Python 统计 SAE 日志脚本

> 之前统计教务系统客户端分布写的脚本，整理备忘。移动教务系统很纯粹，几乎没有任何后台功能，也没xx统计，只能靠分析近期日志进行粗略统计了。

![](/images/2018/04/1209604956.png)

![](/images/2018/04/4203486238.png)

```python
# coding = utf-8
import os
import re

x = [
    'null','选课查看','选课课表查看','选课历史查看','免修查看','补考查看','累加成绩查询',
   '循环考核','毕业资格审核','学位资格审核',
   '个人信息','注册报道信息',
    '缓考信息','分层教学指定','个人课表','查询成绩','考试安排','退出登录','成绩绩点'
  ]
data = [0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0]

print(len(x),len(data))

for log in os.listdir('./log'):
 with open('./log/'+ log,'r') as f:
    for line in f:
      page = re.findall('view.php\?id=(.*?) HTTP',line,re.S)
     if(len(page)>0):
        num = re.findall('\\d+',page[0])
        if(len(num)>0):
         i = int(num[0])
         if(i<20):
           data[i]+=1
print(data)

import numpy as np    
import matplotlib.mlab as mlab    
import matplotlib.pyplot as plt

from matplotlib.font_manager import FontManager
from pylab import mpl
import subprocess

def get_matplot_zh_font():
    fm = FontManager()
    mat_fonts = set(f.name for f in fm.ttflist)

output = subprocess.check_output('fc-list :lang=zh -f "%{family}\n"', shell=True)
    zh_fonts = set(f.split(',', 1)[0] for f in output.split('\n'))
    available = list(mat_fonts & zh_fonts)

print ('*' * 10, '可用的字体', '*' * 10)
    for f in available:
        print (f)
    return available

def set_matplot_zh_font():
    available = get_matplot_zh_font()
    if len(available) > 0:
        mpl.rcParams['font.sans-serif'] = [available[0]]    # 指定默认字体
        mpl.rcParams['axes.unicode_minus'] = False          # 解决保存图像是负号'-'显示为方块的问题

mpl.rcParams['font.sans-serif'] = ['SimHei']

def draw_bar(labels,quants):    
    width = 0.4  
    ind = np.linspace(0.5,9.5,19)  
    # make a square figure  
    fig = plt.figure(1)  
    ax  = fig.add_subplot(111)  
    # Bar Plot  
    ax.bar(ind-width/2,quants,width,color='green')  
    # Set the ticks on x-axis  
    ax.set_xticks(ind)  
    ax.set_xticklabels(labels)  
    # labels  
    ax.set_xlabel('Country')  
    ax.set_ylabel('GDP (Billion US dollar)')  
    # title  
    ax.set_title('Top 10 GDP Countries', bbox={'facecolor':'0.8', 'pad':5})  
    plt.grid(True)  
    plt.show()  
 
draw_bar(x,data)
```

```python
# coding = utf-8
import os
import re

ips = []

Android = 0
iPhone = 0
Windows = 0
Others = 0
for log in os.listdir('./log'):
 with open('./log/'+ log,'r') as f:
    for line in f:
      ip = re.findall('jxxx.feelncut.com (.*?) ',line,re.S)
     if(len(ip)>0):
        if(ip[0] not in ips):
         ips.append(ip[0])
         if(line.find('Android')!=-1):
           Android += 1
          elif(line.find('iPhone')!=-1):
            iPhone += 1
         elif(line.find('Windows')!=-1):
           Windows += 1
          else:
           Others += 1
print(Android,iPhone,Windows,Android+iPhone+Windows)
print(len(ips))

import numpy as np
import matplotlib.pyplot as plt
 
labels = 'Others' ,'Android', 'iPhone', 'Windows'
fracs = [Others,Android,iPhone,Windows]
explode = [0, 0, 0, 0] # 0.1 凸出这部分，
plt.axes(aspect=1)  # set this , Figure is round, otherwise it is an ellipse
#autopct ，show percet
plt.pie(x=fracs, labels=labels, explode=explode,autopct='%3.1f %%',
        shadow=True, labeldistance=1.1, startangle = 90,pctdistance = 0.6
 
        )
'''
labeldistance，文本的位置离远点有多远，1.1指1.1倍半径的位置
autopct，圆里面的文本格式，%3.1f%%表示小数有三位，整数有一位的浮点数
shadow，饼是否有阴影
startangle，起始角度，0，表示从0开始逆时针转，为第一块。一般选择从90度开始比较好看
pctdistance，百分比的text离圆心的距离
patches, l_texts, p_texts，为了得到饼图的返回值，p_texts饼图内部文本的，l_texts饼图外label的文本
'''
 
plt.show()
```

Python 统计 SAE 日志脚本

最新文章

最近回复

分类

归档

其它