weapp
/
video_decode


			
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285
							#!/usr/bin/env python3
"""
脚本结果可视化工具 V2
功能：为 output_demo_script_v2.json 中的每个视频生成独立的HTML可视化页面
交互形式：卡片+点击详情
"""

import json
import argparse
import sys
from pathlib import Path
from datetime import datetime
from typing import List, Dict, Any, Optional
import html as html_module

# 保证可以从项目根目录导入
PROJECT_ROOT = Path(__file__).parent.parent
if str(PROJECT_ROOT) not in sys.path:
    sys.path.insert(0, str(PROJECT_ROOT))

# 导入tab模块
from static.visualize_v2.tab1 import generate_tab1_content
from static.visualize_v2.tab2 import generate_tab2_content
from static.visualize_v2.tab3 import generate_tab3_content
from static.visualize_v2.tab4 import generate_tab4_content


class ScriptResultVisualizerV2:
    """脚本结果可视化器 V2"""

    def __init__(self, json_file: str = None):
        """
        初始化可视化器

        Args:
            json_file: JSON文件路径
        """
        if json_file is None:
            self.json_file = None
        else:
            self.json_file = Path(json_file)
            if not self.json_file.is_absolute():
                self.json_file = Path.cwd() / json_file

    def load_json_data(self, file_path: Path) -> Optional[Dict[str, Any]]:
        """
        加载JSON文件

        Args:
            file_path: JSON文件路径

        Returns:
            JSON数据字典，加载失败返回None
        """
        try:
            with open(file_path, 'r', encoding='utf-8') as f:
                return json.load(f)
        except Exception as e:
            print(f"加载文件失败 {file_path}: {e}")
            return None

    def generate_html(self, data: Dict[str, Any], video_data: Dict[str, Any], json_filename: str) -> str:
        """生成完整的HTML页面"""
        # 开始构建HTML
        html = '<!DOCTYPE html>\n'
        html += '<html lang="zh-CN">\n'
        html += '<head>\n'
        html += '    <meta charset="UTF-8">\n'
        html += '    <meta name="viewport" content="width=device-width, initial-scale=1.0">\n'
        html += f'    <title>脚本结果可视化 V2 - {json_filename}</title>\n'
        html += '    <link rel="stylesheet" href="visualize/style.css">\n'
        html += '</head>\n'
        html += '<body>\n'

        html += '<div class="container">\n'

        # 页眉
        html += '<div class="header">\n'
        html += '    <h1>脚本结果可视化 V2</h1>\n'

        # 显示视频信息
        video_title = video_data.get("title", "")
        video_id = video_data.get("video_id", "")
        if video_title:
            html += f'    <div class="subtitle">{html_module.escape(video_title)}</div>\n'
        if video_id:
            html += f'    <div class="subtitle">视频ID: {video_id}</div>\n'
        html += f'    <div class="subtitle">{json_filename}</div>\n'
        html += f'    <div class="subtitle">生成时间: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}</div>\n'
        html += '</div>\n'

        # Tab导航
        html += '<div class="tabs">\n'
        html += '    <button class="tab active" onclick="switchTab(\'tab1\')">结构化内容库</button>\n'
        html += '    <button class="tab" onclick="switchTab(\'tab2\')">L3单元解构</button>\n'
        html += '    <button class="tab" onclick="switchTab(\'tab3\')">整体结构理解</button>\n'
        html += '    <button class="tab" onclick="switchTab(\'tab4\')">金句提取</button>\n'
        html += '</div>\n'

        # 主内容
        html += '<div class="content">\n'

        # Tab1内容：结构化内容库
        html += generate_tab1_content(data)

        # Tab2内容：L3单元解构
        html += generate_tab2_content(data)

        # Tab3内容：整体结构理解
        html += generate_tab3_content(data)

        # Tab4内容：金句提取
        html += generate_tab4_content(data)

        html += '</div>\n'

        # 页脚
        html += '<div class="footer">\n'
        html += f'    <p>生成时间: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}</p>\n'
        html += '</div>\n'

        html += '</div>\n'

        # JavaScript
        html += '<script src="visualize/script.js"></script>\n'

        html += '</body>\n'
        html += '</html>\n'

        return html

    def save_all_html(self, output_dir: str | Path | None = None) -> List[str]:
        """
        基于 output_demo_script_v2.json，为其中每个视频生成一个独立的 HTML 页面。

        支持结构：
        {
          "results": [
            {
              "video_data": {...},
              "script_result": {...}
            },
            ...
          ]
        }
        """
        if self.json_file is None:
            print("❌ 错误: 未指定JSON文件")
            return []

