Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,4 +1,551 @@
|
|
| 1 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
import os
|
| 3 |
os.system('conda install -c conda-forge youtube-transcript-api -y')
|
| 4 |
import subprocess
|
|
@@ -136,7 +683,7 @@ def extract_video_id(url):
|
|
| 136 |
return match.group(1)
|
| 137 |
return None
|
| 138 |
|
| 139 |
-
|
| 140 |
try:
|
| 141 |
if not url.strip():
|
| 142 |
return None, "Please enter a YouTube URL", "N/A", ""
|
|
@@ -362,187 +909,3 @@ with gr.Blocks(theme=gr.themes.Soft()) as app:
|
|
| 362 |
|
| 363 |
if __name__ == "__main__":
|
| 364 |
app.launch()
|
| 365 |
-
|
| 366 |
-
|
| 367 |
-
########################
|
| 368 |
-
# import os
|
| 369 |
-
# os.system('conda install -c conda-forge youtube-transcript-api -y')
|
| 370 |
-
# import subprocess
|
| 371 |
-
# subprocess.check_call(["pip", "install", "transformers==4.34.0"])
|
| 372 |
-
# subprocess.check_call(["pip", "install", "torch>=1.7.1"])
|
| 373 |
-
# subprocess.check_call(["pip", "install", "youtube_transcript_api>=0.6.3"])
|
| 374 |
-
# subprocess.check_call(["pip", "install", "pytube>=12.1.0"])
|
| 375 |
-
# subprocess.check_call(["pip", "install", "huggingface_hub>=0.19.0"])
|
| 376 |
-
# subprocess.check_call(["pip", "install", "PyPDF2>=3.0.1"])
|
| 377 |
-
# subprocess.check_call(["pip", "install", "google-generativeai>=0.3.0"])
|
| 378 |
-
# subprocess.check_call(["pip", "install", "textblob>=0.17.1"])
|
| 379 |
-
# subprocess.check_call(["pip", "install", "python-dotenv>=1.0.0"])
|
| 380 |
-
# subprocess.check_call(["pip", "install", "genai"])
|
| 381 |
-
# subprocess.check_call(["pip", "install", "google-cloud-aiplatform==1.34.0"])
|
| 382 |
-
# subprocess.check_call(["pip", "install", "scikit-learn>=1.0.0"])
|
| 383 |
-
# import transformers
|
| 384 |
-
# import torch
|
| 385 |
-
# import os
|
| 386 |
-
# import youtube_transcript_api
|
| 387 |
-
# import pytube
|
| 388 |
-
# import gradio
|
| 389 |
-
# import PyPDF2
|
| 390 |
-
# import pathlib
|
| 391 |
-
# import pandas
|
| 392 |
-
# import numpy
|
| 393 |
-
# import textblob
|
| 394 |
-
# import gradio as gr
|
| 395 |
-
# from youtube_transcript_api import YouTubeTranscriptApi
|
| 396 |
-
# import google.generativeai as genai
|
| 397 |
-
# import requests
|
| 398 |
-
# from textblob import TextBlob
|
| 399 |
-
# import re
|
| 400 |
-
# from dotenv import load_dotenv
|
| 401 |
-
# from sklearn.feature_extraction.text import TfidfVectorizer
|
| 402 |
-
# from sklearn.metrics.pairwise import cosine_similarity
|
| 403 |
-
|
| 404 |
-
|
| 405 |
-
# #from google.cloud import generativeai
|
| 406 |
-
# from huggingface_hub import login
|
| 407 |
-
# from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound
|
| 408 |
-
# def install_missing_packages():
|
| 409 |
-
# required_packages = {
|
| 410 |
-
# "torch":">=1.11.0",
|
| 411 |
-
# "transformers":">=4.34.0",
|
| 412 |
-
# "youtube_transcript_api" :">=0.6.3" ,
|
| 413 |
-
# "pytube":">=12.1.0",
|
| 414 |
-
# "huggingface_hub": ">=0.19.0",
|
| 415 |
-
# "PyPDF2": ">=3.0.1",
|
| 416 |
-
# "textblob":">=0.17.1",
|
| 417 |
-
# "python-dotenv":">=1.0.0",
|
| 418 |
-
# "genai":None,
|
| 419 |
-
# "google-generativeai": ">=0.3.0",
|
| 420 |
-
# "google-cloud-aiplatform":"==1.34.0",
|
| 421 |
-
# "scikit-learn": ">=1.0.0"
|
| 422 |
-
# }
|
| 423 |
-
|
| 424 |
-
|
| 425 |
-
# for package, version in required_packages.items():
|
| 426 |
-
# try:
|
| 427 |
-
# __import__(package)
|
| 428 |
-
# except ImportError:
|
| 429 |
-
# package_name = f"{package}{version}" if version else package
|
| 430 |
-
# subprocess.check_call(["pip", "install", package_name])
|
| 431 |
-
|
| 432 |
-
# install_missing_packages()
|
| 433 |
-
# # # Configuration
|
| 434 |
-
# # USER_CREDENTIALS = {
|
| 435 |
-
# # "admin": "password123",
|
| 436 |
-
# # "teacher": "teach2024",
|
| 437 |
-
# # "student": "learn2024"
|
| 438 |
-
# # }
|
| 439 |
-
|
| 440 |
-
# hf_token = os.getenv("HF_TOKEN")
|
| 441 |
-
# if hf_token:
|
| 442 |
-
# login(hf_token)
|
| 443 |
-
# else:
|
| 444 |
