天堂图片 def 方法获取

目标地址

import requests
from lxml import etree
import time

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36'
}
name = 1   #  全局变量
# 下载网页
def get_html(link):
    print("正在获取第{}页数据".format(page))
    respon = requests.get(link,headers=headers).content.decode('utf-8')
    return respon

#  解析网页 提取图片真实地址
def parse_html(html):
    html_etree = etree.HTML(html)
    img_urls = html_etree.xpath('//div[@class="il_img"]/a/img/@src')
    return img_urls

#   保存图片到本地
def save_img(img_urls):
    global name
    for img_url in img_urls:
        new_link = 'https:' +img_url
        time.sleep(3)  #  每暂停 3 s 请求一次  
        a = requests.get(new_link,headers=headers).content
        print("正在下载{}张图片".format(name))
        with open(r'C:\Users\DELL\Desktop\python_wd\mig\天堂\\'+str(name)+'.jpg','wb')as f:
            f.write(a)
        name += 1



def main(page):
    link = 'https://www.ivsky.com/tupian/meinv_t50/index_{}.html'.format(page)
    html = get_html(link)
    img_urls = parse_html(html)
    save_img(img_urls)

if __name__ == '__main__':
    for page in  range(1,4):
        main(page)

运行代码数据部分结果：

————————END