python爬虫获取图片2

import urllib.request
import re

隐藏登录信息

def get_html(url):
    request = urllib.request.Request(url) #添加地址
    request.add_header("user-agent","Mozilla/4.0 (Windows NT 6.5.0;\
    Win32; x86; rv:69.0) Gecko/20100101 Firefox/69.0") #添加头部信息
    response = urllib.request.urlopen(request) #提交信息包含头部信息
    html = str(response.read(),encoding="utf8") #获取页面后转换为字符串
    return html

通过正则获取图片信息

def get_imglist(html):

    imglist = re.findall("http://i-r7.ibuka.cn/pics/222517/65537/t5756486\w{5}\.jpg",html)
    return imglist

将图片下载到本地

def get_img(imglist):
    num = 0
    for i in imglist: #每一个图的地址
        request = urllib.request.Request(i) #添加地址
        request.add_header("user-agent","Mozilla/4.0 (Windows NT 6.5.0;\
        Win32; x86; rv:69.0) Gecko/20100101 Firefox/69.0") #添加头部信息
        response = urllib.request.urlopen(request) #提交信息包含头部信息
        html = response.read() #获取图片的二进制内容
        num += 1 #为了文件名称定义
        with open(r"C:\Users\changpin\Desktop\b\b\%s.jpg" %num,"wb") as f: #图片用二进制图片写入
            f.write(html)

主函数

if __name__ == "__main__":
    url = "http://www.buka.cn/view/222517/65537.html"
    html = get_html(url)
    #print(html)
    imglist = get_imglist(html)
    #print(imglist)
    get_img(imglist)