main.py

#coding=utf-8
import os
os.system("wget -r --spider http://diameizi.diandian.com 2>|log.txt")#非常简单的抓取整个网页树结构的语句————实质上是一种偷懒
filein=open('log.txt','r')
fileout=open('dst','w+')#一个装最后的结果的没用的文件
filelist=list(filein)
import urllib2,time
from bs4 import BeautifulSoup
header={
    'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.7; rv:8.0.1) Gecko/20100101 Firefox/8.0.1'} 
def getsite(url):
    req=urllib2.Request(url,None,header)
    site=urllib2.urlopen(req)
    return site.read()##上面这六句基本万金油了。。
try:
    dst=set()
    for p in filelist:
        if p.find('http://diameizi.diandian.com/post')>-1:
            p=p[p.find('http'):]
            dst.add(p)
    i=0
    for p in dst:
        #if i<191:
        #        i+=1
        #        continue##断点续传部分
        pagesoup=BeautifulSoup(getsite(p))
        pageimg=pagesoup.find_all('img')
        for href in pageimg:
            print i,href['src']
            picpath="pic/"+href['src'][-55:-13]+href['src'][-4:]##名字的起法有问题。。。不过效果还行。。
            pic=getsite(href['src'])
            picfile=open(picpath,'wb')
            picfile.write(pic)
            i+=1
            picfile.close()
finally:
    for p in dst:
        fileout.write(p)
    fileout.close()