URL请求数-Pandas-Python数据分析(7)

A+

所属分类：python

1.1. Pandas分析步骤

载入数据
将请求的URL 进行 COUNT。类似如下SQL:

SELECT request_url,
    count(*)
FROM log
GROUP BY request_url
ORDER BY count(*)
LIMIT 0, 100;

SELECT request_url,

count(*)

FROM log

GROUP BY request_url

ORDER BY count(*)

LIMIT 0, 100;

1.2. 代码

cat pd_ng_log_stat.py
#!/usr/bin/env <a href="http://www.ttlsa.com/python/" title="Python"target="_blank">python</a>
#-*- coding: utf-8 -*-
 
from ng_line_parser import NgLineParser
 
import pandas as pd
import socket
import struct
 
class PDNgLogStat(object):
 
    def __init__(self):
        self.ng_line_parser = NgLineParser()
 
    def _log_line_iter(self, pathes):
        """解析文件中的每一行并生成一个迭代器"""
        for path in pathes:
            with open(path, 'r') as f:
                for index, line in enumerate(f):
                    self.ng_line_parser.parse(line)
                    yield self.ng_line_parser.to_dict()
 
    def load_data(self, path):
        """通过给的文件路径加载数据生成 DataFrame"""
        self.df = pd.DataFrame(self._log_line_iter(path))
 
    def url_req_stat(self):
        """统计那个页面点击量"""
        group_by_cols = ['request_url'] # 需要分组的列,只计算和显示该列
         
        # 直接统计次数
        url_req_grp = self.df[group_by_cols].groupby(
                                     self.df['request_url'])
        return url_req_grp.agg(['count'])['request_url'].sort_values(by='count', ascending=False)
 
 
def main():
    file_pathes = ['www.ttmark.com.access.log']
 
    pd_ng_log_stat = PDNgLogStat()
    pd_ng_log_stat.load_data(file_pathes)
 
    # 统计页面点击量
    print pd_ng_log_stat.url_req_stat()
 
if __name__ == '__main__':
    main()

cat pd_ng_log_stat.py

#!/usr/bin/env python

#-*- coding: utf-8 -*-

from ng_line_parser import NgLineParser

import pandas as pd

import socket

import struct

class PDNgLogStat(object):

def __init__(self):

self.ng_line_parser = NgLineParser()

def _log_line_iter(self, pathes):

"""解析文件中的每一行并生成一个迭代器"""

for path in pathes:

with open(path, 'r') as f:

for index, line in enumerate(f):

self.ng_line_parser.parse(line)

yield self.ng_line_parser.to_dict()

def load_data(self, path):

"""通过给的文件路径加载数据生成 DataFrame"""

self.df = pd.DataFrame(self._log_line_iter(path))

def url_req_stat(self):

"""统计那个页面点击量"""

group_by_cols = ['request_url'] # 需要分组的列,只计算和显示该列

# 直接统计次数

url_req_grp = self.df[group_by_cols].groupby(

self.df['request_url'])

return url_req_grp.agg(['count'])['request_url'].sort_values(by='count', ascending=False)

def main():

file_pathes = ['www.ttmark.com.access.log']

pd_ng_log_stat = PDNgLogStat()

pd_ng_log_stat.load_data(file_pathes)

# 统计页面点击量

print pd_ng_log_stat.url_req_stat()

if __name__ == '__main__':

main()

运行统计和输出结果

python pd_ng_log_stat.py
 
                                                     count
request_url                                               
/wp-admin/admin-ajax.<a href="http://www.ttlsa.com/php/" title="php"target="_blank">php</a>                            246361
/tag/                                               126012
/                                                    57325
......
/chufang/2016/06/25/8634.html                         2312
/chufang/2015/03/26/4686.html                         2293
/jiaju/2014/12/05/1348.html                           2230
 
[29205 rows x 1 columns]

python pd_ng_log_stat.py

count

request_url

/wp-admin/admin-ajax.php 246361

/tag/ 126012

/ 57325

......

/chufang/2016/06/25/8634.html 2312

/chufang/2015/03/26/4686.html 2293

/jiaju/2014/12/05/1348.html 2230

[29205 rows x 1 columns]

昵称: HH

QQ: 275258836

ttlsa群交流沟通(QQ群②: 6690706 QQ群③: 168085569 QQ群④: 415230207（新）微信公众号: ttlsacom)

感觉本文内容不错，读后有收获？

逛逛衣服店，鼓励作者写出更好文章。

微信公众号

扫一扫关注运维生存时间公众号，获取最新技术文章~

1.1. Pandas分析步骤

1.2. 代码

目前评论：2 其中：访客 2 博主 0

登录 注册 找回密码

微信

登录注册找回密码