init repo

docker-compose.yml

@@ -0,0 +1,20 @@
+version: "3.8"
+
+services:
+  api:
+    build:
+      context: .
+      dockerfile: dockerfile
+    container_name: youtube-api
+    ports:
+      - "3011:8000"
+    volumes:
+      - /home/well/youtube-api:/app
+    environment:
+      - PYTHONUNBUFFERED=1
+    networks:
+      - dokploy-network
+
+networks:
+  dokploy-network:
+    external: true

dockerfile

@@ -0,0 +1,15 @@
+FROM python:3.10-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 8000
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

main.py

@@ -0,0 +1,83 @@
+from typing import Optional
+from fastapi import FastAPI, HTTPException, Query
+from youtube_transcript_api import YouTubeTranscriptApi, \
+    TranscriptsDisabled, NoTranscriptFound
+from yt_dlp import YoutubeDL
+
+app = FastAPI(
+    title="YouTube Transcript & Metadata API",
+    version="1.0.0"
+)
+
+def extract_video_id(url: str) -> str:
+    import re
+
+    match = re.search(r"(?:v=|youtu\.be/)([A-Za-z0-9_-]{11})", url)
+
+    if not match:
+        raise ValueError("URL inválida do YouTube")
+    
+    return match.group(1)
+
+@app.get("/get-transcript")
+def get_transcript(
+    url: Optional[str] = Query(None, description="URL completa do vídeo"),
+    videoId: Optional[str] = Query(None, alias="videoId", description="ID do vídeo no YouTube")
+):
+    if not url and not videoId:
+        raise HTTPException(status_code=400, detail="Informe 'url' ou 'videoId'")
+    if url:
+        try:
+            video_id = extract_video_id(url)
+        except ValueError as e:
+            raise HTTPException(status_code=400, detail=str(e))
+    else:
+        video_id = videoId 
+
+    try:
+        transcript_list = YouTubeTranscriptApi.get_transcript(video_id, languages=['pt', 'en'])
+    except TranscriptsDisabled:
+        raise HTTPException(status_code=404, detail="Transcrição desativada para este vídeo")
+    except NoTranscriptFound:
+        raise HTTPException(status_code=404, detail="Nenhuma transcrição encontrada")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Erro ao obter transcrição: {e}")
+
+    full_text = " ".join(item["text"] for item in transcript_list)
+
+    return {
+        "video_id": video_id,
+        "transcript": transcript_list, 
+        "full_text": full_text
+    }
+
+@app.get("/get-video-metadata")
+def get_video_metadata(
+    url: Optional[str] = Query(None, description="URL completa do vídeo"),
+    videoId: Optional[str] = Query(None, alias="videoId", description="ID do vídeo no YouTube")
+):
+    if not url and not videoId:
+        raise HTTPException(status_code=400, detail="Informe 'url' ou 'videoId'")
+    if url:
+        target = url
+    else:
+        target = f"https://www.youtube.com/watch?v={videoId}"
+
+    ydl_opts = {
+        "quiet": True,
+        "skip_download": True,
+        "nocheckcertificate": True,
+        "restrictfilenames": True,
+        "simulate": True,
+        "forcejson": True,
+    }
+
+    try:
+        with YoutubeDL(ydl_opts) as ydl:
+            info = ydl.extract_info(target, download=False)
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Erro ao extrair metadata: {e}")
+
+    return info
+
+# Para executar via: uvicorn main:app --reload --host 0.0.0.0 --port 8000

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+uvicorn[standard]
+youtube-transcript-api
+yt-dlp