python提取pdf转换为word代码

你可以使用Python的pdfminer库来提取PDF文件中的文本，然后使用Python-docx库将提取的文本转换为Word文档。以下是一个示例代码：

import io
import os
import sys
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
from docx import Document

def pdf_to_text(path):
    resource_manager = PDFResourceManager()
    fake_file_handle = io.StringIO()
    converter = TextConverter(resource_manager, fake_file_handle, laparams=LAParams())
    page_interpreter = PDFPageInterpreter(resource_manager, converter)

    with open(path, 'rb') as fh:
        for page in PDFPage.get_pages(fh, caching=True, check_extractable=True):
            page_interpreter.process_page(page)

        text = fake_file_handle.getvalue()

    converter.close()
    fake_file_handle.close()

    if text:
        return text

def text_to_word(text, output_path):
    document = Document()
    document.add_paragraph(text)
    document.save(output_path)

if __name__ == '__main__':
    pdf_path = 'example.pdf'
    text = pdf_to_text(pdf_path)
    if text:
        output_path = 'example.docx'
        text_to_word(text, output_path)

这个代码将提取名为“example.pdf”的PDF文件中的文本，并将其转换为名为“example.docx”的Word文档。