Python For Me

#file io #file management functions classes / modules subprocess / os commands

json

useful standard libs retreive url parse html conda and envs eggs / wheels django databases fabric

exit()

Print and string concat:

x = 5
print("test "   str(x)) 
print("test", x) 

Split string:

a = x.splitlines()   # split string by lines

Sort a list:

sorted(a)

Lambda

• anonymous function
• assigned to a variable that can be passed around
• single expression
• takes args

# lambda args : expression

x = lambda a : a   5
print( x(3) )  

x = lambda a : "Value is: "   str(a * 2)
print(x(5))

Lambda to check if element in dict and return default value:

t = { "a": "test1", "b": "test2" }
b = lambda a,i : a[i] if i in a else "default"
b(t,"c")

Check length:

len(a)   # list length
type(a)  # check type

List comprehension:

newlist = [x for x in fruits if "a" in x]

Enumerate a list with index and value:

a = [ 'a', 'b', 'c' ]

for i in a:
    print(i)

for i,j in enumerate(a):
    print(i   " " j)

Initialize dict or list:

a = []
d = {}

Populate list with regex split:

a = re.split(",", "a,b,c,d,e,f,g")  # populate

List slicing:

a[-1]   # last element

a[2:7]      # 2-7  exclude last
a[2:7:2 ]   # 2-3, step 2, exclude last
a[7:2:-1 ]  # count backwards
a[:5]       # begin to 5
a[5:]       # 5 to end
a[:]        # entire list
a[::-1]     # reverse list

Sorting:

a.sort()    # sort in place
a.sort(reverse=True)
a.sort(key = str.lower)
a.reverse()

Sort with custom function:

def test1(x):
  return len(x)
a.sort(key=test1)

Check if exists in list:

if 5 in a:   

List operations:

a[3] = "x"           # assign value
a.insert(2, "abc")   # insert at index
a[1:3] = ["a", "b"]  # replace slice
a.append("x")        # append element
a.extend(a2)         # append list or any iterable
a = a   a2           # concatenate lists
a.append(a2)         # append entire list as a sublist 

a.remove("x")  # remove first match
a.pop()        # remove/return last
a.pop(5)      # remove/return at index
del a[3]       # delete
del a          # delete entire list
a.clear()      # empty the list

a.index("x")   # get index of first match
a.count("x")   # number of matches

a2 = a.copy() # copy list

Enumerate Dict / Hash:

d = {'a': 123, 'b': 456, 'c':789, 'd': 000}


for i, k in enumerate(d):     # index and key
    print(i, k)

for i, (k, v) in enumerate(d.items()):
    print(i, k, v)

with open("data1.txt") as f1:
    data1 = f1.readlines()

with open("data1.txt") as f1:
    data1 = f1.read()

data1 = [ x.strip() for x in data1 ]     # strip newline and padding

Globbing:

import glob
a = glob.glob('*.txt')
for i in a:
    print(i)

File Management

import os                  # OS module
import shutil              # Some utils
shutil.copy(src, dst)      # Copy file
os.rename(src, dst)        # rename file
os.unlink("/tmp/foo.txt")  # delete file
os.listdir("/dir")         # List files
os.mkdir(path[, mode])     # Create directory
shutil.copy(src, dst)      # copy content and permission
os.rmdir(path)             # remove dir, only empty dirs
os.removedirs(path)        # remove empty dir, recursive

File IO

‘r’ - read - default ‘w’ - write ‘rb’ - read binary ‘wb’ - write binary ‘a’ - append ‘a ‘ - append but also read and seek backwards but always write to end

f = open('workfile', 'w')    # r or w
f.write('This is a test\n')  # write
f.read()                     # entire file
f.readline()                 # line at a time
f.readlines()                # entire file, as list
f.close()                    # close it

Get home dir:

import os
print(os.path.expanduser('~'))

from pathlib import Path
print(Path.home())

