for work_path in work_dir.iterdir(): if work_path.is_dir(): metadata_file = work_path / 'metadata.json' if metadata_file.exists(): with open(metadata_file, 'r', encoding='utf-8') as f: metadata = json.load(f) works.append({ 'work_id': metadata['work_id'], 'title': metadata['title'], 'author': metadata['author'], 'word_count': metadata['word_count'], 'chapters': metadata['chapters'], 'kudos': metadata['kudos'] })
html_path = work_path / 'work.html' if html_path.exists(): with open(html_path, 'r', encoding='utf-8') as f: content = f.read() else: content = "<p>Content not available</p>" ao3 mirror
if format == 'epub': file_path = work_path / 'work.epub' mime_type = 'application/epub+zip' elif format == 'txt': file_path = work_path / 'work.txt' mime_type = 'text/plain' else: file_path = work_path / 'work.html' mime_type = 'text/html' for work_path in work_dir
def _extract_work_id(self, url: str) -> str: """Extract work ID from AO3 URL""" import re match = re.search(r'/works/(\d+)', url) if match: return match.group(1) raise ValueError("Invalid AO3 work URL") Content not available<