python提取pdf中图片和文本

import fitz
import docx
#PyMuPDF对于中文识别还是比较理想的，安装模块pip3 install PyMuPDF
pdf_document1 = "2.pdf"
doc = fitz.open(pdf_document1)
# print ("number of pages: %i" % doc.pageCount)
# print(doc.metadata)
#word文件用于存储提取的内容
'''提取文本'''
file =docx.Document()
for current_page in range(doc.page_count):
  page = doc.load_page(current_page)
  pagetext = page.get_text("text")
  file.add_paragraph(pagetext)
file.save('3.docx')

'''提取图片'''
pdf_document2 = "2.pdf"
pdf_document = fitz.open(pdf_document2)
count=0
for current_page in range(pdf_document.page_count):
    for image in pdf_document.get_page_images(current_page):
        xref = image[0]
        pix = fitz.Pixmap(pdf_document, xref)
        count=count+1
        if pix.n < 5:        # this is GRAY or RGB
            pix.save(".\image\\"+str(current_page)+"_"+str(count)+".png")
        else:                # CMYK: convert to RGB first
            pix1 = fitz.Pixmap(fitz.csRGB, pix)
            pix.save(".\image\\"+str(current_page)+"_"+str(count)+".png")
            pix1 = None
        pix = None