2016-10-02 06:39:18 -05:00
|
|
|
|
# coding: utf-8
|
2014-03-27 15:01:09 -05:00
|
|
|
|
from __future__ import unicode_literals
|
2013-11-23 03:19:44 -06:00
|
|
|
|
|
2014-10-29 05:04:48 -05:00
|
|
|
|
import json
|
2015-04-29 13:24:05 -05:00
|
|
|
|
import datetime
|
2013-11-23 03:19:44 -06:00
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2014-12-13 05:24:42 -06:00
|
|
|
|
from ..compat import (
|
2017-06-07 01:47:25 -05:00
|
|
|
|
compat_parse_qs,
|
2013-11-23 03:19:44 -06:00
|
|
|
|
compat_urlparse,
|
2014-12-13 05:24:42 -06:00
|
|
|
|
)
|
|
|
|
|
from ..utils import (
|
2017-06-07 01:47:25 -05:00
|
|
|
|
determine_ext,
|
2017-08-06 10:07:06 -05:00
|
|
|
|
dict_get,
|
2014-11-05 12:52:34 -06:00
|
|
|
|
ExtractorError,
|
2014-12-13 05:24:42 -06:00
|
|
|
|
int_or_none,
|
2017-08-06 11:19:46 -05:00
|
|
|
|
float_or_none,
|
2014-12-13 05:24:42 -06:00
|
|
|
|
parse_duration,
|
2015-04-29 11:24:24 -05:00
|
|
|
|
parse_iso8601,
|
2017-08-06 11:19:46 -05:00
|
|
|
|
remove_start,
|
2017-08-06 10:07:06 -05:00
|
|
|
|
try_get,
|
|
|
|
|
unified_timestamp,
|
2016-03-25 15:19:24 -05:00
|
|
|
|
urlencode_postdata,
|
2017-06-07 01:47:25 -05:00
|
|
|
|
xpath_text,
|
2013-11-23 03:19:44 -06:00
|
|
|
|
)
|
|
|
|
|
|
2013-11-23 23:37:14 -06:00
|
|
|
|
|
2013-11-23 03:19:44 -06:00
|
|
|
|
class NiconicoIE(InfoExtractor):
|
2014-03-27 15:01:09 -05:00
|
|
|
|
IE_NAME = 'niconico'
|
|
|
|
|
IE_DESC = 'ニコニコ動画'
|
2013-11-23 03:19:44 -06:00
|
|
|
|
|
2015-03-20 09:53:14 -05:00
|
|
|
|
_TESTS = [{
|
2014-03-27 15:01:09 -05:00
|
|
|
|
'url': 'http://www.nicovideo.jp/watch/sm22312215',
|
|
|
|
|
'md5': 'd1a75c0823e2f629128c43e1212760f9',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'sm22312215',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Big Buck Bunny',
|
2017-08-06 10:07:06 -05:00
|
|
|
|
'thumbnail': r're:https?://.*',
|
2014-03-27 15:01:09 -05:00
|
|
|
|
'uploader': 'takuya0301',
|
|
|
|
|
'uploader_id': '2698420',
|
|
|
|
|
'upload_date': '20131123',
|
2017-10-14 22:40:57 -05:00
|
|
|
|
'timestamp': int, # timestamp is unstable
|
2014-03-27 15:01:09 -05:00
|
|
|
|
'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
|
2014-07-04 10:05:46 -05:00
|
|
|
|
'duration': 33,
|
2017-08-06 10:07:06 -05:00
|
|
|
|
'view_count': int,
|
|
|
|
|
'comment_count': int,
|
2013-11-23 03:19:44 -06:00
|
|
|
|
},
|
2017-01-15 08:10:57 -06:00
|
|
|
|
'skip': 'Requires an account',
|
2015-03-20 09:53:14 -05:00
|
|
|
|
}, {
|
2015-04-29 11:47:52 -05:00
|
|
|
|
# File downloaded with and without credentials are different, so omit
|
|
|
|
|
# the md5 field
|
2015-03-20 09:53:14 -05:00
|
|
|
|
'url': 'http://www.nicovideo.jp/watch/nm14296458',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'nm14296458',
|
|
|
|
|
'ext': 'swf',
|
|
|
|
|
'title': '【鏡音リン】Dance on media【オリジナル】take2!',
|
2015-04-29 11:24:24 -05:00
|
|
|
|
'description': 'md5:689f066d74610b3b22e0f1739add0f58',
|
2017-08-06 10:07:06 -05:00
|
|
|
|
'thumbnail': r're:https?://.*',
|
2015-03-20 09:53:14 -05:00
|
|
|
|
'uploader': 'りょうた',
|
|
|
|
|
'uploader_id': '18822557',
|
|
|
|
|
'upload_date': '20110429',
|
2015-04-29 11:24:24 -05:00
|
|
|
|
