使用python过滤html标签

采集后的数据都带有'<>'html标签：

<img src="http://i4.hdfimg.com/www/images/giftrans/3d/da/7b/18414.gif" border="0"/><span class='WmoJPQM2AzpQMA'>科研<span class='WmoJPQM2AzhQMQ'>最早和<span class='WmoJPQM2AzxQNw'>一项<span class='WmoJPQM2AzdQOA'>教学为一体的现代化<span class='WmoJPQM2AzhQOA'>综合<span class='WmoJPQM2AzhQMQ'>师从性省级医院

在这里只要将所有带<>去除即可：

dr = re.compile(r'<[^>]+>',re.S)

dd = dr.sub('',Html)

完整的python脚本：

第一个函数：将一个字段中的刮号去除

第二个函数：将html中的所有标签去除

#!/usr/bin/env python
# -*- coding:utf-8 -*-

import MySQLdb
import sys
import re

conn = MySQLdb.connect(host='127.0.0.1',user='user',passwd='123456',db='hospital',charset='utf8')
cur = conn.cursor()

def update_level():
    cur.execute("SELECT id,level FROM hospital where level like '(%)'")
    for row in cur.fetchall():
        sid=row[0]
        ii=re.sub('\(|\)','',row[1])
        sql = "update hospital set level=%s where id=%s"
        print sid,ii
        param = [ii,sid]
        cur.execute(sql,param)

def update_detail():
    dr = re.compile(r'<[^>]+>',re.S)
    cur.execute("SELECT id,details FROM hospital")
    for row in cur.fetchall():
        did = row[0]
        detail=row[1]
        dd = dr.sub('',detail)
        sql="update hospital set details=%s where id=%s"
        param = (dd,did)
        cur.execute(sql,param)
        print "Finished",did

def main():
    #update_level()
    update_detail()

if __name__ == '__main__':
    main()