example_usage.py 6.98 KB
"""
YouTube Trending Video Crawler - Example Usage
示例代码:使用 YouTubeTrendingCrawler 获取热门视频数据

前置条件:
    export YOUTUBE_API_KEY="your_api_key_here"

安装依赖:
    pip install requests urllib3
"""

import os
import sys

# 添加当前目录到路径以导入 crawler 模块
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))

from youtube_crawler import YouTubeTrendingCrawler


def example_1_basic_usage():
    """示例 1: 基础使用 - 获取美国热门视频"""
    print("=" * 60)
    print("示例 1: 获取美国热门视频 (Top 10)")
    print("=" * 60)

    try:
        # 初始化爬虫
        crawler = YouTubeTrendingCrawler()

        # 获取美国热门视频
        result = crawler.get_trending(region_code="US", max_results=10)

        print(f"\n✅ 成功获取 {result['total_results']} 条视频")
        print(f"📊 配额使用: {result['quota_used']} units")

        # 显示前 3 条视频
        print("\n🎬 热门视频 Top 3:")
        for i, video in enumerate(result['videos'][:3], 1):
            print(f"  {i}. {video['title'][:50]}...")
            print(f"     👤 {video['channelTitle']} | 👁️ {video['viewCount']:,} 次观看")
            print(f"     🔗 {video['url']}")
            print()

        return result

    except ValueError as e:
        print(f"❌ 错误: {e}")
        return None


def example_2_category_filter():
    """示例 2: 分类过滤 - 获取日本音乐类热门视频"""
    print("=" * 60)
    print("示例 2: 获取日本音乐类热门视频")
    print("=" * 60)

    try:
        crawler = YouTubeTrendingCrawler()

        # 获取日本音乐类热门 (category_id=10)
        result = crawler.get_trending(
            region_code="JP",
            category_id=10,  # Music
            max_results=5
        )

        print(f"\n✅ 成功获取 {result['total_results']} 条音乐视频")

        print("\n🎵 日本热门音乐:")
        for video in result['videos']:
            print(f"  🎤 {video['title'][:45]}")
            print(f"     👤 {video['channelTitle']} | 👁️ {video['viewCount']:,} 次观看")
            print()

        return result

    except ValueError as e:
        print(f"❌ 错误: {e}")
        return None


def example_3_multi_region():
    """示例 3: 多地区批量获取"""
    print("=" * 60)
    print("示例 3: 批量获取多地区热门视频")
    print("=" * 60)

    try:
        crawler = YouTubeTrendingCrawler()

        # 批量获取 4 个地区的数据
        regions = ["US", "JP", "KR", "GB"]
        results = crawler.get_multi_region_trending(
            regions=regions,
            max_results=5
        )

        print(f"\n✅ 成功获取 {len(regions)} 个地区的数据")
        print(f"📊 总配额使用: {crawler.quota_used} units")

        print("\n🌍 各地区热门视频数量:")
        for region, data in results.items():
            if "error" not in data:
                print(f"  🇺🇸 {region}: {data['total_results']} 条视频")

        return results

    except ValueError as e:
        print(f"❌ 错误: {e}")
        return None


def example_4_save_data():
    """示例 4: 保存数据到文件"""
    print("=" * 60)
    print("示例 4: 保存数据到 JSON 和 CSV")
    print("=" * 60)

    try:
        crawler = YouTubeTrendingCrawler()

        # 获取数据
        result = crawler.get_trending(region_code="US", max_results=10)

        # 保存为 JSON
        json_path = crawler.save_to_json(
            data=result,
            filepath="output/trending_us.json",
            region="US"
        )
        print(f"\n✅ JSON 已保存: {json_path}")

        # 保存为 CSV
        csv_path = crawler.save_to_csv(
            videos=result['videos'],
            filepath="output/trending_us.csv",
            region="US"
        )
        print(f"✅ CSV 已保存: {csv_path}")

        return json_path, csv_path

    except ValueError as e:
        print(f"❌ 错误: {e}")
        return None, None


def example_5_quota_status():
    """示例 5: 查看配额使用状态"""
    print("=" * 60)
    print("示例 5: 配额使用状态")
    print("=" * 60)

    try:
        crawler = YouTubeTrendingCrawler()

        # 执行一些请求
        crawler.get_trending(region_code="US", max_results=10)
        crawler.get_trending(region_code="JP", max_results=10)
        crawler.get_trending(region_code="KR", max_results=10)

        # 查看配额状态
        quota = crawler.get_quota_status()

        print(f"\n📊 配额使用情况:")
        print(f"  已使用: {quota['quota_used']:,} / {quota['quota_limit']:,} units")
        print(f"  剩余: {quota['quota_remaining']:,} units")
        print(f"  使用率: {quota['usage_percentage']:.2f}%")

        return quota

    except ValueError as e:
        print(f"❌ 错误: {e}")
        return None


def example_6_all_categories():
    """示例 6: 获取所有分类的热门视频"""
    print("=" * 60)
    print("示例 6: 获取所有分类的热门视频 (US)")
    print("=" * 60)

    try:
        crawler = YouTubeTrendingCrawler()

        # 只获取几个主要分类
        main_categories = [10, 20, 24, 28]  # Music, Gaming, Entertainment, Science

        print(f"\n🎯 获取 {len(main_categories)} 个分类的数据...")

        for category_id in main_categories:
            result = crawler.get_trending(
                region_code="US",
                category_id=category_id,
                max_results=3
            )
            category_name = crawler.VIDEO_CATEGORIES.get(category_id, "Unknown")

            print(f"\n  📁 {category_name}:")
            for video in result['videos'][:2]:
                print(f"     • {video['title'][:40]}...")

            # 请求间隔
            import time
            time.sleep(0.5)

        print(f"\n📊 总配额使用: {crawler.quota_used} units")

    except ValueError as e:
        print(f"❌ 错误: {e}")


def main():
    """运行所有示例"""
    print("\n" + "=" * 60)
    print("🎬 YouTube Trending Crawler - 示例程序")
    print("=" * 60)

    # 检查 API Key
    if not os.getenv("YOUTUBE_API_KEY"):
        print("\n⚠️  警告: 未设置 YOUTUBE_API_KEY 环境变量")
        print("请执行: export YOUTUBE_API_KEY='your_api_key_here'")
        print("\n演示模式:展示代码结构和调用方式...\n")

    # 运行示例
    examples = [
        ("基础使用", example_1_basic_usage),
        ("分类过滤", example_2_category_filter),
        ("多地区获取", example_3_multi_region),
        ("保存数据", example_4_save_data),
        ("配额状态", example_5_quota_status),
        ("全部分类", example_6_all_categories),
    ]

    for name, func in examples:
        try:
            print(f"\n{'='*60}")
            func()
        except Exception as e:
            print(f"\n❌ 示例 '{name}' 执行失败: {e}")

    print("\n" + "=" * 60)
    print("✅ 所有示例执行完毕")
    print("=" * 60)


if __name__ == "__main__":
    main()