python爬虫批量下载图片

python爬虫到站长素材下载图片，demo下载的是情侣图片

需要用到 lxml 进行 网页元素路径处理

# 站长素材
"""
1.请求对象的定制
2.获取网页源码
3.下载
"""
# 批量下载图片
# https://sc.chinaz.com/tupian/qinglvtupian.html
# https://sc.chinaz.com/tupian/qinglvtupian_2.html


import urllib.request
from lxml import etree

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'

    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 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 download_img(content):
    # 下载图片
    # urllib.request.urlretrieve('图片地址', '文件名字')
    tree = etree.HTML(content)

    name_list = tree.xpath('//div[@class="tupian-list com-img-txt-list"]/div/img/@alt')
    original_list = tree.xpath('//div[@class="tupian-list com-img-txt-list"]/div/img/@data-original')

    for i in range(len(name_list)):
        name = name_list[i]
        url = 'https:' + original_list[i]
        print(name, url)

        urllib.request.urlretrieve(url=url, filename='./img/' + name + '.jpg')





if __name__ == '__main__':
    start_page = int(input("输入首页"))
    end_page = int(input("输入尾页"))
    for page in (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)
        # 下载图片
        download_img(content)