python使用PyPDF2包：pdf转doc

需要安装 python-docx 和 PyPDF2

pip install python-docx
pip install PyPDF2

记住，不能直接安装 pip install docx ,不然会报错 ImportError: No module named ‘exceptions’

import PyPDF2
from docx import Document

def convert_pdf_to_doc(pdf_path, doc_path):
    with open(pdf_path, 'rb') as pdf_file:
        pdf_reader = PyPDF2.PdfReader(pdf_file)
        doc = Document()
        nums = len(pdf_reader.pages)
        print("total page:", nums)
        for page_num in range(nums):
            page = pdf_reader.pages[page_num]
            text = page.extract_text()
            doc.add_paragraph(text)
            print("current page:", page_num)

        doc.save(doc_path)

# 使用示例
pdf_path = 'in.pdf'  # 输入的PDF文件路径
doc_path = 'out.docx'  # 输出的DOC文件路径
convert_pdf_to_doc(pdf_path, doc_path)