test_youtube_crawler.py 14.1 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429
"""
YouTube Trending Crawler Tests
测试用例验证代码可运行
"""

import os
import sys
import json
import pytest
from unittest.mock import Mock, patch, MagicMock

# 添加父目录到路径
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))

from youtube_crawler import YouTubeTrendingCrawler


class TestYouTubeTrendingCrawler:
    """YouTubeTrendingCrawler 测试类"""

    def test_init_with_api_key(self):
        """测试使用参数传入 API Key"""
        crawler = YouTubeTrendingCrawler(api_key="test_key")
        assert crawler.api_key == "test_key"
        assert crawler.quota_used == 0

    def test_init_with_env_var(self):
        """测试从环境变量读取 API Key"""
        os.environ["YOUTUBE_API_KEY"] = "env_test_key"
        crawler = YouTubeTrendingCrawler()
        assert crawler.api_key == "env_test_key"

    def test_init_without_api_key(self):
        """测试未提供 API Key 时抛出异常"""
        # 清除环境变量
        if "YOUTUBE_API_KEY" in os.environ:
            del os.environ["YOUTUBE_API_KEY"]

        with pytest.raises(ValueError, match="API Key 未提供"):
            YouTubeTrendingCrawler()

    def test_video_categories(self):
        """测试视频分类映射"""
        assert YouTubeTrendingCrawler.VIDEO_CATEGORIES[10] == "Music"
        assert YouTubeTrendingCrawler.VIDEO_CATEGORIES[20] == "Gaming"
        assert YouTubeTrendingCrawler.VIDEO_CATEGORIES[24] == "Entertainment"
        assert YouTubeTrendingCrawler.VIDEO_CATEGORIES[28] == "Science & Technology"

    def test_region_codes(self):
        """测试地区代码列表"""
        assert "US" in YouTubeTrendingCrawler.REGION_CODES
        assert "JP" in YouTubeTrendingCrawler.REGION_CODES
        assert "KR" in YouTubeTrendingCrawler.REGION_CODES


class TestExtractVideoInfo:
    """测试 extract_video_info 方法"""

    def setup_method(self):
        self.crawler = YouTubeTrendingCrawler(api_key="test_key")

    def test_extract_complete_data(self):
        """测试完整数据解析"""
        api_item = {
            "id": "test123",
            "snippet": {
                "title": "Test Video",
                "description": "Test Description",
                "channelTitle": "Test Channel",
                "channelId": "UCtest",
                "publishedAt": "2024-01-15T10:00:00Z",
                "categoryId": "10",
                "thumbnails": {
                    "default": {"url": "https://default.jpg"},
                    "medium": {"url": "https://medium.jpg"},
                    "high": {"url": "https://high.jpg"}
                },
                "tags": ["tag1", "tag2"],
                "liveBroadcastContent": "none"
            },
            "statistics": {
                "viewCount": "1000000",
                "likeCount": "50000",
                "commentCount": "2000"
            },
            "contentDetails": {
                "duration": "PT3M45S"
            }
        }

        result = self.crawler.extract_video_info(api_item)

        assert result["videoId"] == "test123"
        assert result["title"] == "Test Video"
        assert result["url"] == "https://youtube.com/watch?v=test123"
        assert result["channelTitle"] == "Test Channel"
        assert result["viewCount"] == 1000000
        assert result["likeCount"] == 50000
        assert result["commentCount"] == 2000
        assert result["categoryName"] == "Music"
        assert result["duration"] == "PT3M45S"

    def test_extract_minimal_data(self):
        """测试最小数据解析"""
        api_item = {
            "id": "min123",
            "snippet": {
                "title": "Minimal",
                "channelTitle": "Channel"
            },
            "statistics": {}
        }

        result = self.crawler.extract_video_info(api_item)

        assert result["videoId"] == "min123"
        assert result["viewCount"] == 0
        assert result["likeCount"] == 0
        assert result["thumbnails"]["default"] == ""

    def test_extract_invalid_data(self):
        """测试无效数据处理"""
        result = self.crawler.extract_video_info({})
        assert result is None


class TestQuotaStatus:
    """测试配额管理功能"""

    def setup_method(self):
        self.crawler = YouTubeTrendingCrawler(api_key="test_key")

    def test_initial_quota(self):
        """测试初始配额状态"""
        status = self.crawler.get_quota_status()
        assert status["quota_used"] == 0
        assert status["quota_limit"] == 10000
        assert status["quota_remaining"] == 10000
        assert status["usage_percentage"] == 0.0

    def test_quota_after_usage(self):
        """测试使用后的配额状态"""
        self.crawler.quota_used = 500
        status = self.crawler.get_quota_status()
        assert status["quota_used"] == 500
        assert status["quota_remaining"] == 9500
        assert status["usage_percentage"] == 5.0


