py爬虫图片

#首先导入所需的库
import requests
from bs4 import BeautifulSoup   
import time
for i in range(2,200):    #爬取第2页到第200页的壁纸
    url = f"http://www.netbian.com/index_{i}.htm"
    headers = {
        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:99.0) Gecko/20100101 Firefox/99.0"
    }
    resp = requests.get(url,headers=headers)
    print(url)
    resp.encoding = "GBK"    #处理乱码
    href1 = str("")
    href = str("")
    
#将源码转发给bs4
    main_page = BeautifulSoup(resp.text,"html.parser")
    alist = main_page.find("div",class_="list").find_all("a")  #把范围第一次缩小
    print(alist)
    for a in alist:
        href = (a.get("href"))
        if href != "http://pic.netbian.com/":
        #print("http://www.netbian.com/"+href)
        #拿子页面的源代码
           urlmix = requests.get("http://www.netbian.com/"+href)
           urlmix.encoding = "GBK"
           urlmix_text = urlmix.text
           main_page1 = BeautifulSoup(urlmix_text,"html.parser")
           urlmix_s = main_page1.find("div",class_="endpage")
           img = urlmix_s.find("img")
           src = (img.get("src"))
#下载图片
           img_resp = requests.get(src)
           img_resp.content #拿到的是源代码
           img_name = src.split("/")[-1]
           with open(img_name,mode="wb") as f:
            f.write(img_resp.content) #图片内容写入文件
            time.sleep(1)    #这里设置一秒防止ip被过滤