varnish_analysis_log3 

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
#!/usr/bin/python3
#-*-coding=utf-8-*-

# ------------------------------------------------------
# Name:         varnish 日志分析脚本
# Purpose:      此脚本只用来分析varnish的访问日志
# Employ:       python3 varnish_analysis_log3.py VarnishLogFilePath or python3 varnish_analysis_log3.py VarnishLogFilePath number
# ------------------------------------------------------

import time
import sys
from prettytable import PrettyTable

class displayFormat():
    def format_size(self, size):
        # 格式化流量单位
        KB = 1024  # KB -> B  B是字节
        MB = 1048576  # MB -> B
        GB = 1073741824  # GB -> B
        TB = 1099511627776  # TB -> B
        if size >= TB:
            size = str("%.2f" % (float(size / TB)) ) + 'T'
        elif size < KB:
            size = str(size) + 'B'
        elif size >= GB and size < TB:
            size = str("%.2f" % (float(size / GB))) + 'G'
        elif size >= MB and size < GB:
            size = str("%.2f" % (float(size / MB))) + 'M'
        else:
            size = str("%.2f" % (float(size / KB))) + 'K'
        return size

    def error_print(self):
        # 输出错误信息
        print
        print('Usage : ' + sys.argv[0] + ' VarnishLogFilePath [Number]')
        print
        sys.exit(1)

    def execut_time(self):
        # 输出脚本执行的时间
        print
        print("Script Execution Time: %.3f second" % time.clock())
        print

class hostInfo():
    host_info = ['200', '301', '302', '304', '400', '401', '403', '404', '499', '500', '502', '503', '504', 'times', 'size']
    def __init__(self, host):
        self.host = host = {}.fromkeys(self.host_info, 0)
        #out {'500': 0, '502': 0, '302': 0, '304': 0, '301': 0, 'times': 0, '200': 0, '404': 0, '401': 0, '403': 0, 'size': 0, '503': 0, '409': 0}

    def increment(self, status_times_size, is_size):
       # 该方法是用来给host_info中的各个值加1
        if status_times_size == 'times':
            self.host['times'] += 1
        elif is_size:
            self.host['size'] = self.host['size'] + status_times_size
        else:
            self.host[status_times_size] += 1
        #print(self.host) # out
        # ip: 1.1.1.1
        # {'200': 0, '302': 0, '304': 0, 'times': 1, '404': 0, '403': 0, '503': 0, '500': 0, 'size': 0}
        # {'200': 1, '302': 0, '304': 0, 'times': 1, '404': 0, '403': 0, '503': 0, '500': 0, 'size': 0}
        # {'200': 1, '302': 0, '304': 0, 'times': 1, '404': 0, '403': 0, '503': 0, '500': 0, 'size': 27882}
        # ip: 1.1.1.1
        # {'200': 1, '302': 0, '304': 0, 'times': 2, '404': 0, '403': 0, '503': 0, '500': 0, 'size': 27882}
        # {'200': 2, '302': 0, '304': 0, 'times': 2, '404': 0, '403': 0, '503': 0, '500': 0, 'size': 27882}
        # {'200': 2, '302': 0, '304': 0, 'times': 2, '404': 0, '403': 0, '503': 0, '500': 0, 'size': 30884}
        # ip: 2.2.2.2
        # {'200': 0, '302': 0, '304': 0, 'times': 1, '404': 0, '403': 0, '503': 0, '500': 0, 'size': 0}
        # {'200': 1, '302': 0, '304': 0, 'times': 1, '404': 0, '403': 0, '503': 0, '500': 0, 'size': 0}
        # {'200': 1, '302': 0, '304': 0, 'times': 1, '404': 0, '403': 0, '503': 0, '500': 0, 'size': 27882}

    def get_value(self, value):
        # 该方法是取到各个主机信息中对应的值
        return self.host[value]

class analysis_log():
    #内存优化
    __slots__ = ['report_dict', 'total_size_sent', 'total_request_times', 'total_200', 'total_301', \
        'total_302', 'total_304', 'total_400', 'total_401', 'total_403', 'total_404', 'total_499', \
        'total_500', 'total_502', 'total_503', 'total_504']

    def __init__(self):
        #初始化一个空字典
        self.report_dict = {}
        self.total_size_sent, self.total_request_times, self.total_200, self.total_301, \
        self.total_302, self.total_304, self.total_400, self.total_401, self.total_403, \
        self.total_404, self.total_499, self.total_500, self.total_502, self.total_503, \
        self.total_504 = 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0

    def split_eachline_todict(self, line):
        #分割文件中的每一行，并返回一个字典
        split_line = line.split()
        split_dict = {'remote_host': split_line[0], 'status': split_line[8], 'bytes_sent': split_line[9]}
        return split_dict

