xpath ul li 属性值_Xpath解析方法练习

from lxml import etree

data_str = """

<div>

<ul>

<li class="item-0"><a href="link1.html">first item</a></li>

<li class="item-1"><a href="link2.html">second item</a></li>

<li class="item-inactive"><a href="link3.html">third item</a></li>

<li class="item-1"><a href="link4.html">fourth item</a></li>

<li class="item-0"><a href="link5.html">fifth item</a>

</ul>

</div>

"""

#注意.上方数据缺少了一个一个li的闭标签.

#利用etree.HTML可以将字符串或bytes转化为Element python对象,这个对象有Xpath的方法.

#想要用xpath的方法就先用etree.HTML转化格式.

html = etree.HTML(data_str)

print(html)

#etree.tostring(html)可以自动修正html中的缺失代码,补全缺失标签

#使用为了观察修改以后的HTML的样子,根据修改后的HTML去写Xpath

result = etree.tostring(html)

print(result.decode('utf-8'))

#获得class = item-1 的a标签的herf属性

#所有满足条件的值都会返回list[]

result = html.xpath('//li[@class="item-0"]/a/@href')

print(result)

---

#xpath练习二

from lxml import etree

import requests

#ca证书

#https需要增加请求头信息(不然会反爬掉)

#http没有反爬

url = "

http://www.baidu.com/s?wd=python

"

reponse = requests.get(url)

# print(reponse.content.decode('utf-8'))

#转化类型(xpath语法需要找到对应的类型才可以使用)

heml = etree.HTML(reponse.content.decode('utf-8'))

url = heml.xpath('//*[@id ="1"]/h3/a/@href')

print(url)