feat(wistia): add subtitle download support

.env.example

@@ -61,6 +61,9 @@ RESUME_PARTIAL=true
 # Enable detailed logging for troubleshooting
 DEBUG=false
 
+# Download subtitles/captions when available (default: true)
+SUBTITLE_DOWNLOAD_ENABLED=true
+
 # ===============================================
 # ADVANCED SETTINGS
 # ===============================================
@@ -83,4 +86,4 @@ COURSE_DATA_FILE=""
 # ALL_VIDEO_FORMATS=false
 
 # Log level (DEBUG, INFO, WARNING, ERROR)
-# LOG_LEVEL="INFO"
+# LOG_LEVEL="INFO"

README.md

@@ -52,6 +52,7 @@ A modern, feature-rich Python utility to download courses from Thinkific platfor
 | 📄 **HTML Content** | ✅ Full | `downloader.py` | Clean extraction, formatting |
 | 📚 **PDF Documents** | ✅ Full | `downloader.py` | Direct download, validation |
 | 🎵 **Audio Files** | ✅ Full | `downloader.py` | MP3, M4A support |
+| 📝 **Subtitles (Wistia)** | ✅ Full | `wistia_downloader.py` | Multi-language caption downloads |
 | 🎯 **Quizzes** | ✅ Basic | `downloader.py` | Structure extraction |
 | 🎨 **Presentations** | ✅ Full | FFmpeg merge | Multi-slide processing |
 
@@ -70,6 +71,7 @@ A modern, feature-rich Python utility to download courses from Thinkific platfor
 - **Resume Support** - Skip existing files, continue interrupted downloads
 - **Atomic Resume/Backup** - Status file is always safely backed up and updated, works on Windows, Mac, Linux
 - **Multiple Quality Options** - Choose video quality (720p, 1080p, etc.)
+- **Subtitle Downloads** - Automatically grab Wistia caption tracks in multiple languages
 - **Comprehensive Logging** - Debug mode for troubleshooting
 
 ### 🛡️ **Safety & Compliance**
@@ -201,6 +203,7 @@ RATE_LIMIT_MB_S=            # Rate limit in MB/s (empty = unlimited)
 VALIDATE_DOWNLOADS=true     # Enable file integrity validation
 RESUME_PARTIAL=true         # Enable resume for partial downloads
 DEBUG=false                 # Enable debug logging
+SUBTITLE_DOWNLOAD_ENABLED=true # Download subtitles/captions when available
 
 # ===============================================
 # ADVANCED SETTINGS

thinkific_downloader/config.py

@@ -37,6 +37,7 @@ class Settings:
     resume_partial: bool = True
     debug: bool = False
     course_name: str = "Course"
+    subtitle_download_enabled: bool = True
 
     @classmethod
     def from_env(cls):
@@ -67,6 +68,7 @@ def from_env(cls):
         validate_downloads = os.getenv('VALIDATE_DOWNLOADS', 'true').lower() in ('1', 'true', 'yes', 'on')
         resume_partial = os.getenv('RESUME_PARTIAL', 'true').lower() in ('1', 'true', 'yes', 'on')
         debug = os.getenv('DEBUG', 'false').lower() in ('1', 'true', 'yes', 'on')
+        subtitle_download_enabled = os.getenv('SUBTITLE_DOWNLOAD_ENABLED', 'true').lower() in ('1', 'true', 'yes', 'on')
 
         # Clean cookie data to remove Unicode characters that cause encoding issues
         if cookie_data:
@@ -101,5 +103,6 @@ def from_env(cls):
             download_delay=download_delay,
             validate_downloads=validate_downloads,
             resume_partial=resume_partial,
-            debug=debug
+            debug=debug,
+            subtitle_download_enabled=subtitle_download_enabled
         )

thinkific_downloader/downloader.py

@@ -382,10 +382,77 @@ def download_file_chunked(src_url: str, dst_name: str, chunk_mb: int = 1):
     add_download_task(src_url, dst_path, "file")
 
