lxml_test.py 文件源码

def lxml_case3():


    text = '''
    <div>
        <ul>
             <li class="item-0"><a href="link1.html">first item</a></li>
             <li class="item-1"><a href="link2.html">second item</a></li>
             <li class="item-inactive"><a href="link3.html">third item><span>Hello world</span></a></li>
             <li class="item-1"><a href="link4.html">fourth item</a></li>
             <li class="item-0"><a href="link5.html">fifth item</a>
             <li class="de-item-0"><a href="link5.html">fifth item</a>
         </ul>
     </div>
    '''

    tree=etree.HTML(text)
    html_s=etree.tostring(tree)
    #print html_s
    #print tree.xpath('//li//span/text()')[0]
    '''
    reg_case=tree.xpath('//*[starts-with(@class,"item")]')
    for i in reg_case:
        print i.xpath('.//a/@href')
    '''
    result=tree.xpath(r'//*[re:match(@class, "item-0")]')
    print result

    for i in result[0]:
        print i.xpath('.//a/@href')