'timestamp': 1304065916,
|
2015-03-20 09:53:14 -05:00
|
|
|
|
'duration': 209,
|
|
|
|
|
},
|
2017-01-15 08:10:57 -06:00
|
|
|
|
'skip': 'Requires an account',
|
2015-04-29 11:24:24 -05:00
|
|
|
|
}, {
|
|
|
|
|
# 'video exists but is marked as "deleted"
|
2015-04-29 13:24:05 -05:00
|
|
|
|
# md5 is unstable
|
2015-04-29 11:24:24 -05:00
|
|
|
|
'url': 'http://www.nicovideo.jp/watch/sm10000',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'sm10000',
|
|
|
|
|
'ext': 'unknown_video',
|
|
|
|
|
'description': 'deleted',
|
|
|
|
|
'title': 'ドラえもんエターナル第3話「決戦第3新東京市」<前編>',
|
2017-08-06 10:07:06 -05:00
|
|
|
|
'thumbnail': r're:https?://.*',
|
2015-04-29 13:24:05 -05:00
|
|
|
|
'upload_date': '20071224',
|
2017-01-15 08:10:57 -06:00
|
|
|
|
'timestamp': int, # timestamp field has different value if logged in
|
2015-04-29 13:24:05 -05:00
|
|
|
|
'duration': 304,
|
2017-08-06 10:07:06 -05:00
|
|
|
|
'view_count': int,
|
2015-04-29 11:24:24 -05:00
|
|
|
|
},
|
2017-01-15 08:10:57 -06:00
|
|
|
|
'skip': 'Requires an account',
|
2015-04-30 04:05:02 -05:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.nicovideo.jp/watch/so22543406',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '1388129933',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': '【第1回】RADIOアニメロミックス ラブライブ!~のぞえりRadio Garden~',
|
|
|
|
|
'description': 'md5:b27d224bb0ff53d3c8269e9f8b561cf1',
|
2017-08-06 10:07:06 -05:00
|
|
|
|
'thumbnail': r're:https?://.*',
|
2015-04-30 04:05:02 -05:00
|
|
|
|
'timestamp': 1388851200,
|
|
|
|
|
'upload_date': '20140104',
|
|
|
|
|
'uploader': 'アニメロチャンネル',
|
|
|
|
|
'uploader_id': '312',
|
2017-01-15 08:10:57 -06:00
|
|
|
|
},
|
|
|
|
|
'skip': 'The viewing period of the video you were searching for has expired.',
|
2017-08-06 10:07:06 -05:00
|
|
|
|
}, {
|
2017-08-06 11:19:46 -05:00
|
|
|
|
# video not available via `getflv`; "old" HTML5 video
|
2017-08-06 10:07:06 -05:00
|
|
|
|
'url': 'http://www.nicovideo.jp/watch/sm1151009',
|
2017-08-06 11:19:46 -05:00
|
|
|
|
'md5': '8fa81c364eb619d4085354eab075598a',
|
2017-08-06 10:07:06 -05:00
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'sm1151009',
|
2017-08-06 11:19:46 -05:00
|
|
|
|
'ext': 'mp4',
|
2017-08-06 10:07:06 -05:00
|
|
|
|
'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',
|
|
|
|
|
'thumbnail': r're:https?://.*',
|
|
|
|
|
'duration': 184,
|
|
|
|
|
'timestamp': 1190868283,
|
|
|
|
|
'upload_date': '20070927',
|
|
|
|
|
'uploader': 'denden2',
|
|
|
|
|
'uploader_id': '1392194',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
},
|
|
|
|
|
'skip': 'Requires an account',
|
2017-08-06 11:19:46 -05:00
|
|
|
|
}, {
|
|
|
|
|
# "New" HTML5 video
|
2017-10-14 22:40:57 -05:00
|
|
|
|
# md5 is unstable
|
2017-08-06 11:19:46 -05:00
|
|
|
|
'url': 'http://www.nicovideo.jp/watch/sm31464864',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'sm31464864',
|
|
|
|
|
'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',
|
|
|
|
|
'description': 'md5:e52974af9a96e739196b2c1ca72b5feb',
|
|
|
|
|
'timestamp': 1498514060,
|
|
|
|
|
'upload_date': '20170626',
|
2017-10-14 22:40:57 -05:00
|
|
|
|
'uploader': 'ゲスト',
|
2017-08-06 11:19:46 -05:00
|
