python网页抓取练手代码

from urllib import request
import html.parser

class zhuaqu(html.parser.HTMLParser):
    blogHtml = ""
    data = []
    flag = 0

    def getHtml(self):
        res = request.urlopen("http://www.cnblogs.com")
        self.blogHtml = res.read().decode(‘utf-8‘)

    def handle_starttag(self, tag, attrs):
        if(tag == "a"):
            for attr in attrs:
                if(attr[0] == "class" and attr[1] == "titlelnk"):
                    self.flag = 1
                    break
        else:
            pass
    def handle_data(self, data):
        if(self.flag == 1):
            self.data.append(data.strip())
            self.flag = 0
        else:
            pass

    def show(self):
        print(self.blogHtml)


zhua = zhuaqu()
zhua.getHtml()
zhua.feed(zhua.blogHtml)
for item in zhua.data:
    print(item)