-
# raise ValueError("HF_TOKEN environment variable not set.")
|
| 445 |
-
|
| 446 |
-
# # GOOGLE_API_KEY = "AIzaSyAURQb9jueh3dBQ4SITgKoR0L2_33en3yU"
|
| 447 |
-
# # YOUTUBE_API_KEY = "AIzaSyB7X-RYjZmUuDSMTQsvCfyzURw5bhqOto4"
|
| 448 |
-
# # genai.configure(api_key=GOOGLE_API_KEY)
|
| 449 |
-
# # # GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
|
| 450 |
-
# # # genai.configure(api_key=GOOGLE_API_KEY)
|
| 451 |
-
# # # YOUTUBE_API_KEY = os.getenv("YOUTUBE_API_KEY")
|
| 452 |
-
# # # print("GOOGLE_API_KEY:", os.getenv("GOOGLE_API_KEY"))
|
| 453 |
-
# # # print("YOUTUBE_API_KEY:", os.getenv("YOUTUBE_API_KEY"))
|
| 454 |
-
|
| 455 |
-
# import os
|
| 456 |
-
# import gradio as gr
|
| 457 |
-
# from youtube_transcript_api import YouTubeTranscriptApi
|
| 458 |
-
# from dotenv import load_dotenv
|
| 459 |
-
# import google.generativeai as genai
|
| 460 |
-
# import requests
|
| 461 |
-
|
| 462 |
-
# from transformers import pipeline
|
| 463 |
-
# from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound
|
| 464 |
-
# from pytube import YouTube
|
| 465 |
-
# import gradio as gr
|
| 466 |
-
# from transformers import pipeline
|
| 467 |
-
# from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound
|
| 468 |
-
# from pytube import YouTube
|
| 469 |
-
# import gradio as gr
|
| 470 |
-
|
| 471 |
-
# # Function to extract transcript from a YouTube video
|
| 472 |
-
# def extract_transcript(youtube_video_url):
|
| 473 |
-
# try:
|
| 474 |
-
# video_id = youtube_video_url.split("v=")[1].split("&")[0] # Extract video ID from URL
|
| 475 |
-
|
| 476 |
-
# # Try to fetch transcript using YouTubeTranscriptApi
|
| 477 |
-
# try:
|
| 478 |
-
# transcript = YouTubeTranscriptApi.get_transcript(video_id)
|
| 479 |
-
# result = " ".join([i['text'] for i in transcript])
|
| 480 |
-
# return result
|
| 481 |
-
# except (TranscriptsDisabled, NoTranscriptFound):
|
| 482 |
-
# pass # Fallback to pytube if no transcript found
|
| 483 |
-
|
| 484 |
-
# # Fallback to pytube for captions
|
| 485 |
-
# yt = YouTube(youtube_video_url)
|
| 486 |
-
# if yt.captions:
|
| 487 |
-
# captions = yt.captions.get_by_language_code("en")
|
| 488 |
-
# if captions:
|
| 489 |
-
# transcript = captions.generate_srt_captions()
|
| 490 |
-
# return transcript.replace("\n", " ") # Clean SRT captions format
|
| 491 |
-
# else:
|
| 492 |
-
# return "Error: No English captions available for this video."
|
| 493 |
-
# else:
|
| 494 |
-
# return "Error: No captions available for this video."
|
| 495 |
-
|
| 496 |
-
# except Exception as e:
|
| 497 |
-
# return f"Error: Unable to process the video URL. Details: {str(e)}"
|
| 498 |
-
|
| 499 |
-
# # Function to summarize the text
|
| 500 |
-
# def summarize_transcript(transcript_text):
|
| 501 |
-
# try:
|
| 502 |
-
# summarizer = pipeline('summarization', model="facebook/bart-large-cnn") # Using BART model for summarization
|
| 503 |
-
# summarized_text = []
|
| 504 |
-
# num_iters = len(transcript_text) // 1000 + 1
|
| 505 |
-
|
| 506 |
-
# for i in range(num_iters):
|
| 507 |
-
# start = i * 1000
|
| 508 |
-
# end = (i + 1) * 1000
|
| 509 |
-
# chunk = transcript_text[start:end]
|
| 510 |
-
# if chunk.strip():
|
| 511 |
-
# out = summarizer(chunk, max_length=130, min_length=30, do_sample=False)
|
| 512 |
-
# summarized_text.append(out[0]['summary_text'])
|
| 513 |
-
|
| 514 |
-
# return " ".join(summarized_text)
|
| 515 |
-
# except Exception as e:
|
| 516 |
-
# return f"Error during summarization: {str(e)}"
|
| 517 |
-
|
| 518 |
-
# # Gradio Interface function
|
| 519 |
-
# def gradio_interface(youtube_url):
|
| 520 |
-
# transcript = extract_transcript(youtube_url)
|
| 521 |
-
# if transcript.startswith("Error"):
|
| 522 |
-
# return transcript, "Summarization cannot be performed due to transcript error."
|
| 523 |
-
|
| 524 |
-
# summarized_text = summarize_transcript(transcript)
|
| 525 |
-
# return transcript, summarized_text
|
| 526 |
-
|
| 527 |
-
# # Gradio Interface Design
|
| 528 |
-
# with gr.Blocks() as demo:
|
| 529 |
-
# gr.Markdown("# YouTube Video Summarizer")
|
