[ted] Fix subtitles extraction (closes #13628, closes #13629)

This commit is contained in:
Sergey M․ 2017-07-11 21:36:45 +07:00
parent 3615bfe1b4
commit f2bb33a986
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D

View file

@ -271,20 +271,22 @@ def _talk_info(self, url, video_name):
}
def _get_subtitles(self, video_id, talk_info):
languages = [lang['languageCode'] for lang in talk_info.get('languages', [])]
if languages:
sub_lang_list = {}
for l in languages:
sub_lang_list[l] = [
for language in try_get(
talk_info,
(lambda x: x['downloads']['languages'],
lambda x: x['languages']), list):
lang_code = language.get('languageCode') or language.get('ianaCode')
if not lang_code:
continue
sub_lang_list[lang_code] = [
{
'url': 'http://www.ted.com/talks/subtitles/id/%s/lang/%s/format/%s' % (video_id, l, ext),
'url': 'http://www.ted.com/talks/subtitles/id/%s/lang/%s/format/%s' % (video_id, lang_code, ext),
'ext': ext,
}
for ext in ['ted', 'srt']
]
return sub_lang_list
else:
return {}
def _watch_info(self, url, name):
webpage = self._download_webpage(url, name)