python 从pdf中提取图片

需要用到 pymupdf 库

安装

pip install PyMuPDF

　

创建py文件

import fitz

pdf_document = fitz.open("12.pdf") #文件位置
for current_page in range(len(pdf_document)):
    print(current_page)
    for image in  pdf_document.get_page_images(current_page):
        print(image)
        xref = image[0]
        pix = fitz.Pixmap(pdf_document,xref)
        if pix.n<5:
            pix.save('imgs/page%s-%s.jpg' %(current_page,xref)) #保存地址
        else:
            pix1 = fitz.Pixmap(fitz.csRGB,pix)
            pix1.save('imgs/page%s-%s.jpg' %(current_page,xref)) #保存地址
            pix1=None
        pix = None