python读取多类型文件夹中的文档内容

pip install python-docx

import os
from docx import Document

def read_txt_file(file_path):
    with open(file_path, 'r', encoding='utf-8') as file:
        content = file.read()
    return content

def read_docx_file(file_path):
    doc = Document(file_path)
    content = '\n'.join([para.text for para in doc.paragraphs])
    return content

def read_folder_contents(folder_path):
    for root, dirs, files in os.walk(folder_path):
        for file in files:
            file_path = os.path.join(root, file)
            if file_path.endswith('.txt'):
                content = read_txt_file(file_path)
                print(f"File: {file_path}")
                print(f"Content:\n{content}\n")
            elif file_path.endswith('.docx'):
                content = read_docx_file(file_path)
                print(f"File: {file_path}")
                print(f"Content:\n{content}\n")
            # 你可以根据需要添加更多文件类型的处理逻辑

# 使用示例
folder_to_read = 'path/to/your/folder'  # 替换为你的文件夹路径
read_folder_contents(folder_to_read)

data = pd.read_excel('data.xlsx', sheet_name="Sheet1", header = 1)  # header是第几行数据作为列名

csv_data= pd.read_csv('/路径/文件名.csv')

data = pd.read_csv(r'stdout', sep='\t', header=0) # stdout是txt文件