gif爬虫

本人使用python版本为3.6.5

python3中内置urllib模块

python2中内置urllib2模块

#coding:utf-8
import urllib.request
import re


# 将正则表达式编译成Pattern对象
rex=r'src="(https://.*?\.gif)"';
pages = ('1','2');
x=1;
#输入您要爬的网址
pageurl=input()
for page in pages:
    #pageurl = "http://***********.com/default_%s.html" % page;
    Response=urllib.request.urlopen(pageurl);
    print(Response)
    Html=Response.read();
    print(Html.decode('utf-8','ignore'))
    lists = re.findall(rex, Html.decode('utf-8','ignore'));
    #print(lists)
    lensofpage=len(lists);
    print (lensofpage)
    
    picname = 'page' + page; 
    print (picname)
    
    for picurl in lists:
        #设置存储路径
        urllib.request.urlretrieve(picurl,r'C:\Users\hipeson\Desktop\pic\%s.gif' %x);
        print (page+picurl)
        x=x+1;

   
   
print ('DownLoadPicOver')