站长素材网站图片自动下载教程（urllib）

站长素材网站图片自动下载教程

import urllib.request
import urllib.parse
from lxml import etree



headers={
    'User-Agent':
    '#放入自己的ua'
}

def creat_request(page):
    if (page==1):
        url='http://sc.chinaz.com/tupian/siwameinvtupian.html'
    else:
        url='http://sc.chinaz.com/tupian/siwameinvtupian_{}.html'.format(str(page))
    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 downlod(page,content):
    tree=etree.HTML(content)
    name_list=tree.xpath('/html/body/div[3]/div/div/div/a/text()')
    downlod_url=tree.xpath('/html/body/div[3]/div[2]/div/img/@data-original')
    for i in range(len(name_list)):
        name=name_list[i]
        url='http:'+downlod_url[i]
        urllib.request.urlretrieve(url=url,filename='./imag/'+name+'.jpg')
    # with open('kfc_'+str(page)+'.json','w',encoding='utf-8') as fp:
    #     fp.write(content)



if __name__=='__main__':
    start_page=int(input("请输入起始页："))
    end_page=int(input("请输入结束页："))
    for page in range(start_page,end_page+1):
        request=creat_request(page)
        content=get_content(request)
        downlod(page, content)