crawlo 1.4.1__py3-none-any.whl → 1.4.3__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 (326) hide show
  1. crawlo/__init__.py +93 -93
  2. crawlo/__version__.py +1 -1
  3. crawlo/cli.py +75 -75
  4. crawlo/commands/__init__.py +14 -14
  5. crawlo/commands/check.py +594 -594
  6. crawlo/commands/genspider.py +151 -151
  7. crawlo/commands/help.py +138 -138
  8. crawlo/commands/list.py +155 -155
  9. crawlo/commands/run.py +341 -341
  10. crawlo/commands/startproject.py +436 -436
  11. crawlo/commands/stats.py +187 -187
  12. crawlo/commands/utils.py +196 -196
  13. crawlo/config.py +312 -312
  14. crawlo/config_validator.py +277 -277
  15. crawlo/core/__init__.py +52 -52
  16. crawlo/core/engine.py +438 -439
  17. crawlo/core/processor.py +47 -47
  18. crawlo/core/scheduler.py +291 -257
  19. crawlo/crawler.py +650 -650
  20. crawlo/data/__init__.py +5 -5
  21. crawlo/data/user_agents.py +194 -194
  22. crawlo/downloader/__init__.py +273 -273
  23. crawlo/downloader/aiohttp_downloader.py +233 -228
  24. crawlo/downloader/cffi_downloader.py +245 -245
  25. crawlo/downloader/httpx_downloader.py +259 -259
  26. crawlo/downloader/hybrid_downloader.py +212 -212
  27. crawlo/downloader/playwright_downloader.py +402 -402
  28. crawlo/downloader/selenium_downloader.py +472 -472
  29. crawlo/event.py +11 -11
  30. crawlo/exceptions.py +81 -81
  31. crawlo/extension/__init__.py +63 -63
  32. crawlo/extension/health_check.py +141 -141
  33. crawlo/extension/log_interval.py +94 -94
  34. crawlo/extension/log_stats.py +70 -70
  35. crawlo/extension/logging_extension.py +61 -61
  36. crawlo/extension/memory_monitor.py +104 -104
  37. crawlo/extension/performance_profiler.py +133 -133
  38. crawlo/extension/request_recorder.py +107 -107
  39. crawlo/factories/__init__.py +27 -27
  40. crawlo/factories/base.py +68 -68
  41. crawlo/factories/crawler.py +103 -103
  42. crawlo/factories/registry.py +84 -84
  43. crawlo/filters/__init__.py +154 -154
  44. crawlo/filters/aioredis_filter.py +257 -257
  45. crawlo/filters/memory_filter.py +269 -269
  46. crawlo/framework.py +292 -292
  47. crawlo/initialization/__init__.py +44 -44
  48. crawlo/initialization/built_in.py +425 -425
  49. crawlo/initialization/context.py +141 -141
  50. crawlo/initialization/core.py +193 -193
  51. crawlo/initialization/phases.py +148 -148
  52. crawlo/initialization/registry.py +145 -145
  53. crawlo/items/__init__.py +23 -23
  54. crawlo/items/base.py +23 -23
  55. crawlo/items/fields.py +52 -52
  56. crawlo/items/items.py +104 -104
  57. crawlo/logging/__init__.py +45 -37
  58. crawlo/logging/async_handler.py +181 -0
  59. crawlo/logging/config.py +196 -96
  60. crawlo/logging/factory.py +171 -128
  61. crawlo/logging/manager.py +111 -111
  62. crawlo/logging/monitor.py +153 -0
  63. crawlo/logging/sampler.py +167 -0
  64. crawlo/middleware/__init__.py +21 -21
  65. crawlo/middleware/default_header.py +132 -132
  66. crawlo/middleware/download_delay.py +104 -104
  67. crawlo/middleware/middleware_manager.py +135 -135
  68. crawlo/middleware/offsite.py +123 -123
  69. crawlo/middleware/proxy.py +386 -386
  70. crawlo/middleware/request_ignore.py +86 -86
