Come Riassumere Video YouTube con gli LLM

1pip install youtube-transcript-api openai

 1from youtube_transcript_api import YouTubeTranscriptApi
 2from youtube_transcript_api.formatters import TextFormatter
 3from urllib.parse import urlparse, parse_qs
 4
 5def extract_video_id(url):
 6    """Extract video ID from various YouTube URL formats"""
 7    if 'youtu.be/' in url:
 8        return url.split('youtu.be/')[-1].split('?')[0]
 9    elif 'youtube.com/watch?v=' in url:
10        parsed = urlparse(url)
11        return parse_qs(parsed.query)['v'][0]
12    return None
13    
14def get_video_transcript(video_id, languages=['en']):
15    """Fetch transcript for a YouTube video"""
16    try:
17        transcript_api = YouTubeTranscriptApi()
18        transcript_list = transcript_api.fetch(video_id=video_id, languages=languages)
19        
20        if not transcript_list:
21            return None
22        
23        formatter = TextFormatter()
24        transcript_text = formatter.format_transcript(transcript_list)
25        
26        # Clean up the text
27        transcript_text = transcript_text.replace('\n', ' ')
28        transcript_text = ' '.join(transcript_text.split())
29        
30        return transcript_text
31        
32    except Exception as e:
33        print(f"Could not retrieve transcript: {e}")
34        return None
35
36# Example usage
37video_url = "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
38video_id = extract_video_id(video_url)
39transcript = get_video_transcript(video_id)
40print(f"Transcript length: {len(transcript)} characters")

 1import openai
 2
 3class VideoSummarizer:
 4    def __init__(self):
 5        self.client = openai.OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
 6    
 7    def summarize_video(self, transcript, model='gpt-5-mini'):
 8        """Generate summary from video transcript"""
 9        
10        # Truncate if too long (roughly 8000 chars = 2000 tokens)
11        if len(transcript) > 8000:
12            transcript = transcript[:8000] + "..."
13        
14        prompt = f"""
15Analyze this YouTube video transcript and provide a clear, structured summary.
16
17Instructions:
18- Identify the main topic and key points
19- Highlight important insights or conclusions
20- Use bullet points for clarity
21- Keep it concise but comprehensive
22
23Transcript:
24{transcript}
25
26Summary:
27"""
28        
29        try:
30            response = self.client.chat.completions.create(
31                model=model,
32                messages=[{"role": "user", "content": prompt}],
33                max_completion_tokens=4096
34            )
35
36            return response.choices[0].message.content
37            
38        except Exception as e:
39            print(f"Error generating summary: {e}")
40            return f"Summary failed. First 500 chars: {transcript[:500]}..."
41
42# Example usage
43summarizer = VideoSummarizer()
44summary = summarizer.summarize_video(transcript)
45print(summary)

 1def summarize_youtube_video(video_url):
 2    """Complete pipeline to summarize a YouTube video"""
 3    
 4    print(f"Processing: {video_url}")
 5    
 6    # Step 1: Extract video ID and transcript
 7    video_id = extract_video_id(video_url)
 8    if not video_id:
 9        return "Invalid YouTube URL"
10    
11    transcript = get_video_transcript(video_id)
12    if not transcript:
13        return "No transcript available for this video"
14    
15    print(f"Transcript extracted: {len(transcript)} characters")
16    
17    # Step 2: Generate summary
18    summarizer = VideoSummarizer()
19    summary = summarizer.summarize_video(transcript)
20    
21    return summary
22
23# Example usage
24video_url = "https://www.youtube.com/watch?v=your_video_here"
25
26summary = summarize_youtube_video(video_url)
27print("\n" + "="*60)
28print("VIDEO SUMMARY")
29print("="*60)
30print(summary)