crawlo 1.1.8__py3-none-any.whl → 1.2.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of crawlo might be problematic. Click here for more details.

Files changed (191) hide show
  1. crawlo/__init__.py +61 -61
  2. crawlo/__version__.py +1 -1
  3. crawlo/cleaners/__init__.py +60 -60
  4. crawlo/cleaners/data_formatter.py +225 -225
  5. crawlo/cleaners/encoding_converter.py +125 -125
  6. crawlo/cleaners/text_cleaner.py +232 -232
  7. crawlo/cli.py +65 -65
  8. crawlo/commands/__init__.py +14 -14
  9. crawlo/commands/check.py +594 -594
  10. crawlo/commands/genspider.py +151 -151
  11. crawlo/commands/help.py +132 -132
  12. crawlo/commands/list.py +155 -155
  13. crawlo/commands/run.py +292 -292
  14. crawlo/commands/startproject.py +418 -418
  15. crawlo/commands/stats.py +188 -188
  16. crawlo/commands/utils.py +186 -186
  17. crawlo/config.py +312 -312
  18. crawlo/config_validator.py +252 -252
  19. crawlo/core/__init__.py +2 -2
  20. crawlo/core/engine.py +354 -345
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +143 -136
  23. crawlo/crawler.py +1027 -1027
  24. crawlo/downloader/__init__.py +266 -266
  25. crawlo/downloader/aiohttp_downloader.py +220 -220
  26. crawlo/downloader/cffi_downloader.py +256 -256
  27. crawlo/downloader/httpx_downloader.py +259 -259
  28. crawlo/downloader/hybrid_downloader.py +213 -213
  29. crawlo/downloader/playwright_downloader.py +402 -402
  30. crawlo/downloader/selenium_downloader.py +472 -472
  31. crawlo/event.py +11 -11
  32. crawlo/exceptions.py +81 -81
  33. crawlo/extension/__init__.py +37 -37
  34. crawlo/extension/health_check.py +141 -141
  35. crawlo/extension/log_interval.py +57 -57
  36. crawlo/extension/log_stats.py +81 -81
  37. crawlo/extension/logging_extension.py +43 -43
  38. crawlo/extension/memory_monitor.py +104 -104
  39. crawlo/extension/performance_profiler.py +133 -133
  40. crawlo/extension/request_recorder.py +107 -107
  41. crawlo/filters/__init__.py +154 -154
  42. crawlo/filters/aioredis_filter.py +280 -280
  43. crawlo/filters/memory_filter.py +269 -269
  44. crawlo/items/__init__.py +23 -23
  45. crawlo/items/base.py +21 -21
  46. crawlo/items/fields.py +53 -53
  47. crawlo/items/items.py +104 -104
  48. crawlo/middleware/__init__.py +21 -21
  49. crawlo/middleware/default_header.py +32 -32
  50. crawlo/middleware/download_delay.py +28 -28
  51. crawlo/middleware/middleware_manager.py +135 -135
  52. crawlo/middleware/proxy.py +272 -272
  53. crawlo/middleware/request_ignore.py +30 -30
  54. crawlo/middleware/response_code.py +18 -18
  55. crawlo/middleware/response_filter.py +26 -26
  56. crawlo/middleware/retry.py +124 -124
  57. crawlo/mode_manager.py +211 -211
  58. crawlo/network/__init__.py +21 -21
  59. crawlo/network/request.py +338 -338
  60. crawlo/network/response.py +359 -359
  61. crawlo/pipelines/__init__.py +21 -21
  62. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  63. crawlo/pipelines/console_pipeline.py +39 -39
  64. crawlo/pipelines/csv_pipeline.py +316 -316
  65. crawlo/pipelines/database_dedup_pipeline.py +224 -224
  66. crawlo/pipelines/json_pipeline.py +218 -218
  67. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  68. crawlo/pipelines/mongo_pipeline.py +131 -131
  69. crawlo/pipelines/mysql_pipeline.py +316 -316
  70. crawlo/pipelines/pipeline_manager.py +61 -61
  71. crawlo/pipelines/redis_dedup_pipeline.py +167 -167
  72. crawlo/project.py +187 -187
  73. crawlo/queue/pqueue.py +37 -37
  74. crawlo/queue/queue_manager.py +337 -334
