0]['isSsl']),
247 'use_well_known_port': yesno(session_api_data
['urls'][0]['isWellKnownPort']),
250 elif dmc_protocol
== 'hls':
252 segment_duration
= try_get(self
._configuration
_arg
('segment_duration'), lambda x
: int(x
[0])) or 6000
253 parsed_token
= self
._parse
_json
(session_api_data
['token'], video_id
)
254 encryption
= traverse_obj(api_data
, ('media', 'delivery', 'encryption'))
255 protocol_parameters
= {
257 'segment_duration': segment_duration
,
258 'transfer_preset': '',
259 'use_ssl': yesno(session_api_data
['urls'][0]['isSsl']),
260 'use_well_known_port': yesno(session_api_data
['urls'][0]['isWellKnownPort']),
263 if 'hls_encryption' in parsed_token
and encryption
:
264 protocol_parameters
['hls_parameters']['encryption'] = {
265 parsed_token
['hls_encryption']: {
266 'encrypted_key': encryption
['encryptedKey'],
267 'key_uri': encryption
['keyUri'],
271 protocol
= 'm3u8_native'
273 raise ExtractorError(f
'Unsupported DMC protocol: {dmc_protocol}')
275 session_response
= self
._download
_json
(
276 session_api_endpoint
['url'], video_id
,
277 query
={'_format': 'json'}
,
278 headers
={'Content-Type': 'application/json'}
,
279 note
='Downloading JSON metadata for %s' % info_dict
['format_id'],
283 'player_id': session_api_data
.get('playerId'),
286 'auth_type': try_get(session_api_data
, lambda x
: x
['authTypes'][session_api_data
['protocols'][0]]),
287 'content_key_timeout': session_api_data
.get('contentKeyTimeout'),
288 'service_id': 'nicovideo',
289 'service_user_id': session_api_data
.get('serviceUserId')
291 'content_id': session_api_data
.get('contentId'),
292 'content_src_id_sets': [{
293 'content_src_ids': [{
295 'audio_src_ids': [audio_src_id
],
296 'video_src_ids': [video_src_id
],
300 'content_type': 'movie',
304 'lifetime': session_api_data
.get('heartbeatLifetime')
307 'priority': session_api_data
['priority'],
312 'parameters': protocol_parameters
316 'recipe_id': session_api_data
.get('recipeId'),
317 'session_operation_auth': {
318 'session_operation_auth_by_signature': {
319 'signature': session_api_data
.get('signature'),
320 'token': session_api_data
.get('token'),
323 'timing_constraint': 'unlimited'
327 info_dict
['url'] = session_response
['data']['session']['content_uri']
328 info_dict
['protocol'] = protocol
331 heartbeat_info_dict
= {
332 'url': session_api_endpoint
['url'] + '/' + session_response
['data']['session']['id'] + '?_format=json&_method=PUT',
333 'data': json
.dumps(session_response
['data']),
334 # interval, convert milliseconds to seconds, then halve to make a buffer.
