[niconico] Modernize

This commit is contained in:
Jaime Marquínez Ferrándiz 2014-03-27 21:01:09 +01:00
parent 8cdafb47b9
commit 214c22c704
1 changed files with 38 additions and 43 deletions

View File

@ -1,12 +1,10 @@
# encoding: utf-8 # encoding: utf-8
from __future__ import unicode_literals
import re import re
import socket
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_http_client,
compat_urllib_error,
compat_urllib_parse, compat_urllib_parse,
compat_urllib_request, compat_urllib_request,
compat_urlparse, compat_urlparse,
@ -18,57 +16,54 @@ from ..utils import (
class NiconicoIE(InfoExtractor): class NiconicoIE(InfoExtractor):
IE_NAME = u'niconico' IE_NAME = 'niconico'
IE_DESC = u'ニコニコ動画' IE_DESC = 'ニコニコ動画'
_TEST = { _TEST = {
u'url': u'http://www.nicovideo.jp/watch/sm22312215', 'url': 'http://www.nicovideo.jp/watch/sm22312215',
u'file': u'sm22312215.mp4', 'md5': 'd1a75c0823e2f629128c43e1212760f9',
u'md5': u'd1a75c0823e2f629128c43e1212760f9', 'info_dict': {
u'info_dict': { 'id': 'sm22312215',
u'title': u'Big Buck Bunny', 'ext': 'mp4',
u'uploader': u'takuya0301', 'title': 'Big Buck Bunny',
u'uploader_id': u'2698420', 'uploader': 'takuya0301',
u'upload_date': u'20131123', 'uploader_id': '2698420',
u'description': u'(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org', 'upload_date': '20131123',
'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
}, },
u'params': { 'params': {
u'username': u'ydl.niconico@gmail.com', 'username': 'ydl.niconico@gmail.com',
u'password': u'youtube-dl', 'password': 'youtube-dl',
}, },
} }
_VALID_URL = r'^https?://(?:www\.|secure\.)?nicovideo\.jp/watch/([a-z][a-z][0-9]+)(?:.*)$' _VALID_URL = r'^https?://(?:www\.|secure\.)?nicovideo\.jp/watch/([a-z][a-z][0-9]+)(?:.*)$'
_NETRC_MACHINE = 'niconico' _NETRC_MACHINE = 'niconico'
# If True it will raise an error if no login info is provided
_LOGIN_REQUIRED = True
def _real_initialize(self): def _real_initialize(self):
self._login() self._login()
def _login(self): def _login(self):
(username, password) = self._get_login_info() (username, password) = self._get_login_info()
# No authentication to be performed
if username is None: if username is None:
if self._LOGIN_REQUIRED: # Login is required
raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True) raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
return False
# Log in # Log in
login_form_strs = { login_form_strs = {
u'mail': username, 'mail': username,
u'password': password, 'password': password,
} }
# Convert to UTF-8 *before* urlencode because Python 2.x's urlencode # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
# chokes on unicode # chokes on unicode
login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items()) login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8') login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
request = compat_urllib_request.Request( request = compat_urllib_request.Request(
u'https://secure.nicovideo.jp/secure/login', login_data) 'https://secure.nicovideo.jp/secure/login', login_data)
login_results = self._download_webpage( login_results = self._download_webpage(
request, u'', note=u'Logging in', errnote=u'Unable to log in') 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: if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None:
self._downloader.report_warning(u'unable to log in: bad username or password') self._downloader.report_warning('unable to log in: bad username or password')
return False return False
return True return True
@ -82,12 +77,12 @@ class NiconicoIE(InfoExtractor):
video_info = self._download_xml( video_info = self._download_xml(
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id, 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
note=u'Downloading video info page') note='Downloading video info page')
# Get flv info # Get flv info
flv_info_webpage = self._download_webpage( flv_info_webpage = self._download_webpage(
u'http://flapi.nicovideo.jp/api/getflv?v=' + video_id, 'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,
video_id, u'Downloading flv info') video_id, 'Downloading flv info')
video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0] video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
# Start extracting information # Start extracting information
@ -106,22 +101,22 @@ class NiconicoIE(InfoExtractor):
url = 'http://seiga.nicovideo.jp/api/user/info?id=' + video_uploader_id url = 'http://seiga.nicovideo.jp/api/user/info?id=' + video_uploader_id
try: try:
user_info = self._download_xml( user_info = self._download_xml(
url, video_id, note=u'Downloading user information') url, video_id, note='Downloading user information')
video_uploader = user_info.find('.//nickname').text video_uploader = user_info.find('.//nickname').text
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except ExtractorError as err:
self._downloader.report_warning(u'Unable to download user info webpage: %s' % compat_str(err)) self._downloader.report_warning('Unable to download user info webpage: %s' % compat_str(err))
return { return {
'id': video_id, 'id': video_id,
'url': video_real_url, 'url': video_real_url,
'title': video_title, 'title': video_title,
'ext': video_extension, 'ext': video_extension,
'format': video_format, 'format': video_format,
'thumbnail': video_thumbnail, 'thumbnail': video_thumbnail,
'description': video_description, 'description': video_description,
'uploader': video_uploader, 'uploader': video_uploader,
'upload_date': video_upload_date, 'upload_date': video_upload_date,
'uploader_id': video_uploader_id, 'uploader_id': video_uploader_id,
'view_count': video_view_count, 'view_count': video_view_count,
'webpage_url': video_webpage_url, 'webpage_url': video_webpage_url,
} }