2013-11-23 09:19:44 +00:00
|
|
|
|
# encoding: utf-8
|
2014-03-27 20:01:09 +00:00
|
|
|
|
from __future__ import unicode_literals
|
2013-11-23 09:19:44 +00:00
|
|
|
|
|
|
|
|
|
import re
|
2014-10-29 10:04:48 +00:00
|
|
|
|
import json
|
2013-11-23 09:19:44 +00:00
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2014-12-13 11:24:42 +00:00
|
|
|
|
from ..compat import (
|
2013-11-23 09:19:44 +00:00
|
|
|
|
compat_urllib_parse,
|
|
|
|
|
compat_urllib_request,
|
|
|
|
|
compat_urlparse,
|
2014-12-13 11:24:42 +00:00
|
|
|
|
)
|
|
|
|
|
from ..utils import (
|
2014-11-05 18:52:34 +00:00
|
|
|
|
ExtractorError,
|
2014-12-13 11:24:42 +00:00
|
|
|
|
int_or_none,
|
|
|
|
|
parse_duration,
|
2015-04-29 16:24:24 +00:00
|
|
|
|
parse_iso8601,
|
|
|
|
|
xpath_text,
|
|
|
|
|
determine_ext,
|
2013-11-23 09:19:44 +00:00
|
|
|
|
)
|
|
|
|
|
|
2013-11-24 05:37:14 +00:00
|
|
|
|
|
2013-11-23 09:19:44 +00:00
|
|
|
|
class NiconicoIE(InfoExtractor):
|
2014-03-27 20:01:09 +00:00
|
|
|
|
IE_NAME = 'niconico'
|
|
|
|
|
IE_DESC = 'ニコニコ動画'
|
2013-11-23 09:19:44 +00:00
|
|
|
|
|
2015-03-20 14:53:14 +00:00
|
|
|
|
_TESTS = [{
|
2014-03-27 20:01:09 +00:00
|
|
|
|
'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 16:24:24 +00:00
|
|
|
|
'timestamp': 1385182762,
|
2014-03-27 20:01:09 +00:00
|
|
|
|
'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
|
2014-07-04 15:05:46 +00:00
|
|
|
|
'duration': 33,
|
2013-11-23 09:19:44 +00:00
|
|
|
|
},
|
2015-03-20 14:53:14 +00:00
|
|
|
|
}, {
|
2015-04-29 16:47:52 +00:00
|
|
|
|
# File downloaded with and without credentials are different, so omit
|
|
|
|
|
# the md5 field
|
2015-03-20 14:53:14 +00:00
|
|
|
|
'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 16:24:24 +00:00
|
|
|
|
'description': 'md5:689f066d74610b3b22e0f1739add0f58',
|
2015-03-20 14:53:14 +00:00
|
|
|
|
'uploader': 'りょうた',
|
|
|
|
|
'uploader_id': '18822557',
|
|
|
|
|
'upload_date': '20110429',
|
2015-04-29 16:24:24 +00:00
|
|
|
|
'timestamp': 1304065916,
|
2015-03-20 14:53:14 +00:00
|
|
|
|
'duration': 209,
|
|
|
|
|
},
|
2015-04-29 16:24:24 +00:00
|
|
|
|
}, {
|
|
|
|
|
# 'video exists but is marked as "deleted"
|
|
|
|
|
'url': 'http://www.nicovideo.jp/watch/sm10000',
|
|
|
|
|
'md5': '38e53c9aad548f3ecf01ca7680b59b08',
|
|
|
|
|
'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>',
|
|
|
|
|
},
|
2015-03-20 14:53:14 +00:00
|
|
|
|
}]
|
2013-11-23 09:19:44 +00:00
|
|
|
|
|
2015-03-09 17:12:41 +00:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
|
2013-11-23 09:19:44 +00:00
|
|
|
|
_NETRC_MACHINE = 'niconico'
|
2014-10-12 20:18:42 +00:00
|
|
|
|
# Determine whether the downloader used authentication to download video
|
|
|
|
|
_AUTHENTICATED = False
|
2013-11-23 09:19:44 +00:00
|
|
|
|
|
|
|
|
|
def _real_initialize(self):
|
2014-10-12 20:18:42 +00:00
|
|
|
|
self._login()
|
2013-11-23 09:19:44 +00:00
|
|
|
|
|
|
|
|
|
def _login(self):
|
|
|
|
|
(username, password) = self._get_login_info()
|
2014-10-12 20:18:42 +00:00
|
|
|
|
# No authentication to be performed
|
|
|
|
|
if not username:
|
