github/qBittorrent
1
0
Fork 0
mirror of https://github.com/qbittorrent/qBittorrent synced 2025-07-06 05:01:25 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Add parameter to control whether to unescape HTML entities

Browse source 
Some plugin needed the raw data for further processing.
Related: #22074.

PR #22106.
This commit is contained in:
Chocobo1 2025-01-06 19:05:57 +08:00 • committed by GitHub
parent d911928c59
commit 4f3d77963f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 6 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

9
src/searchengine/nova3/helpers.py
View file

@ -1,4 +1,4 @@
#VERSION: 1.50
#VERSION: 1.51
# Author:
# Christophe DUMEZ (chris@qbittorrent.org)
@ -77,7 +77,7 @@ if "sock_proxy" in os.environ and len(os.environ["sock_proxy"].strip()) > 0:
htmlentitydecode = html.unescape
def retrieve_url(url: str, custom_headers: Mapping[str, Any] = {}, request_data: Optional[Any] = None, ssl_context: Optional[ssl.SSLContext] = None) -> str:
def retrieve_url(url: str, custom_headers: Mapping[str, Any] = {}, request_data: Optional[Any] = None, ssl_context: Optional[ssl.SSLContext] = None, unescape_html_entities: bool = True) -> str:
""" Return the content of the url page as a string """
request = urllib.request.Request(url, request_data, {**headers, **custom_headers})
@ -101,7 +101,10 @@ def retrieve_url(url: str, custom_headers: Mapping[str, Any] = {}, request_data:
pass
dataStr = data.decode(charset, 'replace')
dataStr = htmlentitydecode(dataStr)
if unescape_html_entities:
dataStr = html.unescape(dataStr)
return dataStr