Xpath

基础规则

nodename 选取此节点的所有子节点
/ 从当前节点选取直接子节点
// 从当前节点选取子孙节点
@ 选取属性

//title[@lang='eng']
选择所有名称为 `title`，同时属性 `lang` 的值为 `eng` 的节点。

lxml库使用

pip3 install lxml

from lxml import etree
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</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>
     </ul>
 </div>
'''
html = etree.HTML(text)
result = etree.tostring(html)
print(result.decode('utf-8'))

节点选取

#获取子节点
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
result = html.xpath('//*')
print(result)

#获取父节点
from lxml import etree

html = etree.parse('./test.html', etree.HTMLParser())
result = html.xpath('//a[@href="link4.html"]/../@class')
print(result)

#属性匹配
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
result = html.xpath('//li[@class="item-0"]')
print(result)

有时候，我们在选择的时候某些属性可能同时匹配了多个节点，但是只想要其中的某个节点，如第二个节点或者最后一个节点

from lxml import etree

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</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>
     </ul>
 </div>
'''
html = etree.HTML(text)
result = html.xpath('//li[1]/a/text()')
print(result)
result = html.xpath('//li[last()]/a/text()')
print(result)
result = html.xpath('//li[position()<3]/a/text()')
print(result)
result = html.xpath('//li[last()-2]/a/text()')
print(result)

我们可以使用索引或者一些特定方法。同时xpath提供一个叫做节点轴的东西，来获取子元素、兄弟元素、父元素、祖先元素等。

from lxml import etree

text = '''
<div>
    <ul>
         <li class="item-0"><a href="link1.html"><span>first item</span></a></li>
         <li class="item-1"><a href="link2.html">second item</a></li>
         <li class="item-inactive"><a href="link3.html">third item</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>
     </ul>
 </div>
'''
html = etree.HTML(text)
result = html.xpath('//li[1]/ancestor::*')
print(result)
result = html.xpath('//li[1]/ancestor::div')
print(result)
result = html.xpath('//li[1]/attribute::*')
print(result)
result = html.xpath('//li[1]/child::a[@href="link1.html"]')
print(result)
result = html.xpath('//li[1]/descendant::span')
print(result)
result = html.xpath('//li[1]/following::*[2]')
print(result)
result = html.xpath('//li[1]/following-sibling::*')
print(result)

文本获取

使用test()来获取对应的一个文本值。

from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
result = html.xpath('//li[@class="item-0"]/a/text()')
print(result)

属性获取

使用@符号来进行一个获取。

from lxml import etree

html = etree.parse('./test.html', etree.HTMLParser())
result = html.xpath('//li/a/@href')
print(result)

但有时候一个节点属性有多个值，如

from lxml import etree
text = '''
<li class="li li-first"><a href="link.html">first item</a></li>
'''
html = etree.HTML(text)
result = html.xpath('//li[@class="li"]/a/text()')
print(result)

那么我们就要使用contains方法了

from lxml import etree
text = '''
<li class="li li-first"><a href="link.html">first item</a></li>
'''
html = etree.HTML(text)
result = html.xpath('//li[contains(@class, "li")]/a/text()')
print(result)

并且contains方法可以使用逻辑关系词的

from lxml import etree
text = '''
<li class="li li-first" name="item"><a href="link.html">first item</a></li>
'''
html = etree.HTML(text)
result = html.xpath('//li[contains(@class, "li") and @name="item"]/a/text()')
print(result)