2 from __future__
import unicode_literals
11 from .common
import InfoExtractor
, SearchInfoExtractor
12 from ..compat
import (
14 compat_urllib_parse_urlparse
,
41 class NiconicoIE(InfoExtractor
):
46 'url': 'http://www.nicovideo.jp/watch/sm22312215',
47 'md5': 'd1a75c0823e2f629128c43e1212760f9',
51 'title': 'Big Buck Bunny',
52 'thumbnail': r
're:https?://.*',
53 'uploader': 'takuya0301',
54 'uploader_id': '2698420',
55 'upload_date': '20131123',
56 'timestamp': int, # timestamp is unstable
57 'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
62 'skip': 'Requires an account',
64 # File downloaded with and without credentials are different, so omit
66 'url': 'http://www.nicovideo.jp/watch/nm14296458',
70 'title': '【鏡音リン】Dance on media【オリジナル】take2!',
71 'description': 'md5:689f066d74610b3b22e0f1739add0f58',
72 'thumbnail': r
're:https?://.*',
74 'uploader_id': '18822557',
75 'upload_date': '20110429',
76 'timestamp': 1304065916,
79 'skip': 'Requires an account',
81 # 'video exists but is marked as "deleted"
83 'url': 'http://www.nicovideo.jp/watch/sm10000',
86 'ext': 'unknown_video',
87 'description': 'deleted',
88 'title': 'ドラえもんエターナル第3話「決戦第3新東京市」<前編>',
89 'thumbnail': r
're:https?://.*',
90 'upload_date': '20071224',
91 'timestamp': int, # timestamp field has different value if logged in
95 'skip': 'Requires an account',
97 'url': 'http://www.nicovideo.jp/watch/so22543406',
101 'title': '【第1回】RADIOアニメロミックス ラブライブ!~のぞえりRadio Garden~',
102 'description': 'md5:b27d224bb0ff53d3c8269e9f8b561cf1',
103 'thumbnail': r
're:https?://.*',
104 'timestamp': 1388851200,
105 'upload_date': '20140104',
106 'uploader': 'アニメロチャンネル',
107 'uploader_id': '312',
109 'skip': 'The viewing period of the video you were searching for has expired.',
111 # video not available via `getflv`; "old" HTML5 video
112 'url': 'http://www.nicovideo.jp/watch/sm1151009',
113 'md5': '8fa81c364eb619d4085354eab075598a',
117 '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)',
118 'description': 'md5:6ee077e0581ff5019773e2e714cdd0b7',
119 'thumbnail': r
're:https?://.*',
121 'timestamp': 1190868283,
122 'upload_date': '20070927',
123 'uploader': 'denden2',
124 'uploader_id': '1392194',
126 'comment_count': int,
128 'skip': 'Requires an account',
132 'url': 'http://www.nicovideo.jp/watch/sm31464864',
136 'title': '新作TVアニメ「戦姫絶唱シンフォギアAXZ」PV 最高画質',
137 'description': 'md5:e52974af9a96e739196b2c1ca72b5feb',
138 'timestamp': 1498514060,
139 'upload_date': '20170626',
141 'uploader_id': '40826363',
142 'thumbnail': r
're:https?://.*',
145 'comment_count': int,
147 'skip': 'Requires an account',
149 # Video without owner
150 'url': 'http://www.nicovideo.jp/watch/sm18238488',
151 'md5': 'd265680a1f92bdcbbd2a507fc9e78a9e',
155 'title': '【実写版】ミュータントタートルズ',
156 'description': 'md5:15df8988e47a86f9e978af2064bf6d8e',
157 'timestamp': 1341160408,
158 'upload_date': '20120701',
161 'thumbnail': r
're:https?://.*',
164 'comment_count': int,
166 'skip': 'Requires an account',
168 'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
169 'only_matching': True,
171 'note': 'a video that is only served as an ENCRYPTED HLS.',
172 'url': 'https://www.nicovideo.jp/watch/so38016254',
173 'only_matching': True,
176 _VALID_URL
= r
'https?://(?:(?:www\.|secure\.|sp\.)?nicovideo\.jp/watch|nico\.ms)/(?P<id>(?:[a-z]{2})?[0-9]+)'
177 _NETRC_MACHINE
= 'niconico'
178 _COMMENT_API_ENDPOINTS
= (
179 'https://nvcomment.nicovideo.jp/legacy/api.json',
