python解析html

解析html，得到想要的数据

from HTMLParser import HTMLParser
import urllib

class MyHTMLParser(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self._count=0
        self._events=dict()
        self._flag=None
	# 开始标签
    def handle_starttag(self,tag,attrs):
        if tag=='h3' and attrs.__contains__(('class','event-title')):
            self._flag='even-title'
            self._count+=1
            self._events[self._count]=dict()
        if tag=='time':
            self._flag='time'
        if tag=='span' and attrs.__contains__(('class','event-location')):
            self._flag='event-location'
	# 标签中的元素
    def handle_data(self,data):
        if self._flag=='even-title':
            self._events[self._count]['even-title']=data
        if self._flag=='time':
            self._events[self._count]['time']=data
        if self._flag=='event-location':
            self._events[self._count]['event-location']=data
        self._flag=None

    def get_events(self):
        return self._events

try:
    page=urllib.urlopen('https://www.python.org/events/python-events/')
    html=page.read()
except IOError,e:
    print e
else:
    parser=MyHTMLParser()
    parser.feed(html)
    events=parser.get_events()
    print events
finally:
    if page:
        page.close()