python之xpath

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# author：Momo time:2018/6/29

import urllib.request
import urllib

from lxml import etree


def get_html(url):
    html_page = urllib.request.urlopen(url)
    html_code = html_page.read().decode('utf-8')
    return html_code

html = get_html("http://www.runoob.com/python3/python3-reg-expressions.html")

selector = etree.HTML(html)
"""
    // 定位根节点
    /  往下一层寻找
    /text()  提取文本内容
    /@XXXX   提取属性内容
"""
# # 提取文本
# content = selector.xpath('//*[@id="content"]/p/text()')  # /text()
# for each in content:
#     print(each)

# # 提取属性
# link = selector.xpath('/html/body/link/@href')
# for each in link:
#     print(each)

table = selector.xpath('//*[@id="content"]/table/@class')
for each in table:
    print(each)