作业

#coding:utf-8
from HTMLParser import HTMLParser
import sys
listCount=[]

class MyHTMLParser(HTMLParser):

    #处理开始标签
    def handle_starttag(self, tag, attrs):
        """
        recognize start tag, like <div>
        :param tag:
        :param attrs:
        :return:
        """


        print("Encountered a start tag:", tag)

    #处理结束标签
    def handle_endtag(self, tag):
        """
        recognize end tag, like </div>
        :param tag:
        :return:
        """
        print("Encountered an end tag :", tag)

    #处理数据，标签之间的文本，并进行统计
    def handle_data(self, data):
        """
        recognize data, html content string
        :param data:
        :return:
        """
        print("Encountered some data  :", data)
        print('-----------------------------------')

        listCount.append(data)
        changdu=len(listCount)
        print listCount
        print changdu
        if changdu==54:
            FailCount=listCount.count('Fail')
            PassCount=listCount.count('Pass')
            print('统计失败的次数为：'+str(FailCount))
            print('统计成功的次数为：'+str(PassCount))

        else:
            print('continue')


    #处理结束的标签
    def handle_startendtag(self, tag, attrs):
        """
        recognize tag that without endtag, like <img />
        :param tag:
        :param attrs:
        :return:
        """
        print("Encountered startendtag :", tag)

    #处理注释
    def handle_comment(self,data):
        """

        :param data:
        :return:
        """
        print("Encountered comment :", data)


#打开html文件并逐行读取然后传给HTMLPrase进行解析
file=open('123.html','r')
while 1:
    readFile=file.readline()
    print(readFile)
    parser = MyHTMLParser()
    parser.feed(readFile)
    if not readFile:
        break
file.close()