【原创】python爬虫获取网站数据并存入本地数据库

#coding=utf-8
import urllib
import re
import MySQLdb
dbnumber = MySQLdb.connect('localhost', 'root', '*******', 'dbname')           #连接本地数据库
cursor = dbnumber.cursor()
def getHtml(url):
    page=urllib.urlopen(url)
    html=page.read()
    return html

def getnumber(html):
    reg=r'm>(\d+)<'         #通过正则表达抓取网站数字
    number=re.compile(reg)
    numberlist=re.findall(number,html)
    return numberlist
html=getHtml("http://baidu.lecai.com/lottery/draw/list/50?type=range_date&start=2005-06-08&end=2003-02-23")          #目标网站页面

for i in range(10000):           #设置一个循环
    try:
        n = 7 * i
        sql_insert = "INSERT INTO dbnumber(red_1) VALUES(%s)" %getnumber(html)[n]            #将获取的数据存入本地数据库
        cursor.execute(sql_insert)
    except Exception:
        break
dbnumber.commit()
dbnumber.close()             #最后关闭数据库连接

 

转载于:https://www.cnblogs.com/huangxiaocheng/p/7200390.html