python pdf批量转txt

可以使用Python中的pdfminer库来实现将PDF文件批量转换为txt文件。

以下是一个示例代码，它可以将指定文件夹中的所有PDF文件转换为txt文件：

import os
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage

def pdf_to_txt(pdf_path, txt_path):
    resource_manager = PDFResourceManager()
    codec = 'utf-8'
    laparams = LAParams()
    with open(txt_path, 'wb') as output:
        with open(pdf_path, 'rb') as input:
            device = TextConverter(resource_manager, output, codec=codec, laparams=laparams)
            interpreter = PDFPageInterpreter(resource_manager, device)
            for page in PDFPage.get_pages(input):
                interpreter.process_page(page)
            device.close()

if __name__ == '__main__':
    pdf_folder = './pdf_folder/'
    txt_folder = './txt_folder/'
    for file_name in os.listdir(pdf_folder):
        if file_name.endswith('.pdf'):
            pdf_path = os.path.join(pdf_folder, file_name)
            txt_path = os.path.join(txt_folder, file_name.replace('.pdf', '.txt'))
            pdf_to_txt(pdf_path, txt_path)

将以上代码保存为一个Python文件并运行，即可将指定文件夹中的所有PDF文件转换为txt文件。