UPDATE

Author: mazzasaverio

backend/.dockerignore

@@ -0,0 +1,20 @@
+# Ignore data and checkpoints directories
+backend/data/
+backend/checkpoints/
+data
+checkpoints
+
+# Ignore Git and version control
+.git
+.gitignore
+
+# Ignore other unnecessary files
+*.pyc
+*.pyo
+*.pyd
+__pycache__
+*.swp
+.DS_Store
+
+# Ignore specific files or other directories as needed
+# e.g., local environment files, IDE-specific files,

backend/Dockerfile

@@ -20,18 +20,21 @@ WORKDIR /code
 # Copy the project files to the container
 COPY . /code/
 
-# Install aria2 and unzip
-RUN apt-get update && apt-get install -y aria2 unzip
+# Install necessary system packages
+RUN apt-get update && apt-get install -y aria2 unzip && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
 
 # Download and unzip the checkpoints
 RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://myshell-public-repo-hosting.s3.amazonaws.com/checkpoints_1226.zip -d /code -o checkpoints_1226.zip && \
     unzip /code/checkpoints_1226.zip -d /code/checkpoints && \
     rm /code/checkpoints_1226.zip
 
-# If requirements.txt has other necessary packages, uncomment the next line
-RUN pip install -r requirements.txt
-# Install additional Python dependencies
-RUN pip install --upgrade pip && \
+COPY requirements.txt /code/
+
+# Install Python dependencies
+RUN pip install -r requirements.txt && \
     pip install pytube moviepy fastapi uvicorn loguru youtube-dl youtube-transcript-api librosa googletrans==4.0.0-rc1
 
 

backend/app/api/v1/endpoints.py

@@ -8,19 +8,37 @@
 from fastapi.responses import FileResponse, StreamingResponse
 import os
 from starlette.status import HTTP_404_NOT_FOUND
-
+import re
+from typing import Dict
 
 router = APIRouter()
 
+# Global dictionary to track the status of tasks
+task_status: Dict[str, str] = {}
+
 
 # Retrieve the DATA_DIR from environment variable or use default
 DATA_DIR = os.getenv("DATA_DIR", "/home/sam/github/youtube-auto-dub/backend/data")
 
+def extract_video_id(url: str) -> str:
+    """
+    Extracts the video ID from a YouTube URL.
+    """
+    pattern = r"(?:v=|\/)([0-9A-Za-z_-]{11}).*"
+    match = re.search(pattern, str(url))
+    return match.group(1) if match else None
+
 
 @router.post("/download/")
-async def download_video(
-    request: VideoDownloadRequest, background_tasks: BackgroundTasks
-):
+async def download_video(request: VideoDownloadRequest, background_tasks: BackgroundTasks):
+    # Correctly access youtube_url from the request object
+    video_id = extract_video_id(request.url)
+    if not video_id:
+        logger.error("Invalid YouTube URL provided.")
+        raise HTTPException(status_code=400, detail="Invalid YouTube URL")
+
+    if not video_id:
+        raise HTTPException(status_code=400, detail="Invalid YouTube URL")
     try:
         url = str(request.url)
         logger.info(f"Received download request for URL: {url}")
@@ -44,19 +62,26 @@ async def download_video(
         output_path = os.path.join(
             DATA_DIR, "final_videos", os.path.basename(video_path)
         )
+        task_status[video_id] = "Processing"
 
         background_tasks.add_task(
             process_audio_and_assemble_video,
             video_path,
             audio_path,
             output_path,
             translated_text,
+            video_id
         )
-        return {"message": "Video processing started.", "caption_path": caption_path}
+
+        return {"video_id": video_id, "status": "Processing started"}
     except Exception as e:
         logger.error(f"Error in download_video endpoint: {e}")
         raise HTTPException(status_code=500, detail=str(e))
 
+@router.get("/status/{video_id}")
+def get_task_status(video_id: str):
+    status = task_status.get(video_id, "Not Found")
+    return {"video_id": video_id, "status": status}
 
 @router.get("/download-video/{video_id}")
 async def download_video(video_id: str):
@@ -67,7 +92,7 @@ async def download_video(video_id: str):
 
 
 def process_audio_and_assemble_video(
-    video_path: str, audio_path: str, output_path: str, text_to_speak: str
+    video_path: str, audio_path: str, output_path: str, text_to_speak: str, video_id: str
 ):
     try:
         style = "default"
@@ -94,5 +119,8 @@ def process_audio_and_assemble_video(
             video_path, processed_audio_path, output_path
         )
 
+        task_status[video_id] = "Completed"
+
     except Exception as e:
+        task_status[video_id] = "Failed"
         logger.error(f"Error in process_audio_and_assemble_video: {e}")