8个Python实用脚本，赶紧收藏

脚本写的好，下班下得早！程序员的日常工作除了编写程序代码，还不可避免地需要处理相关的测试和验证工作。

例如，访问某个网站一直不通，需要确定此地址是否可访问，服务器返回什么，进而确定问题在于什么。完成这个任务，如果一味希望采用编译型语言来编写这样的代码，实践中的时间和精力是不够的，这个时候就需要发挥脚本的神奇作用！

这里还要注意：不管你是为了python就业还是兴趣爱好，记住：项目开发经验永远是核心，如果你没有2020最新python入门到高级实战视频教程，可以去小编的python交流.裙 ：七衣衣九七七巴而五（数字的谐音）转换下可以找到了，里面很多新python教程项目，还可以跟老司机交流讨教！

好不夸张的说，能否写出高效实用的脚本代码，直接影响着一个程序员的幸福生活[下班时间]。下面整理 8 个实用的 python 脚本，需要的时候改改直接用，建议收藏！

1.解决 linux 下 unzip 乱码的问题。

import os
import sys
import zipfile
import argparse

s = '\x1b[%d;%dm%s\x1b[0m'       

def unzip(path):

    file = zipfile.zipfile(path,"r")
    if args.secret:
        file.setpassword(args.secret)

    for name in file.namelist():
        try:
            utf8name=name.decode('gbk')
            pathname = os.path.dirname(utf8name)
        except:
            utf8name=name
            pathname = os.path.dirname(utf8name)

        #print s % (1, 92, '  >> extracting:'), utf8name
        #pathname = os.path.dirname(utf8name)
        if not os.path.exists(pathname) and pathname != "":
            os.makedirs(pathname)
        data = file.read(name)
        if not os.path.exists(utf8name):
            try:
                fo = open(utf8name, "w")
                fo.write(data)
                fo.close
            except:
                pass
    file.close()

def main(argv):
    ######################################################
    # for argparse
    p = argparse.argumentparser(description='解决unzip乱码')
    p.add_argument('xxx', type=str, nargs='*', \
        help='命令对象.')
    p.add_argument('-s', '--secret', action='store', \
        default=none, help='密码')
    global args
    args = p.parse_args(argv[1:])
    xxx = args.xxx

    for path in xxx:
        if path.endswith('.zip'):
            if os.path.exists(path):
                print s % (1, 97, '  ++ unzip:'), path
                unzip(path)
            else:
                print s % (1, 91, '  !! file doesn\'t exist.'), path
        else:
            print s % (1, 91, '  !! file isn\'t a zip file.'), path

if __name__ == '__main__':
    argv = sys.argv
    main(argv)
复制代码

2.统计当前根目录代码行数。

# coding=utf-8
import os
import time
# 设定根目录
basedir = './'
filelists = []
# 指定想要统计的文件类型
whitelist = ['cpp', 'h']
#遍历文件, 递归遍历文件夹中的所有
def getfile(basedir):
    global filelists
    for parent,dirnames,filenames in os.walk(basedir):
        for filename in filenames:
            ext = filename.split('.')[-1]
            #只统计指定的文件类型，略过一些log和cache文件
            if ext in whitelist:
                filelists.append(os.path.join(parent,filename))
#统计一个的行数
def countline(fname):
    count = 0
    # 把文件做二进制看待,read.
    for file_line in open(fname, 'rb').readlines():
        if file_line != '' and file_line != '\n': #过滤掉空行
            count += 1
    print (fname + '----' , count)
    return count
if __name__ == '__main__' :
    starttime = time.clock()
    getfile(basedir)
    totalline = 0
    for filelist in filelists:
        totalline = totalline + countline(filelist)
    print ('total lines:',totalline)
    print ('done! cost time: %0.2f second' % (time.clock() - starttime))
复制代码

3.扫描当前目录和所有子目录并显示大小。

import os
import sys      
try:
    directory = sys.argv[1]   
except indexerror:
    sys.exit("must provide an argument.")