335 'interval': float_or_none(session_api_data
.get('heartbeatLifetime'), scale
=3000),
339 return info_dict
, heartbeat_info_dict
341 def _extract_format_for_quality(self
, video_id
, audio_quality
, video_quality
, dmc_protocol
):
343 if not audio_quality
.get('isAvailable') or not video_quality
.get('isAvailable'):
346 def extract_video_quality(video_quality
):
347 return parse_filesize('%sB' % self
._search
_regex
(
348 r
'\| ([0-9]*\.?[0-9]*[MK])', video_quality
, 'vbr', default
=''))
350 format_id
= '-'.join(
351 [remove_start(s
['id'], 'archive_') for s
in (video_quality
, audio_quality
)] + [dmc_protocol
])
353 vid_qual_label
= traverse_obj(video_quality
, ('metadata', 'label'))
354 vid_quality
= traverse_obj(video_quality
, ('metadata', 'bitrate'))
357 'url': 'niconico_dmc:%s/%s/%s' % (video_id
, video_quality
['id'], audio_quality
['id']),
358 'format_id': format_id
,
359 'format_note': join_nonempty('DMC', vid_qual_label
, dmc_protocol
.upper(), delim
=' '),
360 'ext': 'mp4', # Session API are used in HTML5, which always serves mp4
363 'abr': float_or_none(traverse_obj(audio_quality
, ('metadata', 'bitrate')), 1000),
364 'vbr': float_or_none(vid_quality
if vid_quality
> 0 else extract_video_quality(vid_qual_label
), 1000),
365 'height': traverse_obj(video_quality
, ('metadata', 'resolution', 'height')),
366 'width': traverse_obj(video_quality
, ('metadata', 'resolution', 'width')),
367 'quality': -2 if 'low' in video_quality
['id'] else None,
368 'protocol': 'niconico_dmc',
369 '_expected_protocol': dmc_protocol
,
371 'Origin': 'https://www.nicovideo.jp',
372 'Referer': 'https://www.nicovideo.jp/watch/' + video_id
,
376 def _real_extract(self
, url
):
377 video_id
= self
._match
_id
(url
)
380 webpage
, handle
= self
._download
_webpage
_handle
(
381 'http://www.nicovideo.jp/watch/' + video_id
, video_id
)
382 if video_id
.startswith('so'):
383 video_id
= self
._match
_id
(handle
.geturl())
385 api_data
= self
._parse
_json
(self
._html
_search
_regex
(
386 'data-api-data="([^"]+)"', webpage
,
387 'API data', default
='{}'), video_id
)
388 except ExtractorError
as e
:
390 api_data
= self
._download
_json
(
391 'https://www.nicovideo.jp/api/watch/v3/%s?_frontendId=6&_frontendVersion=0&actionTrackId=AAAAAAAAAA_%d' % (video_id
, round(time
.time() * 1000)), video_id
,
392 note
='Downloading API JSON', errnote
='Unable to fetch data')['data']
393 except ExtractorError
:
394 if not isinstance(e
.cause
, compat_HTTPError
):
396 webpage
= e
.cause
.read().decode('utf-8', 'replace')
397 error_msg
= self
._html
_search
_regex
(
398 r
'(?s)<section\s+class="(?:(?:ErrorMessage|WatchExceptionPage-message)\s*)+">(.+?)</section>',
399 webpage
, 'error reason', default
=None)
402 raise ExtractorError(re
.sub(r
'\s+', ' ', error_msg
), expected
=True)
406 def get_video_info(*items
, get_first
=True, **kwargs
):
407 return traverse_obj(api_data
, ('video', *items
), get_all
=not get_first
, **kwargs
)
409 quality_info
= api_data
['media']['delivery']['movie']
410 session_api_data
= quality_info
['session']
411 for (audio_quality
, video_quality
, protocol
) in itertools
.product(quality_info
['audios'], quality_info
['videos'], session_api_data
['protocols']):
412 fmt
= self
._extract
_format
_for
_quality
(video_id
, audio_quality
, video_quality
, protocol
)
416 self
._sort
_formats
(formats
)
418 # Start extracting information
421 # use og:video:tag (not logged in)
422 og_video_tags
= re
.finditer(r
'<meta\s+property="og:video:tag"\s*content="(.*?)">', webpage
)
423 tags
= list(filter(None, (clean_html(x
.group(1)) for x
in og_video_tags
)))
425 # use keywords and split with comma (not logged in)
