etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 03:33:02 +00:00
Code Issues Projects Releases Wiki Activity

[ie/niconico] Support DMS formats (#9282)

Browse source 
Closes #8389, Closes #8758, Closes #9254
Authored by: pzhlkj6612, xpadev-net
This commit is contained in:
Mozi 2024-02-29 22:55:44 +00:00 committed by GitHub
parent 8f423cf805
commit aa13a8e3dd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 113 additions and 45 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

158
yt_dlp/extractor/niconico.py
View file

@ -13,13 +13,11 @@
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
OnDemandPagedList, OnDemandPagedList,
bug_reports_message,
clean_html, clean_html,
float_or_none, float_or_none,
int_or_none, int_or_none,
join_nonempty, join_nonempty,
parse_duration, parse_duration,
parse_filesize,
parse_iso8601, parse_iso8601,
parse_resolution, parse_resolution,
qualities, qualities,
@ -55,25 +53,31 @@ class NiconicoIE(InfoExtractor):
'duration': 33, 'duration': 33,
'view_count': int, 'view_count': int,
'comment_count': int, 'comment_count': int,
'genres': ['未設定'],
'tags': [],
'expected_protocol': str,
}, },
'skip': 'Requires an account',
}, { }, {
# File downloaded with and without credentials are different, so omit # File downloaded with and without credentials are different, so omit
# the md5 field # the md5 field
'url': 'http://www.nicovideo.jp/watch/nm14296458', 'url': 'http://www.nicovideo.jp/watch/nm14296458',
'info_dict': { 'info_dict': {
'id': 'nm14296458', 'id': 'nm14296458',
'ext': 'swf', 'ext': 'mp4',
'title': '【鏡音リン】Dance on media【オリジナル】take2!', 'title': '【Kagamine Rin】Dance on media【Original】take2!',
'description': 'md5:689f066d74610b3b22e0f1739add0f58', 'description': 'md5:9368f2b1f4178de64f2602c2f3d6cbf5',
'thumbnail': r're:https?://.*', 'thumbnail': r're:https?://.*',
'uploader': 'りょうた', 'uploader': 'りょうた',
'uploader_id': '18822557', 'uploader_id': '18822557',
'upload_date': '20110429', 'upload_date': '20110429',
'timestamp': 1304065916, 'timestamp': 1304065916,
'duration': 209, 'duration': 208.0,
'comment_count': int,
'view_count': int,
'genres': ['音楽・サウンド'],
'tags': ['Translation_Request', 'Kagamine_Rin', 'Rin_Original'],
'expected_protocol': str,
}, },
'skip': 'Requires an account',
}, { }, {
# 'video exists but is marked as "deleted" # 'video exists but is marked as "deleted"
# md5 is unstable # md5 is unstable
@ -107,22 +111,24 @@ class NiconicoIE(InfoExtractor):
}, { }, {
# video not available via `getflv`; "old" HTML5 video # video not available via `getflv`; "old" HTML5 video
'url': 'http://www.nicovideo.jp/watch/sm1151009', 'url': 'http://www.nicovideo.jp/watch/sm1151009',
'md5': '8fa81c364eb619d4085354eab075598a', 'md5': 'f95a3d259172667b293530cc2e41ebda',
'info_dict': { 'info_dict': {
'id': 'sm1151009', 'id': 'sm1151009',
'ext': 'mp4', 'ext': 'mp4',
'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）', '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）',
'description': 'md5:6ee077e0581ff5019773e2e714cdd0b7', 'description': 'md5:f95a3d259172667b293530cc2e41ebda',
'thumbnail': r're:https?://.*', 'thumbnail': r're:https?://.*',
'duration': 184, 'duration': 184,
'timestamp': 1190868283, 'timestamp': 1190835883,
'upload_date': '20070927', 'upload_date': '20070926',
'uploader': 'denden2', 'uploader': 'denden2',
'uploader_id': '1392194', 'uploader_id': '1392194',
'view_count': int, 'view_count': int,
'comment_count': int, 'comment_count': int,
'genres': ['ゲーム'],
'tags': [],