| 530 |
-
# with gr.Row():
|
| 531 |
-
# youtube_url_input = gr.Textbox(
|
| 532 |
-
# label="YouTube Video URL",
|
| 533 |
-
# placeholder="Enter the YouTube video link here"
|
| 534 |
-
# )
|
| 535 |
-
# summarize_button = gr.Button("Summarize Transcript")
|
| 536 |
-
# with gr.Row():
|
| 537 |
-
# transcript_output = gr.Textbox(label="Original Transcript", lines=10, interactive=False)
|
| 538 |
-
# summary_output = gr.Textbox(label="Summarized Text", lines=10, interactive=False)
|
| 539 |
-
# summarize_button.click(
|
| 540 |
-
# fn=gradio_interface,
|
| 541 |
-
# inputs=[youtube_url_input],
|
| 542 |
-
# outputs=[transcript_output, summary_output]
|
| 543 |
-
# )
|
| 544 |
-
|
| 545 |
-
# # Launch Gradio App
|
| 546 |
-
# if __name__ == "__main__":
|
| 547 |
-
# demo.launch()
|
| 548 |
-
|
|
|
|
| 1 |
|
| 2 |
+
# import os
|
| 3 |
+
# os.system('conda install -c conda-forge youtube-transcript-api -y')
|
| 4 |
+
# import subprocess
|
| 5 |
+
# subprocess.check_call(["pip", "install", "transformers==4.34.0"])
|
| 6 |
+
# subprocess.check_call(["pip", "install", "torch>=1.7.1"])
|
| 7 |
+
# subprocess.check_call(["pip", "install", "youtube_transcript_api>=0.6.3"])
|
| 8 |
+
# subprocess.check_call(["pip", "install", "pytube"])
|
| 9 |
+
# subprocess.check_call(["pip", "install", "huggingface_hub>=0.19.0"])
|
| 10 |
+
# subprocess.check_call(["pip", "install", "PyPDF2>=3.0.1"])
|
| 11 |
+
# subprocess.check_call(["pip", "install", "google-generativeai"])
|
| 12 |
+
# subprocess.check_call(["pip", "install", "textblob>=0.17.1"])
|
| 13 |
+
# subprocess.check_call(["pip", "install", "python-dotenv>=1.0.0"])
|
| 14 |
+
# subprocess.check_call(["pip", "install", "genai"])
|
| 15 |
+
# subprocess.check_call(["pip", "install", "google-cloud-aiplatform==1.34.0"])
|
| 16 |
+
# import transformers
|
| 17 |
+
# import torch
|
| 18 |
+
# import os
|
| 19 |
+
# import youtube_transcript_api
|
| 20 |
+
# import pytube
|
| 21 |
+
# import gradio
|
| 22 |
+
# import PyPDF2
|
| 23 |
+
# import pathlib
|
| 24 |
+
# import pandas
|
| 25 |
+
# import numpy
|
| 26 |
+
# import textblob
|
| 27 |
+
# import gradio as gr
|
| 28 |
+
# from youtube_transcript_api import YouTubeTranscriptApi
|
| 29 |
+
# import google.generativeai as genai
|
| 30 |
+
# import requests
|
| 31 |
+
# from textblob import TextBlob
|
| 32 |
+
# import re
|
| 33 |
+
# #from google.cloud import generativeai
|
| 34 |
+
# from huggingface_hub import login
|
| 35 |
+
# from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound
|
| 36 |
+
# def install_missing_packages():
|
| 37 |
+
# required_packages = {
|
| 38 |
+
# "torch":">=1.11.0",
|
| 39 |
+
# "transformers":">=4.34.0",
|
| 40 |
+
# "youtube_transcript_api" :">=0.6.3" ,
|
| 41 |
+
# "pytube":None,
|
| 42 |
+
# "huggingface_hub": ">=0.19.0",
|
| 43 |
+
# "PyPDF2": ">=3.0.1",
|
| 44 |
+
# "textblob":">=0.17.1",
|
| 45 |
+
# "python-dotenv":">=1.0.0",
|
| 46 |
+
# "genai":None,
|
| 47 |
+
# "google-generativeai": None,
|
| 48 |
+
# "google-cloud-aiplatform":"==1.34.0"
|
| 49 |
+
# }
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
# for package, version in required_packages.items():
|
| 53 |
+
# try:
|
| 54 |
+
# __import__(package)
|
| 55 |
+
# except ImportError:
|
| 56 |
+
# package_name = f"{package}{version}" if version else package
|
| 57 |
+
# subprocess.check_call(["pip", "install", package_name])
|
| 58 |
+
|
| 59 |
+
# install_missing_packages()
|
| 60 |
+
# # Configuration
|
| 61 |
+
|
| 62 |
+
# hf_token = os.getenv("HF_TOKEN")
|
| 63 |
+
# if hf_token:
|
| 64 |
+
# login(hf_token)
|
| 65 |
+
# else:
|
| 66 |
+
# raise ValueError("HF_TOKEN environment variable not set.")
|
| 67 |
+
|
| 68 |
+
# # GOOGLE_API_KEY = "AIzaSyAURQb9jueh3dBQ4SITgKoR0L2_33en3yU"
|
| 69 |
+
# # YOUTUBE_API_KEY = "AIzaSyB7X-RYjZmUuDSMTQsvCfyzURw5bhqOto4"
|
| 70 |
+
# # # genai.configure(api_key=GOOGLE_API_KEY)
|
| 71 |
+
# # GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
|
| 72 |
+
# # genai.configure(api_key=GOOGLE_API_KEY)
|
| 73 |
+
