liulidong
/
knowledge_search


			
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818
							#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Stage5搜索结果可视化工具
生成带图片轮播的交互式HTML页面
"""

import json
import os
from datetime import datetime
from typing import List, Dict, Any


def load_data(json_path: str) -> List[Dict[str, Any]]:
    """加载JSON数据"""
    with open(json_path, 'r', encoding='utf-8') as f:
        return json.load(f)


def calculate_statistics(data: List[Dict[str, Any]]) -> Dict[str, Any]:
    """计算统计数据"""
    total_features = len(data)
    total_search_words = 0
    total_notes = 0
    video_count = 0
    normal_count = 0

    for feature in data:
        search_results = feature.get('组合评估结果', [])
        total_search_words += len(search_results)

        for search_item in search_results:
            search_result = search_item.get('search_result', {})
            notes = search_result.get('data', {}).get('data', [])
            total_notes += len(notes)

            for note in notes:
                note_type = note.get('note_card', {}).get('type', '')
                if note_type == 'video':
                    video_count += 1
                else:
                    normal_count += 1

    return {
        'total_features': total_features,
        'total_search_words': total_search_words,
        'total_notes': total_notes,
        'video_count': video_count,
        'normal_count': normal_count,
        'video_percentage': round(video_count / total_notes * 100, 1) if total_notes > 0 else 0,
        'normal_percentage': round(normal_count / total_notes * 100, 1) if total_notes > 0 else 0
    }


def generate_html(data: List[Dict[str, Any]], stats: Dict[str, Any], output_path: str):
    """生成HTML可视化页面"""

    # 准备数据JSON（用于JavaScript）
    data_json = json.dumps(data, ensure_ascii=False, indent=2)

    html_content = f'''<!DOCTYPE html>
<html lang="zh-CN">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Stage5 搜索结果可视化</title>
    <style>
        * {{
            margin: 0;
            padding: 0;
            box-sizing: border-box;
        }}

        body {{
            font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, "Helvetica Neue", Arial, sans-serif;
            background: #f5f7fa;
            color: #333;
            overflow-x: hidden;
        }}

        /* 顶部统计面板 */
        .stats-panel {{
            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
            color: white;
            padding: 20px;
            box-shadow: 0 2px 10px rgba(0,0,0,0.1);
        }}

        .stats-container {{
            max-width: 1400px;
            margin: 0 auto;
            display: flex;
            justify-content: space-around;
            align-items: center;
            flex-wrap: wrap;
            gap: 20px;
        }}

        .stat-item {{
            text-align: center;
        }}

        .stat-value {{
            font-size: 32px;
            font-weight: bold;
            margin-bottom: 5px;
        }}

        .stat-label {{
            font-size: 14px;
            opacity: 0.9;
        }}

        /* 主容器 */
        .main-container {{
            display: flex;
            max-width: 1400px;
            margin: 20px auto;
            gap: 20px;
            padding: 0 20px;
            height: calc(100vh - 140px);
        }}

        /* 左侧导航 */
        .left-sidebar {{
            width: 30%;
            background: white;
            border-radius: 8px;
            box-shadow: 0 2px 8px rgba(0,0,0,0.1);
            overflow-y: auto;
            position: sticky;
            top: 20px;
            height: fit-content;
            max-height: calc(100vh - 160px);
        }}

        .feature-group {{
            border-bottom: 1px solid #e5e7eb;
        }}

        .feature-header {{
            padding: 15px 20px;
            background: #f9fafb;
            cursor: pointer;
            user-select: none;
            transition: background 0.2s;
        }}

        .feature-header:hover {{
            background: #f3f4f6;
        }}

        .feature-header.active {{
            background: #667eea;
            color: white;
        }}

        .feature-title {{
            font-size: 16px;
            font-weight: 600;
            margin-bottom: 5px;
        }}

        .feature-meta {{
            font-size: 12px;
            color: #6b7280;
        }}

        .feature-header.active .feature-meta {{
            color: rgba(255,255,255,0.8);
        }}

        .search-words-list {{
            display: none;
            padding: 10px 0;
        }}

        .search-words-list.expanded {{
            display: block;
        }}

        .search-word-item {{
            padding: 12px 20px 12px 40px;
            cursor: pointer;
            border-left: 3px solid transparent;
            transition: all 0.2s;
        }}

        .search-word-item:hover {{
            background: #f9fafb;
            border-left-color: #667eea;
        }}

