Update app.py

app.py

@@ -5,26 +5,13 @@ import whisper
 from pydub import AudioSegment
 import tempfile
 from transformers import pipeline
+from pytrends.request import TrendReq
 from youtube_transcript_api import YouTubeTranscriptApi
 import torch
 import openai
 import json
 from urllib.parse import urlparse, parse_qs
 import os
-import gradio as gr
-
-# Set up API keys (ensure these are provided as environment variables)
-youtube_api_key = os.getenv("YOUTUBE_API_KEY")
-openai_api_key = os.getenv("OPENAI_API_KEY")
-openai.api_key = openai_api_key
-
-# Validate API keys
-if not youtube_api_key:
-    raise ValueError("YOUTUBE_API_KEY is not set. Please set it as an environment variable.")
-
-if not openai_api_key:
-    raise ValueError("OPENAI_API_KEY is not set. Please set it as an environment variable.")
-
 
 def extract_video_id(url):
     """Extracts the video ID from a YouTube URL."""
@@ -36,12 +23,12 @@ def extract_video_id(url):
         elif "youtu.be" in parsed_url.netloc:
             return parsed_url.path.strip("/")
         else:
+            print("Invalid YouTube URL.")
             return None
     except Exception as e:
         print(f"Error parsing URL: {e}")
         return None
 
-
 def get_video_duration(video_id, api_key):
     """Fetches the video duration in minutes."""
     try:
@@ -56,14 +43,13 @@ def get_video_duration(video_id, api_key):
             seconds = int(match.group(3)) if match.group(3) else 0
             return hours * 60 + minutes + seconds / 60
         else:
+            print("No video details found.")
             return None
     except Exception as e:
         print(f"Error fetching video duration: {e}")
         return None
 
-
 def download_and_transcribe_with_whisper(youtube_url):
-    """Downloads audio from YouTube and transcribes it using Whisper."""
     try:
         with tempfile.TemporaryDirectory() as temp_dir:
             temp_audio_file = os.path.join(temp_dir, "audio.mp3")
@@ -71,63 +57,73 @@ def download_and_transcribe_with_whisper(youtube_url):
             ydl_opts = {
                 'format': 'bestaudio/best',
                 'outtmpl': temp_audio_file,
-                'postprocessors': [{
-                    'key': 'FFmpegExtractAudio',
-                    'preferredcodec': 'mp3',
-                    'preferredquality': '192',
-                }],
+                'extractaudio': True,
+                'audioquality': 1,
             }
-            # Download audio
+
+            # Download audio using yt-dlp
             with yt_dlp.YoutubeDL(ydl_opts) as ydl:
                 ydl.download([youtube_url])
-            # Convert to WAV
+
+            # Convert to wav for Whisper
             audio = AudioSegment.from_file(temp_audio_file)
             wav_file = os.path.join(temp_dir, "audio.wav")
             audio.export(wav_file, format="wav")
-            # Transcribe using Whisper
+
+            # Run Whisper transcription
             model = whisper.load_model("large")
             result = model.transcribe(wav_file)
-            return result['text']
+            transcript = result['text']
+            return transcript
+
     except Exception as e:
         print(f"Error during transcription: {e}")
         return None
 
-
 def get_transcript_from_youtube_api(video_id, video_length):
     """Fetches transcript using YouTube API if available."""
     try:
         transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
+
         for transcript in transcript_list:
             if not transcript.is_generated:
                 segments = transcript.fetch()
                 return " ".join(segment['text'] for segment in segments)
-        if video_length > 15:  # Use generated transcript for longer videos
+
+        if video_length > 15:
             auto_transcript = transcript_list.find_generated_transcript(['en'])
             if auto_transcript:
                 segments = auto_transcript.fetch()
                 return " ".join(segment['text'] for segment in segments)
+
+        print("Manual transcript not available, and video is too short for auto-transcript.")
         return None
+
     except Exception as e:
         print(f"Error fetching transcript: {e}")
         return None
 
