Python-lxml

 

 

 

 

from lxml import etree
from lxml.etree import HTMLParser


text='''
<?xml version="1.0"?> 
<data> 
  <country name="Singapore"> 
    <rank>4</rank> 
    <year>2011</year> 
    <gdppc>59900</gdppc> 
    <neighbor name="Malaysia" direction="N"/> 
  </country> 
  <country name="Panama"> 
    <rank>68</rank> 
    <year>2011</year> 
    <gdppc>13600</gdppc> 
    <neighbor name="Costa Rica" direction="W"/> 
    <neighbor name="Colombia" direction="E"/> 
  </country> 
</data> 

'''


html=etree.HTML(text,etree.HTMLParser())

#//为以下所有节点  /为子节点   

#读取值 
#result=html.xpath('//data//rank/text()')

#读取属性值
result=html.xpath('//data//country/@name')


print(result)
print(type(result))