python批量爬取图片的方法详解

https://sc.chinaz.com/tupian/qinglvtupian.html

https://sc.chinaz.com/tupian/qinglvtupian_N.html
N从2开始，除了第一页不同，后面跳转其它页面规律相同

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'
    header = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36'
    }
    request = urllib.request.Request(url,headers=header)
    #获取网络源码
    response = urllib.request.urlopen(request)
    content = response.read().decode('utf-8')
    return content

//img[@class="lazy"]/@alt  #获取图片名称
//img[@class="lazy"]/@data-original  #获取图片地址

def down_load(content):
    tree = etree.HTML(content) #解析网页数据   解析本地的html文件  etree.parse('D:/pages/test.html')
    name_list = tree.xpath('//img[@class="lazy"]/@alt')
    # 图片会进行懒加载
    src_list = tree.xpath('//img[@class="lazy"]/@data-original')
    for i in range(len(name_list)):
        name = name_list[i]
        src = src_list[i]
        url = 'https:'+src
        urllib.request.urlretrieve(url,filename='../loveImg/'+name+'.jpg')#先在当前目录下创建loveImg文件夹

if __name__ == '__main__':
    start_page = int(input("开始页"))
    end_page = int(input("结束页"))
    for page in range(start_page,end_page+1):
        context = create_request(page)
        down_load(context)