解析本地的htm文件并把base64编码的图像保存为本地的jpg文件

from lxml.html import parse
import base64
from glob import glob
import os
html_file="D:/DataSet/liusheng/blur/url_blur/*.htm"
for i in glob(html_file):
    print(i)
    floder=i.split("\\")[-1].replace(".","")
    parsed = parse(i)
    doc = parsed.getroot()
    ls=doc.findall(".//img")
    count=0
    for j in ls:
        count+=1
        src=j.get('src')
        data = src.split(',')[1]
        image_data = base64.b64decode(data)
        jpg= "D:/DataSet/liusheng/blur/url_blur_img/" + floder+str(count)+".jpg"
        with open(jpg, 'wb') as f:
            f.write(image_data)

    print(len(ls))

参考文章：

https://www.cnblogs.com/changdasheng/p/11496289.html

https://www.cnblogs.com/wwwwwei/p/10728060.html