xpath提取目录下所有标签内的内容，递归 //text（）

利用xpath来提取所有标签里面的内容，即使标签头不同

 1 #-*-coding:utf8-*-
 2 import re
 3 import os
 4 from lxml import etree
 5 html = '''
 6 <!DOCTYPE html>
 7 <html>
 8 <head lang="en">
 9     <meta charset="UTF-8">
10     <title>测试-常规用法</title>
11 </head>
12 <body>
13 <div id="content">
14     <ul id="useful">
15     <li>我</li>
16     <ml>是</ml>
17     <li>谁</li>
18     </ul>
19     <ul id="useless">
20     <li>who </li>
21     <li>am </li>
22     <li>i！</li>
23     </ul>
24 </div>
25 <div id="content">
26     <ul id="useful"><li>你</li><ml>是</ml><li>谁！</li>
27     </ul>
28     <ul id="useless"><li>who </li><li>you </li><li>are！</li>
29     </ul>
30 </div>
31 
32 </body>
33 </html>
34 '''
35 selector = etree.HTML(html)
36 for k in range(1,3):
37     chinese = selector.xpath('//div[@id="content"][%s]/ul[@id="useful"]//text()'%k)
38     data = "".join([each for each in chinese])
39     english = selector.xpath('//div[@id="content"][%s]/ul[@id="useless"]//text()'%k)
40     Data = "".join([each for each in english])
41     print data
42     print Data

结果：