midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[bbccouk] Remove TTML to srt conversion codes

Browse source 
It's broken. See #6038
This commit is contained in:
Yen Chi Hsuan 2015-06-21 19:22:26 +08:00
parent 4e33577173
commit 78294e6a9c
1 changed files with 0 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
youtube_dl/extractor/bbccouk.py
View file

@ -251,26 +251,11 @@ class BBCCoUkIE(InfoExtractor):
for connection in self._extract_connections(media): for connection in self._extract_connections(media):
captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions') captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') 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] = [ subtitles[lang] = [
{ {
'url': connection.get('href'), 'url': connection.get('href'),
'ext': 'ttml', 'ext': 'ttml',
}, },
{
'data': srt,
'ext': 'srt',
},
] ]
return subtitles return subtitles