# # YOUTUBE_API_KEY = os.getenv("YOUTUBE_API_KEY")
|
| 74 |
+
# # print("GOOGLE_API_KEY:", os.getenv("GOOGLE_API_KEY"))
|
| 75 |
+
# # print("YOUTUBE_API_KEY:", os.getenv("YOUTUBE_API_KEY"))
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
# # Configuration
|
| 80 |
+
# USER_CREDENTIALS = {
|
| 81 |
+
# "admin": "password123",
|
| 82 |
+
# "teacher": "teach2024",
|
| 83 |
+
# "student": "learn2024"
|
| 84 |
+
# }
|
| 85 |
+
|
| 86 |
+
# import os
|
| 87 |
+
# from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound
|
| 88 |
+
|
| 89 |
+
# # Use environment variables
|
| 90 |
+
# GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
|
| 91 |
+
# YOUTUBE_API_KEY = os.getenv("YOUTUBE_API_KEY")
|
| 92 |
+
|
| 93 |
+
# if not GOOGLE_API_KEY or not YOUTUBE_API_KEY:
|
| 94 |
+
# raise ValueError("Please set GOOGLE_API_KEY and YOUTUBE_API_KEY environment variables")
|
| 95 |
+
|
| 96 |
+
# genai.configure(api_key=GOOGLE_API_KEY)
|
| 97 |
+
|
| 98 |
+
# # Database
|
| 99 |
+
# students_data = [
|
| 100 |
+
# (1, "Alice", "A", "Computer Science"),
|
| 101 |
+
# (2, "Aliaa", "B", "Mathematics"),
|
| 102 |
+
# (3, "Charlie", "A", "Machine Learning"),
|
| 103 |
+
# (4, "Daan", "A", "Physics"),
|
| 104 |
+
# (5, "Jhon", "C", "Math"),
|
| 105 |
+
# (6, "Emma", "A+", "Computer Science")
|
| 106 |
+
# ]
|
| 107 |
+
|
| 108 |
+
# teachers_data = [
|
| 109 |
+
# (1, "Dr. Smith", "Math", "MS Mathematics"),
|
| 110 |
+
# (2, "Ms. Johnson", "Science", "MSc Physics"),
|
| 111 |
+
# (3, "Ms. Jack", "Artificial Intelligence Engineer", "MSc AI"),
|
| 112 |
+
# (4, "Ms. Evelyn", "Computer Science", "MSc Computer Science"),
|
| 113 |
+
# ]
|
| 114 |
+
|
| 115 |
+
# courses_data = [
|
| 116 |
+
# (1, "Algebra", "Dr. Smith", "Advanced"),
|
| 117 |
+
# (2, "Biology", "Ms. Mia", "Intermediate"),
|
| 118 |
+
# (3, "Machine Learning", "Ms. Jack", "Intermediate"),
|
| 119 |
+
# (4, "Computer Science", "Ms. Evelyn", "Intermediate"),
|
| 120 |
+
# (5, "Mathematics", "Ms. Smith", "Intermediate")
|
| 121 |
+
# ]
|
| 122 |
+
|
| 123 |
+
# def sanitize_text(text):
|
| 124 |
+
# """Remove invalid Unicode characters."""
|
| 125 |
+
# return text.encode("utf-8", "replace").decode("utf-8")
|
| 126 |
+
|
| 127 |
+
# def extract_video_id(url):
|
| 128 |
+
# if not url:
|
| 129 |
+
# return None
|
| 130 |
+
# patterns = [
|
| 131 |
+
# r'(?:v=|\/videos\/|embed\/|youtu.be\/|\/v\/|\/e\/|watch\?v=|\/watch\?v=)([^#\&\?]*)'
|
| 132 |
+
# ]
|
| 133 |
+
# for pattern in patterns:
|
| 134 |
+
# match = re.search(pattern, url)
|
| 135 |
+
# if match:
|
| 136 |
+
# return match.group(1)
|
| 137 |
+
# return None
|
| 138 |
+
|
| 139 |
+
# # def process_youtube_video(url="", keywords=""):
|
| 140 |
+
# try:
|
| 141 |
+
# if not url.strip():
|
| 142 |
+
# return None, "Please enter a YouTube URL", "N/A", ""
|
| 143 |
+
|
| 144 |
+
# video_id = extract_video_id(url)
|
| 145 |
+
# if not video_id:
|
| 146 |
+
# return None, "Invalid YouTube URL", "N/A", ""
|
| 147 |
+
|
| 148 |
+
# try:
|
| 149 |
+
# # Try multiple transcript options
|
| 150 |
+
# transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
|
| 151 |
+
|
| 152 |
+
# try:
|
| 153 |
+
# transcript = transcript_list.find_transcript(['en'])
|
| 154 |
+
# except:
|
| 155 |
+
# try:
|
| 156 |
+
# transcript = transcript_list.find_transcript(['en-US'])
|
| 157 |
+
# except:
|
| 158 |
+
# try:
|
| 159 |
+
# # Try auto-generated
|
| 160 |
+
# transcript = transcript_list.find_generated_transcript(['en'])
|
| 161 |
+
# except:
|
| 162 |
+
# raise NoTranscriptFound()
|
| 163 |
+
|
| 164 |
+
# text = " ".join([t['text'] for t in transcript.fetch()])
|
| 165 |
+
|
| 166 |
+
# # Generate summary
|
| 167 |
+
# model = genai.GenerativeModel("gemini-pro")
|
| 168 |
+
# summary = model.generate_content(f"Summarize this: {text[:4000]}").text
|
| 169 |
+
|
| 170 |
+
# # Analysis
|
| 171 |
+
# sentiment = TextBlob(text[:1000]).sentiment
|
| 172 |
+
# sentiment_label = f"{'Positive' if sentiment.polarity > 0 else 'Negative' if sentiment.polarity < 0 else 'Neutral'} ({sentiment.polarity:.2f})"
