py-tar

py-tar
======

tar file creation
-----------------
import tarfile
tar = tarfile.open("/tmp/bckup.tar","w")
tar.add("access.log")
tar.add("logparser.py")
tar.close()

Result
------
! tar -tvf /tmp/bckup.tar

-rw-rw-r-- sreehari/sreehari 31179568 2023-03-23 22:00 access.log
-rw-rw-r-- sreehari/sreehari     1002 2023-03-27 20:40 logparser.py

-----------------------------------------------------------

import os
import tarfile
import posixpath

directory = "wave_cafe/img/"
tarName = "/tmp/pics.tar"

tar = tarfile.open(tarName,"w")

for item in os.walk(directory):

  curDir = item[0]
  subDirs = item[1]
  subFiles = item[2]

  for subFile in subFiles:

    absPath = posixpath.join(curDir,subFile)

    if absPath.endswith(".png"):

      tar.add(absPath)

tar.close()

Result
------
! tar -tvf /tmp/pics.tar

-rw-rw-r-- sreehari/sreehari 64185 2020-04-04 11:15 wave_cafe/img/hot-cappuccino.png
-rw-rw-r-- sreehari/sreehari 58287 2020-04-04 11:15 wave_cafe/img/hot-latte.png
-rw-rw-r-- sreehari/sreehari 88979 2020-04-07 11:16 wave_cafe/img/about-2.png
-rw-rw-r-- sreehari/sreehari 46343 2020-04-04 11:15 wave_cafe/img/iced-americano.png
-rw-rw-r-- sreehari/sreehari 43685 2020-04-04 11:15 wave_cafe/img/smoothie-1.png
-rw-rw-r-- sreehari/sreehari 85831 2020-04-07 11:16 wave_cafe/img/about-1.png
-rw-rw-r-- sreehari/sreehari 45394 2020-04-04 11:15 wave_cafe/img/smoothie-4.png
-rw-rw-r-- sreehari/sreehari 52584 2020-04-04 11:15 wave_cafe/img/iced-espresso.png
-rw-rw-r-- sreehari/sreehari 50534 2020-04-04 11:15 wave_cafe/img/iced-latte.png
-rw-rw-r-- sreehari/sreehari 52052 2020-04-04 11:15 wave_cafe/img/iced-cappuccino.png
-rw-rw-r-- sreehari/sreehari 52159 2020-04-04 11:15 wave_cafe/img/smoothie-3.png
-rw-rw-r-- sreehari/sreehari 46647 2020-04-04 11:15 wave_cafe/img/smoothie-2.png
-rw-rw-r-- sreehari/sreehari 61307 2020-04-04 11:15 wave_cafe/img/hot-americano.png
-rw-rw-r-- sreehari/sreehari 55430 2020-04-04 11:15 wave_cafe/img/hot-espresso.png

-----------------------------------------------------------

enabling compression
---------------------

gzip
----

import os
import tarfile
import posixpath

directory = "wave_cafe/img/"
tarName = "/tmp/pics.tar.gz"

tar = tarfile.open(tarName,"w:gz")

for item in os.walk(directory):

  curDir = item[0]
  subDirs = item[1]
  subFiles = item[2]

  for subFile in subFiles:

    absPath = posixpath.join(curDir,subFile)

    if absPath.endswith(".png"):

      tar.add(absPath)

tar.close()

Result
-------
! ls -lh /tmp/pics.tar.gz

-rw-rw-r-- 1 sreehari sreehari 783K Mar 30 17:51 /tmp/pics.tar.gz

-----------------------------------------------------------

import os
import tarfile
import posixpath

directory = "wave_cafe/img/"
tarName = "/tmp/pics.tar.bz2"

tar = tarfile.open(tarName,"w:bz2")

for item in os.walk(directory):

  curDir = item[0]
  subDirs = item[1]
  subFiles = item[2]

  for subFile in subFiles:

    absPath = posixpath.join(curDir,subFile)

    if absPath.endswith(".png"):

      tar.add(absPath)

tar.close()


Result
-------
! ls -lh /tmp/pics.tar.bz2

-rw-rw-r-- 1 sreehari sreehari 778K Mar 30 17:53 /tmp/pics.tar.bz2

-----------------------------------------------------------


running linux commands
----------------------
import subprocess

subprocess.call("mkdir /tmp/test",shell=True)

Result
-------
! ls -d /tmp/test

/tmp/test

-----------------------------------------------------------

reading command line arguments
------------------------------
cat hitcounter.py

import sys
print(sys.argv)

$ python3 hitcounter.py sree hari 94 28
['hitcounter.py', 'sree', 'hari', '94', '28']

-----------------------------------------------------------

cat hitcounter.py

import logparser
import posixpath
import sys

arguments = sys.argv[1:]
use = "python3 ./hitcounter.py /path/to/access.log status-code"

if len(arguments) == 2:

  logFile = arguments[0]
  statusCode = arguments[1]

  if posixpath.isfile(logFile) and statusCode.isdigit():

    print("ok")

  else:

    print(use)

else:

  print(use)


