Python去除文本中所有中英文标点符号

from tqdm import tqdm
import string
from zhon.hanzi import punctuation as pun

allPun = string.punctuation + pun

def delPunctuation(infile, outfile):
    nums_line = 77397242 # 文件行数
    with open(infile, 'r',encoding="utf-8") as readFile, open(outfile, 'w', encoding="utf-8") as writeFile:
        for idx, line in tqdm(enumerate(readFile), total=nums_line):
            out = ''.join([i for i in line if i not in allPun])
            writeFile.write(out)
     readFile.close()
     writeFile.close()

if __name__ == '__main__':
    delPunctuation("test.txt", "ans.txt")

string.punctuation 代表英文标点符号

zhon.hanzi 中的punctuation 代表中文标点符号

查找到文中的所有标点符号，将其删除并将处理后的文本写入到新的文件中。