[改进，多线程下载]下载豆瓣妹子的图片 http://dbmeizi.com 使用方法：python db.py 会在当前目录下创建dbmeizi文件夹并下载所有图片

db2.py

#coding:utf-8
#!/usr/bin/python 
import Queue
import threading
import os
import time
import random

import urlparse,urllib,urllib2,os,time,threading,Queue
from bs4 import BeautifulSoup

def downloadImage(imageURL):
	
	url = urlparse.urlparse(imageURL)
	i = len(url.path) - 1
	while i > 0:
		if url.path[i] == '/':
			break
		i = i - 1

	filename = url.path[i+1:len(url.path)]
	urllib.urlretrieve(imageURL,"./dbmeizi/"+filename);

	print filename+"..... done"


def findMM(startIndex,length):
	#os.makedirs("./dbmeizi")
	index = startIndex
	picList = []
	while index<startIndex+length:
	
		htmlString = urllib2.urlopen("http://www.dbmeizi.com/?p="+str(index)).read()
		soup = BeautifulSoup(htmlString)

		pics = soup.findAll("div",{"class":"pic"})

		#if len(pics) == 0:
		#	return

		for person in pics:
			mz = person.find("img")
			picURL = mz["data-bigimg"]
			picList.append(picURL)
			#downloadImage(picURL)
			#print "==="

		print "find page "+str(index)
		index = index + 1

	return picList

class Download(threading.Thread):
	name = ""
	def __init__(self,que):
		threading.Thread.__init__(self)
		self.que=que
	def run(self):
		while True:

			host = self.que.get()
			#time.sleep(random.random()*3)
			#time.sleep(1)
			downloadImage(host)
			#print "download......"+host+"....done\n"
			self.que.task_done()

	    	#grabs urls of hosts and prints first 1024 bytes of page
	    	#url = urllib2.urlopen(host)
	   		#print url.read(1024)
			
	    	#signals to queue job is done
	    	

			#print "download......"
			#time.sleep(random.random()*3)
			#time.sleep(3)
			#print "download......"+self.name


def main():

	theList = findMM(0,900)

	#print theList[0]

	q = Queue.Queue(0)


	for x in range(10):
		d = Download(q)
		d.name = str(x)
		d.setDaemon(True)
	 	d.start() 

	for url in theList:
		q.put(url)


	q.join()


main()