|
| 173 |
+
|
| 174 |
+
# thumbnail = f"https://img.youtube.com/vi/{video_id}/maxresdefault.jpg"
|
| 175 |
+
|
| 176 |
+
# except TranscriptsDisabled:
|
| 177 |
+
# return thumbnail, "⚠️ This video has disabled subtitles. Please try another video.", "N/A", ""
|
| 178 |
+
# except NoTranscriptFound:
|
| 179 |
+
# return thumbnail, "⚠️ No English transcript available. Please try another video.", "N/A", ""
|
| 180 |
+
# except Exception as e:
|
| 181 |
+
# return None, f"⚠️ Error: {str(e)}", "N/A", ""
|
| 182 |
+
|
| 183 |
+
# # Get recommendations
|
| 184 |
+
# if keywords.strip():
|
| 185 |
+
# recommendations = get_recommendations(keywords)
|
| 186 |
+
# else:
|
| 187 |
+
# recommendations = ""
|
| 188 |
+
|
| 189 |
+
# return thumbnail, summary, sentiment_label, recommendations
|
| 190 |
+
|
| 191 |
+
# except Exception as e:
|
| 192 |
+
# return None, f"Error: {str(e)}", "N/A", ""
|
| 193 |
+
# def get_recommendations(keywords, max_results=5):
|
| 194 |
+
# if not keywords:
|
| 195 |
+
# return "Please provide search keywords"
|
| 196 |
+
# try:
|
| 197 |
+
# response = requests.get(
|
| 198 |
+
# "https://www.googleapis.com/youtube/v3/search",
|
| 199 |
+
# params={
|
| 200 |
+
# "part": "snippet",
|
| 201 |
+
# "q": f"educational {keywords}",
|
| 202 |
+
# "type": "video",
|
| 203 |
+
# "maxResults": max_results,
|
| 204 |
+
# "relevanceLanguage": "en",
|
| 205 |
+
# "key": YOUTUBE_API_KEY
|
| 206 |
+
# }
|
| 207 |
+
# ).json()
|
| 208 |
+
|
| 209 |
+
# results = []
|
| 210 |
+
# for item in response.get("items", []):
|
| 211 |
+
# title = item["snippet"]["title"]
|
| 212 |
+
# channel = item["snippet"]["channelTitle"]
|
| 213 |
+
# video_id = item["id"]["videoId"]
|
| 214 |
+
# results.append(f"📺 {title}\n👤 {channel}\n🔗 https://youtube.com/watch?v={video_id}\n")
|
| 215 |
+
|
| 216 |
+
# return "\n".join(results) if results else "No recommendations found"
|
| 217 |
+
# except Exception as e:
|
| 218 |
+
# return f"Error: {str(e)}"
|
| 219 |
+
|
| 220 |
+
# # Gradio Interface
|
| 221 |
+
# with gr.Blocks(theme=gr.themes.Soft()) as app:
|
| 222 |
+
# # Login Page
|
| 223 |
+
# with gr.Group() as login_page:
|
| 224 |
+
# gr.Markdown("# 🎓 Educational Learning Management System")
|
| 225 |
+
# username = gr.Textbox(label="Username")
|
| 226 |
+
# password = gr.Textbox(label="Password", type="password")
|
| 227 |
+
# login_btn = gr.Button("Login", variant="primary")
|
| 228 |
+
# login_msg = gr.Markdown()
|
| 229 |
+
|
| 230 |
+
# # Main Interface
|
| 231 |
+
# with gr.Group(visible=False) as main_page:
|
| 232 |
+
# with gr.Row():
|
| 233 |
+
# with gr.Column(scale=1):
|
| 234 |
+
# gr.Markdown("### 📋 Navigation")
|
| 235 |
+
# nav_dashboard = gr.Button("📊 Dashboard", variant="primary")
|
| 236 |
+
# nav_students = gr.Button("👥 Students")
|
| 237 |
+
# nav_teachers = gr.Button("👨🏫 Teachers")
|
| 238 |
+
# nav_courses = gr.Button("📚 Courses")
|
| 239 |
+
# nav_youtube = gr.Button("🎥 YouTube Tool")
|
| 240 |
+
# logout_btn = gr.Button("🚪 Logout", variant="stop")
|
| 241 |
+
|
| 242 |
+
# with gr.Column(scale=3):
|
| 243 |
+
# # Dashboard Content
|
| 244 |
+
# dashboard_page = gr.Group()
|
| 245 |
+
# with dashboard_page:
|
| 246 |
+
# gr.Markdown("## 📊 Dashboard")
|
| 247 |
+
# gr.Markdown(f"""
|
| 248 |
+
# ### System Overview
|
| 249 |
+
# - 👥 Total Students: {len(students_data)}
|
| 250 |
+
# - 👨🏫 Total Teachers: {len(teachers_data)}
|
| 251 |
+
# - 📚 Total Courses: {len(courses_data)}
|
| 252 |
+
|
| 253 |
+
# ### Quick Actions
|
| 254 |
+
# - View student performance
|
| 255 |
+
# - Access course materials
|
| 256 |
+
# - Generate learning insights
|
| 257 |
+
# """)
|
| 258 |
+
|
| 259 |
+
# # Students Content
|
| 260 |
+
# students_page = gr.Group(visible=False)
|
| 261 |
+
# with students_page:
|
| 262 |
+
# gr.Markdown("## 👥 Students")
|
| 263 |
+
# gr.DataFrame(
|
| 264 |
+
# value=students_data,
|
| 265 |
+
# headers=["ID", "Name", "Grade", "Program"]
|
| 266 |
+
# )
|
| 267 |
+
|
| 268 |
+
# # Teachers Content
|
| 269 |
+
# teachers_page = gr.Group(visible=False)
|
| 270 |
+
# with teachers_page:
|
| 271 |
+
# gr.Markdown("## 👨🏫 Teachers")
|
| 272 |
+
# gr.DataFrame(
|
| 273 |
+
# value=teachers_data,
|
