diff options
author | fnord <fnord@fnord.mobi> | 2015-06-25 00:34:46 -0500 |
---|---|---|
committer | fnord <fnord@fnord.mobi> | 2015-06-25 00:34:46 -0500 |
commit | aa5740fb61d388754e9278a3e38de12203c1b89d (patch) | |
tree | 8195c113270d167f57225bdaa6f89df807341968 /youtube_dl/extractor/bbc.py | |
parent | da92eeae42f556926cb676b3c14e270603b7e38e (diff) | |
parent | 18b5e1e5348ba3a6d1b6a98e97217eebb3d32a1e (diff) |
Merge remote-tracking branch 'origin/master' into pr-bbcnews
Diffstat (limited to 'youtube_dl/extractor/bbc.py')
-rw-r--r-- | youtube_dl/extractor/bbc.py | 15 |
1 files changed, 0 insertions, 15 deletions
diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index bb671d473..471d865d2 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -255,26 +255,11 @@ class BBCCoUkIE(InfoExtractor): for connection in self._extract_connections(media): captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions') lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') - ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/2006/10/ttaf1}')) - srt = '' - - def _extract_text(p): - if p.text is not None: - stripped_text = p.text.strip() - if stripped_text: - return stripped_text - return ' '.join(span.text.strip() for span in p.findall('{http://www.w3.org/2006/10/ttaf1}span')) - for pos, p in enumerate(ps): - srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), p.get('begin'), p.get('end'), _extract_text(p)) subtitles[lang] = [ { 'url': connection.get('href'), 'ext': 'ttml', }, - { - 'data': srt, - 'ext': 'srt', - }, ] return subtitles |