Update video2.py

video2.py

@@ -14,50 +14,58 @@ CLIPS_DIR = "/tmp/video"
 for path in [IMAGE_DIR, AUDIO_DIR, CLIPS_DIR]:
     os.makedirs(path, exist_ok=True)
 
-def video_func(id, lines):
-    print(f"Processing video for id={id}")
+# Generate audio
+# --- CONFIGURATION ---
+def video_func(id,lines):
+  tts = gTTS(text=lines[id], lang='ta', slow=False)
+  audio_name = "audio"+str(id)+".mp3"
+  audio_path=os.path.join(AUDIO_DIR,audio_name)
+  tts.save(audio_path)
+  if os.path.exists(audio_path):
+      audio = MP3(audio_path)
+      duration = audio.info.length
+  IMAGE_PATH = os.path.join(IMAGE_DIR,f"slide{id}.png")   # Ensure this path is correct
+  VIDEO_DURATION = duration               # seconds
+  HIGHLIGHT_COLOR = (255, 255, 0)   # Yellow highlight
+  HIGHLIGHT_OPACITY = 0.5           # Semi-transparent
 
-    # Generate audio
-    tts = gTTS(text=lines[id], lang='ta', slow=False)
-    audio_path = os.path.join(AUDIO_DIR, f"audio{id}.mp3")
-    tts.save(audio_path)
+  # --- OCR STEP ---
+  img = Image.open(IMAGE_PATH)
+  data = pytesseract.image_to_data(img, output_type=pytesseract.Output.DICT)
 
-    if not os.path.exists(audio_path):
-        raise FileNotFoundError(f"Audio file not created: {audio_path}")
+  # 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)})
 
-    audio = MP3(audio_path)
-    duration = audio.info.length
+  # --- BASE IMAGE CLIP ---
+  image_clip = ImageClip(IMAGE_PATH).set_duration(VIDEO_DURATION)
 
-    img_path = os.path.join(IMAGE_DIR, f"slide{id}.png")
-    if not os.path.exists(img_path):
-        raise FileNotFoundError(f"Missing image: {img_path}")
+  # --- HIGHLIGHT WORDS ONE BY ONE ---
+  n_words = len(words)
+  highlight_duration = VIDEO_DURATION / n_words
 
-    # OCR
-    img = Image.open(img_path)
-    data = pytesseract.image_to_data(img, output_type=pytesseract.Output.DICT)
+  highlight_clips = []
 
-    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)})
+  for i, word in enumerate(words):
+      x, y, w, h = word['box']
+      start = i * highlight_duration
+      end = start + highlight_duration
 
-    image_clip = ImageClip(img_path).set_duration(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)
 
-    n_words = len(words)
-    highlight_duration = duration / n_words if n_words else duration
+      highlight_clips.append(rect)
 
-    highlight_clips = []
-    for i, word in enumerate(words):
-        x, y, w, h = word['box']
-        rect = ColorClip(size=(w, h), color=(255, 255, 0))
-        rect = rect.set_opacity(0.5).set_position((x, y))
-        rect = rect.set_start(i * highlight_duration).set_end((i + 1) * highlight_duration)
-        highlight_clips.append(rect)
+  # --- FINAL VIDEO --
 
-    final = CompositeVideoClip([image_clip] + highlight_clips)
-    final = final.set_audio(AudioFileClip(audio_path))
-
-    video_path = os.path.join(CLIPS_DIR, f"clip{id}.mp4")
-    final.write_videofile(video_path, fps=24, verbose=True)
+  final_clip = CompositeVideoClip([image_clip] + highlight_clips)
+  audio = AudioFileClip(audio_path)
+  final_clip = final_clip.set_audio(audio)
+  clip_name = "clip"+str(id)+".mp4"
+  video_path=os.path.join(CLIPS_DIR,clip_name)
+  final_clip.write_videofile(video_path, fps=24)