yt-dlp/youtube_dl/extractor/niconico.py

286 lines
11 KiB
Python
Raw Normal View History

2013-11-23 04:19:44 -05:00
# encoding: utf-8
2014-03-27 16:01:09 -04:00
from __future__ import unicode_literals
2013-11-23 04:19:44 -05:00
import re
import json
import datetime
2013-11-23 04:19:44 -05:00
from .common import InfoExtractor
from ..compat import (
2013-11-23 04:19:44 -05:00
compat_urllib_parse,
compat_urlparse,
)
from ..utils import (
2015-09-05 21:42:45 -04:00
encode_dict,
ExtractorError,
int_or_none,
parse_duration,
parse_iso8601,
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 11:18:17 -05:00
sanitized_Request,
xpath_text,
determine_ext,
2013-11-23 04:19:44 -05:00
)
2013-11-23 04:19:44 -05:00
class NiconicoIE(InfoExtractor):
2014-03-27 16:01:09 -04:00
IE_NAME = 'niconico'
IE_DESC = 'ニコニコ動画'
2013-11-23 04:19:44 -05:00
2015-03-20 10:53:14 -04:00
_TESTS = [{
2014-03-27 16:01:09 -04:00
'url': 'http://www.nicovideo.jp/watch/sm22312215',
'md5': 'd1a75c0823e2f629128c43e1212760f9',
'info_dict': {
'id': 'sm22312215',
'ext': 'mp4',
'title': 'Big Buck Bunny',
'uploader': 'takuya0301',
'uploader_id': '2698420',
'upload_date': '20131123',
'timestamp': 1385182762,
2014-03-27 16:01:09 -04:00
'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
'duration': 33,
2013-11-23 04:19:44 -05:00
},
2015-03-20 10:53:14 -04:00
}, {
# File downloaded with and without credentials are different, so omit
# the md5 field
2015-03-20 10:53:14 -04:00
'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!',
'description': 'md5:689f066d74610b3b22e0f1739add0f58',
2015-03-20 10:53:14 -04:00
'uploader': 'りょうた',
'uploader_id': '18822557',
'upload_date': '20110429',
'timestamp': 1304065916,
2015-03-20 10:53:14 -04:00
'duration': 209,
},
}, {
# 'video exists but is marked as "deleted"
# md5 is unstable
'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',
'upload_date': '20071224',
'timestamp': 1198527840, # timestamp field has different value if logged in
'duration': 304,
},
}, {
'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',
'timestamp': 1388851200,
'upload_date': '20140104',
'uploader': 'アニメロチャンネル',
'uploader_id': '312',
}
2015-03-20 10:53:14 -04:00
}]
2013-11-23 04:19:44 -05:00
2015-03-09 13:12:41 -04:00
_VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
2013-11-23 04:19:44 -05:00
_NETRC_MACHINE = 'niconico'
# Determine whether the downloader used authentication to download video
_AUTHENTICATED = False
2013-11-23 04:19:44 -05:00
def _real_initialize(self):
self._login()
2013-11-23 04:19:44 -05:00
def _login(self):
(username, password) = self._get_login_info()
# No authentication to be performed
if not username:
return True
2013-11-23 04:19:44 -05:00
# Log in
login_form_strs = {
2014-03-27 16:01:09 -04:00
'mail': username,
'password': password,
2013-11-23 04:19:44 -05:00
}
2015-09-05 21:42:45 -04:00
login_data = compat_urllib_parse.urlencode(encode_dict(login_form_strs)).encode('utf-8')
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 11:18:17 -05:00
request = sanitized_Request(
2014-03-27 16:01:09 -04:00
'https://secure.nicovideo.jp/secure/login', login_data)
login_results = self._download_webpage(
2014-03-27 16:01:09 -04:00
request, None, note='Logging in', errnote='Unable to log in')
if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None:
2014-03-27 16:01:09 -04:00
self._downloader.report_warning('unable to log in: bad username or password')
2013-11-23 04:19:44 -05:00
return False
# Successful login
self._AUTHENTICATED = True
2013-11-23 04:19:44 -05:00
return True
def _real_extract(self, url):
2015-03-09 13:12:41 -04:00
video_id = self._match_id(url)
2013-11-23 04:19:44 -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
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 04:19:44 -05:00
video_info = self._download_xml(
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
2014-03-27 16:01:09 -04:00
