urllib_站长素材

import urllib.request
from lxml import etree
def creat_request(page):
    header={
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'
    }
    req=urllib.request.Request(url=page,headers=header)
    return req
def get_content(req):
    response=urllib.request.urlopen(req)
    content=response.read().decode('utf-8')
    return content
def download_imag(content):
    #下载图片
    #urllib.request.urlretrieve(url,filename)
    tree=etree.HTML(content)
    name_li=tree.xpath('//img[@class="lazy"]/@alt')
    #一般涉及图片的网站都会设计懒加载 按变之前的
    src_li=tree.xpath('//img[@class="lazy"]/@data-original')
    # for i in range(len(name_li)):
    #     url='http:'+name_li[i][:-6]+".jpg"
    #     print(url)
    #     #urllib.request.urlretrieve(url,filename)
    for i in range(len(name_li)):
        name=name_li[i]
        src=src_li[i][:-6]+".jpg"
        url='https:'+src
        print(url)
        try:
            urllib.request.urlretrieve(url=url, filename="./img/"+name_li[i] + ".jpg")
            print("下载完成")
        except Exception as e:
            continue
def main():
    start_num=1#int(input())
    end_num=10#int(input())
    for i in range(start_num,end_num+1):
        if i==1:
            page = 'https://sc.chinaz.com/tupian/rentiyishu.html'
        else:
            page = 'https://sc.chinaz.com/tupian/rentiyishu_'+str(i)+'.html'
        req=creat_request(page)
        content=get_content(req)
        download_imag(content)

main()