426 kwds
= self
._html
_search
_meta
('keywords', webpage
, default
=None)
428 tags
= [x
for x
in kwds
.split(',') if x
]
430 # find in json (logged in)
431 tags
= traverse_obj(api_data
, ('tag', 'items', ..., 'name'))
435 '_api_data': api_data
,
436 'title': get_video_info(('originalTitle', 'title')) or self
._og
_search
_title
(webpage
, default
=None),
438 'thumbnail': get_video_info('thumbnail', 'url') or self
._html
_search
_meta
(
439 ('image', 'og:image'), webpage
, 'thumbnail', default
=None),
440 'description': clean_html(get_video_info('description')),
441 'uploader': traverse_obj(api_data
, ('owner', 'nickname')),
442 'timestamp': parse_iso8601(get_video_info('registeredAt')) or parse_iso8601(
443 self
._html
_search
_meta
('video:release_date', webpage
, 'date published', default
=None)),
444 'uploader_id': traverse_obj(api_data
, ('owner', 'id')),
445 'channel': traverse_obj(api_data
, ('channel', 'name'), ('community', 'name')),
446 'channel_id': traverse_obj(api_data
, ('channel', 'id'), ('community', 'id')),
447 'view_count': int_or_none(get_video_info('count', 'view')),
449 'genre': traverse_obj(api_data
, ('genre', 'label'), ('genre', 'key')),
450 'comment_count': get_video_info('count', 'comment', expected_type
=int),
452 parse_duration(self
._html
_search
_meta
('video:duration', webpage
, 'video duration', default
=None))
453 or get_video_info('duration')),
454 'webpage_url': url_or_none(url
) or f
'https://www.nicovideo.jp/watch/{video_id}',
455 'subtitles': self
.extract_subtitles(video_id
, api_data
, session_api_data
),
458 def _get_subtitles(self
, video_id
, api_data
, session_api_data
):
459 comment_user_key
= traverse_obj(api_data
, ('comment', 'keys', 'userKey'))
460 user_id_str
= session_api_data
.get('serviceUserId')
462 thread_ids
= [x
for x
in traverse_obj(api_data
, ('comment', 'threads')) or [] if x
['isActive']]
463 raw_danmaku
= self
._extract
_all
_comments
(video_id
, thread_ids
, user_id_str
, comment_user_key
)
465 self
.report_warning(f
'Failed to get comments. {bug_reports_message()}')
470 'data': json
.dumps(raw_danmaku
),
474 def _extract_all_comments(self
, video_id
, threads
, user_id
, user_key
):
478 } if user_id
and user_key
else {'user_id': ''}
481 post_data
= [{'ping': {'content': 'rs:0'}
}]
482 for i
, thread
in enumerate(threads
):
483 thread_id
= thread
['id']
484 thread_fork
= thread
['fork']
486 post_data
.append({'ping': {'content': f'ps:{i * 2}
'}})
487 post_data.append({'thread
': {
493 'version
': '20090904',
498 post_data.append({'ping': {'content': f'pf:{i * 2}'}})
501 post_data
.append({'ping': {'content': f'ps:{i * 2 + 1}
'}})
502 post_data.append({'thread_leaves
': {
503 # format is '<bottom of minute
range>-<top of minute
range>:<comments per minute
>,<total last comments
'
504 # unfortunately NND limits (deletes?) comment returns this way, so you're only able to grab the last
1000 per language
505 'content': '0-999999:999999,999999,nicoru:999999',
514 post_data
.append({'ping': {'content': f'pf:{i * 2 + 1}
'}})
516 post_data.append({'ping': {'content': 'rf:0'}})
518 for api_url in self._COMMENT_API_ENDPOINTS:
519 comments = self._download_json(
520 api_url, video_id, data=json.dumps(post_data).encode(), fatal=False,
522 'Referer
': 'https
://www
.nicovideo
.jp
/watch
/%s' % video_id,
523 'Origin
': 'https
://www
.nicovideo
.jp
',
524 'Content
-Type
': 'text
/plain
;charset
=UTF
-8',
526 note='Downloading comments
', errnote=f'Failed to access endpoint {api_url}
')
531 class NiconicoPlaylistBaseIE(InfoExtractor):
535 'X
-Frontend
-ID
': '6',
536 'X
-Frontend
-Version
': '0',
537 'X
-Niconico
-Language