    def generate_log_report(self, logfile):
        # 读取文件，分析split_eachline_todict方法生成的字典
        with open(logfile, 'rb') as infile:
            for line in infile.readlines():
                try:
                    line_dict = self.split_eachline_todict(line)
                    host1 = line_dict['remote_host']
                    host = str(host1).split("'")[1]
                    status1 = line_dict['status']
                    status = str(status1).split("'")[1]
                except ValueError:
                    continue
                except IndexError:
                    continue

                if host not in self.report_dict:
                    host_info_obj = hostInfo(host)
                    # out <__main__.hostInfo object at 0x7fc0aa7ff510>
                    # out {'500': 0, '502': 0, '302': 0, '304': 0, '301': 0, 'times': 0, '200': 0, '404': 0, '401': 0, '403': 0, 'size': 0, '503': 0, '409': 0}
                    self.report_dict[host] = host_info_obj  # 以host_info_obj方法做为value值
                    # out {'1.1.1.1': <__main__.hostInfo object at 0x7fc0aa7ff510>}
                    # out {'1.1.1.1': {'500': 0, '502': 0, '302': 0, '304': 0, '301': 0, 'times': 0, '200': 0, '404': 0, '401': 0, '403': 0, 'size': 0, '503': 0, '409': 0}}
                else:
                    host_info_obj = self.report_dict[host]
                    # out <__main__.hostInfo object at 0x7fc0aa7ff510> 各值加1后的host_info_obj方法
                    # out {'500': 0, '502': 0, '302': 0, '304': 0, '301': 0, 'times': 1, '200': 1, '404': 0, '401': 0, '403': 0, 'size': 1024, '503': 0, '409': 0}
                host_info_obj.increment('times', False)  # 出现的请求次数加1
                if status in host_info_obj.host_info:
                    host_info_obj.increment(status, False)  # 出现的状态码次数加1
                try:
                    bytes_sent = int(line_dict['bytes_sent'])
                except ValueError:
                    bytes_sent = 0
                host_info_obj.increment(bytes_sent, True)  # 发送字节相加
        return self.report_dict
        #out {'1.1.1.1': <__main__.hostInfo object at 0x7ffd3d1cd550>, '2.2.2.2': <__main__.hostInfo object at 0x7ffd3d1cd510>}

    def return_sorted_list(self, true_dict):
        # 输出方法ost_info_obj
        # 计算各个状态次数、流量总量，请求的总次数，并且计算各个状态的总量 并生成一个正真的字典，方便排序
        for host_key in true_dict:
            host_value = true_dict[host_key]
            times = host_value.get_value('times')
            self.total_request_times = self.total_request_times + times
            size = host_value.get_value('size')
            self.total_size_sent = self.total_size_sent + size

            o200 = host_value.get_value('200')
            o301 = host_value.get_value('301')
            o302 = host_value.get_value('302')
            o304 = host_value.get_value('304')
            o400 = host_value.get_value('400')
            o401 = host_value.get_value('401')
            o403 = host_value.get_value('403')
            o404 = host_value.get_value('404')
            o499 = host_value.get_value('499')
            o500 = host_value.get_value('500')
            o502 = host_value.get_value('502')
            o503 = host_value.get_value('503')
            o504 = host_value.get_value('504')

            #字典中如果出现重复的key值，那会以最后传入的key值为准
            true_dict[host_key] = {'200': o200, '301': o301, '302': o302, '304': o304, '400': o400, '401': o401, '403': o403, \
                                   '404': o404, '499': o499, '500': o500, '502': o502, '503': o503, '504': o504, \
                                   'total_request_times': times, 'total_size_sent': size}

            self.total_200 = self.total_200 + o200
            self.total_301 = self.total_301 + o301
            self.total_302 = self.total_302 + o302
            self.total_304 = self.total_304 + o304
            self.total_400 = self.total_400 + o400
            self.total_401 = self.total_401 + o401
            self.total_403 = self.total_403 + o403
            self.total_404 = self.total_404 + o404
            self.total_499 = self.total_499 + o499
            self.total_500 = self.total_500 + o500
            self.total_502 = self.total_502 + o502
            self.total_503 = self.total_503 + o503
            self.total_504 = self.total_504 + o504

        sorted_list = sorted(true_dict.items(), key= lambda k: (k[1]['total_request_times'], k[1]['total_size_sent']), reverse=True)
        return sorted_list