180 'https://nmsg.nicovideo.jp/api.json',)
182 'X-Frontend-ID': '6',
183 'X-Frontend-Version': '0',
184 'X-Niconico-Language': 'en-us',
185 'Referer': 'https://www.nicovideo.jp/',
186 'Origin': 'https://www.nicovideo.jp',
189 def _perform_login(self
, username
, password
):
192 'mail_tel': username
,
193 'password': password
,
195 self
._request
_webpage
(
196 'https://account.nicovideo.jp/login', None,
197 note
='Acquiring Login session')
198 urlh
= self
._request
_webpage
(
199 'https://account.nicovideo.jp/login/redirector?show_button_twitter=1&site=niconico&show_button_facebook=1', None,
200 note
='Logging in', errnote
='Unable to log in',
201 data
=urlencode_postdata(login_form_strs
),
203 'Referer': 'https://account.nicovideo.jp/login',
204 'Content-Type': 'application/x-www-form-urlencoded',
209 parts
= compat_urllib_parse_urlparse(urlh
.geturl())
210 if compat_parse_qs(parts
.query
).get('message', [None])[0] == 'cant_login':
213 self
.report_warning('unable to log in: bad username or password')
216 def _get_heartbeat_info(self
, info_dict
):
217 video_id
, video_src_id
, audio_src_id
= info_dict
['url'].split(':')[1].split('/')
218 dmc_protocol
= info_dict
['_expected_protocol']
221 info_dict
.get('_api_data')
223 self
._html
_search
_regex
(
224 'data-api-data="([^"]+)"',
225 self
._download
_webpage
('http://www.nicovideo.jp/watch/' + video_id
, video_id
),
226 'API data', default
='{}'),
229 session_api_data
= try_get(api_data
, lambda x
: x
['media']['delivery']['movie']['session'])
230 session_api_endpoint
= try_get(session_api_data
, lambda x
: x
['urls'][0])
233 tracking_id
= traverse_obj(api_data
, ('media', 'delivery', 'trackingId'))
235 tracking_url
= update_url_query('https://nvapi.nicovideo.jp/v1/2ab0cbaa/watch', {'t': tracking_id}
)
236 watch_request_response
= self
._download
_json
(
237 tracking_url
, video_id
,
238 note
='Acquiring permission for downloading video', fatal
=False,
239 headers
=self
._API
_HEADERS
)
240 if traverse_obj(watch_request_response
, ('meta', 'status')) != 200:
241 self
.report_warning('Failed to acquire permission for playing video. Video download may fail.')
243 yesno
= lambda x
: 'yes' if x
else 'no'
245 if dmc_protocol
== 'http':
247 protocol_parameters
= {
248 'http_output_download_parameters': {
249 'use_ssl': yesno(session_api_data
['urls'][0]['isSsl']),
250 'use_well_known_port': yesno(session_api_data
['urls'][0]['isWellKnownPort']),
253 elif dmc_protocol
== 'hls':
255 segment_duration
= try_get(self
._configuration
_arg
('segment_duration'), lambda x
: int(x
[0])) or 6000
256 parsed_token
= self
._parse
_json
(session_api_data
['token'], video_id
)
257 encryption
= traverse_obj(api_data
, ('media', 'delivery', 'encryption'))
258 protocol_parameters
= {
260 'segment_duration': segment_duration
,
261 'transfer_preset': '',
262 'use_ssl': yesno(session_api_data
['urls'][0]['isSsl']),
263 'use_well_known_port': yesno(session_api_data
['urls'][0]['isWellKnownPort']),
266 if 'hls_encryption' in parsed_token
and encryption
:
267 protocol_parameters
['hls_parameters']['encryption'] = {
268 parsed_token
['hls_encryption']: {
269 'encrypted_key': encryption
['encryptedKey'],
270 'key_uri': encryption
['keyUri'],
274 protocol
= 'm3u8_native'
276 raise ExtractorError(f
'Unsupported DMC protocol: {dmc_protocol}')
278 session_response
= self
._download
_json
(
279 session_api_endpoint
['url'], video_id
,
280 query
={'_format': 'json'}
,
281 headers
={'Content-Type': 'application/json'}