': 'en
-us
'
540 def _call_api(self, list_id, resource, query):
541 "Implement this in child class"
545 def _parse_owner(item):
547 'uploader
': traverse_obj(item, ('owner
', 'name
')),
548 'uploader_id
': traverse_obj(item, ('owner
', 'id')),
551 def _fetch_page(self, list_id, page):
553 resp = self._call_api(list_id, 'page
%d' % page, {
555 'pageSize
': self._PAGE_SIZE,
557 # this is needed to support both mylist and user
558 for video in traverse_obj(resp, ('items
', ..., ('video
', None))) or []:
559 video_id = video.get('id')
561 # skip {"video": {"id": "blablabla", ...}}
563 count = video.get('count
') or {}
564 get_count = lambda x: int_or_none(count.get(x))
568 'title
': video.get('title
'),
569 'url
': f'https
://www
.nicovideo
.jp
/watch
/{video_id}
',
570 'description
': video.get('shortDescription
'),
571 'duration
': int_or_none(video.get('duration
')),
572 'view_count
': get_count('view
'),
573 'comment_count
': get_count('comment
'),
574 'thumbnail
': traverse_obj(video, ('thumbnail
', ('nHdUrl
', 'largeUrl
', 'listingUrl
', 'url
'))),
575 'ie_key
': NiconicoIE.ie_key(),
576 **self._parse_owner(video),
579 def _entries(self, list_id):
580 return OnDemandPagedList(functools.partial(self._fetch_page, list_id), self._PAGE_SIZE)
583 class NiconicoPlaylistIE(NiconicoPlaylistBaseIE):
584 IE_NAME = 'niconico
:playlist
'
585 _VALID_URL = r'https?
://(?
:(?
:www\
.|sp\
.)?nicovideo\
.jp|nico\
.ms
)/(?
:user
/\d
+/)?
(?
:my
/)?mylist
/(?
:#/)?(?P<id>\d+)'
588 'url': 'http://www.nicovideo.jp/mylist/27411728',
591 'title': 'AKB48のオールナイトニッポン',
592 'description': 'md5:d89694c5ded4b6c693dea2db6e41aa08',
594 'uploader_id': '805442',
596 'playlist_mincount': 291,
598 'url': 'https://www.nicovideo.jp/user/805442/mylist/27411728',
599 'only_matching': True,
601 'url': 'https://www.nicovideo.jp/my/mylist/#/68048635',
602 'only_matching': True,
605 def _call_api(self
, list_id
, resource
, query
):
606 return self
._download
_json
(
607 f
'https://nvapi.nicovideo.jp/v2/mylists/{list_id}', list_id
,
608 f
'Downloading {resource}', query
=query
,
609 headers
=self
._API
_HEADERS
)['data']['mylist']
611 def _real_extract(self
, url
):
612 list_id
= self
._match
_id
(url
)
613 mylist
= self
._call
_api
(list_id
, 'list', {
616 return self
.playlist_result(
617 self
._entries
(list_id
), list_id
,
618 mylist
.get('name'), mylist
.get('description'), **self
._parse
_owner
(mylist
))
621 class NiconicoSeriesIE(InfoExtractor
):
622 IE_NAME
= 'niconico:series'
623 _VALID_URL
= r
'https?://(?:(?:www\.|sp\.)?nicovideo\.jp|nico\.ms)/series/(?P<id>\d+)'
626 'url': 'https://www.nicovideo.jp/series/110226',
629 'title': 'ご立派ァ!のシリーズ',
631 'playlist_mincount': 10, # as of 2021/03/17
633 'url': 'https://www.nicovideo.jp/series/12312/',
636 'title': 'バトルスピリッツ お勧めカード紹介(調整中)',
638 'playlist_mincount': 97, # as of 2021/03/17
640 'url': 'https://nico.ms/series/203559',
641 'only_matching': True,
644 def _real_extract(self
, url
):
645 list_id
= self
._match
_id
(url
)
646 webpage
= self
._download
_webpage
(f
'https://www.nicovideo.jp/series/{list_id}', list_id
)
648 title
= self
._search
_regex
(
650 r
'<div class="TwitterShareButton"\s+data-text="(.+)\s+https:'),
651 webpage
, 'title', fatal
=False)
653 title
= unescapeHTML(title
)
655 self
.url_result(f
'https://www.nicovideo.jp/watch/{v_id}', video_id
=v_id
)
656 for v_id
in re
.findall(r
'href="/watch/([a-z0-9]+)" data-href="/watch/\1', webpage
)]
657 return self
.playlist_result(playlist
, list_id
, title
)
660 class NiconicoHistoryIE(NiconicoPlaylistBaseIE
):
661 IE_NAME
= 'niconico:history'
662 IE_DESC
= 'NicoNico user history. Requires cookies.'
