""" build_course_map.py Lee course_content.json y extrae de los filenames de S3: - Titulo real de cada leccion (del nombre del audio) - Capitulo y numero de historia - Titulo de seccion correcto Genera course_map.json listo para importar a la DB. """ import json import re import sys import urllib.parse from pathlib import Path sys.stdout.reconfigure(encoding="utf-8") SCRIPTS_DIR = Path(__file__).parent CONTENT_FILE = SCRIPTS_DIR / "course_content.json" MAP_FILE = SCRIPTS_DIR / "course_map.json" # Lecciones especiales conocidas (de la DB actual) KNOWN_LESSONS = { 1: {"title": "Introducción a RAIO", "section": "Comienza aquí", "section_order": 1}, 2: {"title": "PORTUGUÊS - Perguntas Frecuentes", "section": "Comienza aquí", "section_order": 1}, } def parse_s3_audio_name(url: str) -> dict | None: """ Extrae chapter, story y topic del filename S3. Patron principal: Chapter X - Story Y - Topic Name - Normal/Interactive version.mp3 Patrones alternativos para Chapter 3 y bonus stories. """ try: path = urllib.parse.unquote_plus(urllib.parse.urlparse(url).path) stem = Path(path).stem # sin extension # 1) Patron principal: "Chapter 1 - Story 1 - Presenting yourself - Normal version" m = re.match( r'Chapter\s+(\d+)\s*[-–]\s*Story\s+(\d+)\s*[-–]\s*(.+?)\s*[-–]\s*(Normal|Interactive)', stem, re.I ) if m: return { "chapter": int(m.group(1)), "story": int(m.group(2)), "topic": m.group(3).strip().title(), } # 2) Chapter 3 sin dash antes de Normal/Interactive: # "Chapter 3 - Story 9 - Culture Normal" / "Chapter 3 - Story 1 - Presenting Yourself" m2 = re.match( r'Chapter\s+(\d+)\s*[-–]\s*Story\s+(\d+)\s*[-–]\s*(.+)', stem, re.I ) if m2: topic_raw = m2.group(3).strip() # Strip trailing Normal/Interactive/mp3/version noise topic_clean = re.sub( r'\s*[-–]?\s*(Normal|Interactive|mp3|version)\s*\.?\s*$', '', topic_raw, flags=re.I ).strip() if topic_clean: return { "chapter": int(m2.group(1)), "story": int(m2.group(2)), "topic": topic_clean.title(), } # 3) Bonus stories: "funny-chapter1-normal", "drama-chapter2-interactive" m3 = re.match( r'^(funny|drama|motivation|psycho|dates)-chapter(\d+)-(normal|interactive)', stem, re.I ) if m3: genre_map = { "funny": "Funny Story", "drama": "Drama Story", "motivation": "Motivation Story", "psycho": "Psychology Story", "dates": "Dates Story", } genre = genre_map.get(m3.group(1).lower(), m3.group(1).title()) return { "chapter": int(m3.group(2)), "story": None, "topic": genre, } # 4) Sin "Story N": "Chapter 2 - Topic - Normal" m4 = re.match( r'Chapter\s+(\d+)\s*[-–]\s*(.+?)\s*[-–]\s*(Normal|Interactive)', stem, re.I ) if m4: return { "chapter": int(m4.group(1)), "story": None, "topic": m4.group(2).strip().title(), } except Exception: pass return None def section_title(chapter: int) -> str: labels = { 1: "Capítulo 1: Historias Interactivas [Yes/No]", 2: "Capítulo 2: Historias Interactivas [Open-Ended]", 3: "Capítulo 3: Conversaciones Avanzadas", 4: "Capítulo 4: Situaciones Reales", 5: "Capítulo 5: Fluencia y Práctica", } return labels.get(chapter, f"Capítulo {chapter}") def main(): if not CONTENT_FILE.exists(): print("No encontre course_content.json. Ejecuta primero scrape_content.py") sys.exit(1) lessons = json.loads(CONTENT_FILE.read_text(encoding="utf-8")) print(f"Procesando {len(lessons)} lecciones...") mapped = [] unknown_titles = 0 for lesson in lessons: num = lesson["num"] audio_urls = lesson.get("audio_urls", []) doc_urls = lesson.get("doc_urls", []) # Usar leccion conocida si existe if num in KNOWN_LESSONS: info = KNOWN_LESSONS[num] mapped.append({ "num": num, "title": info["title"], "section_title": info["section"], "section_order": info["section_order"], "chapter": None, "story": None, "vidalytics_id": lesson.get("vidalytics_id"), "stream_url": lesson.get("stream_url"), "audio_urls": audio_urls, "doc_urls": doc_urls, "notes": lesson.get("notes", ""), "subtitle_en": lesson.get("subtitle_en"), "subtitle_es": lesson.get("subtitle_es"), }) continue # Intentar extraer titulo del filename del audio parsed = None for audio in audio_urls: url = audio.get("url", "") if "normal" in url.lower(): # prioritize "Normal version" parsed = parse_s3_audio_name(url) if parsed: break if not parsed: for audio in audio_urls: parsed = parse_s3_audio_name(audio.get("url", "")) if parsed: break if parsed: title = parsed["topic"] chapter = parsed["chapter"] story = parsed["story"] sect_title = section_title(chapter) sect_order = chapter + 1 # Comienza aqui = order 1, Cap1 = 2, etc. else: # Sin audio — lecciones de reglas, bonus, etc. raw = lesson.get("title", "") bad = {"importante", "working...", "working", "loading"} title = raw if raw.lower() not in bad else f"Lección {num}" chapter = None story = None # Asignar seccion por posicion numerica cuando no hay audio if num <= 2: sect_title = "Comienza aquí" sect_order = 1 elif num <= 37: sect_title = section_title(1) sect_order = 2 chapter = 1 elif num <= 72: sect_title = section_title(2) sect_order = 3 chapter = 2 elif num <= 95: sect_title = section_title(3) sect_order = 4 chapter = 3 else: sect_title = "Contenido Extra" sect_order = 99 unknown_titles += 1 mapped.append({ "num": num, "title": title, "section_title": sect_title, "section_order": sect_order, "chapter": chapter, "story": story, "vidalytics_id": lesson.get("vidalytics_id"), "stream_url": lesson.get("stream_url"), "audio_urls": audio_urls, "doc_urls": doc_urls, "notes": lesson.get("notes", ""), "subtitle_en": lesson.get("subtitle_en"), "subtitle_es": lesson.get("subtitle_es"), }) MAP_FILE.write_text( json.dumps(mapped, ensure_ascii=False, indent=2), encoding="utf-8" ) # Estadisticas chapters = {} for l in mapped: c = l["chapter"] or 0 chapters[c] = chapters.get(c, 0) + 1 print(f"\nResultado -> {MAP_FILE.name}") for c in sorted(chapters): label = "Intro/Especiales" if c == 0 else f"Capítulo {c}" print(f" {label}: {chapters[c]} lecciones") print(f"\nTitulos sin audio: {unknown_titles}") print(f"Total: {len(mapped)} lecciones") if __name__ == "__main__": main()