class Main():
    def main(self):
        #主调函数
        display_format = displayFormat()
        arg_length = len(sys.argv)
        if arg_length == 1:
            display_format.error_print()
        elif arg_length == 2 or arg_length == 3:
            infile_name = sys.argv[1]
            try:
                if arg_length == 3:
                    lines = int(sys.argv[2])
                else:
                    lines = 0
            except IOError as e:
                print
                print(e)
                display_format.error_print()
            except ValueError:
                print
                print("Please Enter A Volid Number !!")
                display_format.error_print()
        else:
            display_format.error_print()
        fileAnalysis_obj = analysis_log()
        not_true_dict = fileAnalysis_obj.generate_log_report(infile_name)
        # out {'1.1.1.1': <__main__.hostInfo object at 0x7ffd3d1cd550>, '2.2.2.2': <__main__.hostInfo object at 0x7ffd3d1cd510>}
        log_report = fileAnalysis_obj.return_sorted_list(not_true_dict)
        total_ip = len(log_report)
        if lines:
            log_report = log_report[0:lines]

        print('\n')
        total_size_sent = display_format.format_size(fileAnalysis_obj.total_size_sent)
        total_request_times = fileAnalysis_obj.total_request_times
        print('Total IP: %s   Total Send Size: %s   Total Request Times: %d' % (total_ip, total_size_sent, total_request_times))
        print('\n')

        X = PrettyTable(['IP', 'Send Size', 'Request Times', 'Request Times%', '200', '301', '302', '304', '400', '401', '403', \
                         '404', '499', '500', '502', '503', '504'])
        X.align["IP"] = "l"  # Left align IP
        X.padding_width = 1  # One space between column edges and contents (default)
        for host in log_report:
            list1 = []
            times = host[1]['total_request_times']
            times_percent = (float(times) / float(total_request_times)) * 100
            list1.append("%s" % host[0])
            list1.append("%s" % (display_format.format_size(host[1]['total_size_sent'])))
            list1.append("%s" % times)
            list1.append("%.2f" % float(times_percent))
            list2 = [host[1]['200'], host[1]['301'], host[1]['302'], host[1]['304'], host[1]['400'], host[1]['401'], host[1]['403'], \
                     host[1]['404'], host[1]['499'], host[1]['500'], host[1]['502'], host[1]['503'], host[1]['504']]
            list1.extend(list2)
            X.add_row(list1)
        print(X)

        print('\n')
        Total_X = PrettyTable(['TIP', 'TSend Size', 'TRequest Times', 'TRequest Times%', 'T200', 'T301', \
                         'T302', 'T304', 'T400', 'T401', 'T403', 'T404', 'T499', 'T500', 'T502', 'T503', 'T504'])
        Total_X.align["T IP"] = "l"  # Left align IP
        Total_X.padding_width = 1  # One space between column edges and contents (default)
        Total_list = []
        Total_list.append(total_ip)
        Total_list.append(total_size_sent)
        Total_list.append(total_request_times)
        Total_list.append('100%')
        Total_list1 = [fileAnalysis_obj.total_200, fileAnalysis_obj.total_301, fileAnalysis_obj.total_302, fileAnalysis_obj.total_304, \
                       fileAnalysis_obj.total_400, fileAnalysis_obj.total_401, fileAnalysis_obj.total_403, fileAnalysis_obj.total_404, \
                       fileAnalysis_obj.total_499, fileAnalysis_obj.total_500, fileAnalysis_obj.total_502, fileAnalysis_obj.total_503, \
                       fileAnalysis_obj.total_504]
        Total_list.extend(Total_list1)
        Total_X.add_row(Total_list)
        print(Total_X)

        print('\n')
        display_format.execut_time()
        print('\n')

if __name__ == '__main__':
    main_obj = Main()
    main_obj.main()

展开全文 >>

Linux扫描进程使用情况 

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
#!/usr/bin/python3
#-*- coding:utf-8 -*-

"""
python io_analysis3.py 4 5 3 ，第一个数位每次收集读写数据的间隔秒数，第二个数是打印出读写最多的n个进程，第三个为运行脚本的次数
如果不接参数，默认是等待5秒，打印前6个进程，脚本运行一次
"""

import os
import re
import sys
import time
from prettytable import PrettyTable

####
sys_proc_path = '/proc/'
re_find_process_number = '^\d+$'

####
# 通过/proc/$pid/io获取读写信息
####

def collect_info():
    _tmp = {}
    re_find_process_dir = re.compile(re_find_process_number)
    for i in os.listdir(sys_proc_path):
        if re_find_process_dir.search(i):
            proc_num = re_find_process_dir.search(i).group()
            # 获得进程名
            try:
                with open("%s%s/stat" % (sys_proc_path, proc_num), "r") as process_name1:
                    process_name = process_name1.read().split(" ")[1]
                    # 读取io信息
                    with open("%s%s/io" % (sys_proc_path, proc_num), "r") as rw_io:
                        for _info in rw_io.readlines():
                            cut_info = _info.strip().split(':')
                            if cut_info[0].strip() == "read_bytes":
                                read_io = int(cut_info[1].strip())
                            if cut_info[0].strip() == "write_bytes":
                                write_io = int(cut_info[1].strip())
                                _tmp[proc_num] = {"name": process_name, "read_bytes": read_io, "write_bytes": write_io}
            except:pass
    return _tmp #返回结果 {10: {'write_bytes': '200', 'read_bytes': '100', 'name': '(httpd)'}, '1782': {'write_bytes': 8192, 'read_bytes': 76390400, 'name': '(gnome-session)'}}

