Python HTMLParser 使用

# coding=utf8

from HTMLParser import HTMLParser

class MyHTMLParser(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self.wanted = []

    # attrs是一个列表，里面存放的是二元组
    def attr_exists(self, attrs, attrname):
        for attr in attrs:
            if attr[0] == attrname:
                return attr[1]
        return None

    def handle_starttag(self, tag, attrs):
        # 遍历attrs中的元素的第一个元素是否为title
        if tag == "a" and self.attr_exists(attrs, "title") != None:
            self.wanted.append(self.attr_exists(attrs, "title"))

myhtml = MyHTMLParser()
# 喂数据，即把需要的内容存放进wanted
myhtml.feed(self.home_page.content)