w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[bbc] Add support for authentication

Browse source
This commit is contained in:
Sergey M․ 2017-05-26 22:12:24 +07:00
parent c130f0a37b
commit 97067db2ae
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 40 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

40
youtube_dl/extractor/bbc.py
View file

@ -6,14 +6,18 @@ import itertools
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
clean_html,
dict_get, dict_get,
ExtractorError, ExtractorError,
float_or_none, float_or_none,
get_element_by_class,
int_or_none, int_or_none,
parse_duration, parse_duration,
parse_iso8601, parse_iso8601,
try_get, try_get,
unescapeHTML, unescapeHTML,
urlencode_postdata,
urljoin,
) )
from ..compat import ( from ..compat import (
compat_etree_fromstring, compat_etree_fromstring,
@ -38,6 +42,9 @@ class BBCCoUkIE(InfoExtractor):
(?P<id>%s)(?!/(?:episodes|broadcasts|clips)) (?P<id>%s)(?!/(?:episodes|broadcasts|clips))
''' % _ID_REGEX ''' % _ID_REGEX
_LOGIN_URL = 'https://account.bbc.com/signin'
_NETRC_MACHINE = 'bbc'
_MEDIASELECTOR_URLS = [ _MEDIASELECTOR_URLS = [
# Provides HQ HLS streams with even better quality that pc mediaset but fails # Provides HQ HLS streams with even better quality that pc mediaset but fails
# with geolocation in some cases when it's even not geo restricted at all (e.g. # with geolocation in some cases when it's even not geo restricted at all (e.g.
@ -227,6 +234,39 @@ class BBCCoUkIE(InfoExtractor):
_USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8' _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'
def _login(self):
username, password = self._get_login_info()
if username is None:
return
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading signin page')
login_form = self._hidden_inputs(login_page)
login_form.update({
'username': username,
'password': password,
})
post_url = urljoin(self._LOGIN_URL, self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
'post url', default=self._LOGIN_URL, group='url'))
response, urlh = self._download_webpage_handle(
post_url, None, 'Logging in', data=urlencode_postdata(login_form),
headers={'Referer': self._LOGIN_URL})
if self._LOGIN_URL in urlh.geturl():
error = clean_html(get_element_by_class('form-message', response))
if error:
raise ExtractorError(
'Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
def _real_initialize(self):
self._login()
class MediaSelectionError(Exception): class MediaSelectionError(Exception):
def __init__(self, id): def __init__(self, id):
self.id = id self.id = id