log_format main '$remote_addr - $remote_user [$time_local] "$request" ' 
     '$status $body_bytes_sent "$http_referer" ' 
     '"$http_user_agent" "$http_x_forwarded_for"' 
     '$upstream_addr $upstream_response_time $request_time; 

101.226.89.14 - - [10/Jul/2016:07:28:32 +0800] "GET /pocketmoney-2016-XiKXCpCK.html HTTP/1.1" 302 231 "-" "Mozilla/5.0 (Linux; Android 5.1; OPPO R9tm Build/LMY47I) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/37.0.0.0 Mobile MQQBrowser/6.2 TBS/036548 Safari/537.36 MicroMessenger/6.3.22.821 NetType/WIFI Language/zh_CN" 

dog@dog-pc:~$ awk '{a[$1]++}END{for(i in a)print i,a[i]}' nginx.log |sort -t ' ' -k2 -rn|head -n 10 
111.167.50.208 26794 
183.28.6.143 16244 
118.76.216.77 9560 
14.148.114.213 3609 
183.50.96.127 3377 
220.115.235.21 3246 
222.84.160.249 2905 
121.42.0.16 2212 
14.208.240.200 2000 
14.17.37.143 1993 

dog@dog-pc:~$ awk '{if($9>0 && $9==200 && substr($6,2)== "GET") a[$1]++}END{for(i in a)print i,a[i]}' nginx.log|sort -t ' ' -k2 -rn|head -n 10 
222.84.160.249 2856 
183.28.6.143 2534 
116.1.127.110 1625 
14.208.240.200 1521 
14.17.37.143 1335 
219.133.40.13 1014 
219.133.40.15 994 
14.17.37.144 988 
14.17.37.161 960 
183.61.51.195 944 

In [1]: from pymongo import MongoClient 
In [2]: client = MongoClient()

{ 
 "status": 302, //HTTP状态码 
 "addr": "101.226.89.14", //远程IP地址 
 "url": "-", 
 "req": "/pocketmoney-2016-XiCXCpCK.html", //请求的地址 
 "agent": "Mozilla/5.0 (Linux; Android 5.1; OPPO R9tm Build/LMY47I) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/37.0.0.0 Mobile MQQBrowser/6.2 TBS/036548 Safari/537.36 MicroMessenger/6.3.22.821 NetType/WIFI Language/zh_CN", //请求的user-agent 
 "referer": "NetType/WIFI", 
 "t": "2016/07/10 06:28:32", //请求的时间 
 "size": 231, //响应的大小 
 "method": "GET", //请求的方法 
 "user": "-" //用户名称 
} 

db = client['log'] 
col = db['nginx'] 
data = {} 
... 
col.insert_one(data)

In [3]: db = client['log'] 
In [4]: col = db['nginx'] 
In [5]: pipeline = [ 
 ...: {"$match":{"status":200}}, 
 ...: {"$group":{"_id":"$addr","count":{"$sum":1}}}, 
 ...: {"$sort":{"count":-1}}, 
 ...: {"$limit":10} 
 ...: ] 
In [6]: list(col.aggregate(pipeline)) 
Out[6]: 
[{u'_id': u'222.84.160.249', u'count': 2856}, 
 {u'_id': u'183.28.6.143', u'count': 2534}, 
 {u'_id': u'116.1.127.110', u'count': 1625}, 
 {u'_id': u'14.208.240.200', u'count': 1521}, 
 {u'_id': u'14.17.37.143', u'count': 1335}, 
 {u'_id': u'219.133.40.13', u'count': 1014}, 
 {u'_id': u'219.133.40.15', u'count': 994}, 
 {u'_id': u'14.17.37.144', u'count': 988}, 
 {u'_id': u'14.17.37.161', u'count': 960}, 
 {u'_id': u'183.61.51.195', u'count': 944}]