# coding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
-from ..compat import compat_urllib_request
+from ..compat import compat_HTTPError
from ..utils import (
- clean_html,
determine_ext,
- encode_dict,
- sanitized_Request,
+ int_or_none,
+ js_to_json,
ExtractorError,
urlencode_postdata
)
class FunimationIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/official/(?P<id>[^?]+)'
+ _VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/shows/[^/]+/(?P<id>[^/?#&]+)'
+
+ _NETRC_MACHINE = 'funimation'
+ _TOKEN = None
- _TEST = {
- 'url': 'http://www.funimation.com/shows/air/videos/official/breeze',
+ _TESTS = [{
+ 'url': 'https://www.funimation.com/shows/hacksign/role-play/',
'info_dict': {
- 'id': 'AIRENG0001',
- 'title': 'Air - 1 - Breeze ',
+ 'id': '91144',
+ 'display_id': 'role-play',
'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. ',
- }
- }
-
- def _download_webpage(self, url_or_request, video_id, note='Downloading webpage'):
- HEADERS = {
- 'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0',
- }
- if isinstance(url_or_request, compat_urllib_request.Request):
- for header, value in HEADERS.items():
- url_or_request.add_header(header, value)
- else:
- url_or_request = sanitized_Request(url_or_request, headers=HEADERS)
- response = super(FunimationIE, self)._download_webpage(url_or_request, video_id, note)
- return response
+ 'title': '.hack//SIGN - Role Play',
+ 'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd',
+ 'thumbnail': r're:https?://.*\.jpg',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ }, {
+ 'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/',
+ 'info_dict': {
+ 'id': '210051',
+ 'display_id': 'broadcast-dub-preview',
+ 'ext': 'mp4',
+ 'title': 'Attack on Titan: Junior High - Broadcast Dub Preview',
+ 'thumbnail': r're:https?://.*\.(?:jpg|png)',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ }, {
+ 'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
+ 'only_matching': True,
+ }]
def _login(self):
- (username, password) = self._get_login_info()
+ username, password = self._get_login_info()
if username is None:
return
- data = urlencode_postdata(encode_dict({
- 'email_field': username,
- 'password_field': password,
- }))
- login_request = sanitized_Request('http://www.funimation.com/login', data, headers={
- 'Content-Type': 'application/x-www-form-urlencoded'
- })
- login = self._download_webpage(
- login_request, None, 'Logging in as %s' % username)
- 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)
+ try:
+ data = self._download_json(
+ 'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/',
+ None, 'Logging in', data=urlencode_postdata({
+ 'username': username,
+ 'password': password,
+ }))
+ self._TOKEN = data['token']
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+ error = self._parse_json(e.cause.read().decode(), None)['error']
+ raise ExtractorError(error, expected=True)
+ raise
def _real_initialize(self):
self._login()
def _real_extract(self, url):
display_id = self._match_id(url)
-
webpage = self._download_webpage(url, display_id)
- items = self._parse_json(
- self._search_regex(
- r'var\s+playersData\s*=\s*(\[.+?\]);\n',
- webpage, 'players data'),
- display_id)[0]['playlist'][0]['items']
-
- item = next(item for item in items if item.get('itemAK') == display_id)
-
- 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',
- }
+ def _search_kane(name):
+ return self._search_regex(
+ r"KANE_customdimensions\.%s\s*=\s*'([^']+)';" % name,
+ webpage, name, default=None)
+
+ title_data = self._parse_json(self._search_regex(
+ r'TITLE_DATA\s*=\s*({[^}]+})',
+ webpage, 'title data', default=''),
+ display_id, js_to_json, fatal=False) or {}
+
+ video_id = title_data.get('id') or self._search_regex([
+ r"KANE_customdimensions.videoID\s*=\s*'(\d+)';",
+ r'<iframe[^>]+src="/player/(\d+)"',
+ ], webpage, 'video_id', default=None)
+ if not video_id:
+ player_url = self._html_search_meta([
+ 'al:web:url',
+ 'og:video:url',
+ 'og:video:secure_url',
+ ], webpage, fatal=True)
+ video_id = self._search_regex(r'/player/(\d+)', player_url, 'video id')
+
+ title = episode = title_data.get('title') or _search_kane('videoTitle') or self._og_search_title(webpage)
+ series = _search_kane('showName')
+ if series:
+ title = '%s - %s' % (series, title)
+ description = self._html_search_meta(['description', 'og:description'], webpage, fatal=True)
+
+ try:
+ headers = {}
+ if self._TOKEN:
+ headers['Authorization'] = 'Token %s' % self._TOKEN
+ sources = self._download_json(
+ 'https://prod-api-funimationnow.dadcdigital.com/api/source/catalog/video/%s/signed/' % video_id,
+ video_id, headers=headers)['items']
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+ error = self._parse_json(e.cause.read(), video_id)['errors'][0]
+ raise ExtractorError('%s said: %s' % (
+ self.IE_NAME, error.get('detail') or error.get('title')), expected=True)
+ raise
- 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
-
- errors = []
formats = []
- for video in item['videoSet']:
- auth_token = video.get('authToken')
- if not auth_token:
+ for source in sources:
+ source_url = source.get('src')
+ if not source_url:
continue
- funimation_id = video.get('FUNImationID') or video.get('videoId')
- if not auth_token.startswith('?'):
- auth_token = '?%s' % auth_token
- for quality in ('sd', 'hd', 'hd1080'):
- 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':
- m3u8_formats = self._extract_m3u8_formats(
- format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native',
- m3u8_id=funimation_id or 'hls', fatal=False)
- if m3u8_formats:
- formats.extend(m3u8_formats)
- else:
- formats.append({
- 'url': format_url + auth_token,
- })
-
- 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)
-
- 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
+ source_type = source.get('videoType') or determine_ext(source_url)
+ if source_type == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ source_url, video_id, 'mp4',
+ m3u8_id='hls', fatal=False))
+ else:
+ formats.append({
+ 'format_id': source_type,
+ 'url': source_url,
+ })
+ self._sort_formats(formats)
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
- 'thumbnail': thumbnail,
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ 'series': series,
+ 'season_number': int_or_none(title_data.get('seasonNum') or _search_kane('season')),
+ 'episode_number': int_or_none(title_data.get('episodeNum')),
+ 'episode': episode,
+ 'season_id': title_data.get('seriesId'),
'formats': formats,
}