2016-10-02 04:39:18 -07:00
|
|
|
|
# coding: utf-8
|
2014-03-27 13:01:09 -07:00
|
|
|
|
from __future__ import unicode_literals
|
2013-11-23 01:19:44 -08:00
|
|
|
|
|
|
|
|
|
import re
|
2014-10-29 03:04:48 -07:00
|
|
|
|
import json
|
2015-04-29 11:24:05 -07:00
|
|
|
|
import datetime
|
2013-11-23 01:19:44 -08:00
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2014-12-13 03:24:42 -08:00
|
|
|
|
from ..compat import (
|
2013-11-23 01:19:44 -08:00
|
|
|
|
compat_urlparse,
|
2014-12-13 03:24:42 -08:00
|
|
|
|
)
|
|
|
|
|
from ..utils import (
|
2014-11-05 10:52:34 -08:00
|
|
|
|
ExtractorError,
|
2014-12-13 03:24:42 -08:00
|
|
|
|
int_or_none,
|
|
|
|
|
parse_duration,
|
2015-04-29 09:24:24 -07:00
|
|
|
|
parse_iso8601,
|
2015-11-21 08:18:17 -08:00
|
|
|
|
sanitized_Request,
|
2015-04-29 09:24:24 -07:00
|
|
|
|
xpath_text,
|
|
|
|
|
determine_ext,
|
2016-03-25 13:19:24 -07:00
|
|
|
|
urlencode_postdata,
|
2013-11-23 01:19:44 -08:00
|
|
|
|
)
|
|
|
|
|
|
2013-11-23 21:37:14 -08:00
|
|
|
|
|
2013-11-23 01:19:44 -08:00
|
|
|
|
class NiconicoIE(InfoExtractor):
|
2014-03-27 13:01:09 -07:00
|
|
|
|
IE_NAME = 'niconico'
|
|
|
|
|
IE_DESC = 'ニコニコ動画'
|
2013-11-23 01:19:44 -08:00
|
|
|
|
|
2015-03-20 07:53:14 -07:00
|
|
|
|
_TESTS = [{
|
2014-03-27 13:01:09 -07:00
|
|
|
|
'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',
|
2015-04-29 09:24:24 -07:00
|
|
|
|
'timestamp': 1385182762,
|
2014-03-27 13:01:09 -07:00
|
|
|
|
'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
|
2014-07-04 08:05:46 -07:00
|
|
|
|
'duration': 33,
|
2013-11-23 01:19:44 -08:00
|
|
|
|
},
|
2017-01-15 06:10:57 -08:00
|
|
|
|
'skip': 'Requires an account',
|
2015-03-20 07:53:14 -07:00
|
|
|
|
}, {
|
2015-04-29 09:47:52 -07:00
|
|
|
|
# File downloaded with and without credentials are different, so omit
|
|
|
|
|
# the md5 field
|
2015-03-20 07:53:14 -07:00
|
|
|
|
'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 09:24:24 -07:00
|
|
|
|
'description': 'md5:689f066d74610b3b22e0f1739add0f58',
|
2015-03-20 07:53:14 -07:00
|
|
|
|
'uploader': 'りょうた',
|
|
|
|
|
'uploader_id': '18822557',
|
|
|
|
|
'upload_date': '20110429',
|
2015-04-29 09:24:24 -07:00
|
|
|
|
'timestamp': 1304065916,
|
2015-03-20 07:53:14 -07:00
|
|
|
|
'duration': 209,
|
|
|
|
|
},
|
2017-01-15 06:10:57 -08:00
|
|
|
|
'skip': 'Requires an account',
|
2015-04-29 09:24:24 -07:00
|
|
|
|
}, {
|
|
|
|
|
# 'video exists but is marked as "deleted"
|
2015-04-29 11:24:05 -07:00
|
|
|
|
# md5 is unstable
|
2015-04-29 09:24:24 -07:00
|
|
|
|
'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>',
|
2015-04-29 11:24:05 -07:00
|
|
|
|
'upload_date': '20071224',
|
2017-01-15 06:10:57 -08:00
|
|
|
|
'timestamp': int, # timestamp field has different value if logged in
|
2015-04-29 11:24:05 -07:00
|
|
|
|
'duration': 304,
|
2015-04-29 09:24:24 -07:00
|
|
|
|
},
|
2017-01-15 06:10:57 -08:00
|
|
|
|
'skip': 'Requires an account',
|
2015-04-30 02:05:02 -07:00
|
|
|
|
}, {
|
|
|
|
|
'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',
|
|
|
|
|
'timestamp': 1388851200,
|
|
|
|
|
'upload_date': '20140104',
|
|
|
|
|
'uploader': 'アニメロチャンネル',
|
|
|
|
|
'uploader_id': '312',
|
2017-01-15 06:10:57 -08:00
|
|
|
|
},
|
|
|
|
|
'skip': 'The viewing period of the video you were searching for has expired.',
|
2017-06-25 12:30:05 -07:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
|
|
|
|
|
'only_matching': True,
|
2015-03-20 07:53:14 -07:00
|
|
|
|
}]
|
2013-11-23 01:19:44 -08:00
