python批量转换PDF文档为TXT格式

你可以使用Python的第三方库"pdfminer"来实现PDF文档转换为TXT格式。下面是一个简单的示例代码：

import os
import glob
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter, PDFPageAggregator
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from io import StringIO

# 定义PDF转TXT函数
def pdf_to_txt(pdf_path, txt_path):
    rsrcmgr = PDFResourceManager()
    codec = 'utf-8'
    laparams = LAParams()
    with open(txt_path, 'w', encoding=codec) as fp:
        device = TextConverter(rsrcmgr, fp, codec=codec, laparams=laparams)
        with open(pdf_path, 'rb') as fp:
            interpreter = PDFPageInterpreter(rsrcmgr, device)
            for page in PDFPage.get_pages(fp):
                interpreter.process_page(page)
        device.close()

# 批量转换PDF文件夹中的PDF文档为TXT格式
pdf_folder = "your_pdf_folder_path"
txt_folder = "your_txt_folder_path"
for pdf_file in glob.glob(os.path.join(pdf_folder, '*.pdf')):
    txt_file = os.path.splitext(os.path.basename(pdf_file))[0] + ".txt"
    txt_path = os.path.join(txt_folder, txt_file)
    pdf_to_txt(pdf_file, txt_path)

你只需要将"your_pdf_folder_path"替换为你的PDF文件夹路径，"your_txt_folder_path"替换为你想要保存TXT文件的文件夹路径，然后运行该代码即可实现批量转换PDF文档为TXT格式。