Python实现快速将pdf文件剪切成多个图片

import os
import fitz
import glob
import requests


os.environ['NLS_LANG'] = 'SIMPLIFIED CHINESE_CHINA.UTF8'

#剪切pdf为图片
def CutPdf(pdfPath,savePath,pdfSavePath):
	try:
		doc = fitz.open(pdfPath) #pdf路径
		for pg in range(doc.pageCount):
			page = doc[pg]
			rotate = int(0)
		    # 每个尺寸的缩放系数为2，这将为我们生成分辨率提高四倍的图像。
			zoom_x = 2.0
			zoom_y = 2.0
			trans = fitz.Matrix(zoom_x, zoom_y).preRotate(rotate)
			pm = page.getPixmap(matrix=trans, alpha=False)
			imagePath = savePath + '%s.png' % str(pg + 1)
			pm.writePNG(imagePath) #最终存储路径
			newpdfPath = pdfSavePath + '%s.pdf' % str(pg + 1)
			print("剪切一张图片：" + str(pg + 1))
			frompic2pdf(imagePath,pdfSavePath,newpdfPath)
			print("转换成功一张pdf：" + str(pg + 1))
	except Exception as e:
		print('CutPdf出现异常:' + str(e))

#图片转pdf
def frompic2pdf(img_path,pdfSavePath, pdf_path):
	# 使用glob读图
	for img in sorted(glob.glob(img_path)):
		if not os.path.exists(pdfSavePath):
			 os.makedirs(pdfSavePath)
		
		# 打开空文档
		doc = fitz.open()
		# 打开指定图片
		imgdoc = fitz.open(img)
		# 使用图片创建单页的PDF
		pdfbytes = imgdoc.convertToPDF()
		imgpdf = fitz.open("pdf", pdfbytes)
		# 将当前页写入文档
		doc.insertPDF(imgpdf)
		# 保存为指定名称的PDF文件
		doc.save(pdf_path)
		# 关闭
		doc.close()


def main():
    pdfUrl = "cards"
    fileList = os.listdir(pdfUrl)
    index = 1
    for item in  fileList:
        print("开始裁剪" + item)
        url = pdfUrl + "/" + item

        foldStr = "images/" + item.split('.')[0]
        url2 = foldStr + "/" + item.split('.')[0]
        foldStr3 = "pdf/" + item.split('.')[0]
        url3 = foldStr3 + "/"
        if not os.path.exists(foldStr):
            os.makedirs(foldStr)

        CutPdf(url,url2,url3)
        print("完成裁剪")
        index+=1

if __name__ == "__main__":
    main()

# 获取页面尺寸
page_width = page.mediaBox.getWidth()
page_height = page.mediaBox.getHeight()

# 定义剪裁区域的位置和大小
x = 100  # 起始点的x坐标
y = 100  # 起始点的y坐标
width = 200  # 剪裁区域的宽度
height = 300  # 剪裁区域的高度

# 剪裁PDF页面
page.trimBox.lowerLeft = (x, y)
page.trimBox.upperRight = (x + width, y + height)
page.cropBox.lowerLeft = (x, y)
page.cropBox.upperRight = (x + width, y + height)

from PIL import Image

# 将剪裁后的页面保存为图片
with open('output.jpg', 'wb') as image_file:
    page_data = page.extract_xobject().get('/Im0').getData()
    image = Image.open(io.BytesIO(page_data))
    image.save(image_file, 'JPEG')

from PyPDF2 import PdfFileReader, PdfFileWriter
 
 
# PDF文件分割
def split_pdf(read_file, out_detail):
    try:
        fp_read_file = open(read_file, 'rb')
        pdf_input = PdfFileReader(fp_read_file)  # 将要分割的PDF内容格式话
        page_count = pdf_input.getNumPages()  # 获取PDF页数
        print(page_count)  # 打印页数
 
        with open(out_detail, 'r',True,'utf-8')as fp:
            # print(fp)
            txt = fp.readlines()
            # print(txt)
            for detail in txt:  # 打开分割标准文件
                # print(type(detail))
                pages, write_file = detail.split()  # 空格分组
               #  write_file, write_ext = os.path.splitext(write_file)  # 用于返回文件名和扩展名元组
                pdf_file = r'C:\Users\GZTSALFIEL\Desktop\excel问题文件\pdf\\'+f'{write_file}.pdf'
                # liststr=list(map(int, pages.split('-')))
                # print(type(liststr))
                start_page, end_page = list(map(int, pages.split('-')))  # 将字符串数组转换成整形数组
                start_page -= 1
                try:
                    print(f'开始分割{start_page}页-{end_page}页，保存为{pdf_file}......')
                    pdf_output = PdfFileWriter()  # 实例一个 PDF文件编写器
                    for i in range(start_page, end_page):
                        pdf_output.addPage(pdf_input.getPage(i))
                    with open(pdf_file, 'wb') as sub_fp:
                        pdf_output.write(sub_fp)
                    print(f'完成分割{start_page}页-{end_page}页，保存为{pdf_file}!')
                except IndexError:
                    print(f'分割页数超过了PDF的页数')
        # fp.close()
    except Exception as e:
        print(e)
    finally:
        fp_read_file.close()
 
 
 
# def main():
#     fire.Fire(split_pdf)
#
# if __name__ == '__main__':
#     main()
 
split_pdf(r'..\pdfdocement\myfile.pdf', 'consult.txt')