[ie/yandexdisk] supported password,thumbnail

yt_dlp/extractor/dropbox.py

@@ -42,24 +42,18 @@ def _real_extract(self, url):
         webpage = self._download_webpage(url, video_id)
         fn = urllib.parse.unquote(url_basename(url))
         title = os.path.splitext(fn)[0]
+
         password = self.get_param('videopassword')
-        thumbnail = None
-
-        for encoded in reversed(re.findall(r'registerStreamedPrefetch\s*\(\s*"[\w/+=]+"\s*,\s*"([\w/+=]+)"', webpage)):
-            part = base64.b64decode(encoded).decode('utf-8', 'ignore')
-            if 'sm/password' in part:
-                webpage = self._download_webpage(
-                    'https://www.dropbox.com/sm/password?' + part.split('?')[1], video_id)
-
         if (self._og_search_title(webpage) == 'Dropbox - Password Required'
                 or 'Enter the password for this link' in webpage):
 
             if password:
                 content_id = self._search_regex(r'content_id=(.*?)["\']', webpage, 'content_id')
-                payload = f'is_xhr=true&t={self._get_cookies("https://www.dropbox.com").get("t").value}&content_id={content_id}&password={password}&url={url.replace("https://www.dropbox.com", "")}'
+                payload = f'is_xhr=true&t={self._get_cookies("https://www.dropbox.com").get("t").value}&content_id={content_id}&password={password}&url={url}'
                 response = self._download_json(
                     'https://www.dropbox.com/sm/auth', video_id, 'POSTing video password', data=payload.encode(),
                     headers={'content-type': 'application/x-www-form-urlencoded; charset=UTF-8'})
+
                 if response.get('status') != 'authed':
                     raise ExtractorError('Authentication failed!', expected=True)
                 webpage = self._download_webpage(url, video_id)
@@ -79,8 +73,6 @@ def _real_extract(self, url):
             if not transcode_url:
                 continue
             formats, subtitles = self._extract_m3u8_formats_and_subtitles(transcode_url, video_id, 'mp4')
-            thumbnail = self._search_regex(
-                r'(https://www\.dropbox\.com/temp_thumb_from_token/c/(.*?)\?preserve_transparency=False&rlkey=(.*?)&secure_hash=&size=(.*?)&size_mode=4)', decoded, 'thumbnail url', default=None)
             break
 
         # downloads enabled we can get the original file
@@ -94,7 +86,6 @@ def _real_extract(self, url):
 
         return {
             'id': video_id,
-            'thumbnail': thumbnail,
             'title': title,
             'formats': formats,
             'subtitles': subtitles,

yt_dlp/extractor/yandexdisk.py

@@ -1,12 +1,15 @@
 import json
+import urllib.parse
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     determine_ext,
     float_or_none,
     int_or_none,
     join_nonempty,
     mimetype2ext,
+    traverse_obj,
     try_get,
     urljoin,
 )
@@ -62,6 +65,40 @@ def _real_extract(self, url):
             webpage, 'store'), video_id)
         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 = self._og_search_property('image', webpage)
         title = resource['name']
         meta = resource.get('meta') or {}
 
@@ -132,6 +169,7 @@ def call_api(action):
         return {
             'id': video_id,
             'title': title,
+            'thumbnail': thumbnail,
             'duration': float_or_none(video_streams.get('duration'), 1000),
             'uploader': display_name,
             'uploader_id': uid,