嘿！我用python帮我干这些事

Posted 2020-12-30 等你归去来

　　python 无疑是当下火上天的语言，但是我们又不拿来工作，那么能拿来干啥呢？我是这么干的。

1. 平时工作开发用不上，就当个计算器吧！

python
# 加减乘除
>>> (3 + 2) - 5 * 1
5
# 位运算
>>> 3 << 2
12
# x ^ y 幂次方运算,不能开方运算
>>> 3 ** 2
9
# 用另一种计算幂次方的运算，可以开方运算
>>> pow(9, 0.5)
3.0
# 作进制转换，如二进制转换，十进制转n进制
>>> bin(2)
\'0b10\'
>>> hex(25)
\'0x19\'
>>> oct(10)
\'012\'
>>> int(\'e0\', 16)
224
# 将十进制转换为二进制，以全0占位形式显示二进制，更方便查看,默认为32位，使用如下图所示
def decbin(i, bit=32):
　　return (bin(((1 << bit) - 1) & i)[2:]).zfill(bit)

2. 做简单爬虫

#!/usr/bin/python
# -*- coding: UTF-8 -*-

import urllib,urllib2
import re
import os
import HTMLParser
dirbase = \'/tmp\'
urlbase = \'http://hg.openjdk.java.net\'
url= urlbase + \'/jdk8u/jdk8u/jdk/file/dddb1b026323/src\'        #/jdk,/hotspot
skip_to_p = \'\'
skip_find = False;
textmod ={\'user\':\'admin\',\'password\':\'admin\'}
textmod = urllib.urlencode(textmod)
print(url)
req = urllib2.Request(url = \'%s%s%s\' % (url,\'?\',textmod))
res = urllib2.urlopen(req)
res = res.read()
alink = re.findall(r\'<a\',res)
allflist = []

table=re.findall(r\'<tbody class="stripes2">(.+)<\\/tbody>\',res, re.S)

harr = re.findall(r\'href="(/jdk8u[\\w\\/\\._]+)">(?!\\[up\\])\', table[0])

def down_src_recursion(harr):
  global allflist,skip_find;
  if(not harr):
    return False;
  i=0; arrlen = len(harr)
  lock_conflict_jump_max = 2;   # 遇到文件锁时跳过n个文件,当前仍需跳过的文件数量
  lock_conflict_jumping = 0;
  print("in new dir cur...")
  if(len(allflist) > 1500):
     print(\'over 1500, cut to 50 exists...\')
     allflist = allflist[-800:]
  for alink in harr:
    i += 1;
    alink = alink.rstrip(\'/\')
    if(skip_to_p and not skip_find):
    if(alink != skip_to_p):
      print(\'skip file, cause no find..., skip=%s,now=%s\' % (skip_to_p, alink))
      continue;
    else:
      skip_find = True;
    if(alink in allflist):
      print(\'目录已搜寻过:\' + alink)
      continue;
    pa = dirbase + alink
    if(os.path.isfile(pa)):
      print(\'文件已存在，无需下载: \' + pa)
      continue;
    lockfile=pa+\'.tmp\'
    if(os.path.isfile(lockfile)):
　　　 lock_conflict_jumping = lock_conflict_jump_max;
      print(\'文件正在下载中，跳过+%s...: %s\' % (lock_conflict_jumping, lockfile))continue; 
    else:
      if(lock_conflict_jumping > 0):
         lock_conflict_jumping -= 1;
         print(\'文件正在下载中，跳过+%s...: %s\' % (lock_conflict_jumping, lockfile))continue;
    # 首先根据后缀把下载中的标识标记好，因为网络下载时间更慢，等下载好后再加标识其实已为时已晚
    if(pa.endswith((\'.gif\',\'.jpg\',\'.png\', \'.xml\', \'.cfg\', \'.properties\', \'.make\', \'.sh\', \'.bat\', \'.html\', \'.c\',\'.cpp\', \'.h\', \'.hpp\', \'.java\', \'.1\'))):
       os.mknod(lockfile);
    reqt = urllib2.Request(urlbase + alink)
    rest = urllib2.urlopen(reqt)
    rest = rest.read()
    allflist.append(alink)
    if(rest.find(\'class="sourcefirst"\') > 0):
       print(\'这是个资源文件:%s         %d/%d\' % (alink, i, arrlen))
       if(not os.path.isfile(lockfile)):
          os.mknod(lockfile);
       filename = alink.split(\'/\')[-1]
       linearr = re.findall(r\'<span id=".+">(.+)</span>\', rest)
       fileObject = open(dirbase + alink, \'w\')
       for line in linearr:
          try:
            line = HTMLParser.HTMLParser().unescape(line)
          except UnicodeDecodeError as e:
            print(\'oops, ascii convert error accour:\', e)
          fileObject.write(line + \'\\r\\n\')
       fileObject.close()
       os.remove(lockfile); 
    else:
      print(\'这是目录:%s        %d/%d\' % (alink, i, arrlen))
      if(not os.path.exists(pa)):
         print(\'创建目录:%s\' % alink)
         os.makedirs(\'/tmp\' + alink, mode=0777)
      ta=re.findall(r\'<tbody class="stripes2">(.+)<\\/tbody>\',rest, re.S)
      ha = re.findall(r\'href="(/jdk8u[\\w\\/\\._]+)">(?!\\[up\\])\', ta[0])
      down_src_recursion(ha)

