import urllib2,urllib,re,os

'''

http://www.dbmeizi.com/category/2?p=%

'''

def get_url_from_douban():

    url_list=[]

    p=re.compile(r'''<img.*?src="(.+?\.jpg)''') #找出发布人的标题和url

    for i in range(1,50):

        target = r"http://www.dbmeizi.com/category/2?p=%d"%i

        # print target

        req=urllib2.urlopen(target)

        result=req.read()

        matchs=p.findall(result)

        url_list.extend(matchs)

        # print matchs

        # print "-----"*40

    return url_list

def download_pic(url_list):

    # print url_lists

    count=0

    if not os.path.exists('/tmp/pic'):

        os.mkdir('/tmp/pic/')

    for url in url_list:

        urllib.urlretrieve(url,'/tmp/pic/'+str(count)+'.jpg')

        count+=1

if __name__=='__main__':

    # start_time=time.time()

    print "start getting url..."

    url_lists=get_url_from_douban()

    print "url getted! downloading..."

    download_pic(url_lists)

    print "download finish!!!"

    # cost_time=time.time() - start_time()

    # print cost_time

    # download_pic(url_lists)

－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－

/System/Library/Frameworks/Python.framework/Versions/2.7/bin/python /Users/lsf/PycharmProjects/some_subject/get_doubanmeizi_pic.py
start getting url...
url getted! downloading...
download finish!!!

Process finished with exit code 0