,
282 note
='Downloading JSON metadata for %s' % info_dict
['format_id'],
286 'player_id': session_api_data
.get('playerId'),
289 'auth_type': try_get(session_api_data
, lambda x
: x
['authTypes'][session_api_data
['protocols'][0]]),
290 'content_key_timeout': session_api_data
.get('contentKeyTimeout'),
291 'service_id': 'nicovideo',
292 'service_user_id': session_api_data
.get('serviceUserId')
294 'content_id': session_api_data
.get('contentId'),
295 'content_src_id_sets': [{
296 'content_src_ids': [{
298 'audio_src_ids': [audio_src_id
],
299 'video_src_ids': [video_src_id
],
303 'content_type': 'movie',
307 'lifetime': session_api_data
.get('heartbeatLifetime')
310 'priority': session_api_data
['priority'],
315 'parameters': protocol_parameters
319 'recipe_id': session_api_data
.get('recipeId'),
320 'session_operation_auth': {
321 'session_operation_auth_by_signature': {
322 'signature': session_api_data
.get('signature'),
323 'token': session_api_data
.get('token'),
326 'timing_constraint': 'unlimited'
330 info_dict
['url'] = session_response
['data']['session']['content_uri']
331 info_dict
['protocol'] = protocol
334 heartbeat_info_dict
= {
335 'url': session_api_endpoint
['url'] + '/' + session_response
['data']['session']['id'] + '?_format=json&_method=PUT',
336 'data': json
.dumps(session_response
['data']),
337 # interval, convert milliseconds to seconds, then halve to make a buffer.
338 'interval': float_or_none(session_api_data
.get('heartbeatLifetime'), scale
=3000),
342 return info_dict
, heartbeat_info_dict
344 def _extract_format_for_quality(self
, video_id
, audio_quality
, video_quality
, dmc_protocol
):
346 if not audio_quality
.get('isAvailable') or not video_quality
.get('isAvailable'):
349 def extract_video_quality(video_quality
):
350 return parse_filesize('%sB' % self
._search
_regex
(
351 r
'\| ([0-9]*\.?[0-9]*[MK])', video_quality
, 'vbr', default
=''))
353 format_id
= '-'.join(
354 [remove_start(s
['id'], 'archive_') for s
in (video_quality
, audio_quality
)] + [dmc_protocol
])
356 vid_qual_label
= traverse_obj(video_quality
, ('metadata', 'label'))
357 vid_quality
= traverse_obj(video_quality
, ('metadata', 'bitrate'))
360 'url': 'niconico_dmc:%s/%s/%s' % (video_id
, video_quality
['id'], audio_quality
['id']),
361 'format_id': format_id
,
362 'format_note': join_nonempty('DMC', vid_qual_label
, dmc_protocol
.upper(), delim
=' '),
363 'ext': 'mp4', # Session API are used in HTML5, which always serves mp4
366 'abr': float_or_none(traverse_obj(audio_quality
, ('metadata', 'bitrate')), 1000),
367 'vbr': float_or_none(vid_quality
if vid_quality
> 0 else extract_video_quality(vid_qual_label
), 1000),
368 'height': traverse_obj(video_quality
, ('metadata', 'resolution', 'height')),
369 'width': traverse_obj(video_quality
, ('metadata', 'resolution', 'width')),
370 'quality': -2 if 'low' in video_quality
['id'] else None,
371 'protocol': 'niconico_dmc',
372 '_expected_protocol': dmc_protocol
,
374 'Origin': 'https://www.nicovideo.jp',
375 'Referer': 'https://www.nicovideo.jp/watch/' + video_id
,
379 def _real_extract(self
, url
):
380 video_id
= self
._match
_id
(url
)
383 webpage
, handle
= self
._download
_webpage
_handle
(
384 'http://www.nicovideo.jp/watch/' + video_id
, video_id
)
385 if video_id
.startswith('so'):
386 video_id
= self
._match
_id
(handle
.geturl())
388 api_data
= self
._parse
_json
(self
._html
_search
_regex
(
389 'data-api-data="([^"]+)"', webpage
