python pdf转word

你可以使用Python的第三方库`pdfminer`来解析PDF文档中的文本，然后使用Python的`docx`库将解析出来的文本写入Word文档中。以下是一个简单的示例代码：

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

def convert_pdf_to_txt(path):
    rsrcmgr = PDFResourceManager()
    retstr = io.StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    fp = open(path, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0
    caching = True
    pagenos = set()
    for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True):
        interpreter.process_page(page)
    fp.close()
    device.close()
    text = retstr.getvalue()
    retstr.close()
    return text

def convert_to_docx(pdf_path, docx_path):
    text = convert_pdf_to_txt(pdf_path)
    doc = docx.Document()
    doc.add_paragraph(text)
    doc.save(docx_path)

pdf_path = 'example.pdf'
docx_path = 'example.docx'
convert_to_docx(pdf_path, docx_path)

在这个例子中，`convert_pdf_to_txt()`函数使用`pdfminer`解析PDF文档中的文本并返回一个字符串。`convert_to_docx()`函数将解析出来的文本写入Word文档中，并保存为.docx文件。你可以将`pdf_path`和`docx_path`替换为你自己的文件路径。