[vivo] Fix extraction (closes #18906)

This commit is contained in:
Daniel Höpfl 2019-02-13 16:29:43 +01:00 committed by Sergey M․
parent 6ab30ff50b
commit 0e6f914b3b
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D

View file

@ -1,5 +1,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_b64decode from ..compat import compat_b64decode
from ..utils import ( from ..utils import (
@ -7,6 +9,7 @@
int_or_none, int_or_none,
url_or_none, url_or_none,
urlencode_postdata, urlencode_postdata,
unescapeHTML,
) )
@ -22,8 +25,7 @@ def _real_extract(self, url):
video_url = self._extract_video_url(webpage, video_id, url) video_url = self._extract_video_url(webpage, video_id, url)
title = compat_b64decode(self._html_search_meta( title = self._extract_title(webpage)
'full:title', webpage, 'title')).decode('utf-8')
filesize = int_or_none(self._html_search_meta( filesize = int_or_none(self._html_search_meta(
'full:size', webpage, 'file size', fatal=False)) 'full:size', webpage, 'file size', fatal=False))
@ -35,6 +37,10 @@ def _real_extract(self, url):
'title': title, 'title': title,
} }
def _extract_title(self, webpage):
return compat_b64decode(self._html_search_meta(
'full:title', webpage, 'title')).decode('utf-8')
class SharedIE(SharedBaseIE): class SharedIE(SharedBaseIE):
IE_DESC = 'shared.sx' IE_DESC = 'shared.sx'
@ -86,6 +92,14 @@ 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 self._og_search_title(webpage)
def _extract_video_url(self, webpage, video_id, *args): def _extract_video_url(self, webpage, video_id, *args):
def decode_url(encoded_url): def decode_url(encoded_url):
return compat_b64decode(encoded_url).decode('utf-8') return compat_b64decode(encoded_url).decode('utf-8')