Method process_frames

CutSubtitle.py:63–112

处理文件夹中的所有帧并生成字幕

(self, input_folder, output_folder)

        return text.strip() if text else None

    def process_frames(self, input_folder, output_folder):
        """处理文件夹中的所有帧并生成字幕"""
        if not os.path.exists(output_folder):
            os.makedirs(output_folder)

        for filename in sorted(os.listdir(input_folder)):
            if not filename.endswith(('.jpg', '.png')):
                continue

            match = re.match(self.pattern, filename)
            if not match:
                continue

            episode_num, title, timestamp, similarity = match.groups()
            video_title = f"{episode_num}{title}"
            print(f"处理文件: {filename}")
            
            img_path = os.path.join(input_folder, filename)
            text = self.process_image(img_path)
            
            if not text:
                continue

            print(f"识别到文本: {text}")
            
            # 检查重复
            subtitles = self.subtitles_dict[video_title]
            if subtitles and subtitles[-1]["text"] == text:
                continue
            
            # 添加字幕
            self.subtitles_dict[video_title].append({
                "timestamp": timestamp,
                "similarity": float(similarity),
                "text": text
            })

        # 保存字幕文件
        for video_title, subtitles in self.subtitles_dict.items():
            sorted_subtitles = sorted(subtitles, key=lambda x: self.parse_timestamp(x["timestamp"]))
            output_json = os.path.join(output_folder, f"{video_title}.json")
            
            try:
                with open(output_json, 'w', encoding='utf-8') as f:
                    json.dump(sorted_subtitles, f, ensure_ascii=False, indent=4)
                print(f"成功保存 {video_title} 的字幕")
            except Exception as e:
                print(f"保存文件时出错: {str(e)}")

        print("\n处理完成")