| 274 |
+
# headers=["ID", "Name", "Subject", "Qualification"]
|
| 275 |
+
# )
|
| 276 |
+
|
| 277 |
+
# # Courses Content
|
| 278 |
+
# courses_page = gr.Group(visible=False)
|
| 279 |
+
# with courses_page:
|
| 280 |
+
# gr.Markdown("## 📚 Courses")
|
| 281 |
+
# gr.DataFrame(
|
| 282 |
+
# value=courses_data,
|
| 283 |
+
# headers=["ID", "Name", "Instructor", "Level"]
|
| 284 |
+
# )
|
| 285 |
+
|
| 286 |
+
# # YouTube Tool Content
|
| 287 |
+
# youtube_page = gr.Group(visible=False)
|
| 288 |
+
# with youtube_page:
|
| 289 |
+
# gr.Markdown("## Agent for YouTube Content Exploration")
|
| 290 |
+
# with gr.Row():
|
| 291 |
+
# with gr.Column(scale=2):
|
| 292 |
+
# video_url = gr.Textbox(
|
| 293 |
+
# label="YouTube URL",
|
| 294 |
+
# placeholder="https://youtube.com/watch?v=..."
|
| 295 |
+
# )
|
| 296 |
+
# keywords = gr.Textbox(
|
| 297 |
+
# label="Keywords for Recommendations",
|
| 298 |
+
# placeholder="e.g., python programming, machine learning"
|
| 299 |
+
# )
|
| 300 |
+
# analyze_btn = gr.Button("🔍 Analyze Video", variant="primary")
|
| 301 |
+
|
| 302 |
+
# with gr.Column(scale=1):
|
| 303 |
+
# video_thumbnail = gr.Image(label="Video Preview")
|
| 304 |
+
|
| 305 |
+
# with gr.Row():
|
| 306 |
+
# with gr.Column():
|
| 307 |
+
# summary = gr.Textbox(label="📝 Summary", lines=8)
|
| 308 |
+
# sentiment = gr.Textbox(label="😊 Content Sentiment")
|
| 309 |
+
# with gr.Column():
|
| 310 |
+
# recommendations = gr.Textbox(label="🎯 Related Videos", lines=10)
|
| 311 |
+
|
| 312 |
+
# def login_check(user, pwd):
|
| 313 |
+
# if USER_CREDENTIALS.get(user) == pwd:
|
| 314 |
+
# return {
|
| 315 |
+
# login_page: gr.update(visible=False),
|
| 316 |
+
# main_page: gr.update(visible=True),
|
| 317 |
+
# login_msg: ""
|
| 318 |
+
# }
|
| 319 |
+
# return {
|
| 320 |
+
# login_page: gr.update(visible=True),
|
| 321 |
+
# main_page: gr.update(visible=False),
|
| 322 |
+
# login_msg: "❌ Invalid credentials"
|
| 323 |
+
# }
|
| 324 |
+
|
| 325 |
+
# def show_page(page_name):
|
| 326 |
+
# updates = {
|
| 327 |
+
# dashboard_page: gr.update(visible=False),
|
| 328 |
+
# students_page: gr.update(visible=False),
|
| 329 |
+
# teachers_page: gr.update(visible=False),
|
| 330 |
+
# courses_page: gr.update(visible=False),
|
| 331 |
+
# youtube_page: gr.update(visible=False)
|
| 332 |
+
# }
|
| 333 |
+
# updates[page_name] = gr.update(visible=True)
|
| 334 |
+
# return updates
|
| 335 |
+
|
| 336 |
+
# # Event Handlers
|
| 337 |
+
# login_btn.click(
|
| 338 |
+
# login_check,
|
| 339 |
+
# inputs=[username, password],
|
| 340 |
+
# outputs=[login_page, main_page, login_msg]
|
| 341 |
+
# )
|
| 342 |
+
|
| 343 |
+
# nav_dashboard.click(lambda: show_page(dashboard_page), outputs=list(show_page(dashboard_page).keys()))
|
| 344 |
+
# nav_students.click(lambda: show_page(students_page), outputs=list(show_page(students_page).keys()))
|
| 345 |
+
# nav_teachers.click(lambda: show_page(teachers_page), outputs=list(show_page(teachers_page).keys()))
|
| 346 |
+
# nav_courses.click(lambda: show_page(courses_page), outputs=list(show_page(courses_page).keys()))
|
| 347 |
+
# nav_youtube.click(lambda: show_page(youtube_page), outputs=list(show_page(youtube_page).keys()))
|
| 348 |
+
|
| 349 |
+
# analyze_btn.click(
|
| 350 |
+
# process_youtube_video,
|
| 351 |
+
# inputs=[video_url, keywords],
|
| 352 |
+
# outputs=[video_thumbnail, summary, sentiment, recommendations]
|
| 353 |
+
# )
|
| 354 |
+
|
| 355 |
+
# logout_btn.click(
|
| 356 |
+
# lambda: {
|
| 357 |
+
# login_page: gr.update(visible=True),
|
| 358 |
+
# main_page: gr.update(visible=False)
|
| 359 |
+
# },
|
| 360 |
+
# outputs=[login_page, main_page]
|
| 361 |
+
# )
|
| 362 |
+
|
| 363 |
+
# if __name__ == "__main__":
|
| 364 |
+
# app.launch()
|
| 365 |
+
|
| 366 |
+
|
| 367 |
+
########################
|
| 368 |
+
# import os
|
| 369 |
+
# os.system('conda install -c conda-forge youtube-transcript-api -y')
|
| 370 |
+
# import subprocess
|
| 371 |
+
# subprocess.check_call(["pip", "install", "transformers==4.34.0"])
|
| 372 |
+
# subprocess.check_call(["pip", "install", "torch>=1.7.1"])
|
| 373 |
+
# subprocess.check_call(["pip", "install", "youtube_transcript_api>=0.6.3"])
|