$ python3 hitcounter.py access.log 200
ok

$ python3 hitcounter.py access.log 4a4
python3 ./hitcounter.py /path/to/access.log status-code

-----------------------------------------------------------

cat hitcounter.py

import logparser
import posixpath
import sys

arguments = sys.argv[1:]
usage = "python3 ./hitcounter.py /path/to/access.log status-code"

if len(arguments) == 2:


  logFile = arguments[0]
  statusCode = arguments[1]

  if posixpath.isfile(logFile) and statusCode.isdigit():
    logHandler = open(logFile,"r")
    hitCounter = {}

    for logLine in logHandler:
      logDetails = logparser.parser(logLine)
      host = logDetails["host"]
      status = logDetails["status"]

      if status == statusCode:

        if host not in hitCounter:

          hitCounter[host] = 1

        else:

          hitCounter[host] += 1

    def getFreq(t):

      return t[1]

    sortedResult = sorted(hitCounter.items(),key=getFreq)[-10:]


    for item in sortedResult:

      ip = item[0]
      freq = item[1]

      print("{:15} - {}".format(ip,freq))

  else:

    print(usage)

else:

  print(usage)


Result
------
$ python3 hitcounter.py access.log 200
45.138.4.22     - 830
45.153.227.31   - 834
45.153.227.55   - 837
45.132.207.154  - 845
176.222.58.254  - 882
45.144.0.179    - 906
45.15.143.155   - 1285
173.255.176.5   - 2154
51.210.183.78   - 2684
193.106.31.130  - 89514

$ python3 hitcounter.py access.log 404
90.191.124.115  - 51
104.140.103.41  - 57
51.210.243.185  - 58
104.131.51.209  - 63
5.180.107.194   - 66
89.159.228.206  - 72
193.106.30.100  - 75
13.77.204.88    - 78
212.9.160.24    - 99
173.255.176.5   - 2026

$ python3 hitcounter.py access.log 301
223.238.196.236 - 1
52.15.188.132   - 1
52.14.77.107    - 1
3.22.12.117     - 1
109.127.18.197  - 2
66.249.66.158   - 2
66.249.66.129   - 2
193.29.107.244  - 3
82.117.212.186  - 3
173.255.176.5   - 948

-----------------------------------------------------------

cat hitcounter.py

import logparser
import posixpath
import sys
import ipgeolocation


arguments = sys.argv[1:]
usage = "python3 ./hitcounter.py /path/to/access.log status-code"

if len(arguments) == 2:
  logFile = arguments[0]
  statusCode = arguments[1]

  if posixpath.isfile(logFile) and statusCode.isdigit():
    logHandler = open(logFile,'r')
    hitCounter = {}

    for logLine in logHandler:
      logDetails = logparser.parser(logLine)
      host = logDetails['host']
      status = logDetails['status']

      if status == statusCode:

        if host not in hitCounter:

          hitCounter[host] = 1

        else:

          hitCounter[host] = hitCounter[host] + 1


    def getFreq(t):
      return t[1]
    sortedResult = sorted(hitCounter.items(),key=getFreq)[-10:]


    for item in sortedResult:

      ip = item[0]
      freq = item[1]

      country = ipgeolocation.ip2country(ip=ip,api_key="c9e54a40c52346358b5e1135c973a71b")

      print("{:15} - {:5} [{}]".format(ip,freq,country))

  else:

    print(usage)

else:

  print(usage)


Result
------
$ python3 hitcounter.py access.log 200
45.138.4.22     -   830 [Germany]
45.153.227.31   -   834 [Germany]
45.153.227.55   -   837 [Germany]
45.132.207.154  -   845 [Germany]
176.222.58.254  -   882 [Germany]
45.144.0.179    -   906 [Germany]
45.15.143.155   -  1285 [United States]
173.255.176.5   -  2154 [United States]
51.210.183.78   -  2684 [France]
193.106.31.130  - 89514 [Ukraine]

$ python3 hitcounter.py access.log 404
90.191.124.115  -    51 [Estonia]
104.140.103.41  -    57 [Netherlands]
51.210.243.185  -    58 [France]
104.131.51.209  -    63 [United States]
5.180.107.194   -    66 [Turkey]
89.159.228.206  -    72 [France]
193.106.30.100  -    75 [Ukraine]
13.77.204.88    -    78 [United States]
212.9.160.24    -    99 [Germany]
173.255.176.5   -  2026 [United States]

-----------------------------------------------------------


while loop
----------
x = 1
while x <= 10:
  print(x)
  x = x + 1

Result
-------
1
2
3
4
5
6
7
8
9
10

-----------------------------------------------------------

l = []

if l:

  print("not empty")

else:

  print("empty")

Result
-------
empty

-----------------------------------------------------------

l = [2]

if l:

  print("not empty")

else:

  print("empty")

Result
-------
not empty

-----------------------------------------------------------

if 1:

  print("not empty")

else:

  print("empty")

Result
-------
not empty

-----------------------------------------------------------

if "sree":

  print("not empty")

else:

  print("empty")

Result
-------
not empty

-----------------------------------------------------------

if "":

  print("not empty")

else:

  print("empty")

Result
-------
empty

-----------------------------------------------------------