  75. crawlo/queue/redis_priority_queue.py +298 -298
  76. crawlo/settings/__init__.py +7 -7
  77. crawlo/settings/default_settings.py +219 -219
  78. crawlo/settings/setting_manager.py +122 -122
  79. crawlo/spider/__init__.py +639 -639
  80. crawlo/stats_collector.py +59 -59
  81. crawlo/subscriber.py +130 -130
  82. crawlo/task_manager.py +30 -30
  83. crawlo/templates/crawlo.cfg.tmpl +10 -10
  84. crawlo/templates/project/__init__.py.tmpl +3 -3
  85. crawlo/templates/project/items.py.tmpl +17 -17
  86. crawlo/templates/project/middlewares.py.tmpl +109 -109
  87. crawlo/templates/project/pipelines.py.tmpl +96 -96
  88. crawlo/templates/project/run.py.tmpl +45 -45
  89. crawlo/templates/project/settings.py.tmpl +326 -326
  90. crawlo/templates/project/settings_distributed.py.tmpl +119 -119
  91. crawlo/templates/project/settings_gentle.py.tmpl +94 -94
  92. crawlo/templates/project/settings_high_performance.py.tmpl +151 -151
  93. crawlo/templates/project/settings_simple.py.tmpl +68 -68
  94. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  95. crawlo/templates/spider/spider.py.tmpl +141 -141
  96. crawlo/tools/__init__.py +182 -182
  97. crawlo/tools/anti_crawler.py +268 -268
  98. crawlo/tools/authenticated_proxy.py +240 -240
  99. crawlo/tools/data_validator.py +180 -180
  100. crawlo/tools/date_tools.py +35 -35
  101. crawlo/tools/distributed_coordinator.py +386 -386
  102. crawlo/tools/retry_mechanism.py +220 -220
  103. crawlo/tools/scenario_adapter.py +262 -262
  104. crawlo/utils/__init__.py +35 -35
  105. crawlo/utils/batch_processor.py +260 -260
  106. crawlo/utils/controlled_spider_mixin.py +439 -439
  107. crawlo/utils/date_tools.py +290 -290
  108. crawlo/utils/db_helper.py +343 -343
  109. crawlo/utils/enhanced_error_handler.py +359 -359
  110. crawlo/utils/env_config.py +105 -105
  111. crawlo/utils/error_handler.py +125 -125
  112. crawlo/utils/func_tools.py +82 -82
  113. crawlo/utils/large_scale_config.py +286 -286
  114. crawlo/utils/large_scale_helper.py +343 -343
  115. crawlo/utils/log.py +128 -128
  116. crawlo/utils/performance_monitor.py +284 -284
  117. crawlo/utils/queue_helper.py +175 -175
  118. crawlo/utils/redis_connection_pool.py +334 -334
  119. crawlo/utils/redis_key_validator.py +199 -199
  120. crawlo/utils/request.py +267 -267
  121. crawlo/utils/request_serializer.py +219 -219
  122. crawlo/utils/spider_loader.py +62 -62
  123. crawlo/utils/system.py +11 -11
  124. crawlo/utils/tools.py +4 -4
  125. crawlo/utils/url.py +39 -39
  126. crawlo-1.2.0.dist-info/METADATA +697 -0
  127. crawlo-1.2.0.dist-info/RECORD +190 -0
  128. examples/__init__.py +7 -7
  129. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  130. tests/__init__.py +7 -7
  131. tests/advanced_tools_example.py +275 -275
  132. tests/authenticated_proxy_example.py +236 -236
  133. tests/cleaners_example.py +160 -160
  134. tests/config_validation_demo.py +102 -102
  135. tests/controlled_spider_example.py +205 -205
  136. tests/date_tools_example.py +180 -180
  137. tests/dynamic_loading_example.py +523 -523
  138. tests/dynamic_loading_test.py +104 -104
  139. tests/env_config_example.py +133 -133
  140. tests/error_handling_example.py +171 -171
  141. tests/redis_key_validation_demo.py +130 -130
  142. tests/response_improvements_example.py +144 -144
  143. tests/test_advanced_tools.py +148 -148
  144. tests/test_all_redis_key_configs.py +145 -145
  145. tests/test_authenticated_proxy.py +141 -141
  146. tests/test_cleaners.py +54 -54
