MongoDB

http://www.cnblogs.com/libingql/archive/2011/06/09/2076440.html

===

> show dbs
admin          (empty)
local          0.031GB
nutch_eclipse  0.031GB
test           (empty)
> use nutch_eclipse
switched to db nutch_eclipse
> show collections
system.indexes
webpage
> db.webpage.count()
467
> 

 ==

> db.webpage.findOne()
{
    "_id" : "cn.edu.hist.crjyxy:http/info/1012/1085.htm",
    "status" : 1,
    "fetchTime" : NumberLong("1439345028815"),
    "fetchInterval" : 2592000,
    "retriesSinceFetch" : 0,
    "score" : 0,
    "inlinks" : {
        "http://crjyxy·hist·edu·cn/zzjd·htm" : "关于2009年度中等职业学校专业骨干教师国家级培训的通知"
    },
    "markers" : {
        "dist" : "2"
    },
    "metadata" : {
        "_csh_" : BinData(0,"AAAAAA==")
    }
}

==

> db.webpage.distinct("_id")
[
    "cn.edu.hist.chengj:http/pxjd/index.asp",
    "cn.edu.hist.crjyxy:http/200936122845946.rar",
    "cn.edu.hist.crjyxy:http/index.htm",
    "cn.edu.hist.crjyxy:http/info/1012/1075.htm",
    "cn.edu.hist.crjyxy:http/info/1012/1079.htm",
    "cn.edu.hist.yyylxy:http/",
    "cn.edu.hist.zdxx:http/",
    "cn.edu.hist.zgwyhdx:http/",
    "cn.edu.hist.zsxx:http/",
    "cn.edu.hist.zyyhjxy:http/",
    "cn.edu.hist.zzb:http/"
]
> 

==

> db.webpage.find().count()
467

==

> db.webpage.find().limit(5)
{ "_id" : "cn.edu.hist.crjyxy:http/info/1012/1085.htm", "status" : 1, "fetchTime" : NumberLong("1439345028815"), "fetchInterval" : 2592000, "retriesSinceFetch" : 0, "score" : 0, "inlinks" : { "http://crjyxy·hist·edu·cn/zzjd·htm" : "关于2009年度中等职业学校专业骨干教师国家级培训的通知" }, "markers" : { "dist" : "2" }, "metadata" : { "_csh_" : BinData(0,"AAAAAA==") } }
{ "_id" : "cn.edu.hist.jwc:http/jwxw.htm", "status" : 1, "fetchTime" : NumberLong("1439345028926"), "fetchInterval" : 2592000, "retriesSinceFetch" : 0, "score" : 0, "inlinks" : { "http://jwc·hist·edu·cn/" : "" }, "markers" : { "dist" : "2" }, "metadata" : { "_csh_" : BinData(0,"AAAAAA==") } }
{ "_id" : "cn.edu.hist.chengj:http/pxjd/index.asp", "status" : 1, "fetchTime" : NumberLong("1439345028769"), "fetchInterval" : 2592000, "retriesSinceFetch" : 0, "score" : 0, "inlinks" : { "http://crjyxy·hist·edu·cn/info/1012/1078·htm" : "http://chengj.hist.edu.cn/pxjd/index.asp" }, "markers" : { "dist" : "3" }, "metadata" : { "_csh_" : BinData(0,"AAAAAA==") } }
{ "_id" : "cn.edu.hist.crjyxy:http/200936122845946.rar", "status" : 1, "fetchTime" : NumberLong("1439345028786"), "fetchInterval" : 2592000, "retriesSinceFetch" : 0, "score" : 0, "inlinks" : { "http://crjyxy·hist·edu·cn/info/1012/1084·htm" : "教育部文件.rar" }, "markers" : { "dist" : "3" }, "metadata" : { "_csh_" : BinData(0,"AAAAAA==") } }
{ "_id" : "cn.edu.hist.www:http/info/1099/9733.htm", "status" : 1, "fetchTime" : NumberLong("1439345029107"), "fetchInterval" : 2592000, "retriesSinceFetch" : 0, "score" : 0, "inlinks" : { "http://www·hist·edu·cn/index/sy/tzgg/kjc·htm" : "关于我校组织参加“第四届中国创新创业大赛河南赛区暨河南省科技创业雏鹰大赛”的通知" }, "markers" : { "dist" : "2" }, "metadata" : { "_csh_" : BinData(0,"AAAAAA==") } }

== 

> db.webpage.find().skip(466)
{ "_id" : "cn.edu.hist.zzb:http/", "status" : 1, "fetchTime" : NumberLong("1439345029199"), "fetchInterval" : 2592000, "retriesSinceFetch" : 0, "score" : 0, "inlinks" : { "http://www·hist·edu·cn/jgsz/dqjg·htm" : "党委组织部" }, "markers" : { "dist" : "2" }, "metadata" : { "_csh_" : BinData(0,"AAAAAA==") } }

====

> db.webpage.remove({})
WriteResult({ "nRemoved" : 467 })
> db.webpage.find().count()
0

==