python批量抓取美女图片

#!/usr/bin/env python
#-*- coding: utf-8 -*-
#通过urllib(2)模块下载网络内容
import urllib,urllib2,gevent
#引入正则表达式模块，时间模块
import re,time
from gevent import monkey
   
monkey.patch_all()
   
def geturllist(url):
    url_list=[]
    print url       
    s = urllib2.urlopen(url)
    text = s.read()
    #正则匹配，匹配其中的图片
    html = re.search(r&#39;<ol.*</ol>&#39;, text, re.S)
    urls = re.finditer(r&#39;<p><img  src="(.+?)jpg" / alt="python批量抓取美女图片" ></p>&#39;,html.group(),re.I)
    for i in urls:
        url=i.group(1).strip()+str("jpg")
        url_list.append(url)
    return url_list
   
def download(down_url):
    name=str(time.time())[:-3]+"_"+re.sub(&#39;.+?/&#39;,&#39;&#39;,down_url)
    print name
    urllib.urlretrieve(down_url, "D:\\TEMP\\"+name)
   
def getpageurl():
    page_list = []
    #进行列表页循环
    for page in range(1,700):
        url="http://jandan.net/ooxx/page-"+str(page)+"#comments"
        #把生成的url加入到page_list中
        page_list.append(url)
    print page_list
    return page_list
if __name__ == &#39;__main__&#39;:
    jobs = []
    pageurl = getpageurl()[::-1]
    #进行图片下载
    for i in pageurl:
        for (downurl) in geturllist(i):
            jobs.append(gevent.spawn(download, downurl))
    gevent.joinall(jobs)