标签:
#实时索引配置文件
index rt
{
    type                    = rt
    path            = C:\usr\local\coreseek-4.0.1-win32\var\data\rt
    
    #中文分词配置
    charset_dictpath = C:\usr\local\coreseek-4.0.1-win32\etc\                             
    charset_type        = zh_cn.utf-8
    #文档编号字段
    #id                                         
    #全文索引字段
    rt_field                  = movie            
    rt_field                  = url              
    #属性字段
    rt_attr_uint            = groupid
    
    #存储内容字段,字符串类型
    rt_attr_string			= date                 
    rt_attr_string          = movie              
    rt_attr_string          = url       		  
    #RT实时索引内存设置
    rt_mem_limit = 1024M
}
#searchd服务定义
searchd
{
    workers             =   threads
    listen              =   9312
    listen              = localhost:9306:mysql41    
    read_timeout        = 5
    max_children        = 30
    max_matches         = 1000
    seamless_rotate     = 0
    preopen_indexes     = 0
    unlink_old          = 1
    pid_file = C:\usr\local\coreseek-4.0.1-win32\var\log\searchd_rt.pid  
    binlog_flush = 2
    
    binlog_max_log_size = 16M
}
import MySQLdb
#connect to mysql db
try:
    db = MySQLdb.connect(host="127.0.0.1", user="root", passwd="1234", port=9306)
    cursor = db.cursor()
    print "Connect to db successfully!"
   
except:
    print "Fail to connect to db!"
#insert data to db
for line in open('C:\Users\Administrator\Desktop\ml-100k\u.item'):
    
    (identity,title,date,other,url) = line.split('|')[0:5]
    
    param = (identity,title,url,'1',date)
    
    sql = "insert into rt (id,movie,url,groupid,date) values(%s,%s,%s,%s,%s)"
    
    cursor.execute(sql,param)
db.commit()
db.close
标签:
原文地址:http://blog.csdn.net/ns2250225/article/details/43877419