  71. crawlo/middleware/response_code.py +150 -150
  72. crawlo/middleware/response_filter.py +136 -136
  73. crawlo/middleware/retry.py +124 -124
  74. crawlo/middleware/simple_proxy.py +65 -65
  75. crawlo/mode_manager.py +219 -219
  76. crawlo/network/__init__.py +21 -21
  77. crawlo/network/request.py +379 -379
  78. crawlo/network/response.py +359 -359
  79. crawlo/pipelines/__init__.py +21 -21
  80. crawlo/pipelines/bloom_dedup_pipeline.py +146 -146
  81. crawlo/pipelines/console_pipeline.py +39 -39
  82. crawlo/pipelines/csv_pipeline.py +316 -316
  83. crawlo/pipelines/database_dedup_pipeline.py +197 -197
  84. crawlo/pipelines/json_pipeline.py +218 -218
  85. crawlo/pipelines/memory_dedup_pipeline.py +105 -105
  86. crawlo/pipelines/mongo_pipeline.py +131 -131
  87. crawlo/pipelines/mysql_pipeline.py +325 -325
  88. crawlo/pipelines/pipeline_manager.py +100 -84
  89. crawlo/pipelines/redis_dedup_pipeline.py +156 -156
  90. crawlo/project.py +349 -338
  91. crawlo/queue/pqueue.py +42 -42
  92. crawlo/queue/queue_manager.py +526 -522
  93. crawlo/queue/redis_priority_queue.py +370 -367
  94. crawlo/settings/__init__.py +7 -7
  95. crawlo/settings/default_settings.py +284 -284
  96. crawlo/settings/setting_manager.py +219 -219
  97. crawlo/spider/__init__.py +657 -657
  98. crawlo/stats_collector.py +73 -73
  99. crawlo/subscriber.py +129 -129
  100. crawlo/task_manager.py +138 -138
  101. crawlo/templates/crawlo.cfg.tmpl +10 -10
  102. crawlo/templates/project/__init__.py.tmpl +3 -3
  103. crawlo/templates/project/items.py.tmpl +17 -17
  104. crawlo/templates/project/middlewares.py.tmpl +118 -118
  105. crawlo/templates/project/pipelines.py.tmpl +96 -96
  106. crawlo/templates/project/settings.py.tmpl +170 -170
  107. crawlo/templates/project/settings_distributed.py.tmpl +169 -169
  108. crawlo/templates/project/settings_gentle.py.tmpl +166 -166
  109. crawlo/templates/project/settings_high_performance.py.tmpl +167 -167
  110. crawlo/templates/project/settings_minimal.py.tmpl +65 -65
  111. crawlo/templates/project/settings_simple.py.tmpl +164 -164
  112. crawlo/templates/project/spiders/__init__.py.tmpl +9 -9
  113. crawlo/templates/run.py.tmpl +34 -34
  114. crawlo/templates/spider/spider.py.tmpl +143 -143
  115. crawlo/templates/spiders_init.py.tmpl +9 -9
  116. crawlo/tools/__init__.py +200 -200
  117. crawlo/tools/anti_crawler.py +268 -268
  118. crawlo/tools/authenticated_proxy.py +240 -240
  119. crawlo/tools/data_formatter.py +225 -225
  120. crawlo/tools/data_validator.py +180 -180
  121. crawlo/tools/date_tools.py +289 -289
  122. crawlo/tools/distributed_coordinator.py +384 -384
  123. crawlo/tools/encoding_converter.py +127 -127
  124. crawlo/tools/network_diagnostic.py +364 -364
  125. crawlo/tools/request_tools.py +82 -82
  126. crawlo/tools/retry_mechanism.py +224 -224
  127. crawlo/tools/scenario_adapter.py +262 -262
  128. crawlo/tools/text_cleaner.py +232 -232
  129. crawlo/utils/__init__.py +34 -34
  130. crawlo/utils/batch_processor.py +259 -259
  131. crawlo/utils/class_loader.py +25 -25
  132. crawlo/utils/controlled_spider_mixin.py +439 -439
  133. crawlo/utils/db_helper.py +343 -343
  134. crawlo/utils/enhanced_error_handler.py +356 -356
  135. crawlo/utils/env_config.py +142 -142
  136. crawlo/utils/error_handler.py +165 -165
  137. crawlo/utils/fingerprint.py +122 -122
  138. crawlo/utils/func_tools.py +82 -82
  139. crawlo/utils/large_scale_config.py +286 -286
  140. crawlo/utils/large_scale_helper.py +344 -344
  141. crawlo/utils/log.py +79 -79
  142. crawlo/utils/performance_monitor.py +285 -285
  143. crawlo/utils/queue_helper.py +175 -175
  144. crawlo/utils/redis_connection_pool.py +388 -388
  145. crawlo/utils/redis_key_validator.py +198 -198
  146. crawlo/utils/request.py +267 -267
  147. crawlo/utils/request_serializer.py +225 -225
  148. crawlo/utils/spider_loader.py +61 -61
  149. crawlo/utils/system.py +11 -11
  150. crawlo/utils/tools.py +4 -4
  151. crawlo/utils/url.py +39 -39
  152. crawlo-1.4.3.dist-info/METADATA +190 -0
  153. crawlo-1.4.3.dist-info/RECORD +326 -0
  154. examples/__init__.py +7 -7
  155. examples/test_project/__init__.py +7 -7
  156. examples/test_project/run.py +34 -34
  157. examples/test_project/test_project/__init__.py +3 -3
  158. examples/test_project/test_project/items.py +17 -17
  159. examples/test_project/test_project/middlewares.py +118 -118
  160. examples/test_project/test_project/pipelines.py +96 -96
  161. examples/test_project/test_project/settings.py +169 -169
  162. examples/test_project/test_project/spiders/__init__.py +9 -9
  163. examples/test_project/test_project/spiders/of_week_dis.py +143 -143
  164. tests/__init__.py +7 -7
  165. tests/advanced_tools_example.py +275 -275
  166. tests/authenticated_proxy_example.py +106 -106
  167. tests/baidu_performance_test.py +108 -108
  168. tests/baidu_test.py +59 -59
  169. tests/cleaners_example.py +160 -160
  170. tests/comprehensive_framework_test.py +212 -212
  171. tests/comprehensive_test.py +81 -81
  172. tests/comprehensive_testing_summary.md +186 -186
  173. tests/config_validation_demo.py +142 -142
  174. tests/controlled_spider_example.py +205 -205
  175. tests/date_tools_example.py +180 -180
  176. tests/debug_configure.py +69 -69
  177. tests/debug_framework_logger.py +84 -84
  178. tests/debug_log_config.py +126 -126
  179. tests/debug_log_levels.py +63 -63
  180. tests/debug_pipelines.py +66 -66
  181. tests/detailed_log_test.py +233 -233
  182. tests/distributed_test.py +66 -66
  183. tests/distributed_test_debug.py +76 -76
  184. tests/dynamic_loading_example.py +523 -523
  185. tests/dynamic_loading_test.py +104 -104
  186. tests/env_config_example.py +133 -133
  187. tests/error_handling_example.py +171 -171
  188. tests/final_comprehensive_test.py +151 -151
  189. tests/final_log_test.py +260 -260
  190. tests/final_validation_test.py +182 -182
  191. tests/fix_log_test.py +142 -142
  192. tests/framework_performance_test.py +202 -202
  193. tests/log_buffering_test.py +111 -111
  194. tests/log_generation_timing_test.py +153 -153
  195. tests/optimized_performance_test.py +211 -211
  196. tests/performance_comparison.py +245 -245
  197. tests/queue_blocking_test.py +113 -113
  198. tests/queue_test.py +89 -89
  199. tests/redis_key_validation_demo.py +130 -130
  200. tests/request_params_example.py +150 -150
  201. tests/response_improvements_example.py +144 -144
  202. tests/scrapy_comparison/ofweek_scrapy.py +138 -138
  203. tests/scrapy_comparison/scrapy_test.py +133 -133
  204. tests/simple_command_test.py +119 -119
  205. tests/simple_crawlo_test.py +127 -127
  206. tests/simple_log_test.py +57 -57
  207. tests/simple_log_test2.py +137 -137
  208. tests/simple_optimization_test.py +128 -128
  209. tests/simple_queue_type_test.py +41 -41
  210. tests/simple_spider_test.py +49 -49
  211. tests/simple_test.py +47 -47
  212. tests/spider_log_timing_test.py +177 -177
  213. tests/test_advanced_tools.py +148 -148
  214. tests/test_all_commands.py +230 -230
  215. tests/test_all_pipeline_fingerprints.py +133 -133
  216. tests/test_all_redis_key_configs.py +145 -145
  217. tests/test_authenticated_proxy.py +141 -141
  218. tests/test_batch_processor.py +178 -178
  219. tests/test_cleaners.py +54 -54
  220. tests/test_component_factory.py +174 -174
  221. tests/test_comprehensive.py +146 -146
  222. tests/test_config_consistency.py +80 -80
  223. tests/test_config_merge.py +152 -152
  224. tests/test_config_validator.py +182 -182
  225. tests/test_controlled_spider_mixin.py +79 -79
  226. tests/test_crawlo_proxy_integration.py +108 -108
  227. tests/test_date_tools.py +123 -123
  228. tests/test_dedup_fix.py +220 -220
  229. tests/test_dedup_pipeline_consistency.py +125 -0
  230. tests/test_default_header_middleware.py +313 -313
  231. tests/test_distributed.py +65 -65
  232. tests/test_double_crawlo_fix.py +204 -204
  233. tests/test_double_crawlo_fix_simple.py +124 -124
  234. tests/test_download_delay_middleware.py +221 -221
  235. tests/test_downloader_proxy_compatibility.py +268 -268
  236. tests/test_dynamic_downloaders_proxy.py +124 -124
  237. tests/test_dynamic_proxy.py +92 -92
  238. tests/test_dynamic_proxy_config.py +146 -146
  239. tests/test_dynamic_proxy_real.py +109 -109
  240. tests/test_edge_cases.py +303 -303
  241. tests/test_enhanced_error_handler.py +270 -270
  242. tests/test_enhanced_error_handler_comprehensive.py +245 -245
  243. tests/test_env_config.py +121 -121
  244. tests/test_error_handler_compatibility.py +112 -112
  245. tests/test_factories.py +252 -252
  246. tests/test_final_validation.py +153 -153
  247. tests/test_fingerprint_consistency.py +135 -135
  248. tests/test_fingerprint_simple.py +51 -51
  249. tests/test_framework_env_usage.py +103 -103
  250. tests/test_framework_logger.py +66 -66
  251. tests/test_framework_startup.py +64 -64
  252. tests/test_get_component_logger.py +83 -83
  253. tests/test_hash_performance.py +99 -99
  254. tests/test_integration.py +169 -169
  255. tests/test_item_dedup_redis_key.py +122 -122
  256. tests/test_large_scale_config.py +112 -112
  257. tests/test_large_scale_helper.py +235 -235
  258. tests/test_logging_enhancements.py +375 -0
  259. tests/test_logging_final.py +185 -0
  260. tests/test_logging_integration.py +313 -0
  261. tests/test_logging_system.py +282 -282
  262. tests/test_middleware_debug.py +142 -0
  263. tests/test_mode_change.py +72 -72
  264. tests/test_mode_consistency.py +51 -51
  265. tests/test_offsite_middleware.py +244 -244
  266. tests/test_offsite_middleware_simple.py +203 -203
  267. tests/test_parsel.py +29 -29
  268. tests/test_performance.py +327 -327
  269. tests/test_performance_monitor.py +115 -115
  270. tests/test_pipeline_fingerprint_consistency.py +86 -86
  271. tests/test_priority_behavior.py +212 -0
  272. tests/test_priority_consistency.py +152 -0
  273. tests/test_priority_consistency_fixed.py +250 -0
  274. tests/test_proxy_api.py +264 -264
  275. tests/test_proxy_health_check.py +32 -32
  276. tests/test_proxy_middleware.py +121 -121
  277. tests/test_proxy_middleware_enhanced.py +216 -216
  278. tests/test_proxy_middleware_integration.py +136 -136
  279. tests/test_proxy_middleware_refactored.py +184 -184
  280. tests/test_proxy_providers.py +56 -56
  281. tests/test_proxy_stats.py +19 -19
  282. tests/test_proxy_strategies.py +59 -59
  283. tests/test_queue_empty_check.py +41 -41
  284. tests/test_queue_manager_double_crawlo.py +173 -173
  285. tests/test_queue_manager_redis_key.py +179 -179
  286. tests/test_queue_naming.py +154 -154
  287. tests/test_queue_type.py +106 -106
  288. tests/test_queue_type_redis_config_consistency.py +131 -0
  289. tests/test_random_headers_default.py +323 -0
  290. tests/test_random_headers_necessity.py +309 -0
  291. tests/test_random_user_agent.py +72 -72
  292. tests/test_real_scenario_proxy.py +195 -195
  293. tests/test_redis_config.py +28 -28
  294. tests/test_redis_connection_pool.py +294 -294
  295. tests/test_redis_key_naming.py +181 -181
  296. tests/test_redis_key_validator.py +123 -123
  297. tests/test_redis_queue.py +224 -224
  298. tests/test_redis_queue_name_fix.py +175 -175
  299. tests/test_redis_queue_type_fallback.py +130 -0
  300. tests/test_request_ignore_middleware.py +182 -182
  301. tests/test_request_params.py +111 -111
  302. tests/test_request_serialization.py +70 -70
  303. tests/test_response_code_middleware.py +349 -349
  304. tests/test_response_filter_middleware.py +427 -427
  305. tests/test_response_improvements.py +152 -152
  306. tests/test_retry_middleware.py +334 -242
  307. tests/test_retry_middleware_realistic.py +274 -0
  308. tests/test_scheduler.py +252 -252
  309. tests/test_scheduler_config_update.py +133 -133
  310. tests/test_simple_response.py +61 -61
  311. tests/test_telecom_spider_redis_key.py +205 -205
  312. tests/test_template_content.py +87 -87
  313. tests/test_template_redis_key.py +134 -134
  314. tests/test_tools.py +159 -159
  315. tests/test_user_agent_randomness.py +177 -0
  316. tests/test_user_agents.py +96 -96
  317. tests/tools_example.py +260 -260
  318. tests/untested_features_report.md +138 -138
  319. tests/verify_debug.py +51 -51
  320. tests/verify_distributed.py +117 -117
  321. tests/verify_log_fix.py +111 -111
  322. crawlo-1.4.1.dist-info/METADATA +0 -1199
  323. crawlo-1.4.1.dist-info/RECORD +0 -309
  324. {crawlo-1.4.1.dist-info → crawlo-1.4.3.dist-info}/WHEEL +0 -0
  325. {crawlo-1.4.1.dist-info → crawlo-1.4.3.dist-info}/entry_points.txt +0 -0
  326. {crawlo-1.4.1.dist-info → crawlo-1.4.3.dist-info}/top_level.txt +0 -0
@@ -1,151 +1,151 @@
1
- #!/usr/bin/python
2
- # -*- coding: UTF-8 -*-
3
- """
4
- Request参数处理示例
5
- """
6
- from crawlo.network.request import Request
7
-
8
-
9
- def demo_get_params():
10
- """演示GET参数处理"""
11
- print("=== GET参数处理演示 ===\n")
12
-
13
- # 使用get_params参数
14
- params = {"page": 1, "limit": 10, "search": "python"}
15
- request = Request(
16
- url="https://api.example.com/articles",
17
- method="GET",
18
- get_params=params
19
- )
20
-
21
- print(f"URL: {request.url}")
22
- print(f"Method: {request.method}")
23
- print()
24
-
25
-
26
- def demo_form_data_with_get():
27
- """演示GET请求使用form_data"""
28
- print("=== GET请求使用form_data演示 ===\n")
29
-
30
- # GET请求使用form_data参数
31
- form_data = {"category": "technology", "sort": "date"}
32
- request = Request(
33
- url="https://api.example.com/posts",
34
- method="GET",
35
- form_data=form_data
36
- )
37
-
38
- print(f"URL: {request.url}")
39
- print(f"Method: {request.method}")
40
- print()
41
-
42
-
43
- def demo_form_data_with_post():
44
- """演示POST请求使用form_data"""
45
- print("=== POST请求使用form_data演示 ===\n")
46
-
47
- # POST请求使用form_data参数
48
- form_data = {"username": "testuser", "password": "secret"}
49
- request = Request(
50
- url="https://api.example.com/login",
51
- method="POST",
52
- form_data=form_data
53
- )
54
-
55
- print(f"URL: {request.url}")
56
- print(f"Method: {request.method}")
57
- print(f"Body: {request.body.decode('utf-8')}")
58
- print(f"Content-Type: {request.headers.get('Content-Type')}")
59
- print()
60
-
61
-
62
- def demo_json_body():
63
- """演示JSON请求体"""
64
- print("=== JSON请求体演示 ===\n")
65
-
66
- # 使用json_body参数
67
- json_data = {"name": "John Doe", "email": "john@example.com", "age": 30}
68
- request = Request(
69
- url="https://api.example.com/users",
70
- method="POST",
71
- json_body=json_data
72
- )
73
-
74
- print(f"URL: {request.url}")
75
- print(f"Method: {request.method}")
76
- print(f"Body: {request.body.decode('utf-8')}")
77
- print(f"Content-Type: {request.headers.get('Content-Type')}")
78
- print()
79
-
80
-
81
- def demo_combined_usage():
82
- """演示组合使用"""
83
- print("=== 组合使用演示 ===\n")
84
-
85
- # 复杂的请求示例
86
- request = Request(
87
- url="https://api.example.com/search",
88
- method="GET",
89
- get_params={"q": "python爬虫", "lang": "zh"},
90
- headers={"User-Agent": "Crawlo/1.0", "Accept": "application/json"},
91
- meta={"retries": 3, "priority": 1}
92
- )
93
-
94
- print(f"URL: {request.url}")
95
- print(f"Method: {request.method}")
96
- print(f"Headers: {request.headers}")
97
- print(f"Meta: {request.meta}")
98
- print()
99
-
100
-
101
- if __name__ == '__main__':
102
- # 运行演示
103
- demo_get_params()
104
- demo_form_data_with_get()
105
- demo_form_data_with_post()
106
- demo_json_body()
107
- demo_combined_usage()
108
-
109
- print("=== 在爬虫中使用Request参数 ===\n")
110
- print("在爬虫项目中,您可以这样使用Request参数:")
111
- print("""
112
- from crawlo import Spider, Request
113
-
114
- class ExampleSpider(Spider):
115
- def start_requests(self):
116
- # GET请求带参数
117
- yield Request(
118
- url="https://api.example.com/articles",
119
- method="GET",
120
- get_params={"page": 1, "limit": 20},
121
- callback=self.parse_articles
122
- )
123
-
124
- # POST请求带表单数据
125
- yield Request(
126
- url="https://api.example.com/login",
127
- method="POST",
128
- form_data={"username": "user", "password": "pass"},
129
