爬取站长图片（图片懒加载）

已加载的图片
未加载的图片

通过观察发现img下的data-original 属性是固定不变的，可以通过抓取这个数据，来得到图片的信息

import requests 
from lxml import etree
from fake_useragent import UserAgent

headers = {
    "User-Agent":UserAgent().chrome
}
def get_page():
    page = int(input("要爬取几页数据："))
    urls = ["https://sc.chinaz.com/tupian/meinvtupian.html"]
    for i in range(2,page+1):
        if page == 1:
            url = urls[0]
        else:
            url = f"https://sc.chinaz.com/tupian/meinvtupian_{i}.html"
        urls.append(url)
    # print(urls)
    j = 1
    for url in urls:
        print(f"-----第{j}页开始爬取-----")
        get_img(url)
        print(f"-----第{j}页爬取完成-----")
        j += 1
    print(f"爬取共{j-1}页{(j-1)*40}张图片")

def get_img(url):
    resp = requests.get(url,headers)
    resp.encoding = "utf-8"
    e = etree.HTML(resp.content)
    imgs_src = e.xpath("//div[@class='container']/div[2]/div/img/@data-original")
    for src in imgs_src:
        img_src = "https:" + src
        pic_name = src.split("imgs")[-1].split("/")[-1]
        response = requests.get(img_src)
        with open(f"imgs/{pic_name}","wb") as f:
            f.write(response.content)
if __name__ == "__main__":
    get_page()