# go...
down_src_recursion(harr);

以上python2 版本的爬虫，在python3中则要改编下呢！

#!/usr/bin/python
# -*- coding: UTF-8 -*-
# for python3

import urllib.parse
import urllib.request
import re
import os
import html
dirbase = \'/tmp\'
urlbase = \'http://hg.openjdk.java.net\'
url= urlbase + \'/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/sun/misc\'
#skip_to_p = \'/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/sun/misc\'
skip_to_p = \'\'
skip_find = False;
textmod ={\'user\':\'admin\',\'password\':\'admin\'}
textmod = urllib.parse.urlencode(textmod)
print(url)
res = urllib.request.urlopen(url = \'%s%s%s\' % (url,\'?\',textmod))
res = res.read().decode(\'utf-8\')
alink = re.findall(r\'<a\', res)
allflist = []

table=re.findall(r\'<tbody class="stripes2">(.+)<\\/tbody>\',res, re.S)

harr = re.findall(r\'href="(/jdk8u[\\w\\/\\._]+)">(?!\\[up\\])\', table[0])

def down_src_cur(harr):
    global allflist,skip_find;
    if(not harr):
        return False;
    i=0; 
    arrlen = len(harr);
    print("- In new dir cur...")
    if(len(allflist) > 1500):
        print(\'- Over 1500, cut to 50 exists...\')
    allflist = allflist[-800:]
    for alink in harr:
        i += 1;
        alink = alink.rstrip(\'/\')
        if(skip_to_p and not skip_find):
            if(alink != skip_to_p):
                print(\'- Skip file, cause no find..., skip=%s,now=%s\' % (skip_to_p, alink))
                continue;
            else:
                skip_find = True;
        if(alink in allflist):
            print(\'- Searched before:\' + alink)
            continue;
        rest=\'\';
        try:    
            res = urllib.request.urlopen(urlbase + alink)
            rest = res.read().decode(\'utf-8\')
        except Exception as e:
            print(e)
            print(" ERROR accour, continue;")
            continue;
        allflist.append(alink)
        if(rest.find(\'class="sourcefirst"\') > 0):
            print(\'- Code resourse:%s         %d/%d\' % (alink, i, arrlen))
            filename = alink.split(\'/\')[-1]
            linearr = re.findall(r\'<span id=".+">(.+)</span>\', rest)
            fileObject = open(dirbase + alink, \'w\')
            for line in linearr:
                fileObject.write(html.unescape(line) + \'\\r\\n\')
            fileObject.close()
        else:
            pa = dirbase + alink
            print(\'- Directory:%s        %d/%d\' % (alink, i, arrlen))
            if(not os.path.exists(pa)):
                print(\'makedirs:%s\' % alink);
                os.makedirs(\'/tmp\' + alink, mode=0o777 );
            ta=re.findall(r\'<tbody class="stripes2">(.+)<\\/tbody>\',rest, re.S)
            ha = re.findall(r\'href="(/jdk8u[\\w\\/\\._]+)">(?!\\[up\\])\', ta[0])
            # 递归爬取解析
            down_src_cur(ha)

down_src_cur(harr);

 

做文件搜索，替换：

4. 做简单代码验证

# 做简单字符查找验证
>>> \'234234fdgdfs\'.find(\'f\')
6
>>> \'234234fdgdfs\'.index(\'f\')
6
>>> \'234234fdgdfs\'[2:5]
\'423\'
# 做正则匹配
>>> re.findall(r\'[a-zA-Z0-9]*\\.[a-zA-Z1-9]*[\\.|com]*\', \'www.baidu.com\')
[\'www.baidu.com\']

 

5. 写个运维脚本，监听本机8080端口的运行状态，如果发现挂了，就发送邮件通知主人，并重启服务器。

#!/usr/bin/env python
#!coding=utf-8
import os
import time
import sys
import smtplib
from email.mime.text import MIMEText
 
def send_email (warning):
    msg = MIMEText(warning)
    msg[\'Subject\'] = \'python send warning mail\'
    msg[\'From\'] = \'测试了<[e-mail]>\'
    try:
       smtp = smtplib.SMTP()
       to_mail = \'[e-mail]\'
       from_mail = \'[e-mail]\'
       smtp.connect(r\'smtp.qiye.163.com\')
       smtp.login(\'[e-mail]\', \'xxx123\')
       smtp.sendmail(from_mail, to_mail, msg.as_string())
       smtp.close()
       print(\'send mail to %s, content is: %s\' % (to_mail, msg))
    except Exception as e:
       print("Send mail Error: %s" % e)
# 监听状态中。。。
while True:
    http_status = os.popen(\'netstat -tulnp | grep ":8080"\',\'r\').readlines()
    try:
        if http_status == []:
            os.system(\'service tomcat7 start\')
        time.sleep(3)    # 等待启动
            new_http_status = os.popen(\'netstat -tulnp | grep ":8080"\',\'r\').readlines()
            str1 = \'\'.join(new_http_status)
            is_port = -1;
            send_email(warning = "8080 port shutdown, This is a warning!!!")  # 发送通知
        try:
              is_port = str1.split()[3].split(\':\')[-1]
        except IndexError, e:
          print("out of range:", e)
            if is_port != \'8080\':
                print \'tomcat 启动失败\'
            else:
                print \'tomcat 启动成功\'
        else:
            print \'8080端口正常\'
        time.sleep(5)
    except KeyboardInterrupt:
        sys.exit(\'out order\\n\')  

 

6. 科学计算，大数据，图形识别。。。  

　　看工作需要！

 

以下命令为反向kill某个端口的服务

# netstat -tunlp | grep \':8080\' | awk \'{split($7, arr, "/"); print(arr[1])}\' | kill -9