BeautifulSoup 获取标签属性 http://segmentfault.com/q/1010000000185964

get_elem_attr.py

# -*- coding: utf-8 -*-
from BeautifulSoup import BeautifulSoup 
import re

def get_timestamp(html):
    soup = BeautifulSoup(html)
    authi_elems = soup.findAll('div', { 'class': 'authi' })
    for authi_elem in authi_elems:
        date_elem = authi_elem.find('span', title=re.compile(r'20\d{2}-\d+-\d+\s\d{2}:\d{2}:\d{2}'))
        print date_elem.get('title')
    # print date_elem


if __name__ == '__main__':
    html = """
    <div class="authi">
    <img class="authicn vm" id="" src="static/image/common/online_member.gif" />
    <em id="">发表于 <span title="2013-4-2 08:30:11">4&nbsp;天前</span></em>
    <span class="pipe">|</span><a href=>倒序浏览</a>
    <div style="float:right;position:relative;top:-6px;"><ul>
    <li style="float: left; width: 130px; height: 24px;"><wb:follow-button uid="" type="gray_2" width="136" height="24"></wb:follow-button></li>
    <li style=" float:left; width: 160px; height: 24px;"></li>
    </ul></div></div>
    """

    get_timestamp(html)