Python中的html.parser

class WebPageParser(html.parser.HTMLParser):
    def __init__(self, strict = False):
        super().__init__(strict)
        self.urls = []
        self.data = []
        self.is_href = False;
    def handle_starttag(self, tag, attrs):
        if tag == 'a':
            self.urls.extend([v for k , v in attrs if k == 'href'])
            self.is_href = True
    def handle_endtag(self, tag):
        print(tag)
        self.is_href = False
    def handle_startendtag(self, tag, attrs):
        print(tag, attrs)
    def handle_data(self, data):
        if self.is_href:
            self.data.append(data)
            
    def reset(self):
        super().reset()
        self.urls = []
        self.data = []
        self.is_href = False
        
if __name__ == '__main__':
    webUrl = r"http://www.baidu.com"
    webPage = urllib.request.urlopen(webUrl)
    webPageParser = WebPageParser()
    webPageParser.feed(str(webPage.read()))
    print(webPageParser.urls)
    print(webPageParser.data)

该类的使用很简单，主要是要继承html.parser.HTMLParser，然后重载相对应的方法。