app.py

app-2.py

@@ -0,0 +1,94 @@
+
+import whisper
+from moviepy.editor import VideoFileClip
+from transformers import pipeline
+import nltk
+import os
+import re
+import random
+import subprocess
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+from nltk.tokenize import sent_tokenize
+from nltk.corpus import stopwords
+
+nltk.download('punkt')
+nltk.download('stopwords')
+stop_words = set(stopwords.words('english'))
+
+def download_youtube_video(youtube_url, filename="youtube_video.mp4"):
+    print(f"⬇️ Downloading YouTube video via yt-dlp: {youtube_url}")
+    command = ["yt-dlp", "-f", "best[ext=mp4]+bestaudio/best", "-o", filename, youtube_url]
+    result = subprocess.run(command, capture_output=True, text=True)
+    if result.returncode != 0:
+        raise Exception("YouTube download failed: " + result.stderr)
+    return filename
+
+def extract_audio(video_path):
+    clip = VideoFileClip(video_path)
+    audio_path = "temp_audio.wav"
+    clip.audio.write_audiofile(audio_path, codec='pcm_s16le')
+    return audio_path
+
+def transcribe_audio(audio_path):
+    model = whisper.load_model("base")
+    result = model.transcribe(audio_path)
+    return result["text"]
+
+def generate_summary(text, max_len=130):
+    summarizer = pipeline("summarization")
+    sentences = sent_tokenize(text)
+    chunks = [' '.join(sentences[i:i+10]) for i in range(0, len(sentences), 10)]
+    summary = ""
+    for chunk in chunks:
+        summary += summarizer(chunk, max_length=max_len, min_length=30, do_sample=False)[0]["summary_text"] + " "
+    return summary.strip()
+
+def generate_subtitles(text):
+    sentences = sent_tokenize(text)
+    subtitles = []
+    for i, sentence in enumerate(sentences):
+        start_time = i * 5
+        end_time = start_time + 5
+        subtitles.append(f"{i+1}\n00:00:{start_time:02},000 --> 00:00:{end_time:02},000\n{sentence}\n")
+    return "\n".join(subtitles)
+
+def generate_quiz(text, num_questions=5):
+    sentences = sent_tokenize(text)
+    tfidf = TfidfVectorizer(stop_words='english')
+    X = tfidf.fit_transform(sentences)
+    quiz = []
+    used = set()
+    for _ in range(num_questions):
+        i = random.choice([x for x in range(len(sentences)) if x not in used])
+        used.add(i)
+        question = sentences[i]
+        options = [question]
+        while len(options) < 4:
+            j = random.randint(0, len(sentences) - 1)
+            if j != i and sentences[j] not in options:
+                options.append(sentences[j])
+        random.shuffle(options)
+        quiz.append({
+            "question": question,
+            "options": options,
+            "answer": question
+        })
+    return "\n\n".join(
+        [f"Q{i+1}: {q['question']}\nOptions:\n" + "\n".join([f"{chr(65+j)}. {opt}" for j, opt in enumerate(q['options'])]) for i, q in enumerate(quiz)]
+    )
+
+def process_video(video_path, selected_services):
+    results = {}
+    print("🔧 Extracting audio...")
+    audio_path = extract_audio(video_path)
+    transcription = transcribe_audio(audio_path) if "Transcription" in selected_services else None
+    if transcription:
+        results["transcription"] = transcription
+        if "Summary" in selected_services:
+            results["summary"] = generate_summary(transcription)
+        if "Subtitles" in selected_services:
+            results["subtitles"] = generate_subtitles(transcription)
+        if "Quiz" in selected_services:
+            results["quiz"] = generate_quiz(transcription)
+    return results