Count duplicates (2023 version)

countduplicates.py

#!/usr/bin/env python3

import collections
import subprocess
import re

theFinal = ""

def getClipboardData():
 p = subprocess.Popen(['pbpaste'], stdout=subprocess.PIPE)
 retcode = p.wait()
 data = p.stdout.read()
 return data

def setClipboardData(data):
 p = subprocess.Popen(['pbcopy'], stdin=subprocess.PIPE)
 p.stdin.write(data)
 p.stdin.close()
 retcode = p.wait()

cd = getClipboardData()
results = cd.decode("utf-8")
results = results.title()
# this first regex normalizes line endings, thanks Excel
results = re.sub(r'\r\n', '\n', results)
results = re.sub(r'\([^)]+\)', '', results)
results = re.sub(r'\n\n', '\n', results)
results = re.sub(r'\nThe ?', '\n', results)
results = re.sub(r'\s+\n', '\n', results)
results = re.sub(r':', '', results)

theResults = results.splitlines(True)

c = collections.Counter(theResults)

# sorted by value (number of occurences, but descending order)
for k, v in c.most_common():
    theFinal += (f'{k[:-1]}\t{v}\n')
    
setClipboardData(str.encode(theFinal))