-
-def get_transcript(youtube_url):
-    """Gets transcript using YouTube API or Whisper."""
+def get_transcript(youtube_url, api_key):
+    """Gets transcript from YouTube API or Whisper if unavailable."""
     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)
+        print("Invalid or unsupported YouTube URL.")
+        return None
+
+    video_length = get_video_duration(video_id, api_key)
     if video_length is not None:
+        print(f"Video length: {video_length:.2f} minutes.")
         transcript = get_transcript_from_youtube_api(video_id, video_length)
         if transcript:
             return transcript
+        print("Using Whisper for transcription.")
         return download_and_transcribe_with_whisper(youtube_url)
-    return "Error fetching video duration."
-
+    else:
+        print("Error fetching video duration.")
+        return None
 
-def summarize_text(text):
-    """Summarizes text using Hugging Face pipeline."""
+def summarize_text_huggingface(text):
+    """Summarizes text using a Hugging Face summarization model."""
     summarizer = pipeline("summarization", model="facebook/bart-large-cnn", device=0 if torch.cuda.is_available() else -1)
     max_input_length = 1024
     chunk_overlap = 100
@@ -141,9 +137,9 @@ def summarize_text(text):
     ]
     return " ".join(summaries)
 
+def generate_optimized_content(api_key, summarized_transcript):
+    openai.api_key = api_key
 
-def generate_optimized_content(summary):
-    """Generates optimized content using OpenAI GPT."""
     prompt = f"""
     Analyze the following summarized YouTube video transcript and:
     1. Extract the top 10 keywords.
@@ -152,9 +148,9 @@ def generate_optimized_content(summary):
     4. Generate related tags for the video.
 
     Summarized Transcript:
-    {summary}
+    {summarized_transcript}
 
-    Provide the results in JSON format:
+    Provide the results in the following JSON format:
     {{
         "keywords": ["keyword1", "keyword2", ..., "keyword10"],
         "title": "Generated Title",
@@ -162,7 +158,9 @@ def generate_optimized_content(summary):
         "tags": ["tag1", "tag2", ..., "tag10"]
     }}
     """
+
     try:
+        # Use the updated OpenAI API format for chat completions
         response = openai.ChatCompletion.create(
             model="gpt-3.5-turbo",
             messages=[
@@ -170,28 +168,39 @@ def generate_optimized_content(summary):
                 {"role": "user", "content": prompt}
             ]
         )
-        return json.loads(response['choices'][0]['message']['content'])
+        # Extract and parse the response
+        response_content = response['choices'][0]['message']['content']
+        content = json.loads(response_content)
+        return content
+
     except Exception as e:
-        return {"error": str(e)}
+        print(f"Error generating content: {e}")
+        return None
+
+
+def main():
+    youtube_url = input("Enter a YouTube video URL: ").strip()
+    youtube_api_key = "AIzaSyDzvaQzykj94MWl5fmY3wIBQchqXiCClUc"  # Set your YouTube API key as an environment variable
+    openai_api_key = "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"    # Set your OpenAI API key as an environment variable
 
+    if not youtube_api_key or not openai_api_key:
+        print("Missing API keys. Please set your YOUTUBE_API_KEY and OPENAI_API_KEY environment variables.")
+        return
 
-def process_video(youtube_url):
-    """Processes video and returns optimized metadata."""
-    transcript = get_transcript(youtube_url)
+    transcript = get_transcript(youtube_url, youtube_api_key)
     if not transcript:
-        return {"error": "Could not fetch the transcript."}
-    summary = summarize_text(transcript)
-    return generate_optimized_content(summary)
+        print("Could not fetch the transcript. Please try another video.")
+        return
 
+    summary = summarize_text_huggingface(transcript)
+    print("\nSummarized Transcript:\n", summary)
 
-# Gradio Interface
-iface = gr.Interface(
-    fn=process_video,
-    inputs=gr.Textbox(label="Enter a YouTube video URL"),
-    outputs=gr.JSON(label="Optimized Content"),
-    title="YouTube Video Optimization Tool",
-    description="Enter a YouTube URL to generate SEO-optimized titles, descriptions, and tags."
-)
+    optimized_content = generate_optimized_content(openai_api_key, summary)
+    if optimized_content:
+        print("\nOptimized Content:")
+        print(json.dumps(optimized_content, indent=4))
+    else:
+        print("Error generating optimized content.")
 
 if __name__ == "__main__":
-    iface.launch()
+    main()