        .search-word-item.active {{
            background: #ede9fe;
            border-left-color: #7c3aed;
        }}

        .search-word-text {{
            font-size: 14px;
            font-weight: 500;
            color: #374151;
            margin-bottom: 4px;
        }}

        .search-word-score {{
            display: inline-block;
            padding: 2px 8px;
            border-radius: 12px;
            font-size: 11px;
            font-weight: 600;
            margin-left: 8px;
        }}

        .score-high {{
            background: #d1fae5;
            color: #065f46;
        }}

        .score-medium {{
            background: #fef3c7;
            color: #92400e;
        }}

        .score-low {{
            background: #fee2e2;
            color: #991b1b;
        }}

        .search-word-reasoning {{
            font-size: 12px;
            color: #6b7280;
            margin-top: 4px;
            display: -webkit-box;
            -webkit-line-clamp: 2;
            -webkit-box-orient: vertical;
            overflow: hidden;
        }}

        /* 右侧结果区 */
        .right-content {{
            flex: 1;
            overflow-y: auto;
            padding-bottom: 40px;
        }}

        .result-block {{
            background: white;
            border-radius: 8px;
            box-shadow: 0 2px 8px rgba(0,0,0,0.1);
            margin-bottom: 30px;
            padding: 20px;
            scroll-margin-top: 20px;
        }}

        .result-header {{
            margin-bottom: 20px;
            padding-bottom: 15px;
            border-bottom: 2px solid #e5e7eb;
        }}

        .result-title {{
            font-size: 20px;
            font-weight: 600;
            color: #111827;
            margin-bottom: 10px;
        }}

        .result-stats {{
            display: flex;
            gap: 15px;
            font-size: 13px;
            color: #6b7280;
        }}

        .stat-badge {{
            background: #f3f4f6;
            padding: 4px 10px;
            border-radius: 4px;
        }}

        /* 帖子网格 */
        .notes-grid {{
            display: grid;
            grid-template-columns: repeat(auto-fill, minmax(280px, 1fr));
            gap: 20px;
        }}

        .note-card {{
            border: 1px solid #e5e7eb;
            border-radius: 8px;
            overflow: hidden;
            cursor: pointer;
            transition: all 0.3s;
            background: white;
        }}

        .note-card:hover {{
            transform: translateY(-4px);
            box-shadow: 0 10px 25px rgba(0,0,0,0.15);
        }}

        /* 图片轮播 */
        .image-carousel {{
            position: relative;
            width: 100%;
            height: 280px;
            background: #f3f4f6;
            overflow: hidden;
        }}

        .carousel-images {{
            display: flex;
            height: 100%;
            transition: transform 0.3s ease;
        }}

        .carousel-image {{
            min-width: 100%;
            height: 100%;
            object-fit: cover;
        }}

        .carousel-btn {{
            position: absolute;
            top: 50%;
            transform: translateY(-50%);
            background: rgba(0,0,0,0.5);
            color: white;
            border: none;
            width: 32px;
            height: 32px;
            border-radius: 50%;
            cursor: pointer;
            font-size: 16px;
            display: none;
            align-items: center;
            justify-content: center;
            transition: background 0.2s;
            z-index: 10;
        }}

        .carousel-btn:hover {{
            background: rgba(0,0,0,0.7);
        }}

        .carousel-btn.prev {{
            left: 8px;
        }}

        .carousel-btn.next {{
            right: 8px;
        }}

        .note-card:hover .carousel-btn {{
            display: flex;
        }}

        .carousel-indicators {{
            position: absolute;
            bottom: 10px;
            left: 50%;
            transform: translateX(-50%);
            display: flex;
            gap: 6px;
            z-index: 10;
        }}

        .dot {{
            width: 8px;
            height: 8px;
            border-radius: 50%;
            background: rgba(255,255,255,0.5);
            cursor: pointer;
            transition: all 0.2s;
        }}

        .dot.active {{
            background: white;
            width: 24px;
            border-radius: 4px;
        }}

        .image-counter {{
            position: absolute;
            top: 10px;
            right: 10px;
            background: rgba(0,0,0,0.6);
            color: white;
            padding: 4px 8px;
            border-radius: 4px;
            font-size: 12px;
            z-index: 10;
        }}

