Improve URL extraction

This commit is contained in:
Sergey M․ 2018-07-21 19:08:28 +07:00
parent 4ecf300d13
commit 3052a30d42
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
47 changed files with 166 additions and 139 deletions

View file

@ -3,7 +3,6 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
extract_attributes,
@ -12,6 +11,7 @@ from ..utils import (
parse_age_limit,
remove_end,
unescapeHTML,
url_or_none,
)
@ -69,9 +69,8 @@ class DiscoveryGoBaseIE(InfoExtractor):
captions = stream.get('captions')
if isinstance(captions, list):
for caption in captions:
subtitle_url = caption.get('fileUrl')
if (not subtitle_url or not isinstance(subtitle_url, compat_str) or
not subtitle_url.startswith('http')):
subtitle_url = url_or_none(caption.get('fileUrl'))
if not subtitle_url or not subtitle_url.startswith('http'):
continue
lang = caption.get('fileLang', 'en')
ext = determine_ext(subtitle_url)