01-lxml解析html代码和文件（python爬虫）

python爬虫
lxml解析html代码和文件

1. 先将html代码解析为html文档
2. 按字符串序列化
3. 成功解析

# -*- codeing = utf-8 -*-
# coding=gbk
# @Autor:ggui20

from lxml import etree

text = '''
<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>
'''
# 将字符串解析为html文档
html = etree.HTML(text)
print(html)
# 按字符串序列化html
result = etree.tostring(html).decode('utf-8')
print(result)

# 读取
html = etree.parse('hello.html')

result = etree.tostring(html).decode('utf-8')
print(result)