# This is a sample Python script.

# Press Shift+F10 to execute it or replace it with your code.
# Press Double Shift to search everywhere for classes, files, tool windows, actions, and settings





import os
import pdfplumber

def parsePDF(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 = '/Users/liujingyu/Downloads/gitee/cipin/3/pdf'
txt_dir = '/Users/liujingyu/Downloads/gitee/cipin/3/txt'

for root, dirs, files in os.walk(pdf_dir):
    for file in files:
        if file.endswith('.pdf'):
            pdf_path = os.path.join(root, file)
            relative_path = os.path.relpath(pdf_path, pdf_dir)
            txt_path = os.path.join(txt_dir, os.path.splitext(relative_path)[0] + '.txt')
            try:
                parsePDF(pdf_path, txt_path)
            except Exception as e:
                with open('错误信息.txt', 'a', encoding='UTF-8', errors='ignore') as f:
                    f.write(f"{pdf_path}: {str(e)}\n")