import os
import pdfplumber

def parse_pdf(pdf_path, txt_path):
    try:
        with open(txt_path, "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{pdf_path}-{i + 1}页')
                    txt.write(page.extract_text())
    except Exception as e:
        print(f"发生异常: {str(e)}")
 
 
pdf_dir = r'/Users/liujingyu/Downloads/gitee/cipin/3/pdf'
txt_dir = r'/Users/liujingyu/Downloads/gitee/cipin/3/txt'

if not os.path.exists(txt_dir):
    os.makedirs(txt_dir)

for root, dirs, files in os.walk(pdf_dir, topdown=False):
    for file in files:
        try:
            pdf_path = os.path.join(root, file)
            file_name = os.path.basename(pdf_path)
            txt_path = os.path.join(txt_dir, file_name.split('.')[0] + '.txt')
            parse_pdf(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')