This script for removing mojibake characters from a json

json_mojibake_fixer.py

import json
from ftfy import fix_text

def fix_obj(o):
    if isinstance(o, str):
        return fix_text(o)
    if isinstance(o, list):
        return [fix_obj(x) for x in o]
    if isinstance(o, dict):
        return {k: fix_obj(v) for k,v in o.items()}
    return o

with open('data.json', 'r', encoding='utf-8', errors='replace') as f:
    data = json.load(f)

fixed = fix_obj(data)

with open('data_fixed.json', 'w', encoding='utf-8') as f:
    json.dump(fixed, f, ensure_ascii=False, indent=2)

print("✅ Written data_fixed.json (ftfy).")