工作要求找部分美女图片--贴代码啦

# 抓去高清图片

# 1、进入主页面，提取主页面的超链接
# 2、点击进去获取高清图片

import requests
from bs4 import BeautifulSoup
import time

headers = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36"

}
#临时存的变换页码的字典
list = {'0'}
#获取路径后缀字典
def query_url(mainUrl):
    init_url = mainUrl
    for i in range(5):
        if i > 1:
            #替换路径后缀
            init_url = mainUrl +'index_'+str(i)+'.htm'
        resp = requests.get(url=init_url , headers=headers)
        resp.encoding = 'utf-8'
        # 源代码交到beatifulsoup
        main_page = BeautifulSoup(resp.text, "html.parser")
        # print(main_page)
        ahref = main_page.find("div", class_="item_list infinite_scroll")
        ahref = ahref.find_all("a")
        for a in ahref:
            ss = a.get('href')
            #将获取到的网址放到字典中
            list.add(ss)
#进入页面获取高清图
def get_inner_img(url,child_url):
    url = url+child_url
    resp = requests.get(url=url , headers=headers)
    resp.encoding = 'utf-8'
    main_page = BeautifulSoup(resp.text, "html.parser")
    ahref = main_page.find("div", class_="pages")
    li_all = ahref.find_all('li')
    li_url = li_all[-1].find('a').get('href')
    #获取一个页面中的尾页的最大数
    max_int = li_url.split('_')[-1].split('.')[0]
    get_photo(url,int(max_int))
#通过心地址获取页面元素
def get_photo(url,max_int):
    init_url = url
    for i in range(max_int):
        if i < 1:
            continue
        if i > 1:
            old = init_url.split('/')[-1]

            end = old.split('.')[0]+"_"+str(i)+".htm"
            url = init_url.replace(old,end)

        resp = requests.get(url=url , headers=headers)
        resp.encoding = 'utf-8'

        main_page = BeautifulSoup(resp.text, "html.parser")

        ahref = main_page.find("div", class_="big-pic")
        # print(type(ahref))
        aimg = ahref.find("img")
        src = aimg.get('src')
        img_resource = requests.get(src, headers=headers)
        img_name = src.split("/")[-1]
        #写文件途径
        with open("touxiang/" + img_name+ '.jpg', mode="wb") as f:
            f.write(img_resource.content)  # 图片写入文件
        print("over", img_name)
        time.sleep(0.1)
        #下载一页数据

if __name__ == '__main__':
    # mainUrl = 'https://www.umei.cc/meinvtupian/meinvzipai/'
    mainUrl = 'https://更换成你的路径www.umei.cc/meinvtupian/meinvzipai/'
    #获取所有新的地址
    # update_url(mainUrl)
    query_url(mainUrl)

    #查询数据
    for i in list:
        if i == 0:
            continue
        get_inner_img('https://更换成你的路径www.umei.cc',i)