12 Essential Python Programming Basics: Regular Expressions, Directory Traversal, List Sorting, Deduplication, Dictionary Sorting, Data Conversion, Time Operations, Command‑Line Parsing, Print Formatting, Base Conversion, System Commands, Signal Handling, and File I/O

1. Regular Expression Replacement

>> line = ' ' >> mo = re.compile(r'(?<=SRC)"([\w+\.]+)"', re.I) >> mo.sub(r'"\1****"', line) ' ' >> mo.sub(r'replace_str_\1', line) ' ' >> mo.sub(r'"testetstset"', line) ' '

Note: \1 refers to the captured group.

2. Directory Traversal

import os fileList = [] rootdir = "/data" for root, subFolders, files in os.walk(rootdir): if '.svn' in subFolders: subFolders.remove('.svn') # exclude specific dirs for file in files: if file.find('.t2t') != -1: # find files with .t2t extension file_dir_path = os.path.join(root, file) fileList.append(file_dir_path) print fileList

3. List Sorting by Column

>> a = [('2011-03-17', '2.26', 6429600, '0.0'), ('2011-03-16', '2.26', 12036900, '-3.0'), ('2011-03-15', '2.33', 15615500, '-19.1')] >> b = sorted(a, key=lambda result: result[1], reverse=True) >> print b [('2011-03-15', '2.33', 15615500, '-19.1'), ('2011-03-17', '2.26', 6429600, '0.0'), ('2011-03-16', '2.26', 12036900, '-3.0')] >> c = sorted(a, key=lambda result: result[2], reverse=True) >> print c [('2011-03-15', '2.33', 15615500, '-19.1'), ('2011-03-16', '2.26', 12036900, '-3.0'), ('2011-03-17', '2.26', 6429600, '0.0')]

4. List Deduplication

>> lst = [(1,'sss'), (2,'fsdf'), (1,'sss'), (3,'fd')] >> set(lst) set([(2, 'fsdf'), (3, 'fd'), (1, 'sss')]) >> lst = [1, 1, 3, 4, 4, 5, 6, 7, 6] >> set(lst) set([1, 3, 4, 5, 6, 7])

5. Dictionary Sorting by Value

>> from operator import itemgetter >> aa = {"a":"1", "sss":"2", "ffdf":"5", "ffff2":"3"} >> sort_aa = sorted(aa.items(), key=itemgetter(1)) >> sort_aa [('a', '1'), ('sss', '2'), ('ffff2', '3'), ('ffdf', '5')]

6. Conversions Between Dictionary, List, and String

>> params = {"server":"mpilgrim", "database":"master", "uid":"sa", "pwd":"secret"} >> ["%s=%s" % (k, v) for k, v in params.items()] ['server=mpilgrim', 'uid=sa', 'database=master', 'pwd=secret'] >> ";".join(["%s=%s" % (k, v) for k, v in params.items()]) 'server=mpilgrim;uid=sa;database=master;pwd=secret' >> a = 'server=mpilgrim;uid=sa;database=master;pwd=secret' >> aa = {} >> for i in a.split(';'): aa[i.split('=',1)[0]] = i.split('=',1)[1] >> aa {'pwd': 'secret', 'database': 'master', 'uid': 'sa', 'server': 'mpilgrim'}

7. Time Object Operations

>> import datetime >> datetime.datetime.now().strftime("%Y-%m-%d %H:%M") '2011-01-20 14:05' >> import time >> t1 = time.strptime('2011-01-20 14:05', "%Y-%m-%d %H:%M") >> t2 = time.strptime('2011-01-20 16:05', "%Y-%m-%d %H:%M") >> t1 > t2 False >> t1 < t2 True >> a = 1302153828 >> time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(a)) '2011-04-07 13:23:48'

8. Command‑Line Argument Parsing with getopt

#!/usr/bin/env python # -*- coding: utf-8 -*- import sys, os, getopt def usage(): print '''Usage: analyse_stock.py [options...] Options: -e : Exchange Name -c : User‑Defined Category Name -f : Read stock info from file and save to db -d : delete from db by stock code -n : stock name -s : stock code -h : this help info test.py -s haha -n "HA Ha" try: opts, args = getopt.getopt(sys.argv[1:], 'he:c:f:d:n:s:') except getopt.GetoptError: usage(); sys.exit() if len(opts) == 0: usage(); sys.exit() for opt, arg in opts: if opt in ('-h', '--help'): usage(); sys.exit() elif opt == '-d': print "del stock %s" % arg elif opt == '-f': print "read file %s" % arg elif opt == '-c': print "user-defined %s " % arg elif opt == '-e': print "Exchange Name %s" % arg elif opt == '-s': print "Stock code %s" % arg elif opt == '-n': print "Stock name %s" % arg

9. Print Formatting

9.1 Formatting strings

str = "abcdefg" print "%.3s" % str abc print "%10s" % str abcdefg print "%10.3s" % str abc

9.2 Base conversion

>> num = 10 >> print "Hex = %x, Dec = %d, Oct = %o" % (num, num, num) Hex = a, Dec = 10, Oct = 12

10. Executing System Commands from Python

>> import os >> os.system('ls -l /proc/cpuinfo') 0 >> out = os.popen('ls -l /proc/cpuinfo') >> print out.read() >> import commands >> commands.getstatusoutput('ls /bin/ls') (0, '/bin/ls')

11. Capturing Ctrl+C and Ctrl+D Signals

try: do_some_func() except KeyboardInterrupt: print "User Press Ctrl+C, Exit" except EOFError: print "User Press Ctrl+D, Exit"

12. Reading and Writing Files

# Fast way – read whole file into a list track_file = "track_stock.conf" fd = open(track_file) content_list = fd.readlines() fd.close() for line in content_list: print line # Line‑by‑line – suitable for large files fd = open(file_path) fd.seek(0) title = fd.readline() keyword = fd.readline() uuid = fd.readline() fd.close() # Writing – write vs writelines fd.write(str) # no newline added fd.writelines(content) # writes the iterable as‑is