xpath入门
python爬虫抓取网页内容，需要对html或xml结构的数据进行解析，如果用正则，单是写正则表达式就让很多望而生畏了。
这个问题可以用正则表达式处理，于是，一个问题就变成了两个问题
对于我们这些不喜欢写正则的人来说，xpath提供了更方便的解析数据功能。
xpath全称是：XML Path Language, 见名知意，是专门用于解析结构性语言的
xpath常用规则
使用xpath之前要先安装lxml库
pip install lxml
入门示例：
from lxml import etree
text = '''
<div>
<ul>
<li class="item-0"><a href="link1.html">first</a></li>
<li class="item-1"><a href="link2.html">second</a>
<li class="item-2"><a href="link3.html">third</li>
<li class="item-3"><a href="link4.html">fourth</a></li>
</ul>
</div>
'''
html = etree.HTML(text)
result = etree.tostring(html)
print(result.decode('utf-8'))
注意查看代码中的html片段，第二个li没有闭合，第三个li的a标签没有闭合
查看结果：
<html><body><div>
<ul>
<li class="item-0"><a href="link1.html">first</a></li>
<li class="item-1"><a href="link2.html">second</a>
</li><li class="item-2"><a href="link3.html">third</a></li>
<li class="item-3"><a href="link4.html">fourth</a></li>
</ul>
</div>
</body></html>
可以看到，etree模块不仅将缺少的标签闭合了，而且还加上了html、body节点
还可以读取文本内容进行解析
新建 test.html
<div>
<ul>
<li class="item-0"><a href="link1.html">first</a></li>
<li class="item-1"><a href="link2.html">second</a></li>
<li class="item-2"><a href="link3.html">third</a></li>
<li class="item-3"><a href="link4.html">fourth</a></li>
</ul>
</div>
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
result = etree.tostring(html)
print(result.decode('utf-8'))
结果：
<!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</a></li>
<li class="item-1"><a href="link2.html">second</a></li>
<li class="item-2"><a href="link3.html">third</a></li>
<li class="item-3"><a href="link4.html">fourth</a></li>
</ul>
</div>
</body></html>
获取所有节点 //
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
result = html.xpath('//*')
print(result)
结果：
[<Element html at 0x1085a5e88>, <Element body at 0x1085a5f88>, <Element div at 0x1085a5fc8>, <Element ul at 0x1085c9048>, <Element li at 0x1085c9088>, <Element a at 0x1085c9108>, <Element li at 0x1085c9148>, <Element a at 0x1085c9188>, <Element li at 0x1085c91c8>, <Element a at 0x1085c90c8>, <Element li at 0x1085c9208>, <Element a at 0x1085c9248>]
//* 表示匹配所有节点
匹配指定节点，如获取所有li节点
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
result = html.xpath('//li')
print(result) # 所有li节点
print(result[0]) # 第一个li节点
结果：
[<Element li at 0x110115f88>, <Element li at 0x110115fc8>, <Element li at 0x110139048>, <Element li at 0x110139088>]
<Element li at 0x110115f88>
子节点 /
获取li节点的直接子节点
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
result = html.xpath('//li/a') # 获取所有li节点的直接子节点a
print(result)
[<Element a at 0x103c02f88>, <Element a at 0x103c02fc8>, <Element a at 0x103c26048>, <Element a at 0x103c26088>]
改成 // 可以这么写：
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
result = html.xpath('//div//a') # 获取div的所有后代a节点
print(result)
父节点 ..
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
# 获取href属性为link2.html的a标签的父节点的class名
result = html.xpath('//a[@href="link2.html"]/../@class')
print(result)
# ['item-1']
属性匹配 @
根据属性值匹配节点
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
# 获取属性class值为item-0的li
result = html.xpath('//li[@class="item-0"]')
print(result)
# [<Element li at 0x10c2b1f88>]
获取属性值
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
# 获取所有li的子节点a的属性href
result = html.xpath('//li/a/@href')
print(result)
# ['link1.html', 'link2.html', 'link3.html', 'link4.html']
属性多值匹配
使用contains函数匹配
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)
# []
result = html.xpath('//li[contains(@class, "li")]/a/text()')
print(result)
# ['first item']
多属性匹配
需要匹配满足多个属性的节点，使用 and 运算符
from lxml import etree
text = '''
<li class="li li-first" name="item"><a href="link.html">first item</a></li>
'''
html = etree.HTML(text)
# 通过class和name两个属性进行匹配
result = html.xpath('//li[contains(@class, "li") and @name="item"]/a/text()')
print(result)
# ['first item']
xpath的运算符介绍
运算符
文本获取
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
# 获取属性class值为item-0的li的子节点a的文本内容
result = html.xpath('//li[@class="item-0"]/a/text()')
print(result)
# ['first']
如果想要获取后代节点内部的所有文本，使用 //text()
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
# 获取所有li的后代节点中的文本
result = html.xpath('//li//text()')
print(result)
# ['first', 'second', 'third', 'fourth']
按序选择
根据节点所在的顺序进行提取
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
# 按索引排序
result = html.xpath('//li[1]/a/text()')
print(result)
# ['first']
# last 最后一个
result = html.xpath('//li[last()]/a/text()')
print(result)
# ['fourth']
# position 位置查找
result = html.xpath('//li[position()<3]/a/text()')
print(result)
# ['first', 'second']
# - 运算符
result = html.xpath('//li[last()-2]/a/text()')
print(result)
# ['second']
节点轴选择
from lxml import etree
html = etree.parse('./test.html', etree.HTMLParser())
# 所有祖先节点
result = html.xpath('//li[1]/ancestor::*')
print(result)
# [<Element html at 0x106e4be88>, <Element body at 0x106e4bf88>, <Element div at 0x106e4bfc8>, <Element ul at 0x106e6f048>]
# 祖先节点中的div
result = html.xpath('//li[1]/ancestor::div')
print(result)
# [<Element div at 0x106ce4fc8>]
# 节点的所有属性
result = html.xpath('//li[1]/attribute::*')
print(result)
# ['item-0']
# 子节点
result = html.xpath('//li[1]/child::a[@href="link1.html"]')
print(result)
# [<Element a at 0x107941fc8>]
# 后代节点中的a
result = html.xpath('//li[1]/descendant::a')
print(result)
# [<Element a at 0x10eeb7fc8>]
# 该节点后面所有节点中的第2个 从1开始计数
result = html.xpath('//li[1]/following::*[2]')
print(result)
# [<Element a at 0x10f188f88>]
# 该节点后面的所有兄弟节点
result = html.xpath('//li[1]/following-sibling::*')
print(result)
# [<Element li at 0x104b7f048>, <Element li at 0x104b7f088>, <Element li at 0x104b7f0c8>]
网友评论