|
|
|
|
return True
|
2013-11-23 09:19:44 +00:00
|
|
|
|
|
|
|
|
|
# Log in
|
|
|
|
|
login_form_strs = {
|
2014-03-27 20:01:09 +00:00
|
|
|
|
'mail': username,
|
|
|
|
|
'password': password,
|
2013-11-23 09:19:44 +00:00
|
|
|
|
}
|
|
|
|
|
# Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
|
|
|
|
|
# chokes on unicode
|
2014-03-27 20:01:09 +00:00
|
|
|
|
login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
|
2013-11-24 05:37:14 +00:00
|
|
|
|
login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
|
|
|
|
|
request = compat_urllib_request.Request(
|
2014-03-27 20:01:09 +00:00
|
|
|
|
'https://secure.nicovideo.jp/secure/login', login_data)
|
2013-11-24 05:37:14 +00:00
|
|
|
|
login_results = self._download_webpage(
|
2014-03-27 20:01:09 +00:00
|
|
|
|
request, None, note='Logging in', errnote='Unable to log in')
|
2013-11-24 05:37:14 +00:00
|
|
|
|
if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None:
|
2014-03-27 20:01:09 +00:00
|
|
|
|
self._downloader.report_warning('unable to log in: bad username or password')
|
2013-11-23 09:19:44 +00:00
|
|
|
|
return False
|
2014-10-12 20:18:42 +00:00
|
|
|
|
# Successful login
|
|
|
|
|
self._AUTHENTICATED = True
|
2013-11-23 09:19:44 +00:00
|
|
|
|
return True
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2015-03-09 17:12:41 +00:00
|
|
|
|
video_id = self._match_id(url)
|
2013-11-23 09:19:44 +00:00
|
|
|
|
|
2015-04-29 16:24:24 +00:00
|
|
|
|
# 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 = self._download_webpage('http://www.nicovideo.jp/watch/' + video_id, video_id)
|
2013-11-23 09:19:44 +00:00
|
|
|
|
|
2013-11-26 17:48:52 +00:00
|
|
|
|
video_info = self._download_xml(
|
2013-11-24 05:37:14 +00:00
|
|
|
|
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
|
2014-03-27 20:01:09 +00:00
|
|
|
|
note='Downloading video info page')
|
2013-11-23 09:19:44 +00:00
|
|
|
|
|
2014-10-12 20:18:42 +00:00
|
|
|
|
if self._AUTHENTICATED:
|
2014-07-01 17:32:54 +00:00
|
|
|
|
# Get flv info
|
|
|
|
|
flv_info_webpage = self._download_webpage(
|
2015-03-18 13:19:55 +00:00
|
|
|
|
'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
|
2014-07-01 17:32:54 +00:00
|
|
|
|
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 13:24:17 +00:00
|
|
|
|
|
2014-07-01 17:32:54 +00:00
|
|
|
|
# Get flv info
|
|
|
|
|
flv_info_data = compat_urllib_parse.urlencode({
|
|
|
|
|
'k': thumb_play_key,
|
|
|
|
|
'v': video_id
|
|
|
|
|
})
|
|
|
|
|
flv_info_request = compat_urllib_request.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')
|
|
|
|
|
|
2015-04-29 16:24:24 +00:00
|
|
|
|
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)
|
|
|
|
|
else:
|
|
|
|
|
raise ExtractorError('Unable to find video URL')
|
|
|
|
|
|
|
|
|
|
video_real_url = flv_info['url'][0]
|
2013-11-23 09:19:44 +00:00
|
|
|
|
|
|
|
|
|
# Start extracting information
|
2015-04-29 16:24:24 +00:00
|
|
|
|
title = xpath_text(video_info, './/title')
|
2015-04-29 16:47:52 +00:00
|
|
|
|
if not title:
|
|
|
|
|
title = self._og_search_title(webpage, default=None)
|