| 374 |
+
# subprocess.check_call(["pip", "install", "pytube>=12.1.0"])
|
| 375 |
+
# subprocess.check_call(["pip", "install", "huggingface_hub>=0.19.0"])
|
| 376 |
+
# subprocess.check_call(["pip", "install", "PyPDF2>=3.0.1"])
|
| 377 |
+
# subprocess.check_call(["pip", "install", "google-generativeai>=0.3.0"])
|
| 378 |
+
# subprocess.check_call(["pip", "install", "textblob>=0.17.1"])
|
| 379 |
+
# subprocess.check_call(["pip", "install", "python-dotenv>=1.0.0"])
|
| 380 |
+
# subprocess.check_call(["pip", "install", "genai"])
|
| 381 |
+
# subprocess.check_call(["pip", "install", "google-cloud-aiplatform==1.34.0"])
|
| 382 |
+
# subprocess.check_call(["pip", "install", "scikit-learn>=1.0.0"])
|
| 383 |
+
# import transformers
|
| 384 |
+
# import torch
|
| 385 |
+
# import os
|
| 386 |
+
# import youtube_transcript_api
|
| 387 |
+
# import pytube
|
| 388 |
+
# import gradio
|
| 389 |
+
# import PyPDF2
|
| 390 |
+
# import pathlib
|
| 391 |
+
# import pandas
|
| 392 |
+
# import numpy
|
| 393 |
+
# import textblob
|
| 394 |
+
# import gradio as gr
|
| 395 |
+
# from youtube_transcript_api import YouTubeTranscriptApi
|
| 396 |
+
# import google.generativeai as genai
|
| 397 |
+
# import requests
|
| 398 |
+
# from textblob import TextBlob
|
| 399 |
+
# import re
|
| 400 |
+
# from dotenv import load_dotenv
|
| 401 |
+
# from sklearn.feature_extraction.text import TfidfVectorizer
|
| 402 |
+
# from sklearn.metrics.pairwise import cosine_similarity
|
| 403 |
+
|
| 404 |
+
|
| 405 |
+
# #from google.cloud import generativeai
|
| 406 |
+
# from huggingface_hub import login
|
| 407 |
+
# from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound
|
| 408 |
+
# def install_missing_packages():
|
| 409 |
+
# required_packages = {
|
| 410 |
+
# "torch":">=1.11.0",
|
| 411 |
+
# "transformers":">=4.34.0",
|
| 412 |
+
# "youtube_transcript_api" :">=0.6.3" ,
|
| 413 |
+
# "pytube":">=12.1.0",
|
| 414 |
+
# "huggingface_hub": ">=0.19.0",
|
| 415 |
+
# "PyPDF2": ">=3.0.1",
|
| 416 |
+
# "textblob":">=0.17.1",
|
| 417 |
+
# "python-dotenv":">=1.0.0",
|
| 418 |
+
# "genai":None,
|
| 419 |
+
# "google-generativeai": ">=0.3.0",
|
| 420 |
+
# "google-cloud-aiplatform":"==1.34.0",
|
| 421 |
+
# "scikit-learn": ">=1.0.0"
|
| 422 |
+
# }
|
| 423 |
+
|
| 424 |
+
|
| 425 |
+
# for package, version in required_packages.items():
|
| 426 |
+
# try:
|
| 427 |
+
# __import__(package)
|
| 428 |
+
# except ImportError:
|
| 429 |
+
# package_name = f"{package}{version}" if version else package
|
| 430 |
+
# subprocess.check_call(["pip", "install", package_name])
|
| 431 |
+
|
| 432 |
+
# install_missing_packages()
|
| 433 |
+
# # # Configuration
|
| 434 |
+
# # USER_CREDENTIALS = {
|
| 435 |
+
# # "admin": "password123",
|
| 436 |
+
# # "teacher": "teach2024",
|
| 437 |
+
# # "student": "learn2024"
|
| 438 |
+
# # }
|
| 439 |
+
|
| 440 |
+
# hf_token = os.getenv("HF_TOKEN")
|
| 441 |
+
# if hf_token:
|
| 442 |
+
# login(hf_token)
|
| 443 |
+
# else:
|
| 444 |
+
# raise ValueError("HF_TOKEN environment variable not set.")
|
| 445 |
+
|
| 446 |
+
# # GOOGLE_API_KEY = "AIzaSyAURQb9jueh3dBQ4SITgKoR0L2_33en3yU"
|
| 447 |
+
# # YOUTUBE_API_KEY = "AIzaSyB7X-RYjZmUuDSMTQsvCfyzURw5bhqOto4"
|
| 448 |
+
# # genai.configure(api_key=GOOGLE_API_KEY)
|
| 449 |
+
# # # GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
|
| 450 |
+
# # # genai.configure(api_key=GOOGLE_API_KEY)
|
| 451 |
+
# # # YOUTUBE_API_KEY = os.getenv("YOUTUBE_API_KEY")
|
| 452 |
+
# # # print("GOOGLE_API_KEY:", os.getenv("GOOGLE_API_KEY"))
|
| 453 |
+
# # # print("YOUTUBE_API_KEY:", os.getenv("YOUTUBE_API_KEY"))
|
| 454 |
+
|
| 455 |
+
# import os
|
| 456 |
+
# import gradio as gr
|
| 457 |
+
# from youtube_transcript_api import YouTubeTranscriptApi
|
| 458 |
+
# from dotenv import load_dotenv
|
| 459 |
+
# import google.generativeai as genai
|
| 460 |
+
# import requests
|
| 461 |
+
|
| 462 |
+
# from transformers import pipeline
|
| 463 |
+
# from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound
|
| 464 |
+
# from pytube import YouTube
|
| 465 |
+
# import gradio as gr
|
| 466 |
+
# from transformers import pipeline
|
| 467 |
+
