XPath 用法和实例

Usage_XPath

#!/usr/bin/env python# -*- coding: utf-8 -*-# @Date    : 2017-09-24 20:51:15# @Author  : kangvcar ([e-mail])# @Link    : http://www.github.com/kangvcar/# @Version : $Id$## 安装# pip install lxml## 路径表达式#表达式描述#nodename选取此节点的所有子节点。#/从根节点选取。#//从匹配选择的当前节点选择文档中的节点，而不考虑它们的位置。#.选取当前节点。#..选取当前节点的父节点。#@选取属性from lxml import etreetext = '''
    
         
first item
         
second item
         
third item
         
fourth item
         
fifth item
     
 
'''# html = etree.HTML(text)# result = etree.tostring(html)# print result# html = etree.parse('hello.html')# result = etree.tostring(html, pretty_print=True)# print result# html = etree.HTML(text)# result = html.xpath('//li')# print result# print len(result)# print type(result)# print type(result[0])# html = etree.HTML(text)# result = html.xpath('//li/@class')# print result# html = etree.HTML(text)# result = html.xpath('//li/a[@href="link1.html"]')# print result# html = etree.HTML(text)# result = html.xpath('//li//span')# print result# html = etree.HTML(text)# result = html.xpath('//li/a//@class')# print result# html = etree.HTML(text)# result = html.xpath('//li[last()]/a/@href')# print result# html = etree.HTML(text)# result = html.xpath('//li[last()-1]/a')# print result[0].text# html = etree.HTML(text)# result = html.xpath('//*[@class="bold"]')# print result[0].text