python (自学6) 爬虫 爬取站长素材 （图片）

安装 ：lxml

地址 ： Installing lxml

pip install lxml
或者
sudo pip install lxml

下面开始 写代码  下载 站长素材的图片

 

import urllib.request

from lxml import etree

import os

def create_request(page):
    if(page == 1):
        url = "https://sc.chinaz.com/tupian/qinglvtupian.html"
    else:
        url = "https://sc.chinaz.com/tupian/qinglvtupian_" + str(page) + '.html'

    # print(url,'ssss')


    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.82 Safari/537.36 Edg/116.0.0.0"
    }

    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)
    srve_list = tree.xpath('//div[@class="item"]/img/@data-original')
    name_list = tree.xpath('//div[@class="item"]/img/@alt')
    # print(name_list , srve_list, 'src')

    for i in range(len(name_list)):
        name = name_list[i]
        src = srve_list[i]
        url = "https:" + src
        print(name,url, 'pinjie')
    #

        # 指定保存图片的文件夹和文件名
        directory = './qinglvtupian'
        if not os.path.exists(directory):
            os.makedirs(directory)  # 如果文件夹不存在，则创建它
        filename = os.path.join(directory, name + '.jpg')

        urllib.request.urlretrieve(url=url, filename=filename)

        # 不存文件夹
        # urllib.request.urlretrieve( url = url , filename= "./qinglvtupian" + name+ '.jpg')

if __name__ == '__main__':
    start_page =  int(input("请输入开始值"))
    end_page =  int(input("请输入结束值"))

    for page in range(start_page, end_page + 1):
        # print(page)
        request =  create_request(page)
        content =   get_content(request)

        down_load(content)