2022/3/24 站长素材获取

import urllib.request
from lxml import etree
def create_request(page):
    if(page==1):
        url='https://sc.chinaz.com/tupian/fengjing.html'
    else:
        url='https://sc.chinaz.com/tupian/fengjing.html_'+str(page)+'.html'
    headers={
        'user-agent': '自己的ua'
    }
    request=urllib.request.Request(url=url,headers=headers)
    return request

def get_response(request):
    response=urllib.request.urlopen(request)
    content=response.read().decode('utf-8')
    return content
def download(content):
    tree=etree.HTML(content)
    src_list=tree.xpath('//div/img/@data-original')
    name_list=tree.xpath('//div/img/@alt')
    for i in range(len(src_list)):
        url='https:'+src_list[i]
        name=name_list[i]
        print(url)
        print(name)
        urllib.request.urlretrieve(url=url,filename=name+'.png')