=========================================

Regular Expressions Characters

\d decimal digit [0-9] \s whitespace [ \t\n\r\f\v] \w alphanumeric [a-zA-Z0-9_] \D non decimal \S non whitespace \W non-alphanumeric probably more ….. ^ start $ end . any character except newline

• 0 or more 1 or more ? 0 or 1 {0,1}

Flags

re.S Make . match any char, including newlines re.I Do case-insensitive matches re.M Multi-line matching, affecting ^ and $

import re

m = re.match(r'cups', data1)   # first match, check BEGINNING, ret: match obj or null
m = re.search(r'cups', data1)  # first match, check all lines, ret: match obj or null

m = re.search(r'((sys)t)(emd)', data1)   # using separate and nested groups

m.group()   # match found    - first match
m.groups()  # groups if using grouping - from first match


m = re.findall(r'systemd', data1)      # find all matches, return list of matched strings 
m = re.findall(r'((sys)temd)', data1)  # find all matches, return groups as list of tuples, NOT matched strings
                                       # need more than one group

print(m)

a = re.split(r'\s', data1)     # split into list ( ex: by space )      
a = re.split(r'\W ', data1)    # split out list of words      

x = re.sub( r'xxxx', 'abc', 'xxxx  xxxx') 

x = re.sub( r'(blue|white|red)', 'colour', 'blue socks and red shoes')
x = re.sub( r'xxxx', '5', 'process_data.sh  input_xxxx.dat  output_xxxx.dat')

# check if match found:

if m:
    print 'Match found: ', m.group()

# compile first for efficiency ( if you plan to loop / iterate a lot ):

p = re.compile(r”match this”)     
m = p.search('string goes here')
a = p.split('test test')  
x = p.sub( 'colour', 'blue socks and red shoes')


p = re.compile('ab*', re.I | re.M)       # case insensitive, multi-line

Function:

def function1(one, two='Yes', *name2, **name3):           
    return value

Subprocess / OS Commands:

https://www.datacamp.com/tutorial/python-subprocess <==== review more

import subprocess

subprocess.check_output( "uname -a", stderr=subprocess.STDOUT, shell=True )

subprocess.run(["ls", "-l"]) 

cmd1 = "ls -l /tmp | awk '{print $2,$4}'"

x = subprocess.run(cmd1, shell=True)
x = subprocess.run(cmd1, shell=True, capture_output=True, text=True)

check # raise error on non-zero timeout # specify timeout

x.returncode
x.args
x.stdout
x.stderr

JSON

import json

x =  '{ "name":"John", "age":30, "city":"New York"}'
y = json.loads(x)               # string to object
print(y["age"])

x = {
  "name": "John",
  "age": 30,
  "city": "New York"
}


y = json.dumps(x)               # object to string
print(y)

Error Handling - Try / Except

if x < 0:
  raise Exception("Sorry, no numbers below zero")

if not type(x) is int:
  raise TypeError("Only integers are allowed")

try:
  print(x)
except NameError:
  print("Variable x is not defined")
except:
  print("Something else went wrong")

try:
  print("Hello")
except:
  print("Something went wrong")
else:
  print("Nothing went wrong")

try:
  print(x)
except:
  print("Something went wrong")
finally:
  print("The 'try except' is finished")

nesting:

try:
  f = open("demofile.txt")
  try:
    f.write("Lorum Ipsum")
  except:
    print("Something went wrong when writing to the file")
  finally:
    f.close()
except:
  print("Something went wrong when opening the file")

input

# python 3.6
username = input("Enter username:")
print("Username is: "   username)

# python 2.7
username = raw_input("Enter username:")
print("Username is: "   username)

Args:

import sys

print( sys.argv[0] )        # current script
if len(sys.argv) >= 1:
    print( sys.argv[1] )    # first arg

CSV:

https://realpython.com/python-csv/

More

Check if object has an attribute:

if hasattr(instance, 'tags'):
    ....

Show type:

print(type(instance.tags))

Show members of a class:

print(instance.__dict__