Remove all traces of emoji from a text file.

remove-emoji.py

#!/usr/bin/env python
"""
Remove emoji from a text file and print it to stdout.

Note: doesn't catch certain things that are counted as emoji by e.g. Facebook, like 2⃣.

Usage
-----
    python remove-emoji.py input.txt > output.txt
"""
import re
import sys

# https://stackoverflow.com/a/49146722/330558
def remove_emoji(string):
    emoji_pattern = re.compile("["
                               u"\U0001F600-\U0001F64F"  # emoticons
                               u"\U0001F300-\U0001F5FF"  # symbols & pictographs
                               u"\U0001F680-\U0001F6FF"  # transport & map symbols
                               u"\U0001F1E0-\U0001F1FF"  # flags (iOS)
                               u"\U00002500-\U00002BEF"  # chinese char
                               u"\U00002702-\U000027B0"
                               u"\U00002702-\U000027B0"
                               u"\U000024C2-\U0001F251"
                               u"\U0001f926-\U0001f937"
                               u"\U00010000-\U0010ffff"
                               u"\u2640-\u2642"
                               u"\u2600-\u2B55"
                               u"\u200d"
                               u"\u23cf"
                               u"\u23e9"
                               u"\u231a"
                               u"\ufe0f"  # dingbats
                               u"\u3030"
                               "]+", flags=re.UNICODE)
    stripped = emoji_pattern.sub(r'', string)
    return re.sub(r'([\w\d])\s+(\W)', r'\1\2', stripped)

if __name__ == '__main__':
    text = open(sys.argv[1]).read()
    text = remove_emoji(text)
    print(text)