'expected_protocol': str,
}, },
'skip': 'Requires an account',
}, { }, {
# "New" HTML5 video # "New" HTML5 video
# md5 is unstable # md5 is unstable
@ -132,16 +138,18 @@ class NiconicoIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': '新作TVアニメ「戦姫絶唱シンフォギアAXZ」PV 最高画質', 'title': '新作TVアニメ「戦姫絶唱シンフォギアAXZ」PV 最高画質',
'description': 'md5:e52974af9a96e739196b2c1ca72b5feb', 'description': 'md5:e52974af9a96e739196b2c1ca72b5feb',
'timestamp': 1498514060, 'timestamp': 1498481660,
'upload_date': '20170626', 'upload_date': '20170626',
'uploader': 'ゲスト', 'uploader': 'no-namamae',
'uploader_id': '40826363', 'uploader_id': '40826363',
'thumbnail': r're:https?://.*', 'thumbnail': r're:https?://.*',
'duration': 198, 'duration': 198,
'view_count': int, 'view_count': int,
'comment_count': int, 'comment_count': int,
'genres': ['アニメ'],
'tags': [],
'expected_protocol': str,
}, },
'skip': 'Requires an account',
}, { }, {
# Video without owner # Video without owner
'url': 'http://www.nicovideo.jp/watch/sm18238488', 'url': 'http://www.nicovideo.jp/watch/sm18238488',
@ -151,7 +159,7 @@ class NiconicoIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': '【実写版】ミュータントタートルズ', 'title': '【実写版】ミュータントタートルズ',
'description': 'md5:15df8988e47a86f9e978af2064bf6d8e', 'description': 'md5:15df8988e47a86f9e978af2064bf6d8e',
'timestamp': 1341160408, 'timestamp': 1341128008,
'upload_date': '20120701', 'upload_date': '20120701',
'uploader': None, 'uploader': None,
'uploader_id': None, 'uploader_id': None,
@ -159,8 +167,10 @@ class NiconicoIE(InfoExtractor):
'duration': 5271, 'duration': 5271,
'view_count': int, 'view_count': int,
'comment_count': int, 'comment_count': int,
'genres': ['エンターテイメント'],
'tags': [],
'expected_protocol': str,
}, },
'skip': 'Requires an account',
}, { }, {
'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg', 'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
'only_matching': True, 'only_matching': True,
@ -353,15 +363,10 @@ def _extract_format_for_quality(self, video_id, audio_quality, video_quality, dm
if not audio_quality.get('isAvailable') or not video_quality.get('isAvailable'): if not audio_quality.get('isAvailable') or not video_quality.get('isAvailable'):
return None return None
def extract_video_quality(video_quality):
return parse_filesize('%sB' % self._search_regex(
r'\| ([0-9]*\.?[0-9]*[MK])', video_quality, 'vbr', default=''))
format_id = '-'.join( format_id = '-'.join(
[remove_start(s['id'], 'archive_') for s in (video_quality, audio_quality)] + [dmc_protocol]) [remove_start(s['id'], 'archive_') for s in (video_quality, audio_quality)] + [dmc_protocol])
vid_qual_label = traverse_obj(video_quality, ('metadata', 'label')) vid_qual_label = traverse_obj(video_quality, ('metadata', 'label'))
vid_quality = traverse_obj(video_quality, ('metadata', 'bitrate'))
return { return {
'url': 'niconico_dmc:%s/%s/%s' % (video_id, video_quality['id'], audio_quality['id']), 'url': 'niconico_dmc:%s/%s/%s' % (video_id, video_quality['id'], audio_quality['id']),
@ -370,10 +375,15 @@ def extract_video_quality(video_quality):
'ext': 'mp4', # Session API are used in HTML5, which always serves mp4 'ext': 'mp4', # Session API are used in HTML5, which always serves mp4
'acodec': 'aac', 'acodec': 'aac',
'vcodec': 'h264', 'vcodec': 'h264',
'abr': float_or_none(traverse_obj(audio_quality, ('metadata', 'bitrate')), 1000), **traverse_obj(audio_quality, ('metadata', {
'vbr': float_or_none(vid_quality if vid_quality > 0 else extract_video_quality(vid_qual_label), 1000), 'abr': ('bitrate', {functools.partial(float_or_none, scale=1000)}),
'height': traverse_obj(video_quality, ('metadata', 'resolution', 'height')), 'asr': ('samplingRate', {int_or_none}),
'width': traverse_obj(video_quality, ('metadata', 'resolution', 'width')), })),
**traverse_obj(video_quality, ('metadata', {
'vbr': ('bitrate', {functools.partial(float_or_none, scale=1000)}),
'height': ('resolution', 'height', {int_or_none}),
'width': ('resolution', 'width', {int_or_none}),
})),
'quality': -2 if 'low' in video_quality['id'] else None, 'quality': -2 if 'low' in video_quality['id'] else None,
'protocol': 'niconico_dmc', 'protocol': 'niconico_dmc',
'expected_protocol': dmc_protocol, # XXX: This is not a documented field 'expected_protocol': dmc_protocol, # XXX: This is not a documented field
@ -383,6 +393,63 @@ def extract_video_quality(video_quality):
} }
} }
def _yield_dmc_formats(self, api_data, video_id):
dmc_data = traverse_obj(api_data, ('media', 'delivery', 'movie'))
audios = traverse_obj(dmc_data, ('audios', ..., {dict}))
videos = traverse_obj(dmc_data, ('videos', ..., {dict}))
protocols = traverse_obj(dmc_data, ('session', 'protocols', ..., {str}))
if not all((audios, videos, protocols)):
return
for audio_quality, video_quality, protocol in itertools.product(audios, videos, protocols):
if fmt := self._extract_format_for_quality(video_id, audio_quality, video_quality, protocol):
yield fmt
def _yield_dms_formats(self, api_data, video_id):
fmt_filter = lambda _, v: v['isAvailable'] and v['id']
videos = traverse_obj(api_data, ('media', 'domand', 'videos', fmt_filter))
audios = traverse_obj(api_data, ('media', 'domand', 'audios', fmt_filter))
access_key = traverse_obj(api_data, ('media', 'domand', 'accessRightKey', {str}))
track_id = traverse_obj(api_data, ('client', 'watchTrackId', {str}))
if not all((videos, audios, access_key, track_id)):
return
dms_m3u8_url = self._download_json(
f'https://nvapi.nicovideo.jp/v1/watch/{video_id}/access-rights/hls', video_id,
data=json.dumps({
'outputs': list(itertools.product((v['id'] for v in videos), (a['id'] for a in audios)))
}).encode(), query={'actionTrackId': track_id}, headers={
'x-access-right-key': access_key,
'x-frontend-id': 6,
'x-frontend-version': 0,
'x-request-with': 'https://www.nicovideo.jp',
})['data']['contentUrl']
# Getting all audio formats results in duplicate video formats which we filter out later
dms_fmts = self._extract_m3u8_formats(dms_m3u8_url, video_id)
# m3u8 extraction does not provide audio bitrates, so extract from the API data and fix
for audio_fmt in traverse_obj(dms_fmts, lambda _, v: v['vcodec'] == 'none'):
yield {
**audio_fmt,
**traverse_obj(audios, (lambda _, v: audio_fmt['format_id'].startswith(v['id']), {
'format_id': ('id', {str}),
'abr': ('bitRate', {functools.partial(float_or_none, scale=1000)}),
'asr': ('samplingRate', {int_or_none}),
}), get_all=False),
'acodec': 'aac',
'ext': 'm4a',
}
# Sort before removing dupes to keep the format dicts with the lowest tbr
video_fmts = sorted((fmt for fmt in dms_fmts if fmt['vcodec'] != 'none'), key=lambda f: f['tbr'])
self._remove_duplicate_formats(video_fmts)
# Calculate the true vbr/tbr by subtracting the lowest abr
min_abr = min(traverse_obj(audios, (..., 'bitRate', {float_or_none})), default=0) / 1000
for video_fmt in video_fmts:
video_fmt['tbr'] -= min_abr
video_fmt['format_id'] = f'video-{video_fmt["tbr"]:.0f}'
yield video_fmt
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
