diff options
| author | Sergey M․ <dstftw@gmail.com> | 2019-02-24 21:01:25 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2019-02-24 21:01:25 +0700 |
| commit | f0228f56fb2441510aa966ba9298e388b209cde1 (patch) | |
| tree | e33a218bffb1dfd0e36379be8cd6412224fd917a | |
| parent | 8c80603f1adea843d96c0598b902106c7a3efb7f (diff) | |
[bbccouk] Make subtitles non fatal (#19651)
| -rw-r--r-- | youtube_dl/extractor/bbc.py | 12 |
1 files changed, 10 insertions, 2 deletions
diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index eac9a5a46..13340ec64 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -1,8 +1,9 @@ # coding: utf-8 from __future__ import unicode_literals -import re import itertools +import re +import xml from .common import InfoExtractor from ..utils import ( @@ -17,6 +18,7 @@ from ..utils import ( parse_iso8601, try_get, unescapeHTML, + url_or_none, urlencode_postdata, urljoin, ) @@ -310,7 +312,13 @@ class BBCCoUkIE(InfoExtractor): 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] = [ { |