# coding: utf-8
from __future__ import unicode_literals
+
from .common import InfoExtractor
-from ..compat import compat_HTTPError
from ..utils import (
+ clean_html,
+ determine_ext,
encode_dict,
+ int_or_none,
sanitized_Request,
ExtractorError,
urlencode_postdata
)
-import re
class FunimationIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/.+[^ ]/videos/official/(?P<id>[^?]+)'
+ _VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/(?:official|promotional)/(?P<id>[^/?#&]+)'
+
+ _NETRC_MACHINE = 'funimation'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.funimation.com/shows/air/videos/official/breeze',
'info_dict': {
- 'id': 'AIRENG0001',
- 'title': 'Air - 1 - Breeze ',
+ 'id': '658',
+ 'display_id': 'breeze',
'ext': 'mp4',
- 'thumbnail': 'http://www.funimation.com/admin/uploads/default/recap_thumbnails/7555590/home_spotlight/AIR0001.jpg',
- 'description': 'Travelling puppeteer Yukito arrives in a small town where he hopes to earn money through the magic of his puppets. When a young girl named Misuzu lures him to her home with the promise of food, his life changes forever. ',
- }
- }
+ 'title': 'Air - 1 - Breeze',
+ 'description': 'md5:1769f43cd5fc130ace8fd87232207892',
+ 'thumbnail': 're:https?://.*\.jpg',
+ },
+ }, {
+ 'url': 'http://www.funimation.com/shows/hacksign/videos/official/role-play',
+ 'info_dict': {
+ 'id': '31128',
+ 'display_id': 'role-play',
+ 'ext': 'mp4',
+ 'title': '.hack//SIGN - 1 - Role Play',
+ 'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd',
+ 'thumbnail': 're:https?://.*\.jpg',
+ },
+ }, {
+ 'url': 'http://www.funimation.com/shows/attack-on-titan-junior-high/videos/promotional/broadcast-dub-preview',
+ 'info_dict': {
+ 'id': '9635',
+ 'display_id': 'broadcast-dub-preview',
+ 'ext': 'mp4',
+ 'title': 'Attack on Titan: Junior High - Broadcast Dub Preview',
+ 'description': 'md5:f8ec49c0aff702a7832cd81b8a44f803',
+ 'thumbnail': 're:https?://.*\.(?:jpg|png)',
+ },
+ }]
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
- login_url = 'http://www.funimation.com/login'
data = urlencode_postdata(encode_dict({
- 'loginForm2': 'loginform',
'email_field': username,
'password_field': password,
}))
- login_request = sanitized_Request(login_url, data)
- login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
- try:
- login = self._download_webpage(
- login_request, None, 'Logging in as %s' % username)
- except ExtractorError as e:
- if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
- raise ExtractorError('Funimation is not available in your region.', expected=True)
- raise
- if re.search(r'<meta property="og:url" content="http://www.funimation.com/login"/>', login) is not None:
- raise ExtractorError('Unable to login, wrong username or password.', expected=True)
+ login_request = sanitized_Request('http://www.funimation.com/login', data, headers={
+ 'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0',
+ 'Content-Type': 'application/x-www-form-urlencoded'
+ })
+ login_page = self._download_webpage(
+ login_request, None, 'Logging in as %s' % username)
+ if any(p in login_page for p in ('funimation.com/logout', '>Log Out<')):
+ return
+ error = self._html_search_regex(
+ r'(?s)<div[^>]+id=["\']errorMessages["\'][^>]*>(.+?)</div>',
+ login_page, 'error messages', default=None)
+ if error:
+ raise ExtractorError('Unable to login: %s' % error, expected=True)
+ raise ExtractorError('Unable to log in')
def _real_initialize(self):
self._login()
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
- try:
- webpage = self._download_webpage(url, video_id)
- except ExtractorError as e:
- if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
- raise ExtractorError('Funimation is not available in your region.', expected=True)
- raise
- if re.search(r'"sdUrl":"http', webpage) is None:
- raise ExtractorError('You are not logged-in or the stream requires subscription.', expected=True)
-
- m3u8 = self._search_regex(r'".+Url":"(.+?m3u8)"', webpage, 'm3u8') + self._search_regex(r'"authToken":"(.+?)"', webpage, 'm3u8')
- formats = self._extract_m3u8_formats(m3u8.replace('\\', ''), video_id, ext='mp4', entry_protocol='m3u8_native')
-
- video_show = self._search_regex(r'"artist":"(.+?)"', webpage, 'video_show')
- video_track = self._search_regex(r'"videoNumber":"(\d+).0"', webpage, 'video_track')
- video_title = self._search_regex(r'"title":"({0}.+?)"'.format(video_track), webpage, 'video_title')
- video_id = self._search_regex(r'"FUNImationID":"(.+?)"', webpage, 'video_id')
+ display_id = self._match_id(url)
+
+ errors = []
+ formats = []
+
+ ERRORS_MAP = {
+ 'ERROR_MATURE_CONTENT_LOGGED_IN': 'matureContentLoggedIn',
+ 'ERROR_MATURE_CONTENT_LOGGED_OUT': 'matureContentLoggedOut',
+ 'ERROR_SUBSCRIPTION_LOGGED_OUT': 'subscriptionLoggedOut',
+ 'ERROR_VIDEO_EXPIRED': 'videoExpired',
+ 'ERROR_TERRITORY_UNAVAILABLE': 'territoryUnavailable',
+ 'SVODBASIC_SUBSCRIPTION_IN_PLAYER': 'basicSubscription',
+ 'SVODNON_SUBSCRIPTION_IN_PLAYER': 'nonSubscription',
+ 'ERROR_PLAYER_NOT_RESPONDING': 'playerNotResponding',
+ 'ERROR_UNABLE_TO_CONNECT_TO_CDN': 'unableToConnectToCDN',
+ 'ERROR_STREAM_NOT_FOUND': 'streamNotFound',
+ }
+
+ USER_AGENTS = (
+ # PC UA is served with m3u8 that provides some bonus lower quality formats
+ ('pc', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0'),
+ # Mobile UA allows to extract direct links and also does not fail when
+ # PC UA fails with hulu error (e.g.
