python抓取网页图片示例(python爬虫)

#-*- encoding: utf-8 -*-
'''
created on 2014-4-24

@author: leon wong
'''

import urllib2
import urllib
import re
import time
import os
import uuid

#获取二级页面url
def findurl2(html):
    re1 = r'http://tuchong.com/\d+/\d+/|http://\w+(?<!photos).tuchong.com/\d+/'
    url2list = re.findall(re1,html)
    url2lstfltr = list(set(url2list))
    url2lstfltr.sort(key=url2list.index)
    #print url2lstfltr
    return url2lstfltr

#获取html文本
def gethtml(url):
    html = urllib2.urlopen(url).read().decode('utf-8')#解码为utf-8
    return html

#下载图片到本地
def download(html_page , pageno):  
    #定义文件夹的名字
    x = time.localtime(time.time())
    foldername = str(x.__getattribute__("tm_year"))+"-"+str(x.__getattribute__("tm_mon"))+"-"+str(x.__getattribute__("tm_mday"))
    re2=r'http://photos.tuchong.com/.+/f/.+\.jpg'
    imglist=re.findall(re2,html_page)
    print imglist
    download_img=none
    for imgurl in imglist:
        picpath = 'd:\\tuchong\\%s\\%s'  % (foldername,str(pageno))
        filename = str(uuid.uuid1())
        if not os.path.exists(picpath):
            os.makedirs(picpath)              
        target = picpath+"\\%s.jpg" % filename
        print "the photos location is:"+target
        download_img = urllib.urlretrieve(imgurl, target)#将图片下载到指定路径中
        time.sleep(1)
        print(imgurl)
    return download_img

# def callback(blocknum, blocksize, totalsize):
#     '''回调函数
#     @blocknum: 已经下载的数据块
#     @blocksize: 数据块的大小
#     @totalsize: 远程文件的大小
#     '''
#     print str(blocknum),str(blocksize),str(totalsize)
#     if blocknum * blocksize >= totalsize:
#         print '下载完成'

def quitit():
    print "bye!"
    exit(0)
   

if __name__ == '__main__':
    print '''            *****************************************
            **    welcome to spider for tuchong    **
            **      created on 2014-4-24           **
            **      @author: leon wong             **
            *****************************************'''
    pageno = raw_input("input the page number you want to scratch (1-100),please input 'quit' if you want to quit>")
    while not pageno.isdigit() or int(pageno) > 100 :
        if pageno == 'quit':quitit()
        print "param is invalid , please try again."
        pageno = raw_input("input the page number you want to scratch >")

    #针对图虫人像模块来爬取
    html = gethtml("http://tuchong.com/tags/%e4%ba%ba%e5%83%8f/?page="+str(pageno))

    detllst = findurl2(html)
    for detail in detllst:
        html2 = gethtml(detail)
        download(html2,pageno)
    print "finished."