aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/bbc.py
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2017-05-26 22:12:24 +0700
committerSergey M․ <dstftw@gmail.com>2017-05-26 22:12:24 +0700
commit97067db2ae32b18ef573af99b91d36026b4b1d05 (patch)
tree71953bc2f50d127219d3374ffcad5d94127086c4 /youtube_dl/extractor/bbc.py
parentc130f0a37b5c31fa559373ec319f79830c591c22 (diff)
downloadyoutube-dl-97067db2ae32b18ef573af99b91d36026b4b1d05.zip
youtube-dl-97067db2ae32b18ef573af99b91d36026b4b1d05.tar.gz
youtube-dl-97067db2ae32b18ef573af99b91d36026b4b1d05.tar.bz2
[bbc] Add support for authentication
Diffstat (limited to 'youtube_dl/extractor/bbc.py')
-rw-r--r--youtube_dl/extractor/bbc.py40
1 files changed, 40 insertions, 0 deletions
diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py
index dd65b8d..7cd4446 100644
--- a/youtube_dl/extractor/bbc.py
+++ b/youtube_dl/extractor/bbc.py
@@ -6,14 +6,18 @@ import itertools
from .common import InfoExtractor
from ..utils import (
+ clean_html,
dict_get,
ExtractorError,
float_or_none,
+ get_element_by_class,
int_or_none,
parse_duration,
parse_iso8601,
try_get,
unescapeHTML,
+ urlencode_postdata,
+ urljoin,
)
from ..compat import (
compat_etree_fromstring,
@@ -38,6 +42,9 @@ class BBCCoUkIE(InfoExtractor):
(?P<id>%s)(?!/(?:episodes|broadcasts|clips))
''' % _ID_REGEX
+ _LOGIN_URL = 'https://account.bbc.com/signin'
+ _NETRC_MACHINE = 'bbc'
+
_MEDIASELECTOR_URLS = [
# 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.
@@ -227,6 +234,39 @@ class BBCCoUkIE(InfoExtractor):
_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):
def __init__(self, id):
self.id = id