misc-零宽字符隐写自写脚本

PS: 从零宽字符隐写的javascript代码提取出来的解密方式, 由于零宽字符隐写的题目存在需要先判定存在哪些零宽字符, 勾选对应隐写字符后再进行解密. 而据我调研, 各解密网站都不具备自动识别判断解密的功能, 所以自写了一个

# encoding=utf-8

import re
import math
from typing import Set, Union, Any


def get_use_chars(encode_str: str):
    special_chars = ['\u200a', '\u200b', '\u200c', '\u200d', '\u200e', '\u200f', '\u202a', '\u202b', '\u202c',
                     '\u202d', '\u2062', '\u2063', '\ufeff']
    pattern = "[" + "".join(re.escape(char) for char in special_chars) + "]"
    found_chars = set(re.findall(pattern, encode_str))
    return sorted(list(found_chars))


class UnicodeSteganographer:
    def __init__(self):
        self.chars = []
        self.radix = 0
        self.codelength_text = 0

    def set_use_chars(self, new_chars: str):
        if len(new_chars) >= 2:
            self.chars = list(new_chars)
            self.radix = len(self.chars)
            self.codelength_text = math.ceil(math.log(65536, self.radix))

    def decode_text(self, text: str) -> dict:
        splitted = self.split_zerowidth_characters(text)
        return {
            'originalText': splitted['originalText'],
            # splitted['hiddenText'],
            'hiddenText': self.decode_from_zero_width_characters_text(splitted['hiddenText'])
        }

    def split_zerowidth_characters(self, str1: str) -> dict:
        split_result = {
            'originalText': re.sub('[' + ''.join(re.escape(char) for char in self.chars) + ']', '', str1),
            'hiddenText': re.sub('[^' + ''.join(re.escape(char) for char in self.chars) + ']', '', str1)
        }
        return split_result

    def decode_from_zero_width_characters_text(self, zero_width_str: str) -> str:
        # 初始化
        r = zero_width_str
        decode_result = []

        # 字符替换
        for i in range(len(self.chars)):  # 修改这里为遍历chars的长度
            r = re.sub(self.chars[i], str(i), r)

        # 解码文本字符
        for i in range(0, len(r), self.codelength_text):
            char_code = int(r[i:i + self.codelength_text], self.radix)
            decode_result.append(chr(char_code))

        # 合并结果为字符串并返回
        return ''.join(decode_result)


if __name__ == '__main__':
    # 只需要把零宽隐写的文本粘贴过来
    zerotext = """
    ​​​​‍‬‬flag​​​​‍‬‍‍ ​​​​‍‬‍is ​​​​​‬‬​​​​‍‍​not​​​​‍‬‬ ​​​​‍‬here!​​​​‍‍​​​​​‬​​​​​​‍‍‍​​​​‍‬‬​​​​​‍‬‬‍​​​​‍‍​​​​​‍‬‍‍
    """

    # 自动化计算方式
    stegano = UnicodeSteganographer()
    stegano.set_use_chars("".join(get_use_chars(zerotext)))
    result = stegano.decode_text(zerotext)
    print("try1:" + result['hiddenText'])

    print("---------------------------------------------------------------------------")

    # 默认计算方式
    stegano2 = UnicodeSteganographer()
    stegano2.set_use_chars('\u200c\u200d\u202c\ufeff')
    result2 = stegano2.decode_text(zerotext)
    print("try2:" + result2['hiddenText'])
	

原js解密脚本参考

https://330k.github.io/misc_tools/unicode_steganography.js