|
|
|
'uploader_id': '40826363',
|
|
|
|
|
'thumbnail': r're:https?://.*',
|
|
|
|
|
'duration': 198,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
},
|
|
|
|
|
'skip': 'Requires an account',
|
2017-10-14 22:40:57 -05:00
|
|
|
|
}, {
|
|
|
|
|
# Video without owner
|
|
|
|
|
'url': 'http://www.nicovideo.jp/watch/sm18238488',
|
|
|
|
|
'md5': 'd265680a1f92bdcbbd2a507fc9e78a9e',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'sm18238488',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': '【実写版】ミュータントタートルズ',
|
|
|
|
|
'description': 'md5:15df8988e47a86f9e978af2064bf6d8e',
|
|
|
|
|
'timestamp': 1341160408,
|
|
|
|
|
'upload_date': '20120701',
|
|
|
|
|
'uploader': None,
|
|
|
|
|
'uploader_id': None,
|
|
|
|
|
'thumbnail': r're:https?://.*',
|
|
|
|
|
'duration': 5271,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
},
|
|
|
|
|
'skip': 'Requires an account',
|
2017-06-25 14:30:05 -05:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
|
|
|
|
|
'only_matching': True,
|
2015-03-20 09:53:14 -05:00
|
|
|
|
}]
|
2013-11-23 03:19:44 -06:00
|
|
|
|
|
2017-06-25 14:30:05 -05:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.|secure\.|sp\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
|
2013-11-23 03:19:44 -06:00
|
|
|
|
_NETRC_MACHINE = 'niconico'
|
|
|
|
|
|
|
|
|
|
def _real_initialize(self):
|
2014-10-12 15:18:42 -05:00
|
|
|
|
self._login()
|
2013-11-23 03:19:44 -06:00
|
|
|
|
|
|
|
|
|
def _login(self):
|
2018-05-26 10:12:44 -05:00
|
|
|
|
username, password = self._get_login_info()
|
2014-10-12 15:18:42 -05:00
|
|
|
|
# No authentication to be performed
|
|
|
|
|
if not username:
|
|
|
|
|
return True
|
2013-11-23 03:19:44 -06:00
|
|
|
|
|
|
|
|
|
# Log in
|
2017-06-07 01:47:25 -05:00
|
|
|
|
login_ok = True
|
2013-11-23 03:19:44 -06:00
|
|
|
|
login_form_strs = {
|
2017-06-07 01:47:25 -05:00
|
|
|
|
'mail_tel': username,
|
2014-03-27 15:01:09 -05:00
|
|
|
|
'password': password,
|
2013-11-23 03:19:44 -06:00
|
|
|
|
}
|
2017-06-07 01:47:25 -05:00
|
|
|
|
urlh = self._request_webpage(
|
|
|
|
|
'https://account.nicovideo.jp/api/v1/login', None,
|
|
|
|
|
note='Logging in', errnote='Unable to log in',
|
|
|
|
|
data=urlencode_postdata(login_form_strs))
|
|
|
|
|
if urlh is False:
|
|
|
|
|
login_ok = False
|
|
|
|
|
else:
|
|
|
|
|
parts = compat_urlparse.urlparse(urlh.geturl())
|
|
|
|
|
if compat_parse_qs(parts.query).get('message', [None])[0] == 'cant_login':
|
|
|
|
|
login_ok = False
|
|
|
|
|
if not login_ok:
|
2014-03-27 15:01:09 -05:00
|
|
|
|
self._downloader.report_warning('unable to log in: bad username or password')
|
2017-06-07 01:47:25 -05:00
|
|
|
|
return login_ok
|
2013-11-23 03:19:44 -06:00
|
|
|
|
|
2017-08-06 11:19:46 -05:00
|
|
|
|
def _extract_format_for_quality(self, api_data, video_id, audio_quality, video_quality):
|
|
|
|
|
def yesno(boolean):
|
|
|
|
|
return 'yes' if boolean else 'no'
|
|
|
|
|
|
|
|
|
|
session_api_data = api_data['video']['dmcInfo']['session_api']
|
|
|
|
|
session_api_endpoint = session_api_data['urls'][0]
|
|
|
|
|
|
|
|
|
|
format_id = '-'.join(map(lambda s: remove_start(s['id'], 'archive_'), [video_quality, audio_quality]))