,
390 'API data', default
='{}'), video_id
)
391 except ExtractorError
as e
:
393 api_data
= self
._download
_json
(
394 'https://www.nicovideo.jp/api/watch/v3/%s?_frontendId=6&_frontendVersion=0&actionTrackId=AAAAAAAAAA_%d' % (video_id
, round(time
.time() * 1000)), video_id
,
395 note
='Downloading API JSON', errnote
='Unable to fetch data')['data']
396 except ExtractorError
:
397 if not isinstance(e
.cause
, compat_HTTPError
):
399 webpage
= e
.cause
.read().decode('utf-8', 'replace')
400 error_msg
= self
._html
_search
_regex
(
401 r
'(?s)<section\s+class="(?:(?:ErrorMessage|WatchExceptionPage-message)\s*)+">(.+?)</section>',
402 webpage
, 'error reason', default
=None)
405 raise ExtractorError(re
.sub(r
'\s+', ' ', error_msg
), expected
=True)
409 def get_video_info(*items
, get_first
=True, **kwargs
):
410 return traverse_obj(api_data
, ('video', *items
), get_all
=not get_first
, **kwargs
)
412 quality_info
= api_data
['media']['delivery']['movie']
413 session_api_data
= quality_info
['session']
414 for (audio_quality
, video_quality
, protocol
) in itertools
.product(quality_info
['audios'], quality_info
['videos'], session_api_data
['protocols']):
415 fmt
= self
._extract
_format
_for
_quality
(video_id
, audio_quality
, video_quality
, protocol
)
419 self
._sort
_formats
(formats
)
421 # Start extracting information
424 # use og:video:tag (not logged in)
425 og_video_tags
= re
.finditer(r
'<meta\s+property="og:video:tag"\s*content="(.*?)">', webpage
)
426 tags
= list(filter(None, (clean_html(x
.group(1)) for x
in og_video_tags
)))
428 # use keywords and split with comma (not logged in)
429 kwds
= self
._html
_search
_meta
('keywords', webpage
, default
=None)
431 tags
= [x
for x
in kwds
.split(',') if x
]
433 # find in json (logged in)
434 tags
= traverse_obj(api_data
, ('tag', 'items', ..., 'name'))
436 thumb_prefs
= qualities(['url', 'middleUrl', 'largeUrl', 'player', 'ogp'])
440 '_api_data': api_data
,
441 'title': get_video_info(('originalTitle', 'title')) or self
._og
_search
_title
(webpage
, default
=None),
447 'preference': thumb_prefs(key
),
448 **parse_resolution(url
, lenient
=True),
449 } for key
, url
in (get_video_info('thumbnail') or {}).items() if url
],
450 'description': clean_html(get_video_info('description')),
451 'uploader': traverse_obj(api_data
, ('owner', 'nickname'), ('channel', 'name'), ('community', 'name')),
452 'uploader_id': str_or_none(traverse_obj(api_data
, ('owner', 'id'), ('channel', 'id'), ('community', 'id'))),
453 'timestamp': parse_iso8601(get_video_info('registeredAt')) or parse_iso8601(
454 self
._html
_search
_meta
('video:release_date', webpage
, 'date published', default
=None)),
455 'channel': traverse_obj(api_data
, ('channel', 'name'), ('community', 'name')),
456 'channel_id': traverse_obj(api_data
, ('channel', 'id'), ('community', 'id')),
457 'view_count': int_or_none(get_video_info('count', 'view')),
459 'genre': traverse_obj(api_data
, ('genre', 'label'), ('genre', 'key')),
460 'comment_count': get_video_info('count', 'comment', expected_type
=int),
462 parse_duration(self
._html
_search
_meta
('video:duration', webpage
, 'video duration', default
=None))
463 or get_video_info('duration')),
464 'webpage_url': url_or_none(url
) or f
'https://www.nicovideo.jp/watch/{video_id}',
465 'subtitles': self
.extract_subtitles(video_id
, api_data
, session_api_data
),
468 def _get_subtitles(self
, video_id
, api_data
, session_api_data