  147. tests/test_comprehensive.py +146 -146
  148. tests/test_config_validator.py +193 -193
  149. tests/test_date_tools.py +123 -123
  150. tests/test_double_crawlo_fix.py +207 -207
  151. tests/test_double_crawlo_fix_simple.py +124 -124
  152. tests/test_dynamic_downloaders_proxy.py +124 -124
  153. tests/test_dynamic_proxy.py +92 -92
  154. tests/test_dynamic_proxy_config.py +146 -146
  155. tests/test_dynamic_proxy_real.py +109 -109
  156. tests/test_edge_cases.py +303 -303
  157. tests/test_enhanced_error_handler.py +270 -270
  158. tests/test_env_config.py +121 -121
  159. tests/test_error_handler_compatibility.py +112 -112
  160. tests/test_final_validation.py +153 -153
  161. tests/test_framework_env_usage.py +103 -103
  162. tests/test_integration.py +356 -356
  163. tests/test_item_dedup_redis_key.py +122 -122
  164. tests/test_parsel.py +29 -29
  165. tests/test_performance.py +327 -327
  166. tests/test_proxy_health_check.py +32 -32
  167. tests/test_proxy_middleware_integration.py +136 -136
  168. tests/test_proxy_providers.py +56 -56
  169. tests/test_proxy_stats.py +19 -19
  170. tests/test_proxy_strategies.py +59 -59
  171. tests/test_queue_manager_double_crawlo.py +174 -231
  172. tests/test_queue_manager_redis_key.py +176 -176
  173. tests/test_redis_config.py +28 -28
  174. tests/test_redis_connection_pool.py +294 -294
  175. tests/test_redis_key_naming.py +181 -181
  176. tests/test_redis_key_validator.py +123 -123
  177. tests/test_redis_queue.py +224 -224
  178. tests/test_request_serialization.py +70 -70
  179. tests/test_response_improvements.py +152 -152
  180. tests/test_scheduler.py +241 -241
  181. tests/test_simple_response.py +61 -61
  182. tests/test_telecom_spider_redis_key.py +205 -205
  183. tests/test_template_content.py +87 -87
  184. tests/test_template_redis_key.py +134 -134
  185. tests/test_tools.py +153 -153
  186. tests/tools_example.py +257 -257
  187. crawlo-1.1.8.dist-info/METADATA +0 -626
  188. crawlo-1.1.8.dist-info/RECORD +0 -190
  189. {crawlo-1.1.8.dist-info → crawlo-1.2.0.dist-info}/WHEEL +0 -0
  190. {crawlo-1.1.8.dist-info → crawlo-1.2.0.dist-info}/entry_points.txt +0 -0
  191. {crawlo-1.1.8.dist-info → crawlo-1.2.0.dist-info}/top_level.txt +0 -0
@@ -1,33 +1,33 @@
1
- # tests/test_proxy_health_check.py
2
- import pytest
3
- from unittest.mock import AsyncMock, patch
4
- from crawlo.proxy.health_check import check_single_proxy
5
- import httpx
6
-
7
-
8
- @pytest.mark.asyncio
9
- @patch('httpx.AsyncClient')
10
- async def test_health_check_success(mock_client_class):
11
- """测试健康检查:成功"""
12
- mock_resp = AsyncMock()
13
- mock_resp.status_code = 200
14
- mock_client_class.return_value.__aenter__.return_value.get.return_value = mock_resp
15
-
16
- proxy_info = {'url': 'http://good:8080', 'healthy': False}
17
- await check_single_proxy(proxy_info)
18
-
19
- assert proxy_info['healthy'] is True
20
- assert proxy_info['failures'] == 0
21
-
22
-
23
- @pytest.mark.asyncio
24
- @patch('httpx.AsyncClient')
25
- async def test_health_check_failure(mock_client_class):
26
- """测试健康检查:失败"""
27
- mock_client_class.return_value.__aenter__.return_value.get.side_effect = httpx.ConnectError("Failed")
28
-
29
- proxy_info = {'url': 'http://bad:8080', 'healthy': True, 'failures': 0}
30
- await check_single_proxy(proxy_info)
31
-
32
- assert proxy_info['healthy'] is False
1
+ # tests/test_proxy_health_check.py
2
+ import pytest
3
+ from unittest.mock import AsyncMock, patch
4
+ from crawlo.proxy.health_check import check_single_proxy
