import os import json DIR = '/home/maxi/Projekt/wtc.waiswuaschd.de/data/extracted_texts' files = sorted(os.listdir(DIR)) for f in files: if f in ['Rezeptkarten.txt', 'ramen_rezepte.txt']: continue path = os.path.join(DIR, f) with open(path, 'r', encoding='utf-8', errors='ignore') as fp: txt = fp.read().strip() print(f"=== {f} ===") lines = [l.strip() for l in txt.split('\n') if l.strip()] print("\n".join(lines[:20])) print("\n--- LAST 10 LINES ---") print("\n".join(lines[-10:])) print("="*40)