+ # http://www.funimation.com/shows/hacksign/videos/official/role-play)
+ ('mobile', 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'),
+ )
+
+ for kind, user_agent in USER_AGENTS:
+ request = sanitized_Request(url)
+ request.add_header('User-Agent', user_agent)
+ webpage = self._download_webpage(
+ request, display_id, 'Downloading %s webpage' % kind)
+
+ playlist = self._parse_json(
+ self._search_regex(
+ r'var\s+playersData\s*=\s*(\[.+?\]);\n',
+ webpage, 'players data'),
+ display_id)[0]['playlist']
+
+ items = next(item['items'] for item in playlist if item.get('items'))
+ item = next(item for item in items if item.get('itemAK') == display_id)
+
+ error_messages = {}
+ video_error_messages = self._search_regex(
+ r'var\s+videoErrorMessages\s*=\s*({.+?});\n',
+ webpage, 'error messages', default=None)
+ if video_error_messages:
+ error_messages_json = self._parse_json(video_error_messages, display_id, fatal=False)
+ if error_messages_json:
+ for _, error in error_messages_json.items():
+ type_ = error.get('type')
+ description = error.get('description')
+ content = error.get('content')
+ if type_ == 'text' and description and content:
+ error_message = ERRORS_MAP.get(description)
+ if error_message:
+ error_messages[error_message] = content
+
+ for video in item.get('videoSet', []):
+ auth_token = video.get('authToken')
+ if not auth_token:
+ continue
+ funimation_id = video.get('FUNImationID') or video.get('videoId')
+ preference = 1 if video.get('languageMode') == 'dub' else 0
+ if not auth_token.startswith('?'):
+ auth_token = '?%s' % auth_token
+ for quality, height in (('sd', 480), ('hd', 720), ('hd1080', 1080)):
+ format_url = video.get('%sUrl' % quality)
+ if not format_url:
+ continue
+ if not format_url.startswith(('http', '//')):
+ errors.append(format_url)
+ continue
+ if determine_ext(format_url) == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native',
+ preference=preference, m3u8_id='%s-hls' % funimation_id, fatal=False))
+ else:
+ tbr = int_or_none(self._search_regex(
+ r'-(\d+)[Kk]', format_url, 'tbr', default=None))
+ formats.append({
+ 'url': format_url + auth_token,
+ 'format_id': '%s-http-%dp' % (funimation_id, height),
+ 'height': height,
+ 'tbr': tbr,
+ 'preference': preference,
+ })
+
+ if not formats and errors:
+ raise ExtractorError(
+ '%s returned error: %s'
+ % (self.IE_NAME, clean_html(error_messages.get(errors[0], errors[0]))),
+ expected=True)
+
+ self._sort_formats(formats)
+
+ title = item['title']
+ artist = item.get('artist')
+ if artist:
+ title = '%s - %s' % (artist, title)
+ description = self._og_search_description(webpage) or item.get('description')
+ thumbnail = self._og_search_thumbnail(webpage) or item.get('posterUrl')
+ video_id = item.get('itemId') or display_id
return {
'id': video_id,
- 'title': video_show + ' - ' + video_title + ' ',
+ 'display_id': display_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
'formats': formats,
- 'thumbnail': self._og_search_thumbnail(webpage),
- 'description': self._og_search_description(webpage)
}
projects / youtube-dl / blobdiff