kumi/yt-dlp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[vivo] Improve extraction (closes #19217)

Browse source
This commit is contained in:
Sergey M․ 2019-05-23 03:04:58 +07:00
parent 0e6f914b3b
commit e438e81469
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 21 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

31
youtube_dl/extractor/shared.py
View file

@ -1,15 +1,15 @@
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 (
determine_ext,
ExtractorError, ExtractorError,
int_or_none, int_or_none,
KNOWN_EXTENSIONS,
parse_filesize,
url_or_none, url_or_none,
urlencode_postdata, urlencode_postdata,
unescapeHTML,
) )
@ -26,8 +26,7 @@ class SharedBaseIE(InfoExtractor):
video_url = self._extract_video_url(webpage, video_id, url) video_url = self._extract_video_url(webpage, video_id, url)
title = self._extract_title(webpage) title = self._extract_title(webpage)
filesize = int_or_none(self._html_search_meta( filesize = int_or_none(self._extract_filesize(webpage))
'full:size', webpage, 'file size', fatal=False))
return { return {
'id': video_id, 'id': video_id,
@ -41,6 +40,10 @@ class SharedBaseIE(InfoExtractor):
return compat_b64decode(self._html_search_meta( return compat_b64decode(self._html_search_meta(
'full:title', webpage, 'title')).decode('utf-8') 'full:title', webpage, 'title')).decode('utf-8')
def _extract_filesize(self, webpage):
return self._html_search_meta(
'full:size', webpage, 'file size', fatal=False)
class SharedIE(SharedBaseIE): class SharedIE(SharedBaseIE):
IE_DESC = 'shared.sx' IE_DESC = 'shared.sx'
@ -88,19 +91,27 @@ class VivoIE(SharedBaseIE):
'id': 'd7ddda0e78', 'id': 'd7ddda0e78',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Chicken', 'title': 'Chicken',
'filesize': 528031, 'filesize': 515659,
}, },
} }
def _extract_title(self, webpage): def _extract_title(self, webpage):
data_title = self._search_regex( title = self._html_search_regex(
r'data-name\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1', webpage, r'data-name\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1', webpage,
'title', default=None, group='title') 'title', default=None, group='title')
if data_title: if title:
return unescapeHTML(re.sub(r"\.[a-z0-9]{3,4}$", "", data_title)) ext = determine_ext(title)
if ext.lower() in KNOWN_EXTENSIONS:
title = title.rpartition('.' + ext)[0]
return title
return self._og_search_title(webpage) return self._og_search_title(webpage)
def _extract_video_url(self, webpage, video_id, *args): def _extract_filesize(self, webpage):
return parse_filesize(self._search_regex(
r'data-type=["\']video["\'][^>]*>Watch.*?<strong>\s*\((.+?)\)',
webpage, 'filesize', fatal=False))
def _extract_video_url(self, webpage, video_id, url):
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')