爬取某图片网站的图片（偷懒法）

# @Author:Ps_Y
# -*- coding = utf-8 -*-
# @Time : 2021-05-11 11:15
# @File : req_pic.py
# @Software : PyCharm

import requests
from bs4 import BeautifulSoup
import os
import lxml

def main():
    if not os.path.exists('./girl_pic'):
        os.mkdir('./girl_pic/')

    baseurl = "https://www.ivsky.com/tupian/shishangnvhai_t19861/"
    head =head = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36"}
    for i in range(1,9):
        tolurl = "index_"+str(i)+".html"  #尾部链接的网址变化
        url = baseurl+tolurl
        html =requests.get(url,headers=head)
        # print(html.text)
        soup = BeautifulSoup(html.text, 'lxml')
        # print(soup)
        pic_url1 = soup.find_all("div",class_="il_img")
        # print(pic_url1[1])
        for t in range(0,len(pic_url1)):
            pic_url2 = pic_url1[t].find('img')
            pic_name = pic_url2['alt']+str(t+1)
            pic_url3 = pic_url2['src'][29:len(pic_url2['src'])]
            # print(pic_url3)
            pic_url ="https://img-pre.ivsky.com/img/tupian/pre/" + pic_url3
            print(pic_name)
            print(pic_url)
            pic = requests.get(pic_url)
            with open('./girl_pic/' + pic_name + '.jpg','wb') as f:
                f.write(pic.content)
                print("保存成功")

#//img.ivsky.com/img/tupian/t/202102/16/park_da_hyun.jpg

#//img-pre.ivsky.com/img/tupian/pre/202102/16/park_da_hyun.jpg

#//img.ivsky.com/img/tupian/t/202102/16/piaozhengyun-011.jpg

#//img-pre.ivsky.com/img/tupian/pre/202102/16/piaozhengyun-011.jpg










if __name__ == '__main__':
    main()
           

爬取某网站的部分图片，仅学习使用