[crunchyroll] Bypass maturity wall (Closes #7202)

This commit is contained in:
Sergey M․ 2015-10-18 06:57:57 +06:00
parent 5a11b793fe
commit 80f48920c8

View File

@ -32,6 +32,26 @@
class CrunchyrollBaseIE(InfoExtractor): class CrunchyrollBaseIE(InfoExtractor):
_NETRC_MACHINE = 'crunchyroll'
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
self.report_login()
login_url = 'https://www.crunchyroll.com/?a=formhandler'
data = urlencode_postdata({
'formname': 'RpcApiUser_Login',
'name': username,
'password': password,
})
login_request = compat_urllib_request.Request(login_url, data)
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
self._download_webpage(login_request, None, False, 'Wrong login info')
def _real_initialize(self):
self._login()
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None): def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request) request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
else compat_urllib_request.Request(url_or_request)) else compat_urllib_request.Request(url_or_request))
@ -46,10 +66,22 @@ def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, f
return super(CrunchyrollBaseIE, self)._download_webpage( return super(CrunchyrollBaseIE, self)._download_webpage(
request, video_id, note, errnote, fatal, tries, timeout, encoding) request, video_id, note, errnote, fatal, tries, timeout, encoding)
@staticmethod
def _add_skip_wall(url):
parsed_url = compat_urlparse.urlparse(url)
qs = compat_urlparse.parse_qs(parsed_url.query)
# Always force skip_wall to bypass maturity wall, namely 18+ confirmation message:
# > This content may be inappropriate for some people.
# > Are you sure you want to continue?
# since it's not disabled by default in crunchyroll account's settings.
# See https://github.com/rg3/youtube-dl/issues/7202.
qs['skip_wall'] = ['1']
return compat_urlparse.urlunparse(
parsed_url._replace(query=compat_urllib_parse.urlencode(qs, True)))
class CrunchyrollIE(CrunchyrollBaseIE): class CrunchyrollIE(CrunchyrollBaseIE):
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)' _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
_NETRC_MACHINE = 'crunchyroll'
_TESTS = [{ _TESTS = [{
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
'info_dict': { 'info_dict': {
@ -81,7 +113,6 @@ class CrunchyrollIE(CrunchyrollBaseIE):
# rtmp # rtmp
'skip_download': True, 'skip_download': True,
}, },
}, { }, {
'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697', 'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
'only_matching': True, 'only_matching': True,
@ -94,24 +125,6 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'1080': ('80', '108'), '1080': ('80', '108'),
} }
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
self.report_login()
login_url = 'https://www.crunchyroll.com/?a=formhandler'
data = urlencode_postdata({
'formname': 'RpcApiUser_Login',
'name': username,
'password': password,
})
login_request = compat_urllib_request.Request(login_url, data)
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
self._download_webpage(login_request, None, False, 'Wrong login info')
def _real_initialize(self):
self._login()
def _decrypt_subtitles(self, data, iv, id): def _decrypt_subtitles(self, data, iv, id):
data = bytes_to_intlist(base64.b64decode(data.encode('utf-8'))) data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8'))) iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8')))
@ -254,7 +267,7 @@ def _real_extract(self, url):
else: else:
webpage_url = 'http://www.' + mobj.group('url') webpage_url = 'http://www.' + mobj.group('url')
webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage') webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage')
note_m = self._html_search_regex( note_m = self._html_search_regex(
r'<div class="showmedia-trailer-notice">(.+?)</div>', r'<div class="showmedia-trailer-notice">(.+?)</div>',
webpage, 'trailer-notice', default='') webpage, 'trailer-notice', default='')
@ -352,7 +365,7 @@ def _real_extract(self, url):
class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE): class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
IE_NAME = "crunchyroll:playlist" IE_NAME = "crunchyroll:playlist"
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?$' _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?(?:\?|$)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi', 'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
@ -366,7 +379,7 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
def _real_extract(self, url): def _real_extract(self, url):
show_id = self._match_id(url) show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id) webpage = self._download_webpage(self._add_skip_wall(url), show_id)
title = self._html_search_regex( title = self._html_search_regex(
r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>', r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
webpage, 'title') webpage, 'title')