python爬取捧腹网gif图片

#_*_coding:utf-8_*_
#爬取捧腹网GIF图片
import urllib,re
import urllib.request
import chardet   #需要导入这个模块，检测编码格式
#获取源码
def page(pg):
    header = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.235'}
    url = 'http://www.gaoxiaogif.cn/gif/%s/'%pg
    #reg = urllib.urlopen(url).read()
    request = urllib.request.Request(url, headers=header)
    reg = urllib.request.urlopen(request).read()
    encode_type = chardet.detect(reg)
    reg = reg.decode(encode_type['encoding'])  # 进行相应解码，赋给原标识符（变量）
    #print (reg)
    return reg
#获取图片标题
def title(html):
    #html = page(1)
    name = re.compile(r'<p class="img"><a href=".*?" target="_blank" title="(.*?)">')
    reg = re.findall(name,html)
    #print (reg)
    #for i in reg:
    #    print (i)
    return reg
#获取图片来源
def souce(html):
    reg = r'img class="lazy" data-original="(.*?)"'
    itrm = re.findall(reg,html)
    #print(itrm)
    return itrm
#下载图片到指定文件夹
def download(url,name):
    path = 'img\%s.gif'%name
    urllib.request.urlretrieve(url,path)    #urlretrieve为下载图片的方法
#获取捧腹网前五页图片。并下载
num = int(input("你要爬取几页："))
for i in range(1,num):
    html = page(i)
    title_name = title(html)
    souce_name = souce(html)
    for i,z in zip(title_name,souce_name):  #ZIP函数匹配title_name souce_name
        download(z,i)
        print (i,z)