5
+ import httpx
6
+
7
+
8
+ @pytest.mark.asyncio
9
+ @patch('httpx.AsyncClient')
10
+ async def test_health_check_success(mock_client_class):
11
+ """测试健康检查:成功"""
12
+ mock_resp = AsyncMock()
13
+ mock_resp.status_code = 200
14
+ mock_client_class.return_value.__aenter__.return_value.get.return_value = mock_resp
15
+
16
+ proxy_info = {'url': 'http://good:8080', 'healthy': False}
17
+ await check_single_proxy(proxy_info)
18
+
19
+ assert proxy_info['healthy'] is True
20
+ assert proxy_info['failures'] == 0
21
+
22
+
23
+ @pytest.mark.asyncio
24
+ @patch('httpx.AsyncClient')
25
+ async def test_health_check_failure(mock_client_class):
26
+ """测试健康检查:失败"""
27
+ mock_client_class.return_value.__aenter__.return_value.get.side_effect = httpx.ConnectError("Failed")
28
+
29
+ proxy_info = {'url': 'http://bad:8080', 'healthy': True, 'failures': 0}
30
+ await check_single_proxy(proxy_info)
31
+
32
+ assert proxy_info['healthy'] is False
33
33
  assert proxy_info['failures'] == 1
@@ -1,137 +1,137 @@
1
- # tests/test_proxy_middleware_integration.py
2
- import pytest
3
- import asyncio
4
- import time
5
- from unittest.mock import Mock, AsyncMock, patch
6
- from crawlo import Request, Response, Spider
7
- from crawlo.proxy.middleware import ProxyMiddleware
8
- from crawlo.proxy.stats import ProxyStats
9
-
10
-
11
- @pytest.fixture
12
- def crawler():
13
- class MockSettings:
14
- def get(self, key, default=None):
15
- defaults = {
16
- 'PROXY_ENABLED': True,
17
- 'PROXIES': ['http://p1:8080', 'http://p2:8080'],
18
- 'PROXY_SELECTION_STRATEGY': 'random',
19
- 'PROXY_REQUEST_DELAY_ENABLED': False,
20
- 'PROXY_MAX_RETRY_COUNT': 1,
21
- }
22
- return defaults.get(key, default)
23
-
24
- def get_bool(self, key, default=None):
25
- return self.get(key, default)
26
-
27
- def get_int(self, key, default=None):
28
- return self.get(key, default)
29
-
30
- def get_float(self, key, default=None):
31
- return self.get(key, default)
32
-
33
- def get_list(self, key, default=None):
34
- return self.get(key, default)
35
-
36
- class MockCrawler:
37
- def __init__(self):
38
- self.settings = MockSettings()
39
-
40
- return MockCrawler()
41
-
42
-
43
- @pytest.fixture
44
- def middleware(crawler):
45
- mw = ProxyMiddleware.create_instance(crawler)
46
- mw._load_providers = Mock()
47
- mw._update_proxy_pool = AsyncMock()
48
- mw._health_check = AsyncMock()
49
- mw.scheduler = None
50
-
51
- mw.proxies = [
52
- {
53
- 'url': 'http://p1:8080',
54
- 'healthy': True,
55
- 'failures': 0,
56
- 'last_health_check': 0,
57
- 'unhealthy_since': 0
58
- },
59
- {
60
- 'url': 'http://p2:8080',
61
- 'healthy': True,
62
- 'failures': 0,
63
- 'last_health_check': 0,
64
- 'unhealthy_since': 0
65
- },
66
- ]
67
- mw.stats = ProxyStats()
68
- for p in mw.proxies:
69
- mw.stats.record(p['url'], 'total')
70
-
71
- asyncio.get_event_loop().run_until_complete(mw._initial_setup())
72
- return mw
73
-
74
-
75
- @pytest.fixture
76
- def spider():
77
- return Mock(spec=Spider, logger=Mock())
78
-
79
-
80
- def test_process_request_sets_proxy(middleware, spider):
81
- request = Request("https://example.com")
82
- result = asyncio.get_event_loop().run_until_complete(
83
- middleware.process_request(request, spider)
84
- )
85
- assert result is None
86
- assert hasattr(request, 'proxy')
87
- assert request.proxy in ['http://p1:8080', 'http://p2:8080']
88
-
89
-
90
- def test_process_response_records_success(middleware, spider):
91
- request = Request("https://example.com")
