# -*- coding: utf-8 -*- import re def normalize_file(path): with open(path, 'rb') as f: raw = f.read() text = raw.decode('utf-8', errors='ignore') while text.startswith('\ufeff'): text = text[1:] text = text.replace('\r\n', '\n').replace('\r', '\n') lines = [l.rstrip() for l in text.split('\n')] clean_lines = [] prev_blank = False for l in lines: if l == '': if not prev_blank: clean_lines.append(l) prev_blank = True else: clean_lines.append(l) prev_blank = False while clean_lines and clean_lines[-1] == '': clean_lines.pop() final_text = '\r\n'.join(clean_lines) + '\r\n' with open(path, 'wb') as f: f.write(b'\xef\xbb\xbf' + final_text.encode('utf-8')) print(f"Normalized {path}") def update_dungeon_entry_contains(keyword, url): path_idx = 'dungeons/index.html' with open(path_idx, 'rb') as f: c = f.read().decode('utf-8', errors='ignore') if f'href="{url}"' not in c: c = c.replace('\r\n', '\n') pattern = rf'(