[text] add 'extract_urls()' helper

This commit is contained in:
Mike Fährmann
2026-02-06 20:46:35 +01:00
parent 98ef34a9be
commit c978fe18d4
3 changed files with 22 additions and 3 deletions

View File

@@ -611,7 +611,7 @@ _CONVERSIONS = {
"U": text.unescape,
"H": lambda s: text.unescape(text.remove_html(s)),
"g": text.slugify,
"R": text.re(r"https?://[^\s\"'<>\\]+").findall,
"R": text.extract_urls,
"W": text.sanitize_whitespace,
"S": util.to_string,
"s": str,

View File

@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2015-2025 Mike Fährmann
# Copyright 2015-2026 Mike Fährmann
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
@@ -231,6 +231,9 @@ def extract_from(txt, pos=None, default=""):
return extr
extract_urls = re(r"https?://[^\s\"'<>\\]+").findall
def parse_unicode_escapes(txt):
"""Convert JSON Unicode escapes in 'txt' into actual characters"""
if "\\u" in txt: