爬虫爬取图片

这个代码只适用于搜狗图片的网站，
具体用法我已经在视频里进行讲解

爬虫爬取海绵宝宝

# -*- codeing = utf-8 -*-
# @Time : 2021/1/24 16:56
# @Author : 老七疯狂吸氧
# @file spider.sougou.py
# @Software:PyCharm
import urllib
import requests
import json
import os
import shutil
import re
import time

def main():
    n=1
    m = 1
    for w in range(0,1):
        url = "https://pic.sogou.com/d?query=%E7%A7%91%E6%AF%94&forbidqc=&entityid=&preQuery=&rawQuery=&queryList=&st=&did=" + str(m)
        m += 60
        list = get_html(url)
        reurl = saveurl(list)
        for i in reurl:
            pt = requests.get(i)
            print("爬取完成：", n)
            time.sleep(1)
            with open("科比" + str(n) + ".jpg", "wb+") as file:
                file.write(pt.content)
                file.close()
                n += 1




def get_html(url):         #一次请求
    headers = {
     
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
    }         #请输入你个人的User-Agent
    response = requests.get(url, headers=headers)
    return response.text

def saveurl(baseurl):     #获取真实的html
    findlink=re.compile(r'&url=(.*?)" alt="')
    cid = re.findall(findlink,baseurl)
    return cid

if __name__ == '__main__':
    main()