#coding=utf-8
import urllib2
from HTMLParser import HTMLParser
class HttpParser(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self.move=[]

    def handle_starttag(self,tag,attrs):
        def _attr(attrlist,attrname):
            for attr in attrlist:
                if attr[0]==attrname:
                    return attr[1]
            return None

        if tag==‘li‘ and _attr(attrs,‘data-title‘):
            move={}
            move[‘title‘]=_attr(attrs,‘data-title‘)
            move[‘rate‘] = _attr(attrs, ‘data-rate‘)
            self.move.append(move)

def get(url):

    re=urllib2.urlopen(url)
    parser=HttpParser()
    parser.feed(re.read())
    re.close()
    return parser.move



if __name__ == ‘__main__‘:
    url=‘https://movie.douban.com/‘
    moves=get(url)
    import json
    print json.dumps(moves,ensure_ascii=False,indent=2)

豆瓣電影簡易爬取