|
|
|
|
|
|
|
|
|
|
session_response = self._download_json(
|
|
|
|
|
session_api_endpoint['url'], video_id,
|
|
|
|
|
query={'_format': 'json'},
|
|
|
|
|
headers={'Content-Type': 'application/json'},
|
|
|
|
|
note='Downloading JSON metadata for %s' % format_id,
|
|
|
|
|
data=json.dumps({
|
|
|
|
|
'session': {
|
|
|
|
|
'client_info': {
|
|
|
|
|
'player_id': session_api_data['player_id'],
|
|
|
|
|
},
|
|
|
|
|
'content_auth': {
|
|
|
|
|
'auth_type': session_api_data['auth_types'][session_api_data['protocols'][0]],
|
|
|
|
|
'content_key_timeout': session_api_data['content_key_timeout'],
|
|
|
|
|
'service_id': 'nicovideo',
|
|
|
|
|
'service_user_id': session_api_data['service_user_id']
|
|
|
|
|
},
|
|
|
|
|
'content_id': session_api_data['content_id'],
|
|
|
|
|
'content_src_id_sets': [{
|
|
|
|
|
'content_src_ids': [{
|
|
|
|
|
'src_id_to_mux': {
|
|
|
|
|
'audio_src_ids': [audio_quality['id']],
|
|
|
|
|
'video_src_ids': [video_quality['id']],
|
|
|
|
|
}
|
|
|
|
|
}]
|
|
|
|
|
}],
|
|
|
|
|
'content_type': 'movie',
|
|
|
|
|
'content_uri': '',
|
|
|
|
|
'keep_method': {
|
|
|
|
|
'heartbeat': {
|
|
|
|
|
'lifetime': session_api_data['heartbeat_lifetime']
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
'priority': session_api_data['priority'],
|
|
|
|
|
'protocol': {
|
|
|
|
|
'name': 'http',
|
|
|
|
|
'parameters': {
|
|
|
|
|
'http_parameters': {
|
|
|
|
|
'parameters': {
|
|
|
|
|
'http_output_download_parameters': {
|
|
|
|
|
'use_ssl': yesno(session_api_endpoint['is_ssl']),
|
|
|
|
|
'use_well_known_port': yesno(session_api_endpoint['is_well_known_port']),
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
'recipe_id': session_api_data['recipe_id'],
|
|
|
|
|
'session_operation_auth': {
|
|
|
|
|
'session_operation_auth_by_signature': {
|
|
|
|
|
'signature': session_api_data['signature'],
|
|
|
|
|
'token': session_api_data['token'],
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
'timing_constraint': 'unlimited'
|
|
|
|
|
}
|
2018-09-01 04:04:45 -05:00
|
|
|
|
}).encode())
|
2017-08-06 11:19:46 -05:00
|
|
|
|
|
|
|
|
|
resolution = video_quality.get('resolution', {})
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
'url': session_response['data']['session']['content_uri'],
|
|
|
|
|
'format_id': format_id,
|
|
|
|
|
'ext': 'mp4', # Session API are used in HTML5, which always serves mp4
|
|
|
|
|
'abr': float_or_none(audio_quality.get('bitrate'), 1000),
|
|
|
|
|
'vbr': float_or_none(video_quality.get('bitrate'), 1000),
|
|
|
|
|
'height': resolution.get('height'),
|
|
|
|
|
'width': resolution.get('width'),
|
|
|
|
|
}
|
|
|
|
|
|
2013-11-23 03:19:44 -06:00
|
|
|
|
def _real_extract(self, url):
|
2015-03-09 12:12:41 -05:00
|
|
|
|
video_id = self._match_id(url)
|
2013-11-23 03:19:44 -06:00
|
|
|
|
|
2015-04-29 11:24:24 -05:00
|
|
|
|
# Get video webpage. We are not actually interested in it for normal
|
|
|
|
|
# cases, but need the cookies in order to be able to download the
|
|
|
|
|
# info webpage
|
2015-04-30 04:05:02 -05:00
|
|
|
|
webpage, handle = self._download_webpage_handle(
|
|
|
|
|
'http://www.nicovideo.jp/watch/' + video_id, video_id)
|
|