 
+def _load_cached_progress(cache_file: Path):
+    """Return previously analyzed chapters and queued tasks from the resume cache."""
+    analyzed_chapters = set()
+    saved_tasks: List[Dict[str, Any]] = []
+
+    if not cache_file.exists():
+        return analyzed_chapters, saved_tasks
+
+    try:
+        with open(cache_file, 'r', encoding='utf-8') as f:
+            cache_data = json.load(f)
+
+        analyzed_chapters = set(cache_data.get('analyzed_chapters', []))
+        saved_tasks = cache_data.get('download_tasks', [])
+        print(f"📋 Found previous progress: {len(analyzed_chapters)} chapters analyzed, {len(saved_tasks)} tasks cached")
+
+        # If subtitle downloads were newly enabled, invalidate cache so we can regenerate tasks.
+        if SETTINGS and SETTINGS.subtitle_download_enabled and saved_tasks:
+            has_subtitle_tasks = any(
+                (task.get('content_type') or '').lower() == 'subtitle'
+                for task in saved_tasks
+            )
+            if not has_subtitle_tasks:
+                print("🆕 Subtitle support enabled — refreshing cached analysis to include captions.")
+                analyzed_chapters = set()
+                saved_tasks = []
+                try:
+                    cache_file.unlink()
+                except OSError:
+                    pass
+    except (json.JSONDecodeError, OSError):
+        analyzed_chapters = set()
+        saved_tasks = []
+
+    return analyzed_chapters, saved_tasks
+
+
+def _restore_saved_tasks(saved_tasks: List[Dict[str, Any]]):
+    """Restore cached download tasks, respecting the subtitle feature flag."""
+    if not saved_tasks:
+        return
+
+    restored_tasks = saved_tasks
+    if SETTINGS and hasattr(SETTINGS, 'subtitle_download_enabled') and not SETTINGS.subtitle_download_enabled:
+        filtered_tasks: List[Dict[str, Any]] = []
+        skipped_count = 0
+        for task in saved_tasks:
+            content_type = (task.get('content_type') or 'video').lower()
+            if content_type == 'subtitle':
+                skipped_count += 1
+                continue
+            filtered_tasks.append(task)
+        restored_tasks = filtered_tasks
+        if skipped_count:
+            print(f"⏭️  Skipping {skipped_count} cached subtitle task(s) because subtitle downloads are disabled.")
+
+    if not restored_tasks:
+        return
+
+    print(f"📥 Restoring {len(restored_tasks)} previously collected download tasks...")
+    for task_data in restored_tasks:
+        add_download_task(task_data['url'], Path(task_data['dest_path']), task_data.get('content_type', 'video'))
+
+
 
 def init_course(data: Dict[str, Any]):
     """Initialize course structure and collect ALL download tasks first."""
     global COURSE_CONTENTS, ROOT_PROJECT_DIR, BASE_HOST, DOWNLOAD_TASKS
+
+    # Ensure settings/download manager are initialized so feature flags are available
+    init_settings()
 
     # Initialize download tasks list
     DOWNLOAD_TASKS = []
@@ -409,17 +476,7 @@ def init_course(data: Dict[str, Any]):
     analyzed_chapters = set()
     saved_tasks = []
 
-    if cache_file.exists():
-        try:
-            import json
-            with open(cache_file, 'r', encoding='utf-8') as f:
-                cache_data = json.load(f)
-                analyzed_chapters = set(cache_data.get('analyzed_chapters', []))
-                saved_tasks = cache_data.get('download_tasks', [])
-                print(f"📋 Found previous progress: {len(analyzed_chapters)} chapters analyzed, {len(saved_tasks)} tasks cached")
-        except:
-            analyzed_chapters = set()
-            saved_tasks = []
+    analyzed_chapters, saved_tasks = _load_cached_progress(cache_file)
 
     # Derive base host from landing_page_url if available
     landing = data['course'].get('landing_page_url')
@@ -430,10 +487,7 @@ def init_course(data: Dict[str, Any]):
     print("\n🔍 Phase 1: Analyzing course content and collecting download links...")
 
     # Restore saved download tasks
-    if saved_tasks:
-        print(f"📥 Restoring {len(saved_tasks)} previously collected download tasks...")
-        for task_data in saved_tasks:
-            add_download_task(task_data['url'], Path(task_data['dest_path']), task_data.get('content_type', 'video'))
+    _restore_saved_tasks(saved_tasks)
 
     collect_all_download_tasks(data, analyzed_chapters, cache_file)
 
@@ -835,9 +889,16 @@ def collect_video_task_wistia(wistia_id: str, file_name: str, dest_dir: Path):
             video_url = selected.get('url')
             if video_url:
                 ext = '.mp4'  # Default extension
-                resolved_name = filter_filename(file_name) + ext
+                resolved_name = filter_filename(file_name)
+                if not resolved_name.lower().endswith(ext):
+                    resolved_name += ext
                 print(f"   📹 Found video: {resolved_name}")
                 add_download_task(video_url, dest_dir / resolved_name, "video")
+                try:
+                    from .wistia_downloader import queue_wistia_subtitle_downloads
+                    queue_wistia_subtitle_downloads(data.get('media') or {}, dest_dir, resolved_name)
+                except Exception as subtitle_error:
+                    print(f"   ⚠️  Unable to queue subtitles for {resolved_name}: {subtitle_error}")
     except Exception as e:
         print(f"   ❌ Failed to collect Wistia video {wistia_id}: {e}")
 
@@ -1282,4 +1343,4 @@ def main(argv: List[str]):
 
 
 if __name__ == '__main__':
-    main(sys.argv)
+    main(sys.argv)