htmlparser vs sgmlparser 解析html的单个标签br img

john2007

浏览: 77824 次
性别:
来自: 南京

最近访客更多访客>>

yanghongfeng8888

c.zhiwu

daizj

heavensay

博主相关

博客

微博

相册

留言

关于我

文章分类

社区版块

存档分类

HTML JavaScript CSS Python Google

上一次发现了SGMLParser的bug,（见Python sgmlparser bug）于是就想到了利用HTMLParser，于是对其利用同样的HTML代码做了测试：

测试代码如下：

class postparser(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self.pieces=[]
        
    def handle_starttag(self, tag, attrs):
        print "start tag name: " + tag
        for k,v in attrs:
            print "\t"+k+" : "+v
            
    def handle_endtag(self,tag):
        print "end tag name:"+tag
    
    def handle_data(self,data):
        self.pieces.append(data)
    def gethtmltext(self):
        return "".join(self.pieces)
    
    def reset(self):
        HTMLParser.reset(self)
        
def testmyparser(htmldata):
    parser=postparser()
    parser.feed(htmldata)
    print parser.gethtmltext()
    parser.reset()

    if __name__=="__main__":
    #htmldata=urllib.urlopen("http://www.sogou.com").read().decode("gbk")
    htmldata="""<html><head>
    <title>Google Page</title>
    <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
    <link rel="stylesheet" href="#" type="text/css">
    </head><body> 
    <table id="tab">
        <tr id="tr1"><td id="tr1td1">tr1 td1</td><td>tr1 td2</td><td>tr1 td3</td></tr>
        <tr id="tr2"><td id="tr2td1">tr2 td1</td><td>tr2 td2</td><td>tr2 td3</td></tr>
    </table>
    <br/>
    <p onmousemove="javascript:alert('>p<');"> this is a paragraph.</p>
    <img src="http://www.baidu.com/img/baidu_logo.gif" id="baidulogo" /><br/>
    <a href="http://baidu.com">baidu</a><br/>
    <b>bold font</b><br/>
    
    <script language="javascript">alert("hello, world ");</script>
    <style>#tab{background-color:#fcdad5;}</style>
    </body></html>
    """
    testmyparser(htmldata)

结果输出如下：

start tag name: html
start tag name: head
start tag name: title
end tag name:title
start tag name: meta
	http-equiv : Content-Type
	content : text/html; charset=utf-8
start tag name: link
	rel : stylesheet
	href : #
	type : text/css
end tag name:head
start tag name: body
start tag name: table
	id : tab
start tag name: tr
	id : tr1
start tag name: td
	id : tr1td1
end tag name:td
start tag name: td
end tag name:td
start tag name: td
end tag name:td
end tag name:tr
start tag name: tr
	id : tr2
start tag name: td
	id : tr2td1
end tag name:td
start tag name: td
end tag name:td
start tag name: td
end tag name:td
end tag name:tr
end tag name:table
start tag name: br
end tag name:br
start tag name: p
	onmousemove : javascript:alert('>p<');
end tag name:p
start tag name: img
	src : http://www.baidu.com/img/baidu_logo.gif
	id : baidulogo
end tag name:img
start tag name: br
end tag name:br
start tag name: a
	href : http://baidu.com
end tag name:a
start tag name: br
end tag name:br
start tag name: b
end tag name:b
start tag name: br
end tag name:br
start tag name: script
	language : javascript
end tag name:script
start tag name: style
end tag name:style
end tag name:body
end tag name:html

    Google Page
    
    
     
    
        tr1 td1tr1 td2tr1 td3
        tr2 td1tr2 td2tr2 td3
    
    
     this is a paragraph.
    
    baidu
    bold font
    
    alert("hello, world ");
    #tab{background-color:#fcdad5;}

从测试结果来看，比之于SGMLParser，解析的结果还是不错的，克服了不能解析单个标签的bug，而且onmousemove中的><也得到了正确的解析。

分享到：