xpath复习

最新推荐文章于 2024-02-25 23:58:18 发布

weixin_45872182

最新推荐文章于 2024-02-25 23:58:18 发布

阅读量283

点赞数

文章标签： xpath

本文链接：https://blog.csdn.net/weixin_45872182/article/details/122029769

版权

from lxml import etree
text = '''
<div>
    <ul>
         <li class="item-0"><a href="https://ask.hellobi.com/link1.html">first item</a></li>
         <li class="item-1"><a href="https://ask.hellobi.com/link2.html">second item</a></li>
         <li class="item-inactive"><a href="https://ask.hellobi.com/link3.html">third item</a></li>
         <li class="item-1"><a href="https://ask.hellobi.com/link4.html">fourth item</a></li>
         <li class="item-0"><a href="https://ask.hellobi.com/link5.html">fifth item</a>
     </ul>
 </div>
'''
html=etree.HTML(text)
result = html.xpath('//a[@href="https://ask.hellobi.com/link4.html"]/../@class')
print(result)
result=html.xpath('//a[@href="https://ask.hellobi.com/link4.html"]/../@class')
result=html.xpath('//li[@class="item-0"]/a/text()')
print(result)
result=html.xpath('//li/a/@href')
print(result)
from lxml import etree
text = '''
<li class="li li-first"><a href="https://ask.hellobi.com/link.html">first item</a></li>
'''
html = etree.HTML(text)
result=html.xpath('//li[contains(@class,"li")]/a/text()')
print(result)
from lxml import etree
text = '''
<li class="li li-first" name="item"><a href="https://ask.hellobi.com/link.html">first item</a></li>
'''
html = etree.HTML(text)
result=html.xpath('//li[contains(@class,"li") and @name="item"]/a/text()')
print(result)
text = '''
<div>
    <ul>
         <li class="item-0"><a href="https://ask.hellobi.com/link1.html">first item</a></li>
         <li class="item-1"><a href="https://ask.hellobi.com/link2.html">second item</a></li>
         <li class="item-inactive"><a href="https://ask.hellobi.com/link3.html">third item</a></li>
         <li class="item-1"><a href="https://ask.hellobi.com/link4.html">fourth item</a></li>
         <li class="item-0"><a href="https://ask.hellobi.com/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)
text = '''
<div>
    <ul>
         <li class="item-0"><a href="https://ask.hellobi.com/link1.html"><span>first item</span></a></li>
         <li class="item-1"><a href="https://ask.hellobi.com/link2.html">second item</a></li>
         <li class="item-inactive"><a href="https://ask.hellobi.com/link3.html">third item</a></li>
         <li class="item-1"><a href="https://ask.hellobi.com/link4.html">fourth item</a></li>
         <li class="item-0"><a href="https://ask.hellobi.com/link5.html">fifth item</a>
     </ul>
 </div>
'''
html = etree.HTML(text)