自动化--PDF文件图片相互转换代码

需要安装两个模块

pip install fitz
pip install PyMuPDF

import glob
import fitz
import os
import time

# 1.提取原PDF关键代码
def pdf2pic(filename):
    image_floder='pdf'+str(time.time())
    os.mkdir(image_floder)

    pdffile = filename
    doc = fitz.open(pdffile)
    width, height = fitz.PaperSize("a4")

    totaling = doc.pageCount

    for pg in range(totaling):
        page = doc[pg]
        zoom = int(100)
        rotate = int(0)
        print(page)
        trans = fitz.Matrix(zoom / 100.0, zoom / 100.0).preRotate(rotate)
        pm = page.getPixmap(matrix=trans, alpha=False)
        lurl=image_floder+'/%s.jpg' % str(pg+1)
        pm.writePNG(lurl)
    doc.close()
    return image_floder

# 2.合并图片生成PDF
def pic2pdf(image_floder):
    doc = fitz.open()
    for img in sorted(glob.glob(image_floder+"/*")):  # 读取图片，确保按文件名排序
        print(img)
        imgdoc = fitz.open(img)                 # 打开图片
        pdfbytes = imgdoc.convertToPDF()        # 使用图片创建单页的 PDF
        imgpdf = fitz.open("pdf", pdfbytes)
        doc.insertPDF(imgpdf)                   # 将当前页插入文档
    if os.path.exists("newpdf.pdf"):        # 若文件存在先删除
        os.remove("newpdf.pdf")
    doc.save("newpdf.pdf")                   # 保存pdf文件
    doc.close()

image_floder=pdf2pic(filename='paper.pdf')
pic2pdf(image_floder)