dir_size = 0   
fsizedicr = {'bytes': 1,
             'kilobytes': float(1) / 1024,
             'megabytes': float(1) / (1024 * 1024),
             'gigabytes': float(1) / (1024 * 1024 * 1024)}
for (path, dirs, files) in os.walk(directory):      
    for file in files:                              
        filename = os.path.join(path, file)
        dir_size += os.path.getsize(filename)       

fsizelist = [str(round(fsizedicr[key] * dir_size, 2)) + " " + key for key in fsizedicr] 

if dir_size == 0: print ("file empty") 
else:
  for units in sorted(fsizelist)[::-1]: 
      print ("folder size: " + units)
复制代码

4.将源目录240天以上的所有文件移动到目标目录。

import shutil
import sys
import time
import os
import argparse

usage = 'python move_files_over_x_days.py -src [src] -dst [dst] -days [days]'
description = 'move files from src to dst if they are older than a certain number of days.  default is 240 days'

args_parser = argparse.argumentparser(usage=usage, description=description)
args_parser.add_argument('-src', '--src', type=str, nargs='?', default='.', help='(optional) directory where files will be moved from. defaults to current directory')
args_parser.add_argument('-dst', '--dst', type=str, nargs='?', required=true, help='(required) directory where files will be moved to.')
args_parser.add_argument('-days', '--days', type=int, nargs='?', default=240, help='(optional) days value specifies the minimum age of files to be moved. default is 240.')
args = args_parser.parse_args()

if args.days < 0:
	args.days = 0

src = args.src  # 设置源目录
dst = args.dst  # 设置目标目录
days = args.days # 设置天数
now = time.time()  # 获得当前时间

if not os.path.exists(dst):
	os.mkdir(dst)

for f in os.listdir(src):  # 遍历源目录所有文件
    if os.stat(f).st_mtime < now - days * 86400:  # 判断是否超过240天
        if os.path.isfile(f):  # 检查是否是文件
            shutil.move(f, dst)  # 移动文件
复制代码

5.扫描脚本目录，并给出不同类型脚本的计数。

import os																	
import shutil																
from time import strftime												

logsdir="c:\logs\puttylogs"											
zipdir="c:\logs\puttylogs\zipped_logs"							
zip_program="zip.exe"												

for files in os.listdir(logsdir):										
	if files.endswith(".log"):										
		files1=files+"."+strftime("%y-%m-%d")+".zip"		
		os.chdir(logsdir) 												
		os.system(zip_program + " " +  files1 +" "+ files)	
		shutil.move(files1, zipdir)									 
		os.remove(files)													
复制代码

6.下载leetcode的算法题。

import sys
import re
import os
import argparse
import requests
from lxml import html as lxml_html

try:
    import html
except importerror:
    import htmlparser
    html = htmlparser.htmlparser()

try:
    import cpickle as pk
except importerror:
    import pickle as pk

class leetcodeproblems(object):
    def get_problems_info(self):
        leetcode_url = 'https://leetcode.com/problemset/algorithms'
        res = requests.get(leetcode_url)
        if not res.ok:
            print('request error')
            sys.exit()
        cm = res.text
        cmt = cm.split('tbody>')[-2]
        indexs = re.findall(r'<td>(\d+)</td>', cmt)
        problem_urls = ['https://leetcode.com' + url \
                        for url in re.findall(
                            r'<a href="(/problems/.+?)"', cmt)]
        levels = re.findall(r"<td value='\d*'>(.+?)</td>", cmt)
        tinfos = zip(indexs, levels, problem_urls)
        assert (len(indexs) == len(problem_urls) == len(levels))
        infos = []
        for info in tinfos:
            res = requests.get(info[-1])
            if not res.ok:
                print('request error')
                sys.exit()
            tree = lxml_html.fromstring(res.text)
            title = tree.xpath('//meta[@property="og:title"]/@content')[0]
            description = tree.xpath('//meta[@property="description"]/@content')
            if not description:
                description = tree.xpath('//meta[@property="og:description"]/@content')[0]
            else:
                description = description[0]
            description = html.unescape(description.strip())
            tags = tree.xpath('//div[@id="tags"]/following::a[@class="btn btn-xs btn-primary"]/text()')
            infos.append(
                {
                    'title': title,
                    'level': info[1],
                    'index': int(info[0]),
                    'description': description,
                    'tags': tags
                }
            )

        with open('leecode_problems.pk', 'wb') as g:
            pk.dump(infos, g)
        return infos

