mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-01-10 01:49:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

[GoogleDriveFolderIE] support private folders and my-drive

Browse source
This commit is contained in:
grqx_wsl 2024-08-18 03:08:45 +12:00
parent b81a41d5ff
commit 4a76306868
1 changed files with 8 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
yt_dlp/extractor/googledrive.py
View file

@ -295,7 +295,7 @@ def add_source_format(urlh):
class GoogleDriveFolderIE(InfoExtractor): class GoogleDriveFolderIE(InfoExtractor):
IE_NAME = 'GoogleDrive:Folder' IE_NAME = 'GoogleDrive:Folder'
_VALID_URL = r'https?://(?:docs|drive)\.google\.com/drive/folders/(?P<id>[\w-]{28,})' _VALID_URL = r'https?://(?:docs|drive)\.google\.com/drive/(?:folders/(?P<id>[\w-]{28,})|my-drive)'
_TESTS = [{ _TESTS = [{
'url': 'https://drive.google.com/drive/folders/1dQ4sx0-__Nvg65rxTSgQrl7VyW_FZ9QI', 'url': 'https://drive.google.com/drive/folders/1dQ4sx0-__Nvg65rxTSgQrl7VyW_FZ9QI',
'info_dict': { 'info_dict': {
@ -318,7 +318,7 @@ def _extract_json_meta(self, webpage, video_id, dsval=None, hashval=None, name=N
""" """
Uses regex to search for json metadata with 'ds' value(0-5) or 'hash' value(1-6) Uses regex to search for json metadata with 'ds' value(0-5) or 'hash' value(1-6)
from the webpage. from the webpage.
Folder info: ds=0, hash=1; Folder items: ds=4, hash=6. Folder info: ds=0, hash=1; Folder items: ds=4(public folder)/5(private folder), hash=6.
For example, if the webpage contains the line below, the empty data array For example, if the webpage contains the line below, the empty data array
can be got by passing dsval=3 or hashval=2 to this method. can be got by passing dsval=3 or hashval=2 to this method.
AF_initDataCallback({key: 'ds:3', hash: '2', data:[], sideChannel: {}}); AF_initDataCallback({key: 'ds:3', hash: '2', data:[], sideChannel: {}});
@ -341,6 +341,8 @@ def _extract_json_meta(self, webpage, video_id, dsval=None, hashval=None, name=N
def _real_extract(self, url): def _real_extract(self, url):
def item_url_getter(item, video_id): def item_url_getter(item, video_id):
if not isinstance(item, list):
return None
available_IEs = [GoogleDriveFolderIE, GoogleDriveIE] # subfolder or item available_IEs = [GoogleDriveFolderIE, GoogleDriveIE] # subfolder or item
if 'application/vnd.google-apps.shortcut' in item: # extract real link if 'application/vnd.google-apps.shortcut' in item: # extract real link
entry_url = traverse_obj( entry_url = traverse_obj(
@ -354,7 +356,7 @@ def item_url_getter(item, video_id):
return None return None
return self.url_result(entry_url, video_id=video_id, video_title=item[2]) return self.url_result(entry_url, video_id=video_id, video_title=item[2])
folder_id = self._match_id(url) folder_id = self._match_id(url) or 'my-drive'
headers = self.geo_verification_headers() headers = self.geo_verification_headers()
try: try:
@ -370,13 +372,10 @@ def item_url_getter(item, video_id):
self.raise_login_required('This video is only available for registered users') self.raise_login_required('This video is only available for registered users')
json_folder_info = ( json_folder_info = (
self._extract_json_meta(webpage, folder_id, dsval=0, name='folder info', default=None) self._extract_json_meta(webpage, folder_id, hashval=1, name='folder info', default=None)
or self._extract_json_meta(webpage, folder_id, hashval=1) or self._extract_json_meta(webpage, folder_id, dsval=0, name='folder info - fallback')
)
json_items = (
self._extract_json_meta(webpage, folder_id, dsval=4, name='folder items', default=None)
or self._extract_json_meta(webpage, folder_id, hashval=6)
) )
json_items = self._extract_json_meta(webpage, folder_id, hashval=6, name='folder items')
title = json_folder_info[1][2] title = json_folder_info[1][2]
items = json_items[-1] items = json_items[-1]