def main(_list_num):
    _sort_read_dict = {}
    _sort_write_dict = {}
    # 获取系统读写数据
    process_info_list_frist = collect_info()
    # 将读数据和写数据进行分组，写入两个字典中
    for loop in process_info_list_frist.keys():
        frist_read_v = process_info_list_frist[loop]["read_bytes"]  # out 100
        frist_write_v = process_info_list_frist[loop]["write_bytes"]  # out 200
        # 生成字典
        _sort_read_dict[loop] = frist_read_v  # 赋值{10:读值, 20:读值}
        _sort_write_dict[loop] = frist_write_v  # 赋值{10:写值, 20:写值}
    # 将读写数据进行排序
    sort_read_dict = sorted(_sort_read_dict.items(), key=lambda x: x[1], reverse=True)  # out [(20, 读值), (10, 读值)]
    sort_write_dict = sorted(_sort_write_dict.items(), key=lambda y: y[1], reverse=True)  # out [(20, 写值), (10, 写值)]
    # 打印统计结果
    system_time = time.strftime('%F %T')
    print(system_time)
    X = PrettyTable(["r-pid", "r-process", "read(bytes)", "w-pid", "w-process", "write(btyes)"]) #列表名不能有重复
    X.align["r-pid"] = "l"# Left align r-pid
    X.padding_width = 1# One space between column edges and contents (default)
    for _num in range(_list_num):
        res  = []
        read_pid = sort_read_dict[_num][0]
        write_pid = sort_write_dict[_num][0]
        res.append("%s" % read_pid)
        res.append(process_info_list_frist[read_pid]["name"])
        res.append("%s" % sort_read_dict[_num][1])
        res.append(write_pid)
        res.append(process_info_list_frist[write_pid]["name"])
        res.append("%s" % sort_write_dict[_num][1])
        X.add_row(res)
    print(X)
    print("\n" * 1)

if __name__ == '__main__':
    try:
        _sleep_time = sys.argv[1]
    except:
        _sleep_time = 5
    try:
        _num = sys.argv[2]
    except:
        _num = 6
    try:
        loop = sys.argv[3]
    except:
        loop = 1
    if int(loop) == 1:
        for i in range(int(loop)):
            main(int(_num))
    else:
        for i in range(int(loop)):
            loop1 = int(loop) - 1
            if i == int(loop1):
                main(int(_num))
            else:
                main(int(_num))
                time.sleep(int(_sleep_time))

展开全文 >>

Python3.x标准模块库目录

文本

1
2
3
4
5
6
7
8
1. string：通用字符串操作
2. re：正则表达式操作
3. difflib：差异计算工具
4. textwrap：文本填充
5. unicodedata：Unicode字符数据库
6. stringprep：互联网字符串准备工具
7. readline：GNU按行读取接口
8. rlcompleter：GNU按行读取的实现函数

展开全文 >>

Markdown11种基本语法

1.标题设置（让字体变大，和word的标题意思一样）
在Markdown当中设置标题，有两种方式：

1
2
第一种：通过在文字下方添加“=”和“-”，他们分别表示一级标题和二级标题。
第二种：在文字开头加上 “#”，通过“#”数量表示几级标题。（一共只有1~6级标题，1级标题字体最大）

展开全文 >>

Python3异常处理

与python异常相关的关键字

1
2
3
4
5
6
7
raise：手动抛出/引发异常：raise [exception[,data]]
try/except：捕获异常并处理
pass：忽略异常
as：定义异常实例(except IOError as e)
finally：无论是否出现异常，都执行的代码
else：如果try中的语句没有引发异常，则执行else中的语句
except Exception as error：

展开全文 >>

tag:

    缺失模块。
    1、请确保node版本大于6.2
    2、在博客根目录（注意不是yilia根目录）执行以下命令：
    npm i hexo-generator-json-content --save

    3、在根目录_config.yml里添加配置： 

      jsonContent:
    meta: false
    pages: false
    posts:
      title: true
      date: true
      path: true
      text: false
      raw: false
      content: false
      slug: false
      updated: false
      comments: false
      link: false
      permalink: false
      excerpt: false
      categories: false
      tags: true