):
469 comment_user_key
= traverse_obj(api_data
, ('comment', 'keys', 'userKey'))
470 user_id_str
= session_api_data
.get('serviceUserId')
472 thread_ids
= [x
for x
in traverse_obj(api_data
, ('comment', 'threads')) or [] if x
['isActive']]
473 raw_danmaku
= self
._extract
_all
_comments
(video_id
, thread_ids
, user_id_str
, comment_user_key
)
475 self
.report_warning(f
'Failed to get comments. {bug_reports_message()}')
480 'data': json
.dumps(raw_danmaku
),
484 def _extract_all_comments(self
, video_id
, threads
, user_id
, user_key
):
488 } if user_id
and user_key
else {'user_id': ''}
491 post_data
= [{'ping': {'content': 'rs:0'}
}]
492 for i
, thread
in enumerate(threads
):
493 thread_id
= thread
['id']
494 thread_fork
= thread
['fork']
496 post_data
.append({'ping': {'content': f'ps:{i * 2}
'}})
497 post_data.append({'thread
': {
503 'version
': '20090904',
508 post_data.append({'ping': {'content': f'pf:{i * 2}'}})
511 post_data
.append({'ping': {'content': f'ps:{i * 2 + 1}
'}})
512 post_data.append({'thread_leaves
': {
513 # format is '<bottom of minute
range>-<top of minute
range>:<comments per minute
>,<total last comments
'
514 # unfortunately NND limits (deletes?) comment returns this way, so you're only able to grab the last
1000 per language
515 'content': '0-999999:999999,999999,nicoru:999999',
524 post_data
.append({'ping': {'content': f'pf:{i * 2 + 1}
'}})
526 post_data.append({'ping': {'content': 'rf:0'}})
528 for api_url in self._COMMENT_API_ENDPOINTS:
529 comments = self._download_json(
530 api_url, video_id, data=json.dumps(post_data).encode(), fatal=False,
532 'Referer
': 'https
://www
.nicovideo
.jp
/watch
/%s' % video_id,
533 'Origin
': 'https
://www
.nicovideo
.jp
',
534 'Content
-Type
': 'text
/plain
;charset
=UTF
-8',
536 note='Downloading comments
', errnote=f'Failed to access endpoint {api_url}
')
541 class NiconicoPlaylistBaseIE(InfoExtractor):
545 'X
-Frontend
-ID
': '6',
546 'X
-Frontend
-Version
': '0',
547 'X
-Niconico
-Language
': 'en
-us
'
550 def _call_api(self, list_id, resource, query):
551 "Implement this in child class"
555 def _parse_owner(item):
557 'uploader
': traverse_obj(item, ('owner
', 'name
')),
558 'uploader_id
': traverse_obj(item, ('owner
', 'id')),
561 def _fetch_page(self, list_id, page):
563 resp = self._call_api(list_id, 'page
%d' % page, {
565 'pageSize
': self._PAGE_SIZE,
567 # this is needed to support both mylist and user
568 for video in traverse_obj(resp, ('items
', ..., ('video
', None))) or []:
569 video_id = video.get('id')
571 # skip {"video": {"id": "blablabla", ...}}
573 count = video.get('count
') or {}
574 get_count = lambda x: int_or_none(count.get(x))
578 'title
': video.get('title
'),
579 'url
': f'https
://www
.nicovideo
.jp
/watch
/{video_id}
',
580 'description
': video.get('shortDescription
'),
581 'duration
': int_or_none(video.get('duration
')),
582 'view_count
': get_count('view
'),
583 'comment_count
': get_count('comment
'),
584 'thumbnail
': traverse_obj(video, ('thumbnail
', ('nHdUrl
', 'largeUrl
', 'listingUrl
', 'url
'))),
585 'ie_key
': NiconicoIE.ie_key(),
586 **self._parse_owner(video),
589 def _entries(self, list_id):
590 return OnDemandPagedList(functools.partial(self._fetch_page, list_id), self._PAGE_SIZE)
593 class NiconicoPlaylistIE(NiconicoPlaylistBaseIE):
594 IE_NAME = 'niconico
:playlist
'
595 _VALID_URL = r'https?
://(?
:(?
:www\
.|sp\
.)?nicovideo\
.jp|nico\
.ms
)/(?
:user
/\d
+/)?
(?
:my
/)?mylist
/(?