        /* 帖子信息 */
        .note-info {{
            padding: 12px;
        }}

        .note-title {{
            font-size: 14px;
            font-weight: 500;
            color: #111827;
            margin-bottom: 8px;
            display: -webkit-box;
            -webkit-line-clamp: 2;
            -webkit-box-orient: vertical;
            overflow: hidden;
            line-height: 1.4;
        }}

        .note-meta {{
            display: flex;
            align-items: center;
            justify-content: space-between;
            font-size: 12px;
            color: #6b7280;
        }}

        .note-type {{
            padding: 3px 8px;
            border-radius: 4px;
            font-weight: 500;
        }}

        .type-video {{
            background: #dbeafe;
            color: #1e40af;
        }}

        .type-normal {{
            background: #d1fae5;
            color: #065f46;
        }}

        .note-author {{
            display: flex;
            align-items: center;
            gap: 6px;
        }}

        .author-avatar {{
            width: 24px;
            height: 24px;
            border-radius: 50%;
        }}

        /* SVG连线层 */
        #connection-svg {{
            position: fixed;
            top: 0;
            left: 0;
            width: 100%;
            height: 100%;
            pointer-events: none;
            z-index: 1;
        }}

        .connection-line {{
            stroke: #cbd5e1;
            stroke-width: 1;
            stroke-dasharray: 5,5;
            fill: none;
            opacity: 0.3;
            transition: all 0.2s;
        }}

        .connection-line.active {{
            stroke: #667eea;
            stroke-width: 2;
            stroke-dasharray: none;
            opacity: 1;
        }}

        /* 滚动条样式 */
        ::-webkit-scrollbar {{
            width: 8px;
            height: 8px;
        }}

        ::-webkit-scrollbar-track {{
            background: #f1f1f1;
        }}

        ::-webkit-scrollbar-thumb {{
            background: #888;
            border-radius: 4px;
        }}

        ::-webkit-scrollbar-thumb:hover {{
            background: #555;
        }}
    </style>
</head>
<body>
    <!-- 统计面板 -->
    <div class="stats-panel">
        <div class="stats-container">
            <div class="stat-item">
                <div class="stat-value">📊 {stats['total_features']}</div>
                <div class="stat-label">原始特征数</div>
            </div>
            <div class="stat-item">
                <div class="stat-value">🔍 {stats['total_search_words']}</div>
                <div class="stat-label">搜索词数</div>
            </div>
            <div class="stat-item">
                <div class="stat-value">📝 {stats['total_notes']}</div>
                <div class="stat-label">帖子总数</div>
            </div>
            <div class="stat-item">
                <div class="stat-value">🎬 {stats['video_count']}</div>
                <div class="stat-label">视频类型 ({stats['video_percentage']}%)</div>
            </div>
            <div class="stat-item">
                <div class="stat-value">📷 {stats['normal_count']}</div>
                <div class="stat-label">图文类型 ({stats['normal_percentage']}%)</div>
            </div>
        </div>
    </div>

    <!-- SVG连线层 -->
    <svg id="connection-svg"></svg>

    <!-- 主容器 -->
    <div class="main-container">
        <!-- 左侧导航 -->
        <div class="left-sidebar" id="leftSidebar">
            <!-- 通过JavaScript动态生成 -->
        </div>

        <!-- 右侧结果区 -->
        <div class="right-content" id="rightContent">
            <!-- 通过JavaScript动态生成 -->
        </div>
    </div>

    <script>
        // 数据
        const data = {data_json};

        // 渲染左侧导航
        function renderLeftSidebar() {{
            const sidebar = document.getElementById('leftSidebar');
            let html = '';

            data.forEach((feature, featureIdx) => {{
                const searchWords = feature['组合评估结果'] || [];

                html += `
                    <div class="feature-group">
                        <div class="feature-header" onclick="toggleFeature(${{featureIdx}})" id="feature-header-${{featureIdx}}">
                            <div class="feature-title">${{feature['原始特征名称']}}</div>
                            <div class="feature-meta">
                                ${{feature['来源层级']}} · 权重: ${{feature['权重'].toFixed(2)}} · ${{searchWords.length}}个搜索词
                            </div>
                        </div>
                        <div class="search-words-list" id="search-words-${{featureIdx}}">
                `;

                searchWords.forEach((sw, swIdx) => {{
                    const score = sw.score || 0;
                    const scoreClass = score >= 0.9 ? 'score-high' : score >= 0.7 ? 'score-medium' : 'score-low';
                    const blockId = `block-${{featureIdx}}-${{swIdx}}`;