|
|
|
if video_id.startswith('so'):
|
|
|
|
|
video_id = self._match_id(handle.geturl())
|
2013-11-23 03:19:44 -06:00
|
|
|
|
|
2017-08-06 10:07:06 -05:00
|
|
|
|
api_data = self._parse_json(self._html_search_regex(
|
|
|
|
|
'data-api-data="([^"]+)"', webpage,
|
|
|
|
|
'API data', default='{}'), video_id)
|
|
|
|
|
|
2017-08-06 11:19:46 -05:00
|
|
|
|
def _format_id_from_url(video_url):
|
|
|
|
|
return 'economy' if video_real_url.endswith('low') else 'normal'
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
|
video_real_url = api_data['video']['smileInfo']['url']
|
|
|
|
|
except KeyError: # Flash videos
|
2017-08-06 10:07:06 -05:00
|
|
|
|
# Get flv info
|
|
|
|
|
flv_info_webpage = self._download_webpage(
|
|
|
|
|
'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
|
|
|
|
|
video_id, 'Downloading flv info')
|
|
|
|
|
|
|
|
|
|
flv_info = compat_urlparse.parse_qs(flv_info_webpage)
|
|
|
|
|
if 'url' not in flv_info:
|
|
|
|
|
if 'deleted' in flv_info:
|
|
|
|
|
raise ExtractorError('The video has been deleted.',
|
|
|
|
|
expected=True)
|
|
|
|
|
elif 'closed' in flv_info:
|
|
|
|
|
raise ExtractorError('Niconico videos now require logging in',
|
|
|
|
|
expected=True)
|
|
|
|
|
elif 'error' in flv_info:
|
|
|
|
|
raise ExtractorError('%s reports error: %s' % (
|
|
|
|
|
self.IE_NAME, flv_info['error'][0]), expected=True)
|
|
|
|
|
else:
|
|
|
|
|
raise ExtractorError('Unable to find video URL')
|
|
|
|
|
|
|
|
|
|
video_info_xml = self._download_xml(
|
|
|
|
|
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id,
|
|
|
|
|
video_id, note='Downloading video info page')
|
|
|
|
|
|
|
|
|
|
def get_video_info(items):
|
|
|
|
|
if not isinstance(items, list):
|
|
|
|
|
items = [items]
|
|
|
|
|
for item in items:
|
|
|
|
|
ret = xpath_text(video_info_xml, './/' + item)
|
|
|
|
|
if ret:
|
|
|
|
|
return ret
|
2013-11-23 03:19:44 -06:00
|
|
|
|
|
2017-08-06 11:19:46 -05:00
|
|
|
|
video_real_url = flv_info['url'][0]
|
|
|
|
|
|
|
|
|
|
extension = get_video_info('movie_type')
|
|
|
|
|
if not extension:
|
|
|
|
|
extension = determine_ext(video_real_url)
|
|
|
|
|
|
|
|
|
|
formats = [{
|
|
|
|
|
'url': video_real_url,
|
|
|
|
|
'ext': extension,
|
|
|
|
|
'format_id': _format_id_from_url(video_real_url),
|
|
|
|
|
}]
|
|
|
|
|
else:
|
|
|
|
|
formats = []
|
|
|
|
|
|
|
|
|
|
dmc_info = api_data['video'].get('dmcInfo')
|
|
|
|
|
if dmc_info: # "New" HTML5 videos
|
|
|
|
|
quality_info = dmc_info['quality']
|
|
|
|
|
for audio_quality in quality_info['audios']:
|
|
|
|
|
for video_quality in quality_info['videos']:
|
|
|
|
|
if not audio_quality['available'] or not video_quality['available']:
|
|
|
|
|
continue
|
|
|
|
|
formats.append(self._extract_format_for_quality(
|
|
|
|
|
api_data, video_id, audio_quality, video_quality))
|
|
|
|
|
|
|
|
|
|
self._sort_formats(formats)
|
|
|
|
|
else: # "Old" HTML5 videos
|
|
|
|
|
formats = [{
|
|
|
|
|
'url': video_real_url,
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'format_id': _format_id_from_url(video_real_url),
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
def get_video_info(items):
|
|
|
|
|
return dict_get(api_data['video'], items)
