XPath学习

XPath

# 常用的方法 
# 字符串格式的html文本的情况下 
# 使用etree.HTML()方法把text转化成xpath对象 
html = etree.HTML(text) 
# html文本以文件的形式存在时，使用etree.parse（）解析html文件，转化成xpath对象 
html = etree.parse('./test.html', etree.HTMLParser()) 
# 把xpath对象转化为bytes类型 
result = etree.tostring(html) 
# 输出bytes类型的对象使用decode('utf-8') 
print(result.decode('utf-8')) 
# 使用etree.xpath()方法获取xpath对象的节点，返回的是一个list列表 
result = html.xpath('//li') 

接下来时xpath的语法。

匹配所有节点*

# xpath续！！！！！！！！！！！！ 
from lxml import etree 
html = etree.parse('./test.html', etree.HTMLParser()) 
# 这里使用*代表匹配所有节点 
result = html.xpath('//*') 
print(result) 

返回的result是一个list

from lxml import etree 
html = etree.parse('./test.html', etree.HTMLParser()) 
# //从当前节点选择子孙节点，li选区所有li节点 
result = html.xpath('//li') #list 
print(result) 
# 取出第一个li节点 
print(result[0]) 

子节点/

# 子节点 
from lxml import etree 
html = etree.parse('./test.html', etree.HTMLParser()) 
# 所有ul节点的a节点 
result = html.xpath('//ul//a') 
print(result) 

父节点…

# 父节点 
from lxml import etree 
html = etree.parse('./test.html', etree.HTMLParser()) 
# 获取具有属性href="link4.html"的a标签下的父节点li的属性class的值 
result = html.xpath('//a[@href="link4.html"]/../@class') 
print(result) 

# 父节点方法二 
from lxml import etree 
html = etree.parse('./test.html', etree.HTMLParser()) 
result = html.xpath('//a[@href="link4.html"]/parent::*/@class') 
print(result) 

属性匹配@

# 属性匹配 
from lxml import etree 
html = etree.parse('./test.html', etree.HTMLParser()) 
result = html.xpath('//li[@class="item-1"]') 
for item in result: 
    print(etree.tostring(item)) 

文本获取text()，text

# 文本获取 
from lxml import etree 
html = etree.parse('./test.html', etree.HTMLParser()) 
result = html.xpath('//li[@class="item-0"]//text()') 
# for item in result: 
#     print(etree.tostring(item)) 
print(result) 

上面的写法可能报错，用以下写法

错误代码示例 : 
  
driver.find_element_by_xpath('//*[@class="signTime"]/text()') 
正确代码示例 :  
  
driver.find_element_by_xpath('//*[@class="signTime"]').text 

属性多值匹配contains()

# 属性多值匹配 
# contains()函数 
from lxml import etree 
text = """ 
<li class="li li-first"><a href="link.html">first item</a></li> 
""" 
html = etree.HTML(text) 
# contains()第一个参数传入【@属性名称】，第二个参数传入【属性值】，只要此属性【包含】所传入的属性值就可以完成匹配了 
result = html.xpath('//li[contains(@class, "li")]/a/text()') 
print(result) 

多属性匹配and

# 多属性匹配 
from lxml import etree 
text = """ 
<li class="li li-first" name="item"><a href="link.html">first item</a></li> 
""" 
html = etree.HTML(text) 
# 多个属性使用and操作符相连 
result = html.xpath('//li[contains(@class, "li") and @name="item"]/a/text()') 
print(result) 

按序选择last(),position()

# 按顺序选择 
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的文本 
result = html.xpath('//li[1]/a/text()') 
print(result) 
# 最后一个li的文本 
result = html.xpath('//li[last()]/a/text()') 
print(result) 
# 前两个li的文本 
result = html.xpath('//li[position()<3]/a/text()') 
print(result) 
# last（）=5，取第三个li的文本 
result = html.xpath('//li[last()-2]/a/text()') 
print(result) 

结点轴选择ancestor::,attribute::,descendant::,following::,following-sibling::

# 节点轴选择 
from lxml import etree 
text = """ 
<div> 
<ul class="drs"> 
<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) 
# 获取所有祖先节点 
result = html.xpath('//li[1]/ancestor::*') 
print(result) 
# 获取祖先节点的div节点 
result = html.xpath("//li[1]/ancestor::div") 
print(result) 
# 获取第一个li的属性值 
result = html.xpath("//li[1]/attribute::*") 
print(result) 
# 获取第一个li的子节点的a节点符合href=“link1.html” 
result = html.xpath('//li[1]/child::a[@href="link1.html"]') 
print(result) 
# 获取第一个li的子孙节点的span节点 
result = html.xpath('//li[1]/descendant::span') 
print(result) 
# 获取第一个li节点后面的所有节点的第二个后续节点a 
result = html.xpath('//li[1]/following::*[2]') 
for item in result: 
    print(etree.tostring(item)) 
# 获取第一个li的所有同级节点 
result = html.xpath('//li[1]/following-sibling::*') 
print(result) 

scrapy xpath 获取属性值

export_number = response.xpath('//p[1]/@value')