day4 Python爬虫 获取‘站长素材的图片’ （学习笔记）

#1.xpath的数据解析
#2.文件名的连接
from lxml import etree
import urllib.request

def get_request(page):
    if page == 1:
        url = 'https://sc.chinaz.com/tupian/qinglvtupian.html'
    else:
        url = 'https://sc.chinaz.com/tupian/qinglvtupian_'+str(page)+'.html'
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36 Edg/113.0.1774.42'

    }
    request = urllib.request.Request(url=url,headers=headers)

    return request

def get_content(request):
    response = urllib.request.urlopen(request)
    content = response.read().decode('utf-8')
    return content

def down_load(content):
    #数据解析
    tree = etree.HTML(content)
    #使用xpath语法来进行数据筛选    
    name_list = tree.xpath('//img[@class="lazy"]/@alt')
    src_list = tree.xpath('//div/img/@data-original')
    for i in range(len(name_list)):
        #遍历两个列表，获取下标
        name = name_list[i]
        src = src_list[i]
        url = 'https:' + src
        #camp为自定义文件夹的名称
        urllib.request.urlretrieve(url=url,filename='./camp/'+name+'.jpg')



#程序入口
if __name__ == '__main__':
    start_page = int(input('请输入起始页'))
    end_page = int(input('请输入终止页'))
    for page in range(start_page,end_page+1):
         #定制request请求对象
         request = get_request(page)
         #模拟浏览器向服务器发送请求
         content = get_content(request)
         #下载数据
         down_load(content)