                    html += `
                        <div class="search-word-item" onclick="scrollToBlock('${{blockId}}')"
                             id="sw-${{featureIdx}}-${{swIdx}}"
                             data-block-id="${{blockId}}">
                            <div class="search-word-text">
                                ${{sw.search_word}}
                                <span class="search-word-score ${{scoreClass}}">${{score.toFixed(2)}}</span>
                            </div>
                            <div class="search-word-reasoning" title="${{sw.reasoning}}">
                                ${{sw.reasoning || ''}}
                            </div>
                        </div>
                    `;
                }});

                html += `
                        </div>
                    </div>
                `;
            }});

            sidebar.innerHTML = html;
        }}

        // 渲染右侧结果区
        function renderRightContent() {{
            const content = document.getElementById('rightContent');
            let html = '';

            data.forEach((feature, featureIdx) => {{
                const searchWords = feature['组合评估结果'] || [];

                searchWords.forEach((sw, swIdx) => {{
                    const blockId = `block-${{featureIdx}}-${{swIdx}}`;
                    const searchResult = sw.search_result || {{}};
                    const notes = searchResult.data?.data || [];

                    const videoCount = notes.filter(n => n.note_card?.type === 'video').length;
                    const normalCount = notes.length - videoCount;

                    html += `
                        <div class="result-block" id="${{blockId}}">
                            <div class="result-header">
                                <div class="result-title">${{sw.search_word}}</div>
                                <div class="result-stats">
                                    <span class="stat-badge">📝 ${{notes.length}} 条帖子</span>
                                    <span class="stat-badge">🎬 ${{videoCount}} 视频</span>
                                    <span class="stat-badge">📷 ${{normalCount}} 图文</span>
                                </div>
                            </div>
                            <div class="notes-grid">
                                ${{notes.map((note, noteIdx) => renderNoteCard(note, featureIdx, swIdx, noteIdx)).join('')}}
                            </div>
                        </div>
                    `;
                }});
            }});

            content.innerHTML = html;
        }}

        // 渲染单个帖子卡片
        function renderNoteCard(note, featureIdx, swIdx, noteIdx) {{
            const card = note.note_card || {{}};
            const images = card.image_list || [];
            const title = card.display_title || '无标题';
            const noteType = card.type || 'normal';
            const noteId = note.id || '';
            const user = card.user || {{}};
            const userName = user.nick_name || '未知用户';
            const userAvatar = user.avatar || '';

            const carouselId = `carousel-${{featureIdx}}-${{swIdx}}-${{noteIdx}}`;

            return `
                <div class="note-card" onclick="openNote('${{noteId}}')">
                    <div class="image-carousel" id="${{carouselId}}">
                        <div class="carousel-images">
                            ${{images.map(img => `<img class="carousel-image" src="${{img}}" alt="帖子图片" loading="lazy">`).join('')}}
                        </div>
                        ${{images.length > 1 ? `
                            <button class="carousel-btn prev" onclick="event.stopPropagation(); changeImage('${{carouselId}}', -1)">←</button>
                            <button class="carousel-btn next" onclick="event.stopPropagation(); changeImage('${{carouselId}}', 1)">→</button>
                            <div class="carousel-indicators">
                                ${{images.map((_, i) => `<span class="dot ${{i === 0 ? 'active' : ''}}" onclick="event.stopPropagation(); goToImage('${{carouselId}}', ${{i}})"></span>`).join('')}}
                            </div>
                            <span class="image-counter">1/${{images.length}}</span>
                        ` : ''}}
                    </div>
                    <div class="note-info">
                        <div class="note-title">${{title}}</div>
                        <div class="note-meta">
                            <span class="note-type type-${{noteType}}">
                                ${{noteType === 'video' ? '🎬 视频' : '📷 图文'}}
                            </span>
                            <div class="note-author">
                                ${{userAvatar ? `<img class="author-avatar" src="${{userAvatar}}" alt="${{userName}}">` : ''}}
                                <span>${{userName}}</span>
                            </div>
                        </div>
                    </div>
                </div>
            `;
        }}