92
- request.proxy = 'http://p1:8080'
93
- response = Response("https://example.com", body=b"ok", headers={})
94
- middleware.stats.record(request.proxy, 'total')
95
- middleware.process_response(request, response, spider)
96
- assert middleware.stats.get(request.proxy)['success'] == 1
97
-
98
-
99
- def test_process_exception_switches_proxy(middleware, spider):
100
- request = Request("https://example.com")
101
- request.proxy = 'http://p1:8080'
102
- request.meta['proxy_retry_count'] = 0
103
-
104
- result = middleware.process_exception(request, Exception("Timeout"), spider)
105
- assert result is not None
106
- assert result.proxy != 'http://p1:8080'
107
- assert result.meta['proxy_retry_count'] == 1
108
-
109
- final = middleware.process_exception(result, Exception("Timeout"), spider)
110
- assert final is None
111
-
112
-
113
- def test_mark_failure_disables_proxy(middleware):
114
- proxy_url = 'http://p1:8080'
115
- p = next(p for p in middleware.proxies if p['url'] == proxy_url)
116
- p['failures'] = 2
117
-
118
- middleware._mark_failure(proxy_url)
119
- assert p['failures'] == 3
120
- assert p['healthy'] is False
121
- assert p['unhealthy_since'] > 0
122
-
123
-
124
- @pytest.mark.asyncio
125
- async def test_request_delay(middleware, spider):
126
- """测试请求延迟功能:验证是否调用了 asyncio.sleep"""
127
- with patch("crawlo.proxy.middleware.asyncio.sleep", new_callable=AsyncMock) as mock_sleep:
128
- middleware.delay_enabled = True # 注意:这里应该是 delay_enabled 而不是 request_delay_enabled
129
- middleware.request_delay = 0.1
130
- middleware._last_req_time = time.time() - 0.05 # 50ms 前
131
-
132
- request = Request("https://a.com")
133
- await middleware.process_request(request, spider)
134
-
135
- mock_sleep.assert_called_once()
136
- delay = mock_sleep.call_args[0][0]
1
+ # tests/test_proxy_middleware_integration.py
2
+ import pytest
3
+ import asyncio
4
+ import time
5
+ from unittest.mock import Mock, AsyncMock, patch
6
+ from crawlo import Request, Response, Spider
7
+ from crawlo.proxy.middleware import ProxyMiddleware
8
+ from crawlo.proxy.stats import ProxyStats
9
+
10
+
11
+ @pytest.fixture
12
+ def crawler():
13
+ class MockSettings:
14
+ def get(self, key, default=None):
15
+ defaults = {
16
+ 'PROXY_ENABLED': True,
17
+ 'PROXIES': ['http://p1:8080', 'http://p2:8080'],
18
+ 'PROXY_SELECTION_STRATEGY': 'random',
19
+ 'PROXY_REQUEST_DELAY_ENABLED': False,
20
+ 'PROXY_MAX_RETRY_COUNT': 1,
21
+ }
22
+ return defaults.get(key, default)
23
+
24
+ def get_bool(self, key, default=None):
25
+ return self.get(key, default)
26
+
27
+ def get_int(self, key, default=None):
28
+ return self.get(key, default)
29
+
30
+ def get_float(self, key, default=None):
31
+ return self.get(key, default)
32
+
33
+ def get_list(self, key, default=None):
34
+ return self.get(key, default)
35
+
36
+ class MockCrawler:
37
+ def __init__(self):
38
+ self.settings = MockSettings()
39
+
40
+ return MockCrawler()
41
+
42
+
43
+ @pytest.fixture
44
+ def middleware(crawler):
45
+ mw = ProxyMiddleware.create_instance(crawler)
46
+ mw._load_providers = Mock()
47
+ mw._update_proxy_pool = AsyncMock()
48
+ mw._health_check = AsyncMock()
49
+ mw.scheduler = None
50
+
51
+ mw.proxies = [
52
+ {
53
+ 'url': 'http://p1:8080',
54
+ 'healthy': True,
55
+ 'failures': 0,
56
+ 'last_health_check': 0,
57
+ 'unhealthy_since': 0
58
+ },
59
+ {
60
+ 'url': 'http://p2:8080',
61
+ 'healthy': True,
62
+ 'failures': 0,
63
+ 'last_health_check': 0,
64
+ 'unhealthy_since': 0
65
+ },
66
+ ]
67
+ mw.stats = ProxyStats()
