clear various symbol

python3_clear_symbol.py

#coding=utf8
import string
import sys
import re

def conv_wide(char):
    #全角转半角
    code = ord(char)
    if char == '\u3000': #space
        code = 32
    elif '\uff01' <= char <= '\uff5e':
        code -= 65248
    return chr(code)

def is_symbol(char):
    #常用标点符号
    if '\u2000' <= char <= '\u206f': 
        return True
    #CJK标点符号 e.g.〖〗
    if '\u3000' <= char <= '\u303f' or '\ufe30' <= char <= '\ufe4f' or '\ufe10' <= char <= '\ufe1f': 
        return True
    #注音符号 e.g.ㄡ
    if '\u3100' <= char <= '\u312f':
        return True
    #装饰符号和杂项符号 e.g.⚽'
    if '\u2700' <= char <= '\u27bf': 
        return True
    # Latin-1
    if '\u00A0' <= char <= '\u00FF': 
        return True
    # Geometric Shapes
    if '\u25A0' <= char <= '\u25FF': 
        return True
    #  Miscellaneous Symbols   
    if '\u2600' <= char <= '\u26FF': 
        return True
    #  Cyrillic   
    if '\u0400' <= char <= '\u04FF': 
        return True
    # Mathematical symbols
    if '\u2220' <= char <= '\u22FF': 
        return True
    # Mathematical symbols
    if '\u2220' <= char <= '\u22FF': 
        return True
    # Japanese
    if '\u3040' <= char <= '\u309F' or '\u30A0' <= char <= '\u30FF' : 
        return True
    return False


def clear_symbol(text):
    res = ''

    for char in text:
        char = conv_wide(char)
        if is_symbol(char):
            continue
        res += char

    #res = res.encode('utf8').translate(None, string.punctuation) 
    res = res.translate(str.maketrans('', '', string.punctuation)) # 去除英文标点
    res = res.rstrip()
    res = res.lstrip()
    return res


if __name__ == "__main__":
    text  = "✿✿ヽ(°▽°)ノ✿中文测试@!@#%！！_(:з」∠)_ð"
    print(clear_symbol(text))