:#/)?(?P<id>\d+)'
598 'url': 'http://www.nicovideo.jp/mylist/27411728',
601 'title': 'AKB48のオールナイトニッポン',
602 'description': 'md5:d89694c5ded4b6c693dea2db6e41aa08',
604 'uploader_id': '805442',
606 'playlist_mincount': 291,
608 'url': 'https://www.nicovideo.jp/user/805442/mylist/27411728',
609 'only_matching': True,
611 'url': 'https://www.nicovideo.jp/my/mylist/#/68048635',
612 'only_matching': True,
615 def _call_api(self
, list_id
, resource
, query
):
616 return self
._download
_json
(
617 f
'https://nvapi.nicovideo.jp/v2/mylists/{list_id}', list_id
,
618 f
'Downloading {resource}', query
=query
,
619 headers
=self
._API
_HEADERS
)['data']['mylist']
621 def _real_extract(self
, url
):
622 list_id
= self
._match
_id
(url
)
623 mylist
= self
._call
_api
(list_id
, 'list', {
626 return self
.playlist_result(
627 self
._entries
(list_id
), list_id
,
628 mylist
.get('name'), mylist
.get('description'), **self
._parse
_owner
(mylist
))
631 class NiconicoSeriesIE(InfoExtractor
):
632 IE_NAME
= 'niconico:series'
633 _VALID_URL
= r
'https?://(?:(?:www\.|sp\.)?nicovideo\.jp|nico\.ms)/series/(?P<id>\d+)'
636 'url': 'https://www.nicovideo.jp/series/110226',
639 'title': 'ご立派ァ!のシリーズ',
641 'playlist_mincount': 10, # as of 2021/03/17
643 'url': 'https://www.nicovideo.jp/series/12312/',
646 'title': 'バトルスピリッツ お勧めカード紹介(調整中)',
648 'playlist_mincount': 97, # as of 2021/03/17
650 'url': 'https://nico.ms/series/203559',
651 'only_matching': True,
654 def _real_extract(self
, url
):
655 list_id
= self
._match
_id
(url
)
656 webpage
= self
._download
_webpage
(f
'https://www.nicovideo.jp/series/{list_id}', list_id
)
658 title
= self
._search
_regex
(
660 r
'<div class="TwitterShareButton"\s+data-text="(.+)\s+https:'),
661 webpage
, 'title', fatal
=False)
663 title
= unescapeHTML(title
)
665 self
.url_result(f
'https://www.nicovideo.jp/watch/{v_id}', video_id
=v_id
)
666 for v_id
in re
.findall(r
'href="/watch/([a-z0-9]+)" data-href="/watch/\1', webpage
)]
667 return self
.playlist_result(playlist
, list_id
, title
)
670 class NiconicoHistoryIE(NiconicoPlaylistBaseIE
):
671 IE_NAME
= 'niconico:history'
672 IE_DESC
= 'NicoNico user history. Requires cookies.'
673 _VALID_URL
= r
'https?://(?:www\.|sp\.)?nicovideo\.jp/my/history'
676 'note': 'PC page, with /video',
677 'url': 'https://www.nicovideo.jp/my/history/video',
678 'only_matching': True,
680 'note': 'PC page, without /video',
681 'url': 'https://www.nicovideo.jp/my/history',
682 'only_matching': True,
684 'note': 'mobile page, with /video',
685 'url': 'https://sp.nicovideo.jp/my/history/video',
686 'only_matching': True,
688 'note': 'mobile page, without /video',
689 'url': 'https://sp.nicovideo.jp/my/history',
690 'only_matching': True,
693 def _call_api(self
, list_id
, resource
, query
):
694 return self
._download
_json
(
695 'https://nvapi.nicovideo.jp/v1/users/me/watch/history', 'history',
696 f
'Downloading {resource}', query
=query
,
697 headers
=self
._API
_HEADERS
)['data']
699 def _real_extract(self
, url
):
702 mylist
= self
._call
_api
(list_id
, 'list', {
705 except ExtractorError
as e
:
706 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 401:
707 self
.raise_login_required('You have to be logged in to get your watch history')
709 return self
.playlist_result(self
._entries
(list_id
), list_id
, **self
._parse
_owner
(mylist
))
712 class NicovideoSearchBaseIE(InfoExtractor
):
713 _SEARCH_TYPE
= 'search'
715 def _entries(self
, url
, item_id
, query
=None, note
='Downloading page %(page)s'):
717 pages
= [query
['page']] if 'page' in query
else itertools
.count(1)
718 for page_num
in pages
:
719 query
['page'] = str(page_num
)
720 webpage
= self
._download
_webpage
(url
, item_id
, query
=query
, note
=note
% {'page': page_num}
)
721 results
= re
.findall(r
'(?<=data-video-id=)["\']?
(?P
<videoid
>.*?
)(?
