diff options
Diffstat (limited to 'youtube_dl/extractor/funimation.py')
| -rw-r--r-- | youtube_dl/extractor/funimation.py | 66 |
1 files changed, 24 insertions, 42 deletions
diff --git a/youtube_dl/extractor/funimation.py b/youtube_dl/extractor/funimation.py index e44a2a87f..8c37509ec 100644 --- a/youtube_dl/extractor/funimation.py +++ b/youtube_dl/extractor/funimation.py @@ -2,15 +2,11 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_urllib_parse_unquote_plus, -) +from ..compat import compat_HTTPError from ..utils import ( determine_ext, int_or_none, js_to_json, - sanitized_Request, ExtractorError, urlencode_postdata ) @@ -20,6 +16,7 @@ class FunimationIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/shows/[^/]+/(?P<id>[^/?#&]+)' _NETRC_MACHINE = 'funimation' + _TOKEN = None _TESTS = [{ 'url': 'https://www.funimation.com/shows/hacksign/role-play/', @@ -38,56 +35,38 @@ class FunimationIE(InfoExtractor): }, { 'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/', 'info_dict': { - 'id': '9635', + 'id': '210051', 'display_id': 'broadcast-dub-preview', 'ext': 'mp4', 'title': 'Attack on Titan: Junior High - Broadcast Dub Preview', - 'description': 'md5:f8ec49c0aff702a7832cd81b8a44f803', 'thumbnail': r're:https?://.*\.(?:jpg|png)', }, - 'skip': 'Access without user interaction is forbidden by CloudFlare', + 'params': { + # m3u8 download + 'skip_download': True, + }, }, { 'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/', 'only_matching': True, }] - _LOGIN_URL = 'http://www.funimation.com/login' - - def _extract_cloudflare_session_ua(self, url): - ci_session_cookie = self._get_cookies(url).get('ci_session') - if ci_session_cookie: - ci_session = compat_urllib_parse_unquote_plus(ci_session_cookie.value) - # ci_session is a string serialized by PHP function serialize() - # This case is simple enough to use regular expressions only - return self._search_regex( - r'"user_agent";s:\d+:"([^"]+)"', ci_session, 'user agent', - default=None) - def _login(self): (username, password) = self._get_login_info() if username is None: return - data = urlencode_postdata({ - 'email_field': username, - 'password_field': password, - }) - user_agent = self._extract_cloudflare_session_ua(self._LOGIN_URL) - if not user_agent: - user_agent = 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0' - login_request = sanitized_Request(self._LOGIN_URL, data, headers={ - 'User-Agent': user_agent, - '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') + try: + data = self._download_json( + 'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/', + None, 'Logging in as %s' % username, 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() @@ -125,9 +104,12 @@ class FunimationIE(InfoExtractor): 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)['items'] + 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] |