v/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2020-11-18 19:53:54 -08:00
Code Issues Releases Wiki Activity

Fixes #18906: Fixes title extraction for vivo.sx.

Browse Source
This commit is contained in:
Daniel Höpfl 2019-02-13 16:29:43 +01:00
parent 6f5c1807f4
commit 4b99952e6c
1 changed files with 19 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
youtube_dl/extractor/shared.py
View File

@ -1,6 +1,11 @@
from __future__ import unicode_literals
from .common import InfoExtractor
import re
from .common import (
InfoExtractor,
unescapeHTML
)
from ..compat import compat_b64decode
from ..utils import (
ExtractorError,
@ -22,8 +27,7 @@ class SharedBaseIE(InfoExtractor):
video_url = self._extract_video_url(webpage, video_id, url)
title = compat_b64decode(self._html_search_meta(
'full:title', webpage, 'title')).decode('utf-8')
title = self._extract_title(webpage)
filesize = int_or_none(self._html_search_meta(
'full:size', webpage, 'file size', fatal=False))
@ -35,6 +39,10 @@ class SharedBaseIE(InfoExtractor):
'title': title,
}
def _extract_title(self, webpage):
return compat_b64decode(self._html_search_meta(
'full:title', webpage, 'title')).decode('utf-8')
class SharedIE(SharedBaseIE):
IE_DESC = 'shared.sx'
@ -86,6 +94,14 @@ class VivoIE(SharedBaseIE):
},
}
def _extract_title(self, webpage):
data_title = self._search_regex(
r'data-name\s*=\s*(["\'])(?P<title>(?:.(?!\1))*.)\1', webpage,
'title', default=None, group='title')
if data_title:
return unescapeHTML(re.sub(r"\.[a-z0-9]{3,4}$", "", data_title))
return None
def _extract_video_url(self, webpage, video_id, *args):
def decode_url(encoded_url):
return compat_b64decode(encoded_url).decode('utf-8')