        # 加载JSON数据
        data = self.load_json_data(self.json_file)
        if data is None:
            return []

        results = data.get("results") or []
        if not isinstance(results, list) or not results:
            print("⚠️  JSON 中未找到有效的 results 数组")
            return []

        # 确定输出目录
        if output_dir is None:
            # 默认输出到examples/html目录
            output_dir = Path(__file__).parent / "html"
        else:
            output_dir = Path(output_dir)
            if not output_dir.is_absolute():
                output_dir = Path.cwd() / output_dir

        # 创建输出目录
        output_dir.mkdir(parents=True, exist_ok=True)

        # 确保样式和脚本文件可用：从 html/visualize 拷贝到 输出目录/visualize
        source_visualize_dir = Path(__file__).parent / "html" / "visualize"
        target_visualize_dir = output_dir / "visualize"
        if source_visualize_dir.exists() and source_visualize_dir.is_dir():
            import shutil
            target_visualize_dir.mkdir(parents=True, exist_ok=True)
            for item in source_visualize_dir.iterdir():
                dst = target_visualize_dir / item.name
                if item.is_file():
                    # 如果源文件和目标文件是同一个，跳过
                    if item.resolve() != dst.resolve():
                        shutil.copy2(item, dst)

        generated_paths: List[str] = []

        print(f"📁 检测到 output_demo_script_v2 格式，包含 {len(results)} 条结果")

        for idx, item in enumerate(results, start=1):
            script_data = item.get("script_result")
            if not isinstance(script_data, dict):
                print(f"⚠️  跳过第 {idx} 条结果：缺少 script_result 字段或结构不正确")
                continue

            video_data = item.get("video_data") or {}
            video_id = video_data.get("video_id") or video_data.get("channel_content_id")

            # 用于 HTML 内部展示的"文件名"标签
            json_label = f"{self.json_file.name}#{idx}"

            # 生成输出文件名：{video_id}_v2.html
            if video_id:
                output_filename = f"{video_id}_v2.html"
            else:
                output_filename = f"{self.json_file.stem}_{idx}_v2.html"

            output_path = output_dir / output_filename

            html_content = self.generate_html(script_data, video_data, json_label)

            with open(output_path, "w", encoding="utf-8") as f:
                f.write(html_content)

            generated_paths.append(str(output_path))
            print(f"✅ HTML文件已生成: {output_path}")

        if not generated_paths:
            print("⚠️  未能从 JSON 中生成任何 HTML 文件")

        return generated_paths


def main():
    """主函数"""
    # 解析命令行参数
    parser = argparse.ArgumentParser(
        description='脚本结果可视化工具 V2 - 基于 output_demo_script_v2.json 为每个视频生成独立的HTML页面',
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog="""
使用示例:
  # 在当前 examples 目录下使用默认的 output_demo_script_v2.json 并输出到 examples/html
  python visualize_script_results_v2.py

  # 指定 JSON 文件
  python visualize_script_results_v2.py examples/output_demo_script_v2.json

  # 指定 JSON 文件和输出目录
  python visualize_script_results_v2.py examples/output_demo_script_v2.json --output-dir examples/html
        """
    )

    parser.add_argument(
        'json_file',
        type=str,
        nargs='?',
        help='JSON文件路径（默认为 examples/output_demo_script_v2.json）'
    )

    parser.add_argument(
        '-o', '--output-dir',
        type=str,
        default=None,
        help='输出目录路径（默认: examples/html）'
    )

    args = parser.parse_args()

    # 确定 JSON 文件路径
    if args.json_file:
        json_path = Path(args.json_file)
        if not json_path.is_absolute():
            json_path = Path.cwd() / json_path
    else:
        # 默认使用 examples/output_demo_script_v2.json
        json_path = Path(__file__).parent / "output_demo_script_v2.json"

    print("🚀 开始生成脚本结果可视化 V2...")
    print(f"📁 JSON文件: {json_path}")
    print(f"📄 输出目录: {args.output_dir or (Path(__file__).parent / 'html')}")
    print()

    visualizer = ScriptResultVisualizerV2(json_file=str(json_path))
    generated_files = visualizer.save_all_html(output_dir=args.output_dir)

    if generated_files:
        print()
        print(f"🎉 完成! 共生成 {len(generated_files)} 个HTML文件")
        # 提示其中一个示例文件
        print(f"📄 示例: 请在浏览器中打开: {generated_files[0]}")


if __name__ == "__main__":
    main()