Code extractor

e.py

#!/usr/bin/python3
# -*- coding: utf-8 -*-
# Usage: rm -f a.out && chmod +x e.py && ./e.py i.txt > m.cpp && clang++ -Wall -Wextra -pedantic-errors -fsanitize=address -fsanitize=undefined -fno-sanitize-recover=all m.cpp && ./a.out && echo ""

# Import regex module
import re
# Import html module
import html
# Import sys module
import sys
# Import os module
import os

# Define function to extract the string
def extract(string):
    # Insert new lines
    string = string.replace(r'<pre class=" CodeMirror-line " role="presentation">', '\n')
    # Use regex to extract the string and join to string
    regexList = re.findall(r'(?<=>)([^<]+)(?=<)(?!<\/div)', string)
    string = ''.join(regexList)
    # Replace all occurrences in string of '\u200b' with ''
    string = string.replace('\u200b', '')
    # Unescape
    return html.unescape(string)

# Check the number of arguments
if len(sys.argv) != 2:
    # Print error message
    print("Usage: " + os.path.basename(__file__) + " <input file>")
    sys.exit(0)

# Get the current working directory

inputFile=sys.argv[1]
# Check if inputFile starts with a slash in python
if inputFile[0] != '/':
    # Convert to absolute path
    inputFile = os.path.abspath(inputFile)

# Check if second argument is a file
if not os.path.isfile(inputFile):
    sys.exit("Error: Not a file")

# Open and read
with open(inputFile, 'r') as f:
    input = f.read()

# Extract
string = extract(input)
# Print the extracted string
print(string)