python2.7 爬虫_爬取小说盗墓笔记章节及URL并导入MySQL数据库_20161201

#-*-coding: utf-8 -*-
import urllib
import re
import urlparse
import MySQLdb
rooturl=‘http://www.quanshu.net/book/9/9055/‘
def getlist(url):
    html=urllib.urlopen(url).read()
    html=html.decode(‘gb2312‘).encode(‘utf-8‘)
    reg=r‘<li><a href="(.*?)" title=".*?">(.*?)</a></li>‘
    return re.findall(reg,html)
try:
    conn = MySQLdb.connect(host=‘localhost‘, user=‘root‘, passwd=‘123456‘, db=‘local_db‘, port=3306, charset=‘utf8‘)
    with conn:
        cursor = conn.cursor()
        drop_table_sql=‘DROP  TABLE IF EXISTS daomubiji‘
        cursor.execute(drop_table_sql)
        conn.commit()
        create_table_sql = ‘‘‘
           CREATE TABLE daomubiji (
           ID INT(11),
           title VARCHAR(255),
           titleurl VARCHAR(255)
           )ENGINE=INNODB DEFAULT CHARSET=utf8
        ‘‘‘
        cursor.execute(create_table_sql)
        conn.commit()
        urllist = getlist(rooturl)
        #href属性取得的url不完整 仅取出了完整url的右半段 因此下面for循环变量名起名righturl
        ID=0
        for righturl in urllist:
            title = righturl[1]
            newurl = righturl[0]
            #urlparse 模块的urlparse.urljoin方法将righturl 按照rooturl格式拼接成完整url
            titleurl = urlparse.urljoin(rooturl, newurl)
            ID+=1
            print ID,title, titleurl
            cursor.execute("INSERT INTO  daomubiji values(%s,%s,%s)", (ID,title, titleurl))
            conn.commit()
        print "输入了"+ str(ID) +"条数据"
except MySQLdb.Error:
    print "连接失败！"

SELECT * FROM daomubiji