Update app.py

app.py

@@ -1,12 +1,19 @@
 from flask import Flask, request, jsonify, send_file
-from moviepy.editor import ColorClip,ImageClip, concatenate_videoclips
 import traceback
 import uuid
 import glob
-import os
 import asyncio
 from image_fetcher import main
 from video import create_text_image
+from moviepy.editor import *
+from PIL import Image
+import pytesseract
+import numpy as np
+from gtts import gTTS
+from mutagen.mp3 import MP3
+from gtts import gTTS
+import os
+from multiprocessing import Pool,cpu_count
 
 app = Flask(__name__)
 
@@ -84,18 +91,70 @@ def generate_video():
         image_olst=[]
         for id in range(len(lines)):
           create_text_image(lines[id],id,image_olst)
-        image_files = sorted(glob.glob(os.path.join(image_folder, "*.png")))
-        if not image_files:
-            raise ValueError("No images found in folder!")
-    
-        clips = [ImageClip(m).set_duration(5) for m in image_files]
-        video = concatenate_videoclips(clips, method="compose")
-        video_path = f"/tmp/video_{uuid.uuid4().hex}.mp4"
-        video.write_videofile(video_path, fps=24)
+        def video_func(id):
+          tts = gTTS(text=lines[id], lang='ta', slow=False)
+          filename = "audio"+str(id)+".mp3"
+          tts.save(filename)
+          if os.path.exists(filename):
+              audio = MP3(filename)
+              duration = audio.info.length
+          IMAGE_PATH = "images/slide"+str(id)+".png"     # Ensure this path is correct
+          VIDEO_DURATION = duration               # seconds
+          HIGHLIGHT_COLOR = (255, 255, 0)   # Yellow highlight
+          HIGHLIGHT_OPACITY = 0.5           # Semi-transparent
+        
+          # --- OCR STEP ---
+          img = Image.open(IMAGE_PATH)
+          data = pytesseract.image_to_data(img, output_type=pytesseract.Output.DICT)
+        
+          # Extract words and their positions
+          words = []
+          for i in range(len(data['text'])):
+              word = data['text'][i].strip()
+              if word and int(data['conf'][i]) > 60:
+                  x, y, w, h = data['left'][i], data['top'][i], data['width'][i], data['height'][i]
+                  words.append({'text': word, 'box': (x, y, w, h)})
+        
+          # --- BASE IMAGE CLIP ---
+          image_clip = ImageClip(IMAGE_PATH).set_duration(VIDEO_DURATION)
+        
+          # --- HIGHLIGHT WORDS ONE BY ONE ---
+          n_words = len(words)
+          highlight_duration = VIDEO_DURATION / n_words
+        
+          highlight_clips = []
+        
+          for i, word in enumerate(words):
+              x, y, w, h = word['box']
+              start = i * highlight_duration
+              end = start + highlight_duration
+        
+              # Create highlight rectangle
+              rect = ColorClip(size=(w, h), color=HIGHLIGHT_COLOR)
+              rect = rect.set_opacity(HIGHLIGHT_OPACITY).set_position((x, y)).set_start(start).set_end(end)
+        
+              highlight_clips.append(rect)
+        
+          # --- FINAL VIDEO --
+        
+          final_clip = CompositeVideoClip([image_clip] + highlight_clips)
+          audio = AudioFileClip(filename)
+          final_clip = final_clip.set_audio(audio)
+          final_clip.write_videofile("clip"+str(id)+".mp4", fps=24)
+        id=list(range(len(lines)))
+        with Pool(processes=cpu_count()) as pool:
+          pool.map(video_func,id)
+        clips = []
+        for id in range(len(lines)):
+            clip = VideoFileClip(f"clip{id}.mp4")
+            clips.append(clip)
+        
+        final_video = concatenate_videoclips(clips)
+        final_video.write_videofile("final_output.mp4", fps=24)
         for img in image_files:
             os.remove(img)
 
-        return send_file(video_path, mimetype='video/mp4')
+        return send_file("final_output.mp4", mimetype='video/mp4')
 
     except Exception as e:
         traceback.print_exc()