|
|
|
|
|
2017-06-25 12:30:05 -07:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.|secure\.|sp\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
|
2013-11-23 01:19:44 -08:00
|
|
|
|
_NETRC_MACHINE = 'niconico'
|
|
|
|
|
|
|
|
|
|
def _real_initialize(self):
|
2014-10-12 13:18:42 -07:00
|
|
|
|
self._login()
|
2013-11-23 01:19:44 -08:00
|
|
|
|
|
|
|
|
|
def _login(self):
|
|
|
|
|
(username, password) = self._get_login_info()
|
2014-10-12 13:18:42 -07:00
|
|
|
|
# No authentication to be performed
|
|
|
|
|
if not username:
|
|
|
|
|
return True
|
2013-11-23 01:19:44 -08:00
|
|
|
|
|
|
|
|
|
# Log in
|
|
|
|
|
login_form_strs = {
|
2014-03-27 13:01:09 -07:00
|
|
|
|
'mail': username,
|
|
|
|
|
'password': password,
|
2013-11-23 01:19:44 -08:00
|
|
|
|
}
|
2016-03-25 13:19:24 -07:00
|
|
|
|
login_data = urlencode_postdata(login_form_strs)
|
2015-11-21 08:18:17 -08:00
|
|
|
|
request = sanitized_Request(
|
2014-03-27 13:01:09 -07:00
|
|
|
|
'https://secure.nicovideo.jp/secure/login', login_data)
|
2013-11-23 21:37:14 -08:00
|
|
|
|
login_results = self._download_webpage(
|
2014-03-27 13:01:09 -07:00
|
|
|
|
request, None, note='Logging in', errnote='Unable to log in')
|
2013-11-23 21:37:14 -08:00
|
|
|
|
if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None:
|
2014-03-27 13:01:09 -07:00
|
|
|
|
self._downloader.report_warning('unable to log in: bad username or password')
|
2013-11-23 01:19:44 -08:00
|
|
|
|
return False
|
|
|
|
|
return True
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2015-03-09 10:12:41 -07:00
|
|
|
|
video_id = self._match_id(url)
|
2013-11-23 01:19:44 -08:00
|
|
|
|
|
2015-04-29 09:24:24 -07:00
|
|
|
|
# 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 02:05:02 -07:00
|
|
|
|
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 01:19:44 -08:00
|
|
|
|
|
2013-11-26 09:48:52 -08:00
|
|
|
|
video_info = self._download_xml(
|
2013-11-23 21:37:14 -08:00
|
|
|
|
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
|
2014-03-27 13:01:09 -07:00
|
|
|
|
note='Downloading video info page')
|
2013-11-23 01:19:44 -08:00
|
|
|
|
|
2017-01-15 06:51:54 -08:00
|
|
|
|
# Get flv info
|
|
|
|
|
flv_info_webpage = self._download_webpage(
|
|
|
|
|
'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
|
|
|
|
|
video_id, 'Downloading flv info')
|
2014-07-01 10:32:54 -07:00
|
|
|
|
|
2015-04-29 09:24:24 -07:00
|
|
|
|
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)
|
2017-01-15 06:51:54 -08:00
|
|
|
|
elif 'closed' in flv_info:
|
|
|
|
|
raise ExtractorError('Niconico videos now require logging in',
|
|
|
|
|
expected=True)
|
2015-04-29 09:24:24 -07:00
|
|
|
|
else:
|
|
|
|
|
raise ExtractorError('Unable to find video URL')
|
|
|
|
|
|
|
|
|
|
video_real_url = flv_info['url'][0]
|
2013-11-23 01:19:44 -08:00
|
|
|
|
|
|
|
|
|
# Start extracting information
|
2015-04-29 09:24:24 -07:00
|
|
|
|
title = xpath_text(video_info, './/title')
|
2015-04-29 09:47:52 -07:00
|
|
|
|
if not title:
|
|
|
|
|
title = self._og_search_title(webpage, default=None)
|
2015-04-29 09:24:24 -07:00
|
|
|
|
if not title:
|
|
|
|
|
title = self._html_search_regex(
|
|
|
|
|
r'<span[^>]+class="videoHeaderTitle"[^>]*>([^<]+)</span>',
|
|
|
|
|
webpage, 'video title')
|
|
|
|
|
|
2015-04-29 11:24:05 -07:00
|
|
|
|
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', {})
|
|
|
|
|
|
2015-04-29 09:24:24 -07:00
|
|
|
|
extension = xpath_text(video_info, './/movie_type')
|
|
|
|
|
