[ie/YandexDisk] supported password, thumbnail

This commit is contained in:
ndyanx 2024-08-13 14:32:09 -05:00
parent 92ad6defac
commit 2e703affc8

View File

@ -1,12 +1,17 @@
import json import json
import urllib.parse
from html import unescape
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
ExtractorError,
float_or_none, float_or_none,
int_or_none, int_or_none,
join_nonempty, join_nonempty,
mimetype2ext, mimetype2ext,
traverse_obj,
try_get, try_get,
urljoin, urljoin,
) )
@ -62,6 +67,43 @@ def _real_extract(self, url):
webpage, 'store'), video_id) webpage, 'store'), video_id)
resource = store['resources'][store['rootResourceId']] resource = store['resources'][store['rootResourceId']]
if store['rootResourceId'] == 'password-protected':
data = {
"hash": resource['hash'],
"password": self.get_param('videopassword', default=''),
"sk": traverse_obj(store, ('environment', 'sk')),
}
json_string = json.dumps(data, separators=(',', ':'))
url_encoded_string = urllib.parse.quote(json_string, safe='')
data_bytes = url_encoded_string.encode('utf-8')
token = (self._download_json(
'https://disk.yandex.ru/public/api/check-password',
video_id, data=data_bytes, fatal=False,
headers={
'Accept': '*/*',
'Cache-Control': 'no-cache',
'Connection': 'keep-alive',
'Content-Type': 'text/plain',
'Origin': 'https://disk.yandex.ru',
'Pragma': 'no-cache',
'Referer': url,
'Sec-Fetch-Dest': 'empty',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Site': 'same-origin',
'X-Requested-With': 'XMLHttpRequest',
'X-Retpath-Y': url,
}
) or {}).get('token') or {}
if not token:
raise ExtractorError('Password incorrect!', expected=True)
self._set_cookie('disk.yandex.ru', name='passToken', value=token)
webpage = self._download_webpage(url, video_id)
store = self._parse_json(self._search_regex(
r'<script[^>]+id="store-prefetch"[^>]*>\s*({.+?})\s*</script>',
webpage, 'store'), video_id)
resource = store['resources'][store['rootResourceId']]
thumbnail = unescape(self._og_search_property('image', webpage))
title = resource['name'] title = resource['name']
meta = resource.get('meta') or {} meta = resource.get('meta') or {}
@ -132,6 +174,7 @@ def call_api(action):
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'thumbnail': thumbnail,
'duration': float_or_none(video_streams.get('duration'), 1000), 'duration': float_or_none(video_streams.get('duration'), 1000),
'uploader': display_name, 'uploader': display_name,
'uploader_id': uid, 'uploader_id': uid,