2015-04-29 16:24:24 +00:00
|
|
|
|
if not title:
|
|
|
|
|
title = self._html_search_regex(
|
|
|
|
|
r'<span[^>]+class="videoHeaderTitle"[^>]*>([^<]+)</span>',
|
|
|
|
|
webpage, 'video title')
|
|
|
|
|
|
|
|
|
|
extension = xpath_text(video_info, './/movie_type')
|
|
|
|
|
if not extension:
|
|
|
|
|
extension = determine_ext(video_real_url)
|
2014-07-04 15:05:46 +00:00
|
|
|
|
video_format = extension.upper()
|
2015-04-29 16:24:24 +00:00
|
|
|
|
thumbnail = xpath_text(video_info, './/thumbnail_url')
|
|
|
|
|
description = xpath_text(video_info, './/description')
|
|
|
|
|
timestamp = parse_iso8601(xpath_text(video_info, './/first_retrieve'))
|
|
|
|
|
view_count = int_or_none(xpath_text(video_info, './/view_counter'))
|
|
|
|
|
comment_count = int_or_none(xpath_text(video_info, './/comment_num'))
|
|
|
|
|
duration = parse_duration(xpath_text(video_info, './/length'))
|
|
|
|
|
webpage_url = xpath_text(video_info, './/watch_url')
|
2014-07-04 15:05:46 +00:00
|
|
|
|
|
2014-07-01 18:13:12 +00:00
|
|
|
|
if video_info.find('.//ch_id') is not None:
|
2014-07-04 15:05:46 +00:00
|
|
|
|
uploader_id = video_info.find('.//ch_id').text
|
|
|
|
|
uploader = video_info.find('.//ch_name').text
|
2014-07-01 18:13:12 +00:00
|
|
|
|
elif video_info.find('.//user_id') is not None:
|
2014-07-04 15:05:46 +00:00
|
|
|
|
uploader_id = video_info.find('.//user_id').text
|
|
|
|
|
uploader = video_info.find('.//user_nickname').text
|
|
|
|
|
else:
|
|
|
|
|
uploader_id = uploader = None
|
2013-11-23 09:19:44 +00:00
|
|
|
|
|
2015-04-29 16:24:24 +00:00
|
|
|
|
ret = {
|
2014-03-27 20:01:09 +00:00
|
|
|
|
'id': video_id,
|
|
|
|
|
'url': video_real_url,
|
2014-07-04 15:05:46 +00:00
|
|
|
|
'title': title,
|
|
|
|
|
'ext': extension,
|
2014-03-27 20:01:09 +00:00
|
|
|
|
'format': video_format,
|
2014-07-04 15:05:46 +00:00
|
|
|
|
'thumbnail': thumbnail,
|
|
|
|
|
'description': description,
|
|
|
|
|
'uploader': uploader,
|
2015-04-29 16:24:24 +00:00
|
|
|
|
'timestamp': timestamp,
|
2014-07-04 15:05:46 +00:00
|
|
|
|
'uploader_id': uploader_id,
|
|
|
|
|
'view_count': view_count,
|
|
|
|
|
'comment_count': comment_count,
|
|
|
|
|
'duration': duration,
|
|
|
|
|
'webpage_url': webpage_url,
|
2013-11-23 09:19:44 +00:00
|
|
|
|
}
|
2015-04-29 16:24:24 +00:00
|
|
|
|
return dict((k, v) for k, v in ret.items() if v is not None)
|
2014-10-29 10:04:48 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 20:39:15 +00:00
|
|
|
|
webpage, 'entries')
|
2014-10-29 10:04:48 +00:00
|
|
|
|
entries = json.loads(entries_json)
|
|
|
|
|
entries = [{
|
|
|
|
|
'_type': 'url',
|
|
|
|
|
'ie_key': NiconicoIE.ie_key(),
|
2014-11-08 13:53:23 +00:00
|
|
|
|
'url': ('http://www.nicovideo.jp/watch/%s' %
|
2014-11-23 20:39:15 +00:00
|
|
|
|
entry['item_data']['video_id']),
|
2014-10-29 10:04:48 +00:00
|
|
|
|
} for entry in entries]
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
'_type': 'playlist',
|
|
|
|
|
'title': self._search_regex(r'\s+name: "(.*?)"', webpage, 'title'),
|
|
|
|
|
'id': list_id,
|
|
|
|
|
'entries': entries,
|
|
|
|
|
}
|