爬虫_xpath_爬取站长素材照片

查看网页源码照片的具体路径

import urllib.request
from lxml import etree


# https://sc.chinaz.com/tupian/meinvtupian.html
# https://sc.chinaz.com/tupian/meinvtupian_2.html




def create_request(page):
    url = 'https://sc.chinaz.com/tupian/meinvtupian.html'

    if page != 1:
        url='https://sc.chinaz.com/tupian/meinvtupian_'+str(page)+'.html'

    headers={'user-agent':
                             'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '
                             'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36'
}
    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):
    tree=etree.HTML(content)
    src_list = tree.xpath('//div[@class="container"]/div/div/img/@data-original')

    name_list = tree.xpath('//div[@class="container"]/div/div/img/@alt')
    for i in range (len(src_list)):
        urllib.request.urlretrieve('https:'+src_list[i], '.\datas\站长素材\\'+name_list[i]+'.jpg')


if __name__ == '__main__':
    start_page=int(input("请输入起始页码："))
    end_page=int(input("请输入结束页码："))

    for page in range(start_page,end_page+1):
        # 请求对象定制
        request=create_request(page)
        #获取网页源码
        content = get_content(request)
        #下载照片
        down_load(content)

照片地址为@data-original是因为有懒加载

下载完毕