Create app.py

app.py

@@ -0,0 +1,156 @@
+import os
+import gradio as gr
+import yt_dlp
+import whisper
+from pydub import AudioSegment
+from transformers import pipeline
+from youtube_transcript_api import YouTubeTranscriptApi
+from urllib.parse import urlparse, parse_qs
+import openai
+import json
+import tempfile
+import re
+import torch
+from googleapiclient.discovery import build  # Add the import for Google API client
+
+
+# Function to extract YouTube video ID
+def extract_video_id(url):
+    try:
+        parsed_url = urlparse(url)
+        if "youtube.com" in parsed_url.netloc:
+            query_params = parse_qs(parsed_url.query)
+            return query_params.get('v', [None])[0]
+        elif "youtu.be" in parsed_url.netloc:
+            return parsed_url.path.strip("/")
+        return None
+    except Exception:
+        return None
+
+
+# Function to get video duration
+def get_video_duration(video_id, api_key):
+    try:
+        youtube = build("youtube", "v3", developerKey=api_key)
+        request = youtube.videos().list(part="contentDetails", id=video_id)
+        response = request.execute()
+        if response["items"]:
+            duration = response["items"][0]["contentDetails"]["duration"]
+            match = re.match(r'PT(?:(\d+)H)?(?:(\d+)M)?(?:(\d+)S)?', duration)
+            hours = int(match.group(1)) if match.group(1) else 0
+            minutes = int(match.group(2)) if match.group(2) else 0
+            seconds = int(match.group(3)) if match.group(3) else 0
+            return hours * 60 + minutes + seconds / 60
+        return None
+    except Exception:
+        return None
+
+
+# Download and transcribe with Whisper
+def download_and_transcribe_with_whisper(youtube_url):
+    try:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            temp_audio_file = os.path.join(temp_dir, "audio.mp3")
+
+            ydl_opts = {
+                'format': 'bestaudio/best',
+                'outtmpl': temp_audio_file,
+                'extractaudio': True,
+            }
+
+            with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+                ydl.download([youtube_url])
+
+            audio = AudioSegment.from_file(temp_audio_file)
+            wav_file = os.path.join(temp_dir, "audio.wav")
+            audio.export(wav_file, format="wav")
+
+            model = whisper.load_model("large")
+            result = model.transcribe(wav_file)
+            return result['text']
+    except Exception:
+        return None
+
+
+# Function to summarize using Hugging Face
+def summarize_text_huggingface(text):
+    summarizer = pipeline("summarization", model="facebook/bart-large-cnn", device=0 if torch.cuda.is_available() else -1)
+    max_input_length = 1024
+    chunk_overlap = 100
+    text_chunks = [
+        text[i:i + max_input_length]
+        for i in range(0, len(text), max_input_length - chunk_overlap)
+    ]
+    summaries = [
+        summarizer(chunk, max_length=100, min_length=50, do_sample=False)[0]['summary_text']
+        for chunk in text_chunks
+    ]
+    return " ".join(summaries)
+
+
+# Function to generate optimized content with OpenAI
+def generate_optimized_content(api_key, summarized_transcript):
+    openai.api_key = api_key
+    prompt = f"""
+    Analyze the following summarized YouTube video transcript and:
+    1. Extract the top 10 keywords.
+    2. Generate an optimized title (less than 65 characters).
+    3. Create an engaging description.
+    4. Generate related tags for the video.
+
+    Summarized Transcript:
+    {summarized_transcript}
+
+    Provide the results in the following JSON format:
+    {{
+        "keywords": ["keyword1", "keyword2", ..., "keyword10"],
+        "title": "Generated Title",
+        "description": "Generated Description",
+        "tags": ["tag1", "tag2", ..., "tag10"]
+    }}
+    """
+    try:
+        response = openai.ChatCompletion.create(
+            model="gpt-3.5-turbo",
+            messages=[
+                {"role": "system", "content": "You are an SEO expert."},
+                {"role": "user", "content": prompt}
+            ]
+        )
+        response_content = response['choices'][0]['message']['content']
+        return json.loads(response_content)
+    except Exception:
+        return None
+
+
+# Main Gradio function
+def process_video(youtube_url, youtube_api_key, openai_api_key):
+    video_id = extract_video_id(youtube_url)
+    if not video_id:
+        return "Invalid YouTube URL.", "", ""
+
+    video_length = get_video_duration(video_id, youtube_api_key)
+    if not video_length:
+        return "Error fetching video duration.", "", ""
+
+    transcript = download_and_transcribe_with_whisper(youtube_url)
+    if not transcript:
+        return "Error fetching transcript.", "", ""
+
+    summary = summarize_text_huggingface(transcript)
+    optimized_content = generate_optimized_content(openai_api_key, summary)
+
+    return summary, json.dumps(optimized_content, indent=4), transcript
+
+
+# Gradio Interface
+youtube_api_key = os.getenv("YOUTUBE_API_KEY")
+openai_api_key = os.getenv("OPENAI_API_KEY")
+
+gr.Interface(
+    fn=lambda youtube_url: process_video(youtube_url, youtube_api_key, openai_api_key),
+    inputs="text",
+    outputs=["text", "text", "text"],
+    title="YouTube Transcript Summarizer",
+    description="Enter a YouTube URL to extract, summarize, and optimize content.",
+).launch()