lxml etree xpath

 

from lxml import etree

#####################
基本用法：

#####################

html = '''
<h1 class="header">登录</h1>
<form action="/login" method="post">
    <label for="username">用户: </label><input type="text" name="username" />
    <label for="password">密码：</label><input type="password" name="password" />
    <input type="submit" value="Submit" />
</form>'''

# 生成DOM
dom = etree.HTML(html)

# 取内容 /text()
contents = dom.xpath('//h1[@class="header"]/text()')
print(contents)

# 取属性 /@attrib
attribs = dom.xpath('//form/label[@for="username"]/@for')
print(attribs)




#####################
复杂用法：

#####################

html2 = ''' 
<div class="content"> 
    ==> 有相同字符开头的属性的标签: 
    <p id="test-1">需要的内容1</p> 
    <p id="test-2">需要的内容2</p> 
    <p id="test-default">需要的内容3</p> 
</div> 
<div class="question">
    ==> 签嵌套标签: 
    <p id="class3">美女，
　　　　　　<font color="red">你的微信号是多少？</font> 
    </p> 
</div> '''

 dom = etree.HTML(html2) 

# 取有相同字符开头的属性的标签的内容 starts-with(@attrib, "abcd") 
contents2 = dom.xpath('//p[starts-with(@id, "test")]/text()') 
print(contents2) 

# 取标签嵌套标签的所有内容 xpath('string(.)') 
contents3 = dom.xpath('//div[@class="question"]/p')[0].xpath('string(.)') 
contents3 = contents3.replace('\n', '').replace(' ', '') 
print(contents3)