# coding: utf-8
from __future__ import unicode_literals
-import re
import itertools
+import re
+import xml
from .common import InfoExtractor
from ..utils import (
parse_iso8601,
try_get,
unescapeHTML,
+ url_or_none,
urlencode_postdata,
urljoin,
)
def _get_subtitles(self, media, programme_id):
subtitles = {}
for connection in self._extract_connections(media):
- captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
+ cc_url = url_or_none(connection.get('href'))
+ if not cc_url:
+ continue
+ captions = self._download_xml(
+ cc_url, programme_id, 'Downloading captions', fatal=False)
+ if not isinstance(captions, xml.etree.ElementTree.Element):
+ continue
lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
subtitles[lang] = [
{