批量将PDF文件夹内的PDF文件转图片脚本

批量的PDF转图片的脚本python

import fitz
import os


def mkdir(path):
    folder = os.path.exists(path)
    if not folder:  # 判断是否存在文件夹如果不存在则创建为文件夹
        os.makedirs(path)  # makedirs 创建文件时如果路径不存在会创建这个路径
    else:
        pass


def pdf_image(pdfPath, imgPath, zoom_x, zoom_y, rotation_angle):
    """
    :param pdfPath: pdf文件的路径
    :param imgPath: 图像要保存的文件夹
    :return: None
    """
    # 打开PDF文件
    pdf = fitz.open(pdfPath)
    name = pdf.name
    name = name.replace('C:\Learning\program\\12.1\pdfs/', '').replace('.pdf', '')
    # 逐页读取PDF
    for pg in range(0, pdf.pageCount):
        page = pdf[pg]
        # 设置缩放和旋转系数
        trans = fitz.Matrix(zoom_x, zoom_y).preRotate(rotation_angle)
        pm = page.getPixmap(matrix=trans, alpha=False)
        # 开始写图像
        mkdir(imgPath)
        pm.writePNG(imgPath+str(name)+"_"+str(pg) + ".png")
        
    pdf.close()

file_dir = r'C:\\Learning\\program\\12.1\\pdfs\\'
file_list = []
for items in os.walk(file_dir, topdown=False):
    file_list = items[2]

for file in file_list:
    head = 'C:\\Learning\\program\\12.1\\pdfs/'
    pdf_image(head + file, r"C:\\Learning\\program\\12.1\\images/", 5, 5, 0)