Upload video_analyzer.py

video_analyzer.py

@@ -0,0 +1,124 @@
+
+import moviepy.editor as mp
+import cv2
+import numpy as np
+from PIL import Image
+import os
+import json
+from datetime import datetime
+
+from transformers import BlipProcessor, BlipForConditionalGeneration
+import torch
+
+# === BLIP Setup ===
+blip_processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+blip_model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+
+class VideoSceneAnalyzer:
+    def __init__(self, video_path, scene_duration=8):
+        self.video_path = video_path
+        self.scene_duration = scene_duration
+        self.clip = None
+        self.video_info = {}
+        self.scenes = []
+
+    def load_video(self):
+        try:
+            self.clip = mp.VideoFileClip(self.video_path)
+            self.video_info = {
+                'duration': self.clip.duration,
+                'fps': self.clip.fps,
+                'size': self.clip.size,
+                'aspect_ratio': self.clip.size[0] / self.clip.size[1],
+                'total_frames': int(self.clip.duration * self.clip.fps)
+            }
+            print(f"✅ Vídeo carregado: {self.video_info}")
+            return True
+        except Exception as e:
+            print(f"❌ Erro ao carregar vídeo: {e}")
+            return False
+
+    def describe_image_and_generate_prompt(self, frame, scene_number):
+        temp_img_path = f"temp_scene_{scene_number:02d}.jpg"
+        Image.fromarray(np.uint8(frame)).save(temp_img_path)
+        image = Image.open(temp_img_path).convert("RGB")
+        inputs = blip_processor(images=image, return_tensors="pt")
+        out = blip_model.generate(**inputs)
+        caption = blip_processor.decode(out[0], skip_special_tokens=True)
+        descricao = f"Imagem da cena {scene_number}: {caption.strip().capitalize()}."
+        prompt = (
+            f"{caption.strip().capitalize()}. Realistic lighting, professional cinematography, dynamic scene composition. "
+            "--ar 16:9 --v 6 --style photorealistic --quality 2"
+        )
+        return descricao, prompt
+
+    def extract_scenes(self):
+        if not self.clip:
+            print("❌ Vídeo não carregado.")
+            return False
+
+        total_duration = self.video_info['duration']
+        num_scenes = int(total_duration // self.scene_duration)
+        print(f"📹 Extraindo {num_scenes} cenas de {self.scene_duration}s cada...")
+
+        output_dir = f"scenes_{datetime.now().strftime('%Y%m%d_%H%M%S')}"
+        os.makedirs(output_dir, exist_ok=True)
+        self.scenes = []
+
+        for i in range(num_scenes):
+            start_time = i * self.scene_duration
+            end_time = min((i + 1) * self.scene_duration, total_duration)
+            mid_time = (start_time + end_time) / 2
+            print(f"🎬 Processando cena {i+1}/{num_scenes} ({start_time:.1f}s - {end_time:.1f}s)")
+
+            try:
+                frame = self.clip.get_frame(mid_time)
+                descricao, prompt = self.describe_image_and_generate_prompt(frame, i + 1)
+                img = Image.fromarray(np.uint8(frame))
+                img_path = os.path.join(output_dir, f"scene_{i+1:02d}.jpg")
+                img.save(img_path)
+
+                scene_info = {
+                    'scene_number': i + 1,
+                    'start_time': start_time,
+                    'end_time': end_time,
+                    'mid_time': mid_time,
+                    'image_path': img_path,
+                    'descricao_detalhada': descricao,
+                    'prompt_ia': prompt,
+                    'segment_info': {
+                        'duration': end_time - start_time,
+                        'position_percent': (start_time / total_duration) * 100
+                    }
+                }
+                self.scenes.append(scene_info)
+            except Exception as e:
+                print(f"⚠️ Erro ao processar cena {i+1}: {e}")
+                continue
+
+        print(f"✅ {len(self.scenes)} cenas extraídas com sucesso!")
+        return True
+
+    def save_results(self, output_file=None):
+        if not output_file:
+            output_file = f"video_analysis_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json"
+
+        results = {
+            'video_info': self.video_info,
+            'analysis_settings': {
+                'scene_duration': self.scene_duration,
+                'total_scenes': len(self.scenes)
+            },
+            'scenes': self.scenes,
+            'generated_at': datetime.now().isoformat()
+        }
+
+        with open(output_file, 'w', encoding='utf-8') as f:
+            json.dump(results, f, indent=2, ensure_ascii=False)
+
+        print(f"💾 Resultados salvos em: {output_file}")
+        return output_file
+
+    def cleanup(self):
+        if self.clip:
+            self.clip.close()