|
|
|
|
|
|
2013-11-23 03:19:44 -06:00
|
|
|
|
# Start extracting information
|
2017-08-06 10:07:06 -05:00
|
|
|
|
title = get_video_info('title')
|
2015-04-29 11:47:52 -05:00
|
|
|
|
if not title:
|
|
|
|
|
title = self._og_search_title(webpage, default=None)
|
2015-04-29 11:24:24 -05:00
|
|
|
|
if not title:
|
|
|
|
|
title = self._html_search_regex(
|
|
|
|
|
r'<span[^>]+class="videoHeaderTitle"[^>]*>([^<]+)</span>',
|
|
|
|
|
webpage, 'video title')
|
|
|
|
|
|
2015-04-29 13:24:05 -05:00
|
|
|
|
watch_api_data_string = self._html_search_regex(
|
|
|
|
|
r'<div[^>]+id="watchAPIDataContainer"[^>]+>([^<]+)</div>',
|
|
|
|
|
webpage, 'watch api data', default=None)
|
|
|
|
|
watch_api_data = self._parse_json(watch_api_data_string, video_id) if watch_api_data_string else {}
|
|
|
|
|
video_detail = watch_api_data.get('videoDetail', {})
|
|
|
|
|
|
|
|
|
|
thumbnail = (
|
2019-05-10 15:56:22 -05:00
|
|
|
|
get_video_info(['thumbnail_url', 'thumbnailURL'])
|
|
|
|
|
or self._html_search_meta('image', webpage, 'thumbnail', default=None)
|
|
|
|
|
or video_detail.get('thumbnail'))
|
2015-04-29 13:24:05 -05:00
|
|
|
|
|
2017-08-06 10:07:06 -05:00
|
|
|
|
description = get_video_info('description')
|
2015-04-29 13:24:05 -05:00
|
|
|
|
|
2019-05-10 15:56:22 -05:00
|
|
|
|
timestamp = (parse_iso8601(get_video_info('first_retrieve'))
|
|
|
|
|
or unified_timestamp(get_video_info('postedDateTime')))
|
2015-04-29 13:24:05 -05:00
|
|
|
|
if not timestamp:
|
|
|
|
|
match = self._html_search_meta('datePublished', webpage, 'date published', default=None)
|
|
|
|
|
if match:
|
|
|
|
|
timestamp = parse_iso8601(match.replace('+', ':00+'))
|
|
|
|
|
if not timestamp and video_detail.get('postedAt'):
|
|
|
|
|
timestamp = parse_iso8601(
|
|
|
|
|
video_detail['postedAt'].replace('/', '-'),
|
|
|
|
|
delimiter=' ', timezone=datetime.timedelta(hours=9))
|
|
|
|
|
|
2017-08-06 10:07:06 -05:00
|
|
|
|
view_count = int_or_none(get_video_info(['view_counter', 'viewCount']))
|
2015-04-29 13:24:05 -05:00
|
|
|
|
if not view_count:
|
|
|
|
|
match = self._html_search_regex(
|
|
|
|
|
r'>Views: <strong[^>]*>([^<]+)</strong>',
|
|
|
|
|
webpage, 'view count', default=None)
|
|
|
|
|
if match:
|
|
|
|
|
view_count = int_or_none(match.replace(',', ''))
|
|
|
|
|
view_count = view_count or video_detail.get('viewCount')
|
|
|
|
|
|
2019-05-10 15:56:22 -05:00
|
|
|
|
comment_count = (int_or_none(get_video_info('comment_num'))
|
|
|
|
|
or video_detail.get('commentCount')
|
|
|
|
|
or try_get(api_data, lambda x: x['thread']['commentCount']))
|
2015-04-29 13:24:05 -05:00
|
|
|
|
if not comment_count:
|
|
|
|
|
match = self._html_search_regex(
|
|
|
|
|
r'>Comments: <strong[^>]*>([^<]+)</strong>',
|
|
|
|
|
webpage, 'comment count', default=None)
|
|
|
|
|
if match:
|
|
|
|
|
comment_count = int_or_none(match.replace(',', ''))
|
|
|
|
|
|
|
|
|
|
duration = (parse_duration(
|
2019-05-10 15:56:22 -05:00
|
|
|
|
get_video_info('length')
|
|
|
|
|
or self._html_search_meta(
|
|
|
|
|
'video:duration', webpage, 'video duration', default=None))
|
|
|
|
|
or video_detail.get('length')
|
|
|
|
|
or get_video_info('duration'))
