利用xpath来提取所有标签里面的内容，即使标签头不同

#-*-coding:utf8-*-

import re

import os

from lxml import etree

html = '''

测试-常规用法

'''

selector = etree.HTML(html)

for k in range(1,3):

chinese = selector.xpath('//div[@id="content"][%s]/ul[@id="useful"]//text()'%k)

data = "".join([each for each in chinese])

english = selector.xpath('//div[@id="content"][%s]/ul[@id="useless"]//text()'%k)

Data = "".join([each for each in english])

print data

print Data

结果：