Una implementación de codificación para crear una transcripción interactiva y un análisis PDF con el marco Lyzr ChatBot

!pip install lyzr youtube-transcript-api fpdf2 ipywidgets
!apt-get update -qq && apt-get install -y fonts-dejavu-core

import os
import openai


openai.api_key = os.getenv("OPENAI_API_KEY")
os.environ['OPENAI_API_KEY'] = "YOUR_OPENAI_API_KEY_HERE"

import json
from lyzr import ChatBot
from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound, CouldNotRetrieveTranscript
from fpdf import FPDF
from ipywidgets import Textarea, Button, Output, Layout
from IPython.display import display, Markdown
import re

def transcript_to_pdf(video_id: str, output_pdf_path: str) -> bool:
    """
    Download YouTube transcript (manual or auto) and write it into a PDF
    using the system-installed DejaVuSans.ttf for full Unicode support.
    Fixed to handle long words and text formatting issues.
    """
    try:
        entries = YouTubeTranscriptApi.get_transcript(video_id)
    except (TranscriptsDisabled, NoTranscriptFound, CouldNotRetrieveTranscript):
        try:
            entries = YouTubeTranscriptApi.get_transcript(video_id, languages=['en'])
        except Exception:
            print(f"[!] No transcript for {video_id}")
            return False
    except Exception as e:
        print(f"[!] Error fetching transcript for {video_id}: {e}")
        return False


    text = "\n".join(e['text'] for e in entries).strip()
    if not text:
        print(f"[!] Empty transcript for {video_id}")
        return False


    pdf = FPDF()
    pdf.add_page()


    font_path = "/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf"
    try:
        if os.path.exists(font_path):
            pdf.add_font("DejaVu", "", font_path)
            pdf.set_font("DejaVu", size=10)
        else:
            pdf.set_font("Arial", size=10)
    except Exception:
        pdf.set_font("Arial", size=10)


    pdf.set_margins(20, 20, 20)
    pdf.set_auto_page_break(auto=True, margin=25)


    def process_text_for_pdf(text):
        text = re.sub(r'\s+', ' ', text)
        text = text.replace('\n\n', '\n')


        processed_lines = []
        for paragraph in text.split('\n'):
            if not paragraph.strip():
                continue


            words = paragraph.split()
            processed_words = []
            for word in words:
                if len(word) > 50:
                    chunks = [word[i:i+50] for i in range(0, len(word), 50)]
                    processed_words.extend(chunks)
                else:
                    processed_words.append(word)


            processed_lines.append(' '.join(processed_words))


        return processed_lines


    processed_lines = process_text_for_pdf(text)


    for line in processed_lines:
        if line.strip():
            try:
                pdf.multi_cell(0, 8, line.encode('utf-8', 'replace').decode('utf-8'), align='L')
                pdf.ln(2)
            except Exception as e:
                print(f"[!] Warning: Skipped problematic line: {str(e)[:100]}...")
                continue


    try:
        pdf.output(output_pdf_path)
        print(f"[+] PDF saved: {output_pdf_path}")
        return True
    except Exception as e:
        print(f"[!] Error saving PDF: {e}")
        return False

def create_interactive_chat(agent):
    input_area = Textarea(
        placeholder="Type a question…", layout=Layout(width="80%", height="80px")
    )
    send_button = Button(description="Send", button_style="success")
    output_area = Output(layout=Layout(
        border="1px solid gray", width="80%", height="200px", overflow='auto'
    ))


    def on_send(btn):
        question = input_area.value.strip()
        if not question:
            return
        with output_area:
            print(f">> You: {question}")
            try:
                print("<< Bot:", agent.chat(question), "\n")
            except Exception as e:
                print(f"[!] Error: {e}\n")


    send_button.on_click(on_send)
    display(input_area, send_button, output_area)

def main():
    video_ids = ["dQw4w9WgXcQ", "jNQXAC9IVRw"]
    processed = []


    for vid in video_ids:
        pdf_path = f"{vid}.pdf"
        if transcript_to_pdf(vid, pdf_path):
            processed.append((vid, pdf_path))
        else:
            print(f"[!] Skipping {vid} — no transcript available.")


    if not processed:
        print("[!] No PDFs generated. Please try other video IDs.")
        return


    first_vid, first_pdf = processed[0]
    print(f"[+] Initializing PDF-chat agent for video {first_vid}…")
    bot = ChatBot.pdf_chat(
        input_files=[first_pdf]
    )


    questions = [
        "Summarize the transcript in 2–3 sentences.",
        "What are the top 5 insights and why?",
        "List any recommendations or action items mentioned.",
        "Write 3 quiz questions to test comprehension.",
        "Suggest 5 creative prompts to explore further."
    ]
    responses = {}
    for q in questions:
        print(f"[?] {q}")
        try:
            resp = bot.chat(q)
        except Exception as e:
            resp = f"[!] Agent error: {e}"
        responses[q] = resp
        print(f"[/] {resp}\n" + "-"*60 + "\n")


    with open('responses.json','w',encoding='utf-8') as f:
        json.dump(responses,f,indent=2)
    md = "# Transcript Analysis Report\n\n"
    for q,a in responses.items():
        md += f"## Q: {q}\n{a}\n\n"
    with open('report.md','w',encoding='utf-8') as f:
        f.write(md)


    display(Markdown(md))


    if len(processed) > 1:
        print("[+] Generating comparison…")
        _, pdf1 = processed[0]
        _, pdf2 = processed[1]
        compare_bot = ChatBot.pdf_chat(
            input_files=[pdf1, pdf2]
        )
        comparison = compare_bot.chat(
            "Compare the main themes of these two videos and highlight key differences."
        )
        print("[+] Comparison Result:\n", comparison)


    print("\n=== Interactive Chat (Video 1) ===")
    create_interactive_chat(bot)

if __name__ == "__main__":
    main()