class TestSaveFunctions:
    """测试数据保存功能"""

    def setup_method(self):
        self.crawler = YouTubeTrendingCrawler(api_key="test_key")
        self.test_dir = os.path.dirname(os.path.abspath(__file__))

    def test_save_to_json(self, tmp_path):
        """测试 JSON 保存"""
        test_data = {"region": "US", "videos": [{"id": "1", "title": "Test"}]}
        filepath = str(tmp_path / "test.json")

        result = self.crawler.save_to_json(test_data, filepath=filepath)

        assert os.path.exists(result)
        with open(result, "r", encoding="utf-8") as f:
            loaded = json.load(f)
        assert loaded["region"] == "US"

    def test_save_to_csv(self, tmp_path):
        """测试 CSV 保存"""
        test_videos = [
            {
                "videoId": "vid1",
                "title": "Video 1",
                "channelTitle": "Channel 1",
                "viewCount": 1000,
                "thumbnails": {"high": "https://thumb.jpg"}
            }
        ]
        filepath = str(tmp_path / "test.csv")

        result = self.crawler.save_to_csv(test_videos, filepath=filepath)

        assert os.path.exists(result)
        with open(result, "r", encoding="utf-8") as f:
            content = f.read()
        assert "videoId" in content
        assert "vid1" in content

    def test_save_empty_videos(self, tmp_path):
        """测试保存空视频列表"""
        filepath = str(tmp_path / "empty.csv")
        result = self.crawler.save_to_csv([], filepath=filepath)
        assert os.path.exists(result)


class TestParameterValidation:
    """测试参数验证"""

    def setup_method(self):
        self.crawler = YouTubeTrendingCrawler(api_key="test_key")

    @patch.object(YouTubeTrendingCrawler, '_make_request')
    def test_max_results_validation(self, mock_request):
        """测试 max_results 参数验证"""
        mock_request.return_value = {"items": []}

        # 有效值
        self.crawler.get_trending(max_results=1)
        self.crawler.get_trending(max_results=50)

        # 无效值
        with pytest.raises(ValueError, match="max_results 必须在 1-50 之间"):
            self.crawler.get_trending(max_results=0)
        with pytest.raises(ValueError, match="max_results 必须在 1-50 之间"):
            self.crawler.get_trending(max_results=51)


class TestErrorHandling:
    """测试错误处理"""

    def setup_method(self):
        self.crawler = YouTubeTrendingCrawler(api_key="test_key")

    @patch('requests.Session.get')
    def test_403_quota_exceeded(self, mock_get):
        """测试配额耗尽错误"""
        mock_response = Mock()
        mock_response.status_code = 403
        mock_response.json.return_value = {
            "error": {"errors": [{"reason": "quotaExceeded"}]}
        }
        mock_get.return_value = mock_response

        with pytest.raises(ValueError, match="API 配额已耗尽"):
            self.crawler._make_request("videos", {"part": "snippet"})

    @patch('requests.Session.get')
    def test_403_invalid_key(self, mock_get):
        """测试无效 API Key 错误"""
        mock_response = Mock()
        mock_response.status_code = 403
        mock_response.json.return_value = {
            "error": {"errors": [{"reason": "keyInvalid"}]}
        }
        mock_get.return_value = mock_response

        with pytest.raises(ValueError, match="API Key 无效"):
            self.crawler._make_request("videos", {"part": "snippet"})

    @patch('requests.Session.get')
    def test_timeout_error(self, mock_get):
        """测试超时错误"""
        import requests
        mock_get.side_effect = requests.exceptions.Timeout()

        with pytest.raises(ValueError, match="请求超时"):
            self.crawler._make_request("videos", {"part": "snippet"})


class TestMockAPI:
    """使用 Mock 测试 API 调用"""

    def setup_method(self):
        self.crawler = YouTubeTrendingCrawler(api_key="test_key")

    @patch.object(YouTubeTrendingCrawler, '_make_request')
    def test_get_trending_success(self, mock_request):
        """测试获取热门视频成功"""
        mock_request.return_value = {
            "items": [
                {
                    "id": "video1",
                    "snippet": {
                        "title": "Video 1",
                        "channelTitle": "Channel 1",
                        "publishedAt": "2024-01-01T00:00:00Z",
                        "categoryId": "10",
                        "thumbnails": {"high": {"url": "https://thumb.jpg"}}
                    },
                    "statistics": {"viewCount": "1000"},
                    "contentDetails": {"duration": "PT1M"}
                }
            ],
            "nextPageToken": "token123"
        }

        result = self.crawler.get_trending(region_code="US", max_results=10)

        assert result["region_code"] == "US"
        assert result["total_results"] == 1
        assert result["next_page_token"] == "token123"
        assert len(result["videos"]) == 1
        assert result["videos"][0]["title"] == "Video 1"