        // 图片轮播逻辑
        const carouselStates = {{}};

        function changeImage(carouselId, direction) {{
            if (!carouselStates[carouselId]) {{
                carouselStates[carouselId] = {{ currentIndex: 0 }};
            }}

            const carousel = document.getElementById(carouselId);
            const imagesContainer = carousel.querySelector('.carousel-images');
            const images = carousel.querySelectorAll('.carousel-image');
            const dots = carousel.querySelectorAll('.dot');
            const counter = carousel.querySelector('.image-counter');

            let newIndex = carouselStates[carouselId].currentIndex + direction;
            if (newIndex < 0) newIndex = images.length - 1;
            if (newIndex >= images.length) newIndex = 0;

            carouselStates[carouselId].currentIndex = newIndex;
            imagesContainer.style.transform = `translateX(-${{newIndex * 100}}%)`;

            // 更新指示器
            dots.forEach((dot, i) => {{
                dot.classList.toggle('active', i === newIndex);
            }});

            // 更新计数器
            if (counter) {{
                counter.textContent = `${{newIndex + 1}}/${{images.length}}`;
            }}
        }}

        function goToImage(carouselId, index) {{
            if (!carouselStates[carouselId]) {{
                carouselStates[carouselId] = {{ currentIndex: 0 }};
            }}

            const carousel = document.getElementById(carouselId);
            const imagesContainer = carousel.querySelector('.carousel-images');
            const dots = carousel.querySelectorAll('.dot');
            const counter = carousel.querySelector('.image-counter');

            carouselStates[carouselId].currentIndex = index;
            imagesContainer.style.transform = `translateX(-${{index * 100}}%)`;

            // 更新指示器
            dots.forEach((dot, i) => {{
                dot.classList.toggle('active', i === index);
            }});

            // 更新计数器
            if (counter) {{
                counter.textContent = `${{index + 1}}/${{dots.length}}`;
            }}
        }}

        // 展开/折叠特征组
        function toggleFeature(featureIdx) {{
            const searchWordsList = document.getElementById(`search-words-${{featureIdx}}`);
            const featureHeader = document.getElementById(`feature-header-${{featureIdx}}`);

            searchWordsList.classList.toggle('expanded');
            featureHeader.classList.toggle('active');
        }}

        // 滚动到指定结果块
        function scrollToBlock(blockId) {{
            const block = document.getElementById(blockId);
            if (block) {{
                block.scrollIntoView({{ behavior: 'smooth', block: 'start' }});

                // 高亮对应的搜索词
                document.querySelectorAll('.search-word-item').forEach(item => {{
                    item.classList.remove('active');
                }});

                document.querySelectorAll(`[data-block-id="${{blockId}}"]`).forEach(item => {{
                    item.classList.add('active');
                }});
            }}
        }}

        // 打开小红书帖子
        function openNote(noteId) {{
            if (noteId) {{
                window.open(`https://www.xiaohongshu.com/explore/${{noteId}}`, '_blank');
            }}
        }}

        // 初始化
        document.addEventListener('DOMContentLoaded', () => {{
            renderLeftSidebar();
            renderRightContent();

            // 默认展开第一个特征组
            if (data.length > 0) {{
                toggleFeature(0);
            }}
        }});
    </script>
</body>
</html>
'''

    # 写入文件
    with open(output_path, 'w', encoding='utf-8') as f:
        f.write(html_content)


def main():
    """主函数"""
    # 配置路径
    script_dir = os.path.dirname(os.path.abspath(__file__))
    json_path = os.path.join(script_dir, 'output_v2', 'stage5_with_search_results.json')
    output_dir = os.path.join(script_dir, 'visualization')
    os.makedirs(output_dir, exist_ok=True)

    timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
    output_path = os.path.join(output_dir, f'stage5_interactive_{timestamp}.html')

    # 加载数据
    print(f"📖 加载数据: {json_path}")
    data = load_data(json_path)
    print(f"✓ 加载了 {len(data)} 个原始特征")

    # 计算统计
    print("📊 计算统计数据...")
    stats = calculate_statistics(data)
    print(f"✓ 统计完成:")
    print(f"  - 原始特征: {stats['total_features']}")
    print(f"  - 搜索词: {stats['total_search_words']}")
    print(f"  - 帖子总数: {stats['total_notes']}")
    print(f"  - 视频: {stats['video_count']} ({stats['video_percentage']}%)")
    print(f"  - 图文: {stats['normal_count']} ({stats['normal_percentage']}%)")

    # 生成HTML
    print(f"\n🎨 生成可视化页面...")
    generate_html(data, stats, output_path)
    print(f"✓ 生成完成: {output_path}")

    # 打印访问提示
    print(f"\n🌐 在浏览器中打开查看:")
    print(f"   file://{output_path}")


if __name__ == '__main__':
    main()