    def to_text(self, pm_infos):
        if self.args.index:
            key = 'index'
        elif self.args.title:
            key = 'title'
        elif self.args.tag:
            key = 'tags'
        elif self.args.level:
            key = 'level'
        else:
            key = 'index'

        infos = sorted(pm_infos, key=lambda i: i[key])

        text_template = '## {index} - {title}\n' \
            '~{level}~  {tags}\n' \
            '{description}\n' + '\n' * self.args.line
        text = ''
        for info in infos:
            if self.args.rm_blank:
                info['description'] = re.sub(r'[\n\r]+', r'\n', info['description'])
            text += text_template.format(**info)

        with open('leecode problems.txt', 'w') as g:
            g.write(text)

    def run(self):
        if os.path.exists('leecode_problems.pk') and not self.args.redownload:
            with open('leecode_problems.pk', 'rb') as f:
                pm_infos = pk.load(f)
        else:
            pm_infos = self.get_problems_info()

        print('find %s problems.' % len(pm_infos))
        self.to_text(pm_infos)

def handle_args(argv):
    p = argparse.argumentparser(description='extract all leecode problems to location')
    p.add_argument('--index', action='store_true', help='sort by index')
    p.add_argument('--level', action='store_true', help='sort by level')
    p.add_argument('--tag', action='store_true', help='sort by tag')
    p.add_argument('--title', action='store_true', help='sort by title')
    p.add_argument('--rm_blank', action='store_true', help='remove blank')
    p.add_argument('--line', action='store', type=int, default=10, help='blank of two problems')
    p.add_argument('-r', '--redownload', action='store_true', help='redownload data')
    args = p.parse_args(argv[1:])
    return args

def main(argv):
    args = handle_args(argv)
    x = leetcodeproblems()
    x.args = args
    x.run()

if __name__ == '__main__':
    argv = sys.argv
    main(argv)
复制代码

7.将 markdown 转换为 html。

import sys
import os

from bs4 import beautifulsoup
import markdown

class markdowntohtml:

    headtag = '<head><meta charset="utf-8" /></head>'

    def __init__(self,cssfilepath = none):
        if cssfilepath != none:
            self.genstyle(cssfilepath)

    def genstyle(self,cssfilepath):
        with open(cssfilepath,'r') as f:
            cssstring = f.read()
        self.headtag = self.headtag[:-7] + '<style type="text/css">{}</style>'.format(cssstring) + self.headtag[-7:]

    def markdowntohtml(self, sourcefilepath, destinationdirectory = none, outputfilename = none):
        if not destinationdirectory:
            # 未定义输出目录则将源文件目录(注意要转换为绝对路径)作为输出目录
            destinationdirectory = os.path.dirname(os.path.abspath(sourcefilepath))
        if not outputfilename:
            # 未定义输出文件名则沿用输入文件名
            outputfilename = os.path.splitext(os.path.basename(sourcefilepath))[0] + '.html'
        if destinationdirectory[-1] != '/':
            destinationdirectory += '/'
        with open(sourcefilepath,'r', encoding='utf8') as f:
            markdowntext = f.read()
        # 编译出原始 html 文本
        rawhtml = self.headtag + markdown.markdown(markdowntext,output_format='html5')
        # 格式化 html 文本为可读性更强的格式
        beautifyhtml = beautifulsoup(rawhtml,'html5lib').prettify()
        with open(destinationdirectory + outputfilename, 'w', encoding='utf8') as f:
            f.write(beautifyhtml)

if __name__ == "__main__":
    mth = markdowntohtml()
    # 做一个命令行参数列表的浅拷贝，不包含脚本文件名
    argv = sys.argv[1:]
    # 目前列表 argv 可能包含源文件路径之外的元素（即选项信息）
    # 程序最后遍历列表 argv 进行编译 markdown 时，列表中的元素必须全部是源文件路径
    outputdirectory = none
    if '-s' in argv:
        cssargindex = argv.index('-s') +1
        cssfilepath = argv[cssargindex]
        # 检测样式表文件路径是否有效
        if not os.path.isfile(cssfilepath):
            print('invalid path: '+cssfilepath)
            sys.exit()
        mth.genstyle(cssfilepath)
        # pop 顺序不能随意变化
        argv.pop(cssargindex)
        argv.pop(cssargindex-1)
    if '-o' in argv:
        dirargindex = argv.index('-o') +1
        outputdirectory = argv[dirargindex]
        # 检测输出目录是否有效
        if not os.path.isdir(outputdirectory):
            print('invalid directory: ' + outputdirectory)
            sys.exit()
        # pop 顺序不能随意变化
        argv.pop(dirargindex)
        argv.pop(dirargindex-1)
    # 至此，列表 argv 中的元素均是源文件路径
    # 遍历所有源文件路径
    for filepath in argv:
        # 判断文件路径是否有效
        if os.path.isfile(filepath):
            mth.markdowntohtml(filepath, outputdirectory)
        else:
            print('invalid path: ' + filepath)
复制代码

