Update src/video_processing.py

src/video_processing.py

@@ -3,6 +3,14 @@ import requests
 import uuid
 import subprocess
 import time
+import os
+import tempfile
+import subprocess
+from typing import Optional, Tuple, List
+import pytube
+import docx
+import PyPDF2
+import re
 
 def extract_audio_from_video(video_path, output_format="mp3"):
     if not video_path:
@@ -31,44 +39,44 @@ def extract_audio_from_video(video_path, output_format="mp3"):
     except Exception as e:
         raise Exception(f"Error extracting audio: {str(e)}")
 
-def transcribe_audio(audio_path, api_key, model_id="scribe_v1"):
-    if not api_key:
-        raise Exception("API key required")
-    
-    url = "https://api.elevenlabs.io/v1/speech-to-text"
-    headers = {"xi-api-key": api_key}
+def transcribe_audio(audio_path, elevenlabs_api_key, model_id="scribe_v1"):
+    import requests
+    import tempfile
     
     try:
+        url = "https://api.elevenlabs.io/v1/speech-to-text"
+        headers = {"xi-api-key": elevenlabs_api_key}
+        
         with open(audio_path, "rb") as file:
+            files = {"file": file}
+            data = {"model_id": model_id}
+            
             response = requests.post(
-                url,
+                url, 
                 headers=headers,
-                files={"file": file, "model_id": (None, model_id)},
+                files=files,
+                data=data,
                 timeout=120
             )
         
         if response.status_code == 200:
             result = response.json()
-            transcript_text = result.get("text", "")
+            transcription = result.get('text', '')
             
-            # Save transcript to file
-            transcript_file = f"transcript_{uuid.uuid4().hex[:6]}.txt"
-            with open(transcript_file, "w", encoding="utf-8") as f:
-                f.write(transcript_text)
-            
-            return transcript_text, transcript_file, "Transcription completed successfully"
+            # Save transcription to file
+            transcript_path = tempfile.mktemp(suffix='.txt')
+            with open(transcript_path, 'w', encoding='utf-8') as f:
+                f.write(transcription)
+                
+            return transcription, transcript_path, "Transcription completed successfully"
         else:
-            raise Exception(f"API error: {response.status_code}")
+            return None, None, f"Transcription failed: {response.text}"
     except Exception as e:
-        raise Exception(f"Transcription failed: {str(e)}")
+        return None, None, f"Transcription error: {str(e)}"
 
 def process_video_file(video_path, audio_format, elevenlabs_api_key, model_id, gemini_api_key, language, content_type):
     try:
-        print("Starting video processing...")
-        start = time.time()
-        
         audio_path = extract_audio_from_video(video_path, audio_format)
-        print(f"Audio extracted in {time.time() - start:.2f}s. Transcribing...")
         
         transcription, transcript_path, transcription_status = transcribe_audio(
             audio_path, 
@@ -79,8 +87,6 @@ def process_video_file(video_path, audio_format, elevenlabs_api_key, model_id, g
         if not transcription:
             return audio_path, "Audio extracted, but transcription failed", None, transcription_status, None, None, None
         
-        print(f"Transcription completed in {time.time() - start:.2f}s. Analyzing content...")
-        
         # Generate summary or quiz from transcription
         formatted_output, json_path, txt_path = analyze_document(
             transcription, 
@@ -89,8 +95,45 @@ def process_video_file(video_path, audio_format, elevenlabs_api_key, model_id, g
             content_type
         )
         
-        print(f"Total processing time: {time.time() - start:.2f}s")
         return audio_path, "Processing completed successfully", transcript_path, transcription_status, formatted_output, txt_path, json_path
     except Exception as e:
         error_message = f"Error processing video: {str(e)}"
-        return None, error_message, None, error_message, error_message, None, None
+        return None, error_message, None, error_message, error_message, None, None
+
+
+
+def process_youtube_video(youtube_url, audio_format, elevenlabs_api_key, model_id, gemini_api_key, language, content_type):
+    try:
+        yt = pytube.YouTube(youtube_url)
+        stream = yt.streams.filter(progressive=True, file_extension='mp4').order_by('resolution').desc().first()
+        
+        if not stream:
+            raise Exception("No suitable video stream found")
+        
+        video_path = tempfile.mktemp(suffix='.mp4')
+        stream.download(filename=video_path)
+        
+        audio_path = extract_audio_from_video(video_path, audio_format)
+        
+        transcription, transcript_path, transcription_status = transcribe_audio(
+            audio_path, 
+            elevenlabs_api_key, 
+            model_id
+        )
+        
+        if not transcription:
+            return audio_path, "Audio extracted, but transcription failed", None, transcription_status, None, None, None
+        
+        # Generate summary or quiz from transcription
+        formatted_output, json_path, txt_path = analyze_document(
+            transcription, 
+            gemini_api_key, 
+            language, 
+            content_type
+        )
+        
+        return audio_path, "Processing completed successfully", transcript_path, transcription_status, formatted_output, txt_path, json_path
+    except Exception as e:
+        error_message = f"Error processing YouTube video: {str(e)}"
+        return None, error_message, None, error_message, error_message, None, None
+