# from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound
|
| 468 |
+
# from pytube import YouTube
|
| 469 |
+
# import gradio as gr
|
| 470 |
+
|
| 471 |
+
# # Function to extract transcript from a YouTube video
|
| 472 |
+
# def extract_transcript(youtube_video_url):
|
| 473 |
+
# try:
|
| 474 |
+
# video_id = youtube_video_url.split("v=")[1].split("&")[0] # Extract video ID from URL
|
| 475 |
+
|
| 476 |
+
# # Try to fetch transcript using YouTubeTranscriptApi
|
| 477 |
+
# try:
|
| 478 |
+
# transcript = YouTubeTranscriptApi.get_transcript(video_id)
|
| 479 |
+
# result = " ".join([i['text'] for i in transcript])
|
| 480 |
+
# return result
|
| 481 |
+
# except (TranscriptsDisabled, NoTranscriptFound):
|
| 482 |
+
# pass # Fallback to pytube if no transcript found
|
| 483 |
+
|
| 484 |
+
# # Fallback to pytube for captions
|
| 485 |
+
# yt = YouTube(youtube_video_url)
|
| 486 |
+
# if yt.captions:
|
| 487 |
+
# captions = yt.captions.get_by_language_code("en")
|
| 488 |
+
# if captions:
|
| 489 |
+
# transcript = captions.generate_srt_captions()
|
| 490 |
+
# return transcript.replace("\n", " ") # Clean SRT captions format
|
| 491 |
+
# else:
|
| 492 |
+
# return "Error: No English captions available for this video."
|
| 493 |
+
# else:
|
| 494 |
+
# return "Error: No captions available for this video."
|
| 495 |
+
|
| 496 |
+
# except Exception as e:
|
| 497 |
+
# return f"Error: Unable to process the video URL. Details: {str(e)}"
|
| 498 |
+
|
| 499 |
+
# # Function to summarize the text
|
| 500 |
+
# def summarize_transcript(transcript_text):
|
| 501 |
+
# try:
|
| 502 |
+
# summarizer = pipeline('summarization', model="facebook/bart-large-cnn") # Using BART model for summarization
|
| 503 |
+
# summarized_text = []
|
| 504 |
+
# num_iters = len(transcript_text) // 1000 + 1
|
| 505 |
+
|
| 506 |
+
# for i in range(num_iters):
|
| 507 |
+
# start = i * 1000
|
| 508 |
+
# end = (i + 1) * 1000
|
| 509 |
+
# chunk = transcript_text[start:end]
|
| 510 |
+
# if chunk.strip():
|
| 511 |
+
# out = summarizer(chunk, max_length=130, min_length=30, do_sample=False)
|
| 512 |
+
# summarized_text.append(out[0]['summary_text'])
|
| 513 |
+
|
| 514 |
+
# return " ".join(summarized_text)
|
| 515 |
+
# except Exception as e:
|
| 516 |
+
# return f"Error during summarization: {str(e)}"
|
| 517 |
+
|
| 518 |
+
# # Gradio Interface function
|
| 519 |
+
# def gradio_interface(youtube_url):
|
| 520 |
+
# transcript = extract_transcript(youtube_url)
|
| 521 |
+
# if transcript.startswith("Error"):
|
| 522 |
+
# return transcript, "Summarization cannot be performed due to transcript error."
|
| 523 |
+
|
| 524 |
+
# summarized_text = summarize_transcript(transcript)
|
| 525 |
+
# return transcript, summarized_text
|
| 526 |
+
|
| 527 |
+
# # Gradio Interface Design
|
| 528 |
+
# with gr.Blocks() as demo:
|
| 529 |
+
# gr.Markdown("# YouTube Video Summarizer")
|
| 530 |
+
# with gr.Row():
|
| 531 |
+
# youtube_url_input = gr.Textbox(
|
| 532 |
+
# label="YouTube Video URL",
|
| 533 |
+
# placeholder="Enter the YouTube video link here"
|
| 534 |
+
# )
|
| 535 |
+
# summarize_button = gr.Button("Summarize Transcript")
|
| 536 |
+
# with gr.Row():
|
| 537 |
+
# transcript_output = gr.Textbox(label="Original Transcript", lines=10, interactive=False)
|
| 538 |
+
# summary_output = gr.Textbox(label="Summarized Text", lines=10, interactive=False)
|
| 539 |
+
# summarize_button.click(
|
| 540 |
+
# fn=gradio_interface,
|
| 541 |
+
# inputs=[youtube_url_input],
|
| 542 |
+
# outputs=[transcript_output, summary_output]
|
| 543 |
+
# )
|
| 544 |
+
|
| 545 |
+
# # Launch Gradio App
|
| 546 |
+
# if __name__ == "__main__":
|
| 547 |
+
# demo.launch()
|
| 548 |
+
|
| 549 |
import os
|
| 550 |
os.system('conda install -c conda-forge youtube-transcript-api -y')
|
| 551 |
import subprocess
|
|
|
|
| 683 |
return match.group(1)
|
| 684 |
return None
|
| 685 |
|
| 686 |
+
def process_youtube_video(url="", keywords=""):
|
| 687 |
try:
|
| 688 |
if not url.strip():
|
| 689 |
return None, "Please enter a YouTube URL", "N/A", ""
|
|
|
|
| 909 |
|
| 910 |
if __name__ == "__main__":
|
| 911 |
app.launch()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|