文本预处理4-去除阿拉伯数字

1.针对去除文本中的阿拉伯数字。

2.读取txt文档，将处理后的内容写回原文件。

#文本预处理4-去除阿拉伯数字
import os
import re
def remove_numbers(text):
    # 正则表达式匹配阿拉伯数字
    pattern = re.compile(r'\d+')
    # 使用re.sub()函数将匹配到的数字替换为空字符串
    result = re.sub(pattern, '', text)
    return result


def process_txt_files(folder_path):
    for filename in os.listdir(folder_path):
        if filename.endswith('.txt'):
            file_path = os.path.join(folder_path, filename)
            with open(file_path, 'r', encoding='utf-8') as file:
                content = file.read()
                processed_content = remove_numbers(content)

            # 将处理后的内容写回原文件
            with open(file_path, 'w', encoding='utf-8') as file:
                file.write(processed_content)

            # print(f'Processed content written back to {filename}')


# 替换为你的文件夹路径
folder_path = "C:\\Users\\lenovo\\Desktop"
process_txt_files(folder_path)