=["\'])', webpage)
723 yield self.url_result(f'http://www.nicovideo.jp/watch/{item}', 'Niconico', item)
727 def _search_results(self, query):
728 return self._entries(
729 self._proto_relative_url(f'//www.nicovideo.jp/{self._SEARCH_TYPE}/{query}'), query)
732 class NicovideoSearchIE(NicovideoSearchBaseIE, SearchInfoExtractor):
733 IE_DESC = 'Nico video search'
734 IE_NAME = 'nicovideo:search'
735 _SEARCH_KEY = 'nicosearch'
738 class NicovideoSearchURLIE(NicovideoSearchBaseIE):
739 IE_NAME = f'{NicovideoSearchIE.IE_NAME}_url'
740 IE_DESC = 'Nico video search URLs'
741 _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/search/(?P<id>[^?#&]+)?'
743 'url': 'http://www.nicovideo.jp/search/sm9',
748 'playlist_mincount': 40,
750 'url': 'https://www.nicovideo.jp/search/sm9?sort=h&order=d&end=2020-12-31&start=2020-01-01',
755 'playlist_count': 31,
758 def _real_extract(self, url):
759 query = self._match_id(url)
760 return self.playlist_result(self._entries(url, query), query, query)
763 class NicovideoSearchDateIE(NicovideoSearchBaseIE, SearchInfoExtractor):
764 IE_DESC = 'Nico video search, newest first'
765 IE_NAME = f'{NicovideoSearchIE.IE_NAME}:date'
766 _SEARCH_KEY = 'nicosearchdate'
768 'url': 'nicosearchdateall:a',
773 'playlist_mincount': 1610,
776 _START_DATE = datetime.date(2007, 1, 1)
777 _RESULTS_PER_PAGE = 32
780 def _entries(self, url, item_id, start_date=None, end_date=None):
781 start_date, end_date = start_date or self._START_DATE, end_date or datetime.datetime.now().date()
783 # If the last page has a full page of videos, we need to break down the query interval further
784 last_page_len = len(list(self._get_entries_for_date(
785 url, item_id, start_date, end_date, self._MAX_PAGES,
786 note=f'Checking number of videos from {start_date} to {end_date}')))
787 if (last_page_len == self._RESULTS_PER_PAGE and start_date != end_date):
788 midpoint = start_date + ((end_date - start_date) // 2)
789 yield from self._entries(url, item_id, midpoint, end_date)
790 yield from self._entries(url, item_id, start_date, midpoint)
792 self.to_screen(f'{item_id}: Downloading results from {start_date} to {end_date}')
793 yield from self._get_entries_for_date(
794 url, item_id, start_date, end_date, note=' Downloading page %(page)s')
796 def _get_entries_for_date(self, url, item_id, start_date, end_date=None, page_num=None, note=None):
798 'start': str(start_date),
799 'end': str(end_date or start_date),
804 query['page'] = str(page_num)
806 yield from super()._entries(url, item_id, query=query, note=note)
809 class NicovideoTagURLIE(NicovideoSearchBaseIE):
810 IE_NAME = 'niconico:tag'
811 IE_DESC = 'NicoNico video tag URLs'
813 _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/tag/(?P<id>[^?#&]+)?'
815 'url': 'https://www.nicovideo.jp/tag/ドキュメンタリー淫夢',
818 'title': 'ドキュメンタリー淫夢'
820 'playlist_mincount': 400,
823 def _real_extract(self, url):
824 query = self._match_id(url)
825 return self.playlist_result(self._entries(url, query), query, query)
828 class NiconicoUserIE(InfoExtractor):
829 _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/user/(?P<id>\d+)/?(?:$|[#?])'
831 'url': 'https://www.nicovideo.jp/user/419948',
835 'playlist_mincount': 101,
837 _API_URL = "https
://nvapi
.nicovideo
.jp
/v1
/users
/%s/videos?sortKey
=registeredAt
&sortOrder
=desc
&pageSize
=%s&page
=%s"
841 'X-Frontend-ID': '6',
842 'X-Frontend-Version': '0'
845 def _entries(self, list_id):
848 while count < total_count:
849 json_parsed = self._download_json(
850 self._API_URL % (list_id, self._PAGE_SIZE, page_num + 1), list_id,
851 headers=self._API_HEADERS,
852 note='Downloading JSON metadata%s' % (' page %d' % page_num if page_num else ''))
854 total_count = int_or_none(json_parsed['data'].get('totalCount'))
855 for entry in json_parsed["data
"]["items
"]:
857 yield self.url_result('https://www.nicovideo.jp/watch/%s' % entry['id'])
860 def _real_extract(self, url):
861 list_id = self._match_id(url)
862 return self.playlist_result(self._entries(list_id), list_id, ie=NiconicoIE.ie_key())