网安零基础学习-python-爬虫图片获取(灰帽编程18）

import urllib.request
import re
class GetHtml(object):
    def __init__(self,URL,HEAD):
        self.url=URL
        self.head=HEAD
    def get_index(self):
        self.request = urllib.request.Request(self.url)
        self.request.add_header("user-agent",self.head)
        self.response = urllib.request.urlopen(self.request)
        return self.response.read()
    def get_list(self):
        self.strimglist = []
        self.imglist = re.findall(b"style/\w{60}.jpg",self.get_index())
        #print(self.imglist)
        for i in self.imglist:
            self.strimglist.append(self.url+str(i,encoding="utf8"))
        return self.strimglist

    def get_image(self):
        num=0
        for self.url in self.get_list(self):
            num+=1
            with open(str(num+".jpg"),"wb") as f:
                f.write(self.get_index())
            
html = GetHtml("https://movie.douban.com/subject/1292052/photos?type=R","Mozilla/5.0 (Windows NT 8.1; Win32; rv:95.0) \
Gecko/20100101 Firefox/95.0")
#print(html.get_index(encoding="utf8"))


html.get_image()

#https://img0.baidu.com/it/u=333394868,1938696917&fm=253&fmt=auto&app=138&f=JPEG?w=889&h=500