Python PDF to TXT: Convert and Save Financial Reports

import os
import PyPDF2

# 设置路径和文件名
file_path = r'D:\南巢\第六学期\大数据与会计分析\贵州茅台财务分析\年报'
file_name = '贵州茅台：2018年年度报告（改了一个科目名称）.pdf'

# 打开pdf文件并创建txt文件
with open(os.path.join(file_path, file_name), 'rb') as pdf_file, open(os.path.join(file_path, file_name[:-4]+'.txt'), 'w', encoding='utf-8') as txt_file:
    pdf_reader = PyPDF2.PdfFileReader(pdf_file)
    # 逐页读取pdf文件并写入txt文件
    for page_num in range(pdf_reader.numPages):
        page_obj = pdf_reader.getPage(page_num)
        txt_file.write(page_obj.extractText())