from html import escape from pathlib import Path source = Path('dokumen/Laporan_FS_CMU_GoogleDocs_Rapih.md') out_dir = Path('html') out_file = out_dir / 'bab-02-gambaran-umum-dan-analisis-situasi-eksternal.html' text = source.read_text(encoding='utf-8') lines = text.splitlines() start = None end = None for i, line in enumerate(lines): if line.strip() == 'BAB 2 GAMBARAN UMUM DAN ANALISIS SITUASI EKSTERNAL': # Use second occurrence after daftar isi; first content occurrence has following 2.1 body. if i + 2 < len(lines) and lines[i + 2].strip().startswith('2.1 '): start = i break if start is None: raise SystemExit('BAB 2 content not found') for i in range(start + 1, len(lines)): if lines[i].strip().startswith('BAB 3 '): end = i break if end is None: end = len(lines) chapter_lines = lines[start:end] body = [] i = 0 while i < len(chapter_lines): stripped = chapter_lines[i].strip() if not stripped: i += 1 continue if stripped.startswith('|') and '|' in stripped[1:]: rows = [] while i < len(chapter_lines) and chapter_lines[i].strip().startswith('|'): row = [c.strip() for c in chapter_lines[i].strip().strip('|').split('|')] is_separator = all(set(c.replace(':', '').replace('-', '').strip()) == set() for c in row) if not is_separator: rows.append(row) i += 1 if rows: body.append('
') for r, row in enumerate(rows): tag = 'th' if r == 0 else 'td' body.append('' + ''.join(f'<{tag}>{escape(c)}' for c in row) + '') body.append('
') continue if stripped.startswith('BAB 2'): body.append(f'

{escape(stripped)}

') elif stripped.startswith('Tabel '): body.append(f'

{escape(stripped)}

') elif stripped[:3].count('.') == 1 and stripped[0].isdigit() and ' ' in stripped: body.append(f'

{escape(stripped)}

') elif stripped[:5].count('.') >= 2 and stripped[0].isdigit() and ' ' in stripped: body.append(f'

{escape(stripped)}

') else: body.append(f'

{escape(stripped)}

') i += 1 html = ''' BAB 2 - Gambaran Umum dan Analisis Situasi Eksternal
Laporan Studi Kelayakan CMU RSUD KH Ahmad Hanafiah
''' + '\n'.join(body) + '''
File HTML ini fokus untuk pengembangan BAB 2. Sumber konten: dokumen/Laporan_FS_CMU_GoogleDocs_Rapih.md.
''' out_dir.mkdir(exist_ok=True) out_file.write_text(html, encoding='utf-8') print(out_file)