1. 获取所有的
# xpath_li.py
from lxml import etree
html = etree.parse('hello.html')
print type(html) # 显示etree.parse() 返回类型
result = html.xpath('//li')
print result # 打印标签的元素集合
print len(result)
print type(result)
print type(result[0])
输出结果：
[, , , , ]
5
class属性
# xpath_li.py
from lxml import etree
html = etree.parse('hello.html')
result = html.xpath('//li/@class')
print result
运行结果:
['item-0', 'item-1', 'item-inactive', 'item-1', 'item-0']
hre 为 link1.html的# xpath_li.py
from lxml import etree
html = etree.parse('hello.html')
result = html.xpath('//li/a[@href="link1.html"]')
print result
运行结果
[]
# xpath_li.py
from lxml import etree
html = etree.parse('hello.html')
#result = html.xpath('//li/span')
#注意这么写是不对的：
#因为 / 是用来获取子元素的，而 并不是 的子元素，所以，要用双斜杠
result = html.xpath('//li//span')
print result
运行结果
[]
# xpath_li.py
from lxml import etree
html = etree.parse('hello.html')
result = html.xpath('//li/a//@class')
print result
运行结果
['blod']
# xpath_li.py
from lxml import etree
html = etree.parse('hello.html')
result = html.xpath('//li[last()]/a/@href')
# 谓语 [last()] 可以找到最后一个元素
print result
运行结果
['link5.html']
# xpath_li.py
from lxml import etree
html = etree.parse('hello.html')
result = html.xpath('//li[last()-1]/a')
# text 方法可以获取元素内容
print result[0].text
运行结果
fourth item
# xpath_li.py
from lxml import etree
html = etree.parse('hello.html')
result = html.xpath('//*[@class="bold"]')
# tag方法可以获取标签名
print result[0].tag
运行结果
span