68
+ for p in mw.proxies:
69
+ mw.stats.record(p['url'], 'total')
70
+
71
+ asyncio.get_event_loop().run_until_complete(mw._initial_setup())
72
+ return mw
73
+
74
+
75
+ @pytest.fixture
76
+ def spider():
77
+ return Mock(spec=Spider, logger=Mock())
78
+
79
+
80
+ def test_process_request_sets_proxy(middleware, spider):
81
+ request = Request("https://example.com")
82
+ result = asyncio.get_event_loop().run_until_complete(
83
+ middleware.process_request(request, spider)
84
+ )
85
+ assert result is None
86
+ assert hasattr(request, 'proxy')
87
+ assert request.proxy in ['http://p1:8080', 'http://p2:8080']
88
+
89
+
90
+ def test_process_response_records_success(middleware, spider):
91
+ request = Request("https://example.com")
92
+ request.proxy = 'http://p1:8080'
93
+ response = Response("https://example.com", body=b"ok", headers={})
94
+ middleware.stats.record(request.proxy, 'total')
95
+ middleware.process_response(request, response, spider)
96
+ assert middleware.stats.get(request.proxy)['success'] == 1
97
+
98
+
99
+ def test_process_exception_switches_proxy(middleware, spider):
100
+ request = Request("https://example.com")
101
+ request.proxy = 'http://p1:8080'
102
+ request.meta['proxy_retry_count'] = 0
103
+
104
+ result = middleware.process_exception(request, Exception("Timeout"), spider)
105
+ assert result is not None
106
+ assert result.proxy != 'http://p1:8080'
107
+ assert result.meta['proxy_retry_count'] == 1
108
+
109
+ final = middleware.process_exception(result, Exception("Timeout"), spider)
110
+ assert final is None
111
+
112
+
113
+ def test_mark_failure_disables_proxy(middleware):
114
+ proxy_url = 'http://p1:8080'
115
+ p = next(p for p in middleware.proxies if p['url'] == proxy_url)
116
+ p['failures'] = 2
117
+
118
+ middleware._mark_failure(proxy_url)
119
+ assert p['failures'] == 3
120
+ assert p['healthy'] is False
121
+ assert p['unhealthy_since'] > 0
122
+
123
+
124
+ @pytest.mark.asyncio
125
+ async def test_request_delay(middleware, spider):
126
+ """测试请求延迟功能:验证是否调用了 asyncio.sleep"""
127
+ with patch("crawlo.proxy.middleware.asyncio.sleep", new_callable=AsyncMock) as mock_sleep:
128
+ middleware.delay_enabled = True # 注意:这里应该是 delay_enabled 而不是 request_delay_enabled
129
+ middleware.request_delay = 0.1
130
+ middleware._last_req_time = time.time() - 0.05 # 50ms 前
131
+
132
+ request = Request("https://a.com")
133
+ await middleware.process_request(request, spider)
134
+
135
+ mock_sleep.assert_called_once()
136
+ delay = mock_sleep.call_args[0][0]
137
137
  assert 0.04 <= delay <= 0.06
@@ -1,57 +1,57 @@
1
- # tests/test_proxy_providers.py
2
- import pytest
3
- import pytest
4
- import respx
5
- from httpx import Response
6
- from crawlo.proxy.providers import StaticProxyProvider, FileProxyProvider, APIProxyProvider
7
- import tempfile
8
- import os
9
-
10
-
11
- @pytest.mark.asyncio
12
- async def test_static_provider():
13
- """测试静态代理提供者"""
14
- provider = StaticProxyProvider(['http://1.1.1.1:8080', 'http://2.2.2.2:8080'])
15
- proxies = await provider.fetch_proxies()
16
- assert len(proxies) == 2
17
- assert 'http://1.1.1.1:8080' in proxies
18
- assert 'http://2.2.2.2:8080' in proxies
19
-
20
-
21
- @pytest.mark.asyncio
22
- async def test_file_provider():
23
- """测试文件代理提供者"""
24
- with tempfile.NamedTemporaryFile(mode='w', delete=False) as f:
25
- f.write("http://a.com:8080\nhttp://b.com:8080\n")
26
- temp_path = f.name
27
- try:
28
- provider = FileProxyProvider(temp_path)
29