note='Downloading video info page')
2013-11-23 04:19:44 -05:00
if self._AUTHENTICATED:
# Get flv info
flv_info_webpage = self._download_webpage(
2015-03-18 09:19:55 -04:00
'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
video_id, 'Downloading flv info')
else:
# Get external player info
ext_player_info = self._download_webpage(
'http://ext.nicovideo.jp/thumb_watch/' + video_id, video_id)
thumb_play_key = self._search_regex(
r'\'thumbPlayKey\'\s*:\s*\'(.*?)\'', ext_player_info, 'thumbPlayKey')
2015-03-18 09:24:17 -04:00
# Get flv info
flv_info_data = compat_urllib_parse.urlencode({
'k': thumb_play_key,
'v': video_id
})
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 11:18:17 -05:00
flv_info_request = sanitized_Request(
'http://ext.nicovideo.jp/thumb_watch', flv_info_data,
{'Content-Type': 'application/x-www-form-urlencoded'})
flv_info_webpage = self._download_webpage(
flv_info_request, video_id,
note='Downloading flv info', errnote='Unable to download 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)
else:
raise ExtractorError('Unable to find video URL')
video_real_url = flv_info['url'][0]
2013-11-23 04:19:44 -05:00
# Start extracting information
title = xpath_text(video_info, './/title')
if not title:
title = self._og_search_title(webpage, default=None)
if not title:
title = self._html_search_regex(
r'<span[^>]+class="videoHeaderTitle"[^>]*>([^<]+)</span>',
webpage, 'video title')
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', {})
extension = xpath_text(video_info, './/movie_type')
if not extension:
extension = determine_ext(video_real_url)
thumbnail = (
xpath_text(video_info, './/thumbnail_url') or
self._html_search_meta('image', webpage, 'thumbnail', default=None) or
video_detail.get('thumbnail'))
description = xpath_text(video_info, './/description')
timestamp = parse_iso8601(xpath_text(video_info, './/first_retrieve'))
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))
view_count = int_or_none(xpath_text(video_info, './/view_counter'))
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')
comment_count = int_or_none(xpath_text(video_info, './/comment_num'))
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(',', ''))
comment_count = comment_count or video_detail.get('commentCount')
duration = (parse_duration(
xpath_text(video_info, './/length') or
self._html_search_meta(
'video:duration', webpage, 'video duration', default=None)) or
video_detail.get('length'))
webpage_url = xpath_text(video_info, './/watch_url') or url
if video_info.find('.//ch_id') is not None:
uploader_id = video_info.find('.//ch_id').text
uploader = video_info.find('.//ch_name').text
elif video_info.find('.//user_id') is not None:
uploader_id = video_info.find('.//user_id').text
uploader = video_info.find('.//user_nickname').text
else:
uploader_id = uploader = None
2013-11-23 04:19:44 -05:00
return {
2014-03-27 16:01:09 -04:00
'id': video_id,
'url': video_real_url,
'title': title,
'ext': extension,
2015-06-14 17:43:33 -04:00
'format_id': 'economy' if video_real_url.endswith('low') else 'normal',
'thumbnail': thumbnail,
'description': description,
'uploader': uploader,
'timestamp': timestamp,
'uploader_id': uploader_id,
'view_count': view_count,
'comment_count': comment_count,
'duration': duration,
'webpage_url': webpage_url,
2013-11-23 04:19:44 -05:00
}
class NiconicoPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://www\.nicovideo\.jp/mylist/(?P<id>\d+)'
_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 15:39:15 -05:00
webpage, 'entries')
entries = json.loads(entries_json)
entries = [{
'_type': 'url',
'ie_key': NiconicoIE.ie_key(),
'url': ('http://www.nicovideo.jp/watch/%s' %
2014-11-23 15:39:15 -05:00
entry['item_data']['video_id']),
} for entry in entries]
return {
'_type': 'playlist',
'title': self._search_regex(r'\s+name: "(.*?)"', webpage, 'title'),
'id': list_id,
'entries': entries,
}