663 _VALID_URL
= r
'https?://(?:www\.|sp\.)?nicovideo\.jp/my/history'
666 'note': 'PC page, with /video',
667 'url': 'https://www.nicovideo.jp/my/history/video',
668 'only_matching': True,
670 'note': 'PC page, without /video',
671 'url': 'https://www.nicovideo.jp/my/history',
672 'only_matching': True,
674 'note': 'mobile page, with /video',
675 'url': 'https://sp.nicovideo.jp/my/history/video',
676 'only_matching': True,
678 'note': 'mobile page, without /video',
679 'url': 'https://sp.nicovideo.jp/my/history',
680 'only_matching': True,
683 def _call_api(self
, list_id
, resource
, query
):
684 return self
._download
_json
(
685 'https://nvapi.nicovideo.jp/v1/users/me/watch/history', 'history',
686 f
'Downloading {resource}', query
=query
,
687 headers
=self
._API
_HEADERS
)['data']
689 def _real_extract(self
, url
):
692 mylist
= self
._call
_api
(list_id
, 'list', {
695 except ExtractorError
as e
:
696 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 401:
697 self
.raise_login_required('You have to be logged in to get your watch history')
699 return self
.playlist_result(self
._entries
(list_id
), list_id
, **self
._parse
_owner
(mylist
))
702 class NicovideoSearchBaseIE(InfoExtractor
):
703 _SEARCH_TYPE
= 'search'
705 def _entries(self
, url
, item_id
, query
=None, note
='Downloading page %(page)s'):
707 pages
= [query
['page']] if 'page' in query
else itertools
.count(1)
708 for page_num
in pages
:
709 query
['page'] = str(page_num
)
710 webpage
= self
._download
_webpage
(url
, item_id
, query
=query
, note
=note
% {'page': page_num}
)
711 results
= re
.findall(r
'(?<=data-video-id=)["\']?
(?P
<videoid
>.*?
)(?
=["\'])', webpage)
713 yield self.url_result(f'http://www.nicovideo.jp/watch/{item}', 'Niconico', item)
717 def _search_results(self, query):
718 return self._entries(
719 self._proto_relative_url(f'//www.nicovideo.jp/{self._SEARCH_TYPE}/{query}'), query)
722 class NicovideoSearchIE(NicovideoSearchBaseIE, SearchInfoExtractor):
723 IE_DESC = 'Nico video search'
724 IE_NAME = 'nicovideo:search'
725 _SEARCH_KEY = 'nicosearch'
728 class NicovideoSearchURLIE(NicovideoSearchBaseIE):
729 IE_NAME = f'{NicovideoSearchIE.IE_NAME}_url'
730 IE_DESC = 'Nico video search URLs'
731 _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/search/(?P<id>[^?#&]+)?'