if not extension:
|
|
|
|
|
extension = determine_ext(video_real_url)
|
2015-06-13 21:18:40 -07:00
|
|
|
|
|
2015-04-29 11:24:05 -07:00
|
|
|
|
thumbnail = (
|
|
|
|
|
xpath_text(video_info, './/thumbnail_url') or
|
|
|
|
|
self._html_search_meta('image', webpage, 'thumbnail', default=None) or
|
|
|
|
|
video_detail.get('thumbnail'))
|
|
|
|
|
|
2015-04-29 09:24:24 -07:00
|
|
|
|
description = xpath_text(video_info, './/description')
|
2015-04-29 11:24:05 -07:00
|
|
|
|
|
2015-04-29 09:24:24 -07:00
|
|
|
|
timestamp = parse_iso8601(xpath_text(video_info, './/first_retrieve'))
|
2015-04-29 11:24:05 -07:00
|
|
|
|
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))
|
|
|
|
|
|
2015-04-29 09:24:24 -07:00
|
|
|
|
view_count = int_or_none(xpath_text(video_info, './/view_counter'))
|
2015-04-29 11:24:05 -07:00
|
|
|
|
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')
|
|
|
|
|
|
2015-04-29 09:24:24 -07:00
|
|
|
|
comment_count = int_or_none(xpath_text(video_info, './/comment_num'))
|
2015-04-29 11:24:05 -07:00
|
|
|
|
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(',', ''))
|
|
|
|
|
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
|
2014-07-04 08:05:46 -07:00
|
|
|
|
|
2014-07-01 11:13:12 -07:00
|
|
|
|
if video_info.find('.//ch_id') is not None:
|
2014-07-04 08:05:46 -07:00
|
|
|
|
uploader_id = video_info.find('.//ch_id').text
|
|
|
|
|
uploader = video_info.find('.//ch_name').text
|
2014-07-01 11:13:12 -07:00
|
|
|
|
elif video_info.find('.//user_id') is not None:
|
2014-07-04 08:05:46 -07:00
|
|
|
|
uploader_id = video_info.find('.//user_id').text
|
|
|
|
|
uploader = video_info.find('.//user_nickname').text
|
|
|
|
|
else:
|
|
|
|
|
uploader_id = uploader = None
|
2013-11-23 01:19:44 -08:00
|
|
|
|
|
2015-04-29 11:24:05 -07:00
|
|
|
|
return {
|
2014-03-27 13:01:09 -07:00
|
|
|
|
'id': video_id,
|
|
|
|
|
'url': video_real_url,
|
2014-07-04 08:05:46 -07:00
|
|
|
|
'title': title,
|
|
|
|
|
'ext': extension,
|
2015-06-14 14:43:33 -07:00
|
|
|
|
'format_id': 'economy' if video_real_url.endswith('low') else 'normal',
|
2014-07-04 08:05:46 -07:00
|
|
|
|
'thumbnail': thumbnail,
|
|
|
|
|
'description': description,
|
|
|
|
|
'uploader': uploader,
|
2015-04-29 09:24:24 -07:00
|
|
|
|
'timestamp': timestamp,
|
2014-07-04 08:05:46 -07:00
|
|
|
|
'uploader_id': uploader_id,
|
|
|
|
|
'view_count': view_count,
|
|
|
|
|
'comment_count': comment_count,
|
|
|
|
|
'duration': duration,
|
|
|
|
|
'webpage_url': webpage_url,
|
2013-11-23 01:19:44 -08:00
|
|
|
|
}
|
2014-10-29 03:04:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class NiconicoPlaylistIE(InfoExtractor):
|
2016-09-08 04:29:05 -07:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/mylist/(?P<id>\d+)'
|
2014-10-29 03:04:48 -07:00
|
|
|
|
|
|
|
|
|
_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 12:39:15 -08:00
|
|
|
|
webpage, 'entries')
|
2014-10-29 03:04:48 -07:00
|
|
|
|
entries = json.loads(entries_json)
|
|
|
|
|
entries = [{
|
|
|
|
|
'_type': 'url',
|
|
|
|
|
'ie_key': NiconicoIE.ie_key(),
|
2014-11-08 05:53:23 -08:00
|
|
|
|
'url': ('http://www.nicovideo.jp/watch/%s' %
|
2014-11-23 12:39:15 -08:00
|
|
|
|
entry['item_data']['video_id']),
|
2014-10-29 03:04:48 -07:00
|
|
|
|
} for entry in entries]
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
'_type': 'playlist',
|
|
|
|
|
'title': self._search_regex(r'\s+name: "(.*?)"', webpage, 'title'),
|
|
|
|
|
'id': list_id,
|
|
|
|
|
'entries': entries,
|
|
|
|
|
}
|