- proxies = await provider.fetch_proxies()
30
- assert len(proxies) == 2
31
- assert 'http://a.com:8080' in proxies
32
- assert 'http://b.com:8080' in proxies
33
- finally:
34
- os.unlink(temp_path)
35
-
36
-
37
- @pytest.mark.asyncio
38
- @respx.mock
39
- async def test_api_provider():
40
- """使用 respx 拦截 HTTP 请求,更简洁可靠"""
41
- # 拦截 GET 请求
42
- respx.get("https://api.example.com").mock(
43
- return_value=Response(
44
- 200,
45
- json=[
46
- {"ip": "1.1.1.1", "port": 8080},
47
- {"ip": "2.2.2.2", "port": 8080}
48
- ]
49
- )
50
- )
51
-
52
- provider = APIProxyProvider(url="https://api.example.com")
53
- proxies = await provider.fetch_proxies()
54
-
55
- assert len(proxies) == 2
56
- assert "http://1.1.1.1:8080" in proxies
1
+ # tests/test_proxy_providers.py
2
+ import pytest
3
+ import pytest
4
+ import respx
5
+ from httpx import Response
6
+ from crawlo.proxy.providers import StaticProxyProvider, FileProxyProvider, APIProxyProvider
7
+ import tempfile
8
+ import os
9
+
10
+
11
+ @pytest.mark.asyncio
12
+ async def test_static_provider():
13
+ """测试静态代理提供者"""
14
+ provider = StaticProxyProvider(['http://1.1.1.1:8080', 'http://2.2.2.2:8080'])
15
+ proxies = await provider.fetch_proxies()
16
+ assert len(proxies) == 2
17
+ assert 'http://1.1.1.1:8080' in proxies
18
+ assert 'http://2.2.2.2:8080' in proxies
19
+
20
+
21
+ @pytest.mark.asyncio
22
+ async def test_file_provider():
23
+ """测试文件代理提供者"""
24
+ with tempfile.NamedTemporaryFile(mode='w', delete=False) as f:
25
+ f.write("http://a.com:8080\nhttp://b.com:8080\n")
26
+ temp_path = f.name
27
+ try:
28
+ provider = FileProxyProvider(temp_path)
29
+ proxies = await provider.fetch_proxies()
30
+ assert len(proxies) == 2
31
+ assert 'http://a.com:8080' in proxies
32
+ assert 'http://b.com:8080' in proxies
33
+ finally:
34
+ os.unlink(temp_path)
35
+
36
+
37
+ @pytest.mark.asyncio
38
+ @respx.mock
39
+ async def test_api_provider():
40
+ """使用 respx 拦截 HTTP 请求,更简洁可靠"""
41
+ # 拦截 GET 请求
42
+ respx.get("https://api.example.com").mock(
43
+ return_value=Response(
44
+ 200,
45
+ json=[
46
+ {"ip": "1.1.1.1", "port": 8080},
47
+ {"ip": "2.2.2.2", "port": 8080}
48
+ ]
49
+ )
50
+ )
51
+
52
+ provider = APIProxyProvider(url="https://api.example.com")
53
+ proxies = await provider.fetch_proxies()
54
+
55
+ assert len(proxies) == 2
56
+ assert "http://1.1.1.1:8080" in proxies
57
57
  assert "http://2.2.2.2:8080" in proxies
tests/test_proxy_stats.py CHANGED
@@ -1,20 +1,20 @@
1
- # tests/test_proxy_stats.py
2
- from crawlo.proxy.stats import ProxyStats
3
-
4
-
5
- def test_proxy_stats():
6
- """测试代理统计功能"""
7
- stats = ProxyStats()
8
- url = 'http://proxy1:8080'
9
-
10
- stats.record(url, 'success')
11
- stats.record(url, 'success')
12
- stats.record(url, 'failure')
13
-
14
- assert stats.get(url)['success'] == 2
15
- assert stats.get(url)['failure'] == 1
16
- assert stats.get(url)['total'] == 3
17
-
18
- all_data = stats.all()
19
- assert url in all_data
1
+ # tests/test_proxy_stats.py
2
+ from crawlo.proxy.stats import ProxyStats
3
+
4
+
5
+ def test_proxy_stats():
6
+ """测试代理统计功能"""
7
+ stats = ProxyStats()
8
+ url = 'http://proxy1:8080'
9
+
10
+ stats.record(url, 'success')
11
+ stats.record(url, 'success')
12
+ stats.record(url, 'failure')
13
+
14
+ assert stats.get(url)['success'] == 2
15
+ assert stats.get(url)['failure'] == 1
16
+ assert stats.get(url)['total'] == 3
17
+
18
+ all_data = stats.all()
19
+ assert url in all_data
20
20
  assert all_data[url]['success'] == 2
@@ -1,60 +1,60 @@
1
- # tests/test_proxy_strategies.py
2
- import pytest
3
- from crawlo import Request
4
- from crawlo.proxy.strategies import STRATEGIES
5
-
6
-
7
- @pytest.fixture
8
- def mock_proxies():
9
- """提供测试用的代理列表"""
10
- return [
11
- {'url': 'http://p1:8080'},
12
- {'url': 'http://p2:8080'},
13
- {'url': 'http://p3:8080'},
14
- ]
15
-
16
-
17
- @pytest.fixture
18
- def mock_stats():
19
- """提供测试用的统计信息"""
20
- return {
21
- 'http://p1:8080': {'total': 10},
22
- 'http://p2:8080': {'total': 5},
23
- 'http://p3:8080': {'total': 1},
24
- }
25
-
26
-
27
- @pytest.fixture
28
- def mock_request():
29
- """提供测试用的请求对象"""
30
- return Request("https://example.com")
31
-
32
-
33
- def test_random_strategy(mock_proxies, mock_request, mock_stats):
34
- """测试随机策略"""
35
- strategy = STRATEGIES['random']
36
- chosen = strategy(mock_proxies, mock_request, mock_stats)
37
- assert chosen in [p['url'] for p in mock_proxies]
38
-
39
-
40
- def test_least_used_strategy(mock_proxies, mock_request, mock_stats):
41
- """测试最少使用策略"""
42
- strategy = STRATEGIES['least_used']
43
- chosen = strategy(mock_proxies, mock_request, mock_stats)
44
- assert chosen == 'http://p3:8080' # total=1
45
-
46
-
47
- def test_domain_rule_strategy(mock_proxies, mock_request, mock_stats):
48
- """测试域名规则策略"""
49
- from crawlo.proxy.strategies.domain_rule import domain_rule_strategy
50
- request = Request("https://taobao.com/item/123")
51
- rules = {'taobao.com': 'http://special:8080'}
52
-
53
- # Monkey patch 确保有回退策略
54
- old_strategy = STRATEGIES['least_used']
55
- try:
56
- STRATEGIES['least_used'] = lambda p, r, s: 'http://fallback:8080'
57
- chosen = domain_rule_strategy(mock_proxies, request, mock_stats, rules)
58
- assert chosen == 'http://special:8080'
59
- finally:
1
+ # tests/test_proxy_strategies.py
2
+ import pytest
3
+ from crawlo import Request
4
+ from crawlo.proxy.strategies import STRATEGIES
5
+
6
+
7
+ @pytest.fixture
8
+ def mock_proxies():
9
+ """提供测试用的代理列表"""
10
+ return [
11
+ {'url': 'http://p1:8080'},
12
+ {'url': 'http://p2:8080'},
13
+ {'url': 'http://p3:8080'},
14
+ ]
15
+
16
+
17
+ @pytest.fixture
18
+ def mock_stats():
19
+ """提供测试用的统计信息"""
20
+ return {
21
+ 'http://p1:8080': {'total': 10},
22
+ 'http://p2:8080': {'total': 5},
23
+ 'http://p3:8080': {'total': 1},
24
+ }
25
+
26
+
27
+ @pytest.fixture
28
+ def mock_request():
29
+ """提供测试用的请求对象"""
30
+ return Request("https://example.com")
31
+
32
+
33
+ def test_random_strategy(mock_proxies, mock_request, mock_stats):
34
+ """测试随机策略"""
35
+ strategy = STRATEGIES['random']
36
+ chosen = strategy(mock_proxies, mock_request, mock_stats)
37
+ assert chosen in [p['url'] for p in mock_proxies]
38
+
39
+
40
+ def test_least_used_strategy(mock_proxies, mock_request, mock_stats):
41
+ """测试最少使用策略"""
42
+ strategy = STRATEGIES['least_used']
43
+ chosen = strategy(mock_proxies, mock_request, mock_stats)
44
+ assert chosen == 'http://p3:8080' # total=1
45
+
46
+
47
+ def test_domain_rule_strategy(mock_proxies, mock_request, mock_stats):
48
+ """测试域名规则策略"""
49
+ from crawlo.proxy.strategies.domain_rule import domain_rule_strategy
50
+ request = Request("https://taobao.com/item/123")
51
+ rules = {'taobao.com': 'http://special:8080'}
52
+
53
+ # Monkey patch 确保有回退策略
54
+ old_strategy = STRATEGIES['least_used']
55
+ try:
56
+ STRATEGIES['least_used'] = lambda p, r, s: 'http://fallback:8080'
57
+ chosen = domain_rule_strategy(mock_proxies, request, mock_stats, rules)
58
+ assert chosen == 'http://special:8080'
59
+ finally:
60
60
  STRATEGIES['least_used'] = old_strategy