[Python知识库]python pdf和图片互转

1.安装两个包

pip install PyMuPDF PySimpleGUI

2.pdf转图片

import fitz


def pdf2img(pdf_path, img_dir):
    doc = fitz.open(pdf_path)  # 打开pdf
    for page in doc:  # 遍历pdf的每一页

        zoom_x = 2.0  # 设置每页的水平缩放因子
        zoom_y = 2.0  # 设置每页的垂直缩放因子
        mat = fitz.Matrix(zoom_x, zoom_y)
        pix = page.get_pixmap(matrix=mat)
        pix.save(r"{}page-{}.png".format(img_dir, page.number))     # 保存


if __name__ == '__main__':
	
	# pdf路径
    pdf_path = r"./赵季平影视音乐成功因素分析.pdf"
    # 图片保存位置
    img_dir = r"./img/"
	
	# pdf转图片
    pdf2img(pdf_path, img_dir)

ps：将缩放因子 zoom_x 和 zoom_y 设为 2.0 之后，可以将转换出来的图片大小提高四倍

3.图片转pdf

import os, fitz
import PySimpleGUI as psg  # for showing a progress bar


def img2pdf(pdf_path, imgdir):
    doc = fitz.open()  # PDF with the pictures
    imglist = os.listdir(imgdir)  # list of them
    imgcount = len(imglist)  # pic count

    for i, f in enumerate(imglist):
        img = fitz.open(os.path.join(imgdir, f))  # open pic as document
        rect = img[0].rect  # pic dimension
        pdfbytes = img.convert_to_pdf()  # make a PDF stream
        img.close()  # no longer needed
        imgPDF = fitz.open("tar_pdf", pdfbytes)  # open stream as PDF
        page = doc.new_page(width=rect.width,  # new page with ...
                            height=rect.height)  # pic dimension
        page.show_pdf_page(rect, imgPDF, 0)  # image fills the page
        psg.OneLineProgressMeter("Import Images",  # show our progress
                                 i + 1, imgcount)

    doc.save(pdf_path)

def clear_dir(imgdir):
    imglist = os.listdir(imgdir)
    for img in imglist:
        os.remove(imgdir+img)


if __name__ == '__main__':
	# 图片文件夹路径
    img_dir = r"./img/"
    
    # 要生成的pdf路径
    pdf_path = r"./赵季平影视音乐成功因素分析.pdf"
	
	# 图片转pdf
    img2pdf(pdf_path, img_dir)
	
	# 清空图片
    # clear_dir(img_dir)

ps：其实这个 PyMuPDF 包还有很多功能，具体可以参考官网文档
https://pymupdf.readthedocs.io/en/latest/faq.html#how-to-make-images-from-document-pages