Windy/qBittorrent
1
0
Fork 0
mirror of https://github.com/qbittorrent/qBittorrent.git synced 2025-01-07 03:16:48 +08:00
Code Issues Packages Projects Releases Wiki Activity

Use built-in method for decoding HTML entities

Browse Source
This commit is contained in:
Chocobo1 2024-12-27 01:56:33 +08:00
parent 7487cd7e6d
commit 90e457a671
No known key found for this signature in database
GPG Key ID: 210D9C873253A68C
1 changed files with 4 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
src/searchengine/nova3/helpers.py
View File

@ -1,4 +1,4 @@
#VERSION: 1.49
#VERSION: 1.50
# Author:
# Christophe DUMEZ (chris@qbittorrent.org)
@ -29,7 +29,7 @@
import datetime
import gzip
import html.entities
import html
import io
import os
import re
@ -72,21 +72,8 @@ if "sock_proxy" in os.environ and len(os.environ["sock_proxy"].strip()) > 0:
socket.socket = socks.socksocket # type: ignore[misc]
def htmlentitydecode(s: str) -> str:
# First convert alpha entities (such as é)
# (Inspired from http://mail.python.org/pipermail/python-list/2007-June/443813.html)
def entity2char(m: re.Match[str]) -> str:
entity = m.group(1)
if entity in html.entities.name2codepoint:
return chr(html.entities.name2codepoint[entity])
return " " # Unknown entity: We replace with a space.
t = re.sub('&(%s);' % '|'.join(html.entities.name2codepoint), entity2char, s)
# Then convert numerical entities (such as é)
t = re.sub(r'&#(\d+);', lambda x: chr(int(x.group(1))), t)
# Then convert hexa entities (such as é)
return re.sub(r'&#x(\w+);', lambda x: chr(int(x.group(1), 16)), t)
# This is only provided for backward compatibility, new code should not use it
htmlentitydecode = html.unescape
def retrieve_url(url: str, custom_headers: Mapping[str, Any] = {}, request_data: Optional[Any] = None) -> str: