爬虫笔记-XPath使用
1 Xpath常用规则
2 Xpath实例,自动修正HTML文本
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结果为byte类型
html = etree.HTML(text)
# 转为string
result = etree.tostring(html)
print(result.decode('utf-8'))
输出:
<html><body><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>
</li></ul>
</div>
</body></html>
注意:补全HTML body 和节点
3 Xpath实例,读取HTML文件
test.html:
<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>
代码
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
result = etree.tostring(html)
print(result.decode('utf-8'))
输出:
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">
<html><body><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>
</li></ul>
</div></body></html>
4 Xpath实例,获取所有节点
代码:
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
result = html.xpath('//*')
print(result)
输出:
[<Element html at 0x1f36602a0c8>, <Element body at 0x1f36602a108>,
<Element div at 0x1f36602a148>, <Element ul at 0x1f36602a188>, <Element li at
0x1f36602a1c8>, <Element a at 0x1f36602a248>, <Element li at 0x1f36602a288>,
<Element a at 0x1f36602a2c8>, <Element li at 0x1f36602a308>, <Element a at
0x1f36602a208>, <Element li at 0x1f36602a348>, <Element a at 0x1f36602a588>,
<Element li at 0x1f36602a5c8>, <Element a at 0x1f36602a608>]
5 Xpath实例,获取指定节点
代码:
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
# 获取所有li节点
result = html.xpath('//li')
print(result)
# 第一个li节点
print(result[0])
输出:
[<Element li at 0x24cfa138288>, <Element li at 0x24cfa1383c8>, <Element li at 0x24cfa138408>, <Element li at 0x24cfa138448>, <Element li at 0x24cfa138488>]
<Element li at 0x24cfa138288>
6 Xpath实例,获取元素的子节点(通过//或者/)
/ 获取直接子节点
// 获取所有子孙节点
代码:
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
# 获取所有li节点下的所有直接a节点
result = html.xpath('//li/a')
print(result)
输出:
[<Element a at 0x19ff43fb188>, <Element a at 0x19ff43fb1c8>, <Element a at 0x19ff43fb208>, <Element a at 0x19ff43fb248>, <Element a at 0x19ff43fb288>]
注意: 这里如果用//ul/a,是获取不到数据的,因为li节点的直接子孙没有a节点
代码:
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
# 获取所有li节点下的所有子孙a节点
result = html.xpath('//li//a')
print(result)
输出:
[<Element a at 0x21d418782c8>, <Element a at 0x21d41878308>, <Element a at 0x21d41878348>, <Element a at 0x21d41878388>, <Element a at 0x21d418783c8>]
7 Xpath实例,获取父节点
使用…获取
代码:
from lxml import etree
# 使用..获取
html = etree.parse('./test.html', etree.HTMLParser())
# 属性值为link4.html的a节点的父节点
result = html.xpath('//a[@href="link4.html"]/../@class')
print(result)
输出:
['item-1']
使用parent::获取
代码:
from lxml import etree
# 使用parent::获取
html = etree.parse('./test.html', etree.HTMLParser())
# 属性值为link4.html的a节点的父节点
result = html.xpath('//a[@href="link4.html"]/parent::*/@class')
print(result)
输出:
['item-1']
8 Xpath实例,属性匹配过滤
代码:
from lxml import etree
# 使用@符号过滤
html = etree.parse('./test.html', etree.HTMLParser())
# 选取class为item-1的li节点,使用@class="item-0"是限制了节点的class属性为item-0
result = html.xpath('//li[@class="item-0"]')
print(result)
输出:
[<Element li at 0x28efa6d83c8>, <Element li at 0x28efa6d8408>]
9 Xpath实例,文本获取,text()方法
先选取a节点再获取文本
代码:
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
# 先选取a节点再获取文本
result = html.xpath('//li[@class="item-0"]/a/text()')
print(result)
输出:
['first item', 'fifth item']
直接使用//获取文本
代码:
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
#直接使用//获取文本
result = html.xpath('//li[@class="item-0"]//text()')
print(result)
输出:
['first item', 'fifth item', '\n ']
10 Xpath实例,属性获取,@
代码:
from lxml import etree
# 获取li节点下a节点的href属性
html = etree.parse('./test.html', etree.HTMLParser())
result = html.xpath('//li/a/@href')
print(result)
输出:
['link1.html', 'link2.html', 'link3.html', 'link4.html', 'link5.html']
11 Xpath实例,属性多值获取 contains()
代码:
from lxml import etree
# 含有li li-first两个属性
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)
输出:
['first item']
12 Xpath实例,多个属性确定一个节点-and
代码:
from lxml import etree
# 含有li li-first和name两个属性
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)
输出:
['first item']
注意: 这里的and是XPath的运算符,除了and还有许多其他运算符:
13 Xpath实例,按序选择
代码:
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)
# 第一个li节点
result = html.xpath('//li[1]/a/text()')
print(result)
# 选取最后一个节点
result = html.xpath('//li[last()]/a/text()')
print(result)
# 选取位置小于3的li节点,也就是1和2
result = html.xpath('//li[position()<3]/a/text()')
print(result)
# 选取倒数第三个li节点
result = html.xpath('//li[last()-2]/a/text()')
print(result)
输出:
['first item']
['fifth item']
['first item', 'second item']
['third item']
14 Xpath实例,节点轴选择
代码:
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)
输出:
[<Element html at 0x26e6498d888>, <Element body at 0x26e6498d808>, <Element div at 0x26e6498d788>, <Element ul at 0x26e6498d8c8>]
[<Element div at 0x26e6498d788>]
['item-0']
[<Element a at 0x26e6498d8c8>]
[<Element span at 0x26e6498d788>]
[<Element a at 0x26e6498d8c8>]
[<Element li at 0x26e6498d808>, <Element li at 0x26e6498d908>, <Element li at 0x26e6498d948>, <Element li at 0x26e6498d988>]