    @patch.object(YouTubeTrendingCrawler, '_make_request')
    def test_get_trending_with_category(self, mock_request):
        """测试带分类的获取"""
        mock_request.return_value = {"items": []}

        self.crawler.get_trending(region_code="JP", category_id=10, max_results=5)

        # 验证请求参数
        call_args = mock_request.call_args
        assert call_args[0][0] == "videos"
        params = call_args[0][1]
        assert params["regionCode"] == "JP"
        assert params["videoCategoryId"] == 10
        assert params["maxResults"] == 5


class TestMultiRegion:
    """测试多地区批量获取"""

    def setup_method(self):
        self.crawler = YouTubeTrendingCrawler(api_key="test_key")

    @patch.object(YouTubeTrendingCrawler, 'get_trending')
    def test_multi_region_success(self, mock_get_trending):
        """测试多地区获取成功"""
        mock_get_trending.return_value = {
            "total_results": 5,
            "videos": [{"id": "v1"}]
        }

        results = self.crawler.get_multi_region_trending(
            regions=["US", "JP"],
            max_results=5
        )

        assert "US" in results
        assert "JP" in results
        assert results["US"]["total_results"] == 5

    @patch.object(YouTubeTrendingCrawler, 'get_trending')
    def test_multi_region_partial_failure(self, mock_get_trending):
        """测试部分失败处理"""
        def side_effect(*args, **kwargs):
            if kwargs.get("region_code") == "US":
                return {"total_results": 5, "videos": []}
            raise ValueError("API Error")

        mock_get_trending.side_effect = side_effect

        results = self.crawler.get_multi_region_trending(
            regions=["US", "XX"],
            max_results=5
        )

        assert results["US"]["total_results"] == 5
        assert "error" in results["XX"]


def run_basic_tests():
    """运行基础测试 (无需 pytest)"""
    print("=" * 60)
    print("YouTube Trending Crawler - 基础测试")
    print("=" * 60)

    # 测试 1: 初始化
    print("\n1. 测试初始化...")
    try:
        os.environ["YOUTUBE_API_KEY"] = "test_key"
        crawler = YouTubeTrendingCrawler()
        print("   ✅ 初始化成功")
    except Exception as e:
        print(f"   ❌ 初始化失败: {e}")

    # 测试 2: 分类映射
    print("\n2. 测试分类映射...")
    assert YouTubeTrendingCrawler.VIDEO_CATEGORIES[10] == "Music"
    assert YouTubeTrendingCrawler.VIDEO_CATEGORIES[20] == "Gaming"
    assert YouTubeTrendingCrawler.VIDEO_CATEGORIES[28] == "Science & Technology"
    print("   ✅ 分类映射正确")

    # 测试 3: 数据提取
    print("\n3. 测试数据提取...")
    api_item = {
        "id": "test123",
        "snippet": {
            "title": "Test Video",
            "channelTitle": "Test Channel",
            "publishedAt": "2024-01-15T10:00:00Z",
            "categoryId": "10",
            "thumbnails": {"high": {"url": "https://thumb.jpg"}}
        },
        "statistics": {"viewCount": "1000000"},
        "contentDetails": {"duration": "PT3M45S"}
    }
    result = crawler.extract_video_info(api_item)
    assert result["videoId"] == "test123"
    assert result["title"] == "Test Video"
    assert result["viewCount"] == 1000000
    print("   ✅ 数据提取正确")

    # 测试 4: 配额状态
    print("\n4. 测试配额状态...")
    status = crawler.get_quota_status()
    assert status["quota_limit"] == 10000
    print(f"   ✅ 配额限制: {status['quota_limit']}")

    # 测试 5: 参数验证
    print("\n5. 测试参数验证...")
    try:
        crawler.get_trending(max_results=0)
        print("   ❌ 应该抛出 max_results 无效的错误")
    except ValueError as e:
        if "max_results" in str(e):
            print("   ✅ 参数验证正确")
        else:
            print(f"   ❌ 错误信息不匹配: {e}")

    print("\n" + "=" * 60)
    print("✅ 基础测试通过!")
    print("=" * 60)


if __name__ == "__main__":
    # 运行基础测试
    run_basic_tests()

    # 如果安装了 pytest,运行完整测试
    try:
        import pytest
        print("\n运行 pytest 完整测试...")
        pytest.main([__file__, "-v"])
    except ImportError:
        print("\n未安装 pytest,跳过完整测试")
        print("安装命令: pip install pytest")