import os
import pdfplumber

def  pdf2txt(ThePath:str,aim_path:str ): 
    def parsePDF(dir, file, pdf_path, txtpath):
        try:
            with open(txtpath, "w", encoding='utf-8') as txt:
                with pdfplumber.open(pdf_path) as pdf:
                    for i, page in enumerate(pdf.pages):
                        print(f'正在转换{dir}-{file}-{i + 1}页')
                    txt.write(page.extract_text())
        except Exception as e:
             print(f"发生异常: {str(e)}")

# 主程序
ThePath = r'/Users/liujingyu/Downloads/gitee/cipin/3/pdf/2007年报'
aim_path = r'/Users/liujingyu/Downloads/gitee/cipin/3/txt'


dir_list = os.listdir(ThePath)
for dir in dir_list:
    dir_path = os.path.join(ThePath, dir)  # 使用os.path.join来构建目录路径
    if not os.path.exists(os.path.join(aim_path, dir)):
        os.makedirs(os.path.join(aim_path, dir))  # 使用os.path.join来构建目录路径
    for root, dirs, files in os.walk(dir_path, topdown=False):
        for file in files:
            try:
                pdf_path = os.path.join(root, file)  # 使用os.path.join来构建文件路径
                file_name = os.path.basename(pdf_path)  # 从文件路径中提取文件名
                txt_path = os.path.join(aim_path, dir, file_name.split('.')[0] + '.txt')  # 构建txt文件路径
                parsePDF(dir, file, pdf_path, txt_path)
            except:
                with open('错误信息.txt', 'a', encoding='UTF-8', errors='ignore') as f:
                    f.write(os.path.join(root, file) + '/n')  # 使用os.path.join来构建文件路径
pdf2txt(ThePath,aim_path)