@ -409,19 +476,17 @@ def _real_extract(self, url):
webpage, 'error reason', default=None) webpage, 'error reason', default=None)
if not error_msg: if not error_msg:
raise raise
raise ExtractorError(re.sub(r'\s+', ' ', error_msg), expected=True) raise ExtractorError(clean_html(error_msg), expected=True)
formats = [] club_joined = traverse_obj(api_data, ('channel', 'viewer', 'follow', 'isFollowed', {bool}))
if club_joined is None:
def get_video_info(*items, get_first=True, **kwargs): fail_msg = self._html_search_regex(
return traverse_obj(api_data, ('video', *items), get_all=not get_first, **kwargs) r'<p[^>]+\bclass="fail-message"[^>]*>(?P<msg>.+?)</p>',
webpage, 'fail message', default=None, group='msg')
quality_info = api_data['media']['delivery']['movie'] if fail_msg:
session_api_data = quality_info['session'] self.raise_login_required(clean_html(fail_msg), metadata_available=True)
for (audio_quality, video_quality, protocol) in itertools.product(quality_info['audios'], quality_info['videos'], session_api_data['protocols']): elif not club_joined:
fmt = self._extract_format_for_quality(video_id, audio_quality, video_quality, protocol) self.raise_login_required('This video is for members only', metadata_available=True)
if fmt:
formats.append(fmt)
# Start extracting information # Start extracting information
tags = None tags = None
@ -440,11 +505,15 @@ def get_video_info(*items, get_first=True, **kwargs):
thumb_prefs = qualities(['url', 'middleUrl', 'largeUrl', 'player', 'ogp']) thumb_prefs = qualities(['url', 'middleUrl', 'largeUrl', 'player', 'ogp'])
def get_video_info(*items, get_first=True, **kwargs):
return traverse_obj(api_data, ('video', *items), get_all=not get_first, **kwargs)
return { return {
'id': video_id, 'id': video_id,
'_api_data': api_data, '_api_data': api_data,
'title': get_video_info(('originalTitle', 'title')) or self._og_search_title(webpage, default=None), 'title': get_video_info(('originalTitle', 'title')) or self._og_search_title(webpage, default=None),
'formats': formats, 'formats': [*self._yield_dmc_formats(api_data, video_id),
*self._yield_dms_formats(api_data, video_id)],
'thumbnails': [{ 'thumbnails': [{
'id': key, 'id': key,
'url': url, 'url': url,
@ -472,8 +541,11 @@ def get_video_info(*items, get_first=True, **kwargs):
def _get_subtitles(self, video_id, api_data): def _get_subtitles(self, video_id, api_data):
comments_info = traverse_obj(api_data, ('comment', 'nvComment', {dict})) or {} comments_info = traverse_obj(api_data, ('comment', 'nvComment', {dict})) or {}
if not comments_info.get('server'):
return
danmaku = traverse_obj(self._download_json( danmaku = traverse_obj(self._download_json(
f'{comments_info.get("server")}/v1/threads', video_id, data=json.dumps({ f'{comments_info["server"]}/v1/threads', video_id, data=json.dumps({
'additionals': {}, 'additionals': {},
'params': comments_info.get('params'), 'params': comments_info.get('params'),
'threadKey': comments_info.get('threadKey'), 'threadKey': comments_info.get('threadKey'),
@ -489,10 +561,6 @@ def _get_subtitles(self, video_id, api_data):
note='Downloading comments', errnote='Failed to download comments'), note='Downloading comments', errnote='Failed to download comments'),
('data', 'threads', ..., 'comments', ...)) ('data', 'threads', ..., 'comments', ...))
if not danmaku:
self.report_warning(f'Failed to get comments. {bug_reports_message()}')
return
return { return {
'comments': [{ 'comments': [{
'ext': 'json', 'ext': 'json',