8.文本文件编码检测与转换。

import sys
import os
import argparse
from chardet.universaldetector import universaldetector

parser = argparse.argumentparser(description = '文本文件编码检测与转换')
parser.add_argument('filepaths', nargs = '+',
                   help = '检测或转换的文件路径')
parser.add_argument('-e', '--encoding', nargs = '?', const = 'utf-8',
                   help = '''
目标编码。支持的编码有：
ascii, (default) utf-8 (with or without a bom), utf-16 (with a bom),
utf-32 (with a bom), big5, gb2312/gb18030, euc-tw, hz-gb-2312, iso-2022-cn, euc-jp, shift_jis, iso-2022-jp,
iso-2022-kr, koi8-r, maccyrillic, ibm855, ibm866, iso-8859-5, windows-1251, iso-8859-2, windows-1250, euc-kr,
iso-8859-5, windows-1251, iso-8859-1, windows-1252, iso-8859-7, windows-1253, iso-8859-8, windows-1255, tis-620
''')
parser.add_argument('-o', '--output',
                   help = '输出目录')
# 解析参数，得到一个 namespace 对象
args = parser.parse_args()
# 输出目录不为空即视为开启转换, 若未指定转换编码，则默认为 utf-8
if args.output != none:
    if not args.encoding:
        # 默认使用编码 utf-8
        args.encoding = 'utf-8'
    # 检测用户提供的输出目录是否有效
    if not os.path.isdir(args.output):
        print('invalid directory: ' + args.output)
        sys.exit()
    else:
        if args.output[-1] != '/':
            args.output += '/'
# 实例化一个通用检测器
detector = universaldetector()
print()
print('encoding (confidence)',':','file path')
for filepath in args.filepaths:
    # 检测文件路径是否有效，无效则跳过
    if not os.path.isfile(filepath):
        print('invalid path: ' + filepath)
        continue
    # 重置检测器
    detector.reset()
    # 以二进制模式读取文件
    for each in open(filepath, 'rb'):
        # 检测器读取数据
        detector.feed(each)
        # 若检测完成则跳出循环
        if detector.done:
            break
    # 关闭检测器
    detector.close()
    # 读取结果
    charencoding = detector.result['encoding']
    confidence = detector.result['confidence']
    # 打印信息
    if charencoding is none:
        charencoding = 'unknown'
        confidence = 0.99
    print('{} {:>12} : {}'.format(charencoding.rjust(8),
        '('+str(confidence*100)+'%)', filepath))
    if args.encoding and charencoding != 'unknown' and confidence > 0.6:
        # 若未设置输出目录则覆盖源文件
        outputpath = args.output + os.path.basename(filepath) if args.output else filepath
        with open(filepath, 'r', encoding = charencoding, errors = 'replace') as f:
            temp = f.read()
        with open(outputpath, 'w', encoding = args.encoding, errors = 'replace') as f:
            f.write(temp)

最后两个脚本内容选至实验楼的课程《使用 python3 编写系列实用脚本》课程对这两个脚本有详细的实现过程讲解，最后注意：不管你是为了python就业还是兴趣爱好，记住：项目开发经验永远是核心，如果你没有2020最新python入门到高级实战视频教程，可以去小编的python交流.裙 ：七衣衣九七七巴而五（数字的谐音）转换下可以找到了，里面很多新python教程项目，还可以跟老司机交流讨教！
本文的文字及图片来源于网络加上自己的想法,仅供学习、交流使用,不具有任何商业用途,版权归原作者所有,如有问题请及时联系我们以作处理。