抓取一个简单网页上的所有文字信息 有点急该怎么处理

import urllib
import re


def toText(html):
    html = re.sub(r'<[^<>]*>', '', html)
    html = html.replace('&nbsp;', ' ')
    return html.strip()

def extractHtml(html):
    p = re.findall(r'"navism">(.*?)</td>\s*(:?<td[^<>]*>(.*?)</td>)?', html, re.S)
    p = map(lambda x: (toText(x[0]), toText(x[1])), p)
    p = filter(lambda x: x[0], p)

    for w in p:
        print w[0], w[1]


html = urllib.urlopen('http://www.myjob.edu.cn/enterprise/page/view_student.jsp?id=2000001').read()

extractHtml(html)