733 'url': 'http://www.nicovideo.jp/search/sm9',
738 'playlist_mincount': 40,
740 'url': 'https://www.nicovideo.jp/search/sm9?sort=h&order=d&end=2020-12-31&start=2020-01-01',
745 'playlist_count': 31,
748 def _real_extract(self, url):
749 query = self._match_id(url)
750 return self.playlist_result(self._entries(url, query), query, query)
753 class NicovideoSearchDateIE(NicovideoSearchBaseIE, SearchInfoExtractor):
754 IE_DESC = 'Nico video search, newest first'
755 IE_NAME = f'{NicovideoSearchIE.IE_NAME}:date'
756 _SEARCH_KEY = 'nicosearchdate'
758 'url': 'nicosearchdateall:a',
763 'playlist_mincount': 1610,
766 _START_DATE = datetime.date(2007, 1, 1)
767 _RESULTS_PER_PAGE = 32
770 def _entries(self, url, item_id, start_date=None, end_date=None):
771 start_date, end_date = start_date or self._START_DATE, end_date or datetime.datetime.now().date()
773 # If the last page has a full page of videos, we need to break down the query interval further
774 last_page_len = len(list(self._get_entries_for_date(
775 url, item_id, start_date, end_date, self._MAX_PAGES,
776 note=f'Checking number of videos from {start_date} to {end_date}')))
777 if (last_page_len == self._RESULTS_PER_PAGE and start_date != end_date):
778 midpoint = start_date + ((end_date - start_date) // 2)
779 yield from self._entries(url, item_id, midpoint, end_date)
780 yield from self._entries(url, item_id, start_date, midpoint)
782 self.to_screen(f'{item_id}: Downloading results from {start_date} to {end_date}')
783 yield from self._get_entries_for_date(
784 url, item_id, start_date, end_date, note=' Downloading page %(page)s')
786 def _get_entries_for_date(self, url, item_id, start_date, end_date=None, page_num=None, note=None):
788 'start': str(start_date),
789 'end': str(end_date or start_date),
794 query['page'] = str(page_num)
796 yield from super()._entries(url, item_id, query=query, note=note)
799 class NicovideoTagURLIE(NicovideoSearchBaseIE):
800 IE_NAME = 'niconico:tag'
801 IE_DESC = 'NicoNico video tag URLs'
803 _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/tag/(?P<id>[^?#&]+)?'
805 'url': 'https://www.nicovideo.jp/tag/ドキュメンタリー淫夢',
808 'title': 'ドキュメンタリー淫夢'
810 'playlist_mincount': 400,
813 def _real_extract(self, url):
814 query = self._match_id(url)
815 return self.playlist_result(self._entries(url, query), query, query)
818 class NiconicoUserIE(InfoExtractor):
819 _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/user/(?P<id>\d+)/?(?:$|[#?])'
821 'url': 'https://www.nicovideo.jp/user/419948',
825 'playlist_mincount': 101,
827 _API_URL = "https
://nvapi
.nicovideo
.jp
/v1
/users
/%s/videos?sortKey
=registeredAt
&sortOrder
=desc
&pageSize
=%s&page
=%s"
831 'X-Frontend-ID': '6',
832 'X-Frontend-Version': '0'
835 def _entries(self, list_id):
838 while count < total_count:
839 json_parsed = self._download_json(
840 self._API_URL % (list_id, self._PAGE_SIZE, page_num + 1), list_id,
841 headers=self._API_HEADERS,
842 note='Downloading JSON metadata%s' % (' page %d' % page_num if page_num else ''))
844 total_count = int_or_none(json_parsed['data'].get('totalCount'))
845 for entry in json_parsed["data
"]["items
"]:
847 yield self.url_result('https://www.nicovideo.jp/watch/%s' % entry['id'])
850 def _real_extract(self, url):
851 list_id = self._match_id(url)
852 return self.playlist_result(self._entries(list_id), list_id, ie=NiconicoIE.ie_key())