extract_emojis_v2.py

extract_emojis_v2.py

#!/usr/bin/env python3
import re
import sys
import textwrap

# Regex covering most emoji ranges
emoji_pattern = re.compile(
    "[\U0001F600-\U0001F64F"  # Emoticons
    "\U0001F300-\U0001F5FF"  # Symbols & pictographs
    "\U0001F680-\U0001F6FF"  # Transport & map symbols
    "\U0001F700-\U0001F77F"  # Alchemical symbols
    "\U0001F780-\U0001F7FF"  # Geometric shapes extended
    "\U0001F800-\U0001F8FF"  # Supplemental arrows
    "\U0001F900-\U0001F9FF"  # Supplemental symbols & pictographs
    "\U0001FA00-\U0001FA6F"  # Chess, symbols
    "\U0001FA70-\U0001FAFF"  # Symbols & pictographs extended-A
    "\u2702-\u27B0"          # Dingbats
    "\u24C2-\U0001F251"      # Enclosed characters
    "]+", flags=re.UNICODE)

def extract_emojis(filename):
    with open(filename, "r", encoding="utf-8", errors="ignore") as f:
        text = f.read()
    return emoji_pattern.findall(text)

if __name__ == "__main__":
    if len(sys.argv) < 2:
        print(f"Usage: {sys.argv[0]} <logfile>")
        sys.exit(1)

    emojis = "".join(extract_emojis(sys.argv[1]))
    wrapped = textwrap.fill(emojis, width=80)
    print(wrapped)