python转换并提取pdf文件中的图片

复制代码

#安装fitz包
pip install pymupdf

脚本如下所示：

复制代码

import fitz
import re
import os
import time
import sys

arguments = sys.argv

for arg in arguments:
    print(arg)


def file_name_list(base_dir):
    for i, j, k in os.walk(base_dir):
        name = [i.replace('.pdf', '') for i in k]
        return name


def pdfExtractPic(filePath, pic_path):
    ret = {}
    try:
        iNum = 0
        with fitz.open(filePath) as doc:
            for page in range(len(doc)):
                for image in doc.get_page_images(page):
                    xref = image[0]
                    pix = fitz.Pixmap(doc, xref)
                    iNum += 1
                    fileName = ("%s\%d.png"%(pic_path, iNum))
                    if pix.n < 5:
                        pix.save(fileName)
                    else:
                        pix1 = fitz.Pixmap(fitz.csRGB, pix)
                        pix1.save(fileName)
                        pix1 = None

    except Exception as e:
        print(e)

    return ret

 
def pdf2image(path, pic_path, image_name):
    try:
        with fitz.open(path) as pdf:
            for pg in range(0, pdf.page_count):
                page = pdf[pg]
        # 设置缩放和旋转系数,zoom_x, zoom_y取相同值，表示等比例缩放
                mat = fitz.Matrix(2, 2)
                pm = page.get_pixmap(matrix=mat, alpha=False)
        # if width or height > 2000 pixels, don't enlarge the image
                if pm.width > 2000 or pm.height > 2000:
                    pm = page.get_pixmap(matrix=fitz.Matrix(1, 1), alpha=False)
                page_num = pg + 1  # 页码从1开始
                new_name = '%s_img_%d.png' % (image_name, page_num)
                pm.save(os.path.join(pic_path, new_name)) 
    except Exception as error:
        print(error)                
 
 
if __name__ == '__main__':
    if len(arguments) < 2:
        print("请输入pdf所在目录的路径.")
        sys.exit(1)
        
    base_dir = arguments[1]

    name_list = file_name_list(base_dir)
    start = time.time()
    for name in name_list:
        image_name = name
        file_name = r'\%s.pdf' % name  # PDF 文件路径
        file_path = base_dir + file_name
        pic_name = r'\pic\%s' % name  # 存放图片的文件夹
        pic_path = base_dir + pic_name
        try:
            os.makedirs(pic_path)   # 根据路径，创建对应路径下的文件夹
        except Exception as error:
            print(error)        
        pdf2image(file_path, pic_path, image_name)
        #print(pic_path)
        pic_path += "\\sub\\"
        try:
            os.makedirs(pic_path)   # 根据路径，创建对应路径下的文件夹
        except Exception as error:
            print(error)   
        pdfExtractPic(file_path, pic_path)
    end = time.time()
    print('task is over: %.2f' % (end-start))

如果执行的时候报错：

复制代码

RuntimeError: Directory 'static' does not exist

说明fitz安装错了版本，参考：PyMuPDF: AttributeError:模块'fitz'没有属性'open'_attributeerror: module 'fitz' has no attribute 'op-CSDN博客