|
2015-04-29 13:24:05 -05:00
|
|
|
|
|
2017-08-06 10:07:06 -05:00
|
|
|
|
webpage_url = get_video_info('watch_url') or url
|
2014-07-04 10:05:46 -05:00
|
|
|
|
|
2017-10-14 22:40:57 -05:00
|
|
|
|
# Note: cannot use api_data.get('owner', {}) because owner may be set to "null"
|
|
|
|
|
# in the JSON, which will cause None to be returned instead of {}.
|
|
|
|
|
owner = try_get(api_data, lambda x: x.get('owner'), dict) or {}
|
2017-08-06 10:07:06 -05:00
|
|
|
|
uploader_id = get_video_info(['ch_id', 'user_id']) or owner.get('id')
|
|
|
|
|
uploader = get_video_info(['ch_name', 'user_nickname']) or owner.get('nickname')
|
2013-11-23 03:19:44 -06:00
|
|
|
|
|
2015-04-29 13:24:05 -05:00
|
|
|
|
return {
|
2014-03-27 15:01:09 -05:00
|
|
|
|
'id': video_id,
|
2014-07-04 10:05:46 -05:00
|
|
|
|
'title': title,
|
2017-08-06 11:19:46 -05:00
|
|
|
|
'formats': formats,
|
2014-07-04 10:05:46 -05:00
|
|
|
|
'thumbnail': thumbnail,
|
|
|
|
|
'description': description,
|
|
|
|
|
'uploader': uploader,
|
2015-04-29 11:24:24 -05:00
|
|
|
|
'timestamp': timestamp,
|
2014-07-04 10:05:46 -05:00
|
|
|
|
'uploader_id': uploader_id,
|
|
|
|
|
'view_count': view_count,
|
|
|
|
|
'comment_count': comment_count,
|
|
|
|
|
'duration': duration,
|
|
|
|
|
'webpage_url': webpage_url,
|
2013-11-23 03:19:44 -06:00
|
|
|
|
}
|
2014-10-29 05:04:48 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class NiconicoPlaylistIE(InfoExtractor):
|
2016-09-08 06:29:05 -05:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/mylist/(?P<id>\d+)'
|
2014-10-29 05:04:48 -05:00
|
|
|
|
|
|
|
|
|
_TEST = {
|
|
|
|
|
'url': 'http://www.nicovideo.jp/mylist/27411728',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '27411728',
|
|
|
|
|
'title': 'AKB48のオールナイトニッポン',
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 225,
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
list_id = self._match_id(url)
|
|
|
|
|
webpage = self._download_webpage(url, list_id)
|
|
|
|
|
|
|
|
|
|
entries_json = self._search_regex(r'Mylist\.preload\(\d+, (\[.*\])\);',
|
2014-11-23 14:39:15 -06:00
|
|
|
|
webpage, 'entries')
|
2014-10-29 05:04:48 -05:00
|
|
|
|
entries = json.loads(entries_json)
|
|
|
|
|
entries = [{
|
|
|
|
|
'_type': 'url',
|
|
|
|
|
'ie_key': NiconicoIE.ie_key(),
|
2014-11-08 07:53:23 -06:00
|
|
|
|
'url': ('http://www.nicovideo.jp/watch/%s' %
|
2014-11-23 14:39:15 -06:00
|
|
|
|
entry['item_data']['video_id']),
|
2014-10-29 05:04:48 -05:00
|
|
|
|
} for entry in entries]
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
'_type': 'playlist',
|
|
|
|
|
'title': self._search_regex(r'\s+name: "(.*?)"', webpage, 'title'),
|
|
|
|
|
'id': list_id,
|
|
|
|
|
'entries': entries,
|
|
|
|
|
}
|