- callback=self.parse_login
130
- )
131
-
132
- # POST请求带JSON数据
133
- yield Request(
134
- url="https://api.example.com/users",
135
- method="POST",
136
- json_body={"name": "John", "email": "john@example.com"},
137
- callback=self.parse_user
138
- )
139
-
140
- async def parse_articles(self, response):
141
- # 处理文章列表
142
- pass
143
-
144
- async def parse_login(self, response):
145
- # 处理登录响应
146
- pass
147
-
148
- async def parse_user(self, response):
149
- # 处理用户创建响应
150
- pass
1
+ #!/usr/bin/python
2
+ # -*- coding: UTF-8 -*-
3
+ """
4
+ Request参数处理示例
5
+ """
6
+ from crawlo.network.request import Request
7
+
8
+
9
+ def demo_get_params():
10
+ """演示GET参数处理"""
11
+ print("=== GET参数处理演示 ===\n")
12
+
13
+ # 使用get_params参数
14
+ params = {"page": 1, "limit": 10, "search": "python"}
15
+ request = Request(
16
+ url="https://api.example.com/articles",
17
+ method="GET",
18
+ get_params=params
19
+ )
20
+
21
+ print(f"URL: {request.url}")
22
+ print(f"Method: {request.method}")
23
+ print()
24
+
25
+
26
+ def demo_form_data_with_get():
27
+ """演示GET请求使用form_data"""
28
+ print("=== GET请求使用form_data演示 ===\n")
29
+
30
+ # GET请求使用form_data参数
31
+ form_data = {"category": "technology", "sort": "date"}
32
+ request = Request(
33
+ url="https://api.example.com/posts",
34
+ method="GET",
35
+ form_data=form_data
36
+ )
37
+
38
+ print(f"URL: {request.url}")
39
+ print(f"Method: {request.method}")
40
+ print()
41
+
42
+
43
+ def demo_form_data_with_post():
44
+ """演示POST请求使用form_data"""
45
+ print("=== POST请求使用form_data演示 ===\n")
46
+
47
+ # POST请求使用form_data参数
48
+ form_data = {"username": "testuser", "password": "secret"}
49
+ request = Request(
50
+ url="https://api.example.com/login",
51
+ method="POST",
52
+ form_data=form_data
53
+ )
54
+
55
+ print(f"URL: {request.url}")
56
+ print(f"Method: {request.method}")
57
+ print(f"Body: {request.body.decode('utf-8')}")
58
+ print(f"Content-Type: {request.headers.get('Content-Type')}")
59
+ print()
60
+
61
+
62
+ def demo_json_body():
63
+ """演示JSON请求体"""
64
+ print("=== JSON请求体演示 ===\n")
65
+
66
+ # 使用json_body参数
67
+ json_data = {"name": "John Doe", "email": "john@example.com", "age": 30}
68
+ request = Request(
69
+ url="https://api.example.com/users",
70
+ method="POST",
71
+ json_body=json_data
72
+ )
73
+
74
+ print(f"URL: {request.url}")
75
+ print(f"Method: {request.method}")
76
+ print(f"Body: {request.body.decode('utf-8')}")
77
+ print(f"Content-Type: {request.headers.get('Content-Type')}")
78
+ print()
79
+
80
+
81
+ def demo_combined_usage():
82
+ """演示组合使用"""
83
+ print("=== 组合使用演示 ===\n")
84
+
85
+ # 复杂的请求示例
86
+ request = Request(
87
+ url="https://api.example.com/search",
88
+ method="GET",
89
+ get_params={"q": "python爬虫", "lang": "zh"},
90
+ headers={"User-Agent": "Crawlo/1.0", "Accept": "application/json"},
91
+ meta={"retries": 3, "priority": 1}
92
+ )
93
+
94
+ print(f"URL: {request.url}")
95
+ print(f"Method: {request.method}")
96
+ print(f"Headers: {request.headers}")
97
+ print(f"Meta: {request.meta}")
98
+ print()
99
+
100
+
101
+ if __name__ == '__main__':
102
+ # 运行演示
103
+ demo_get_params()
104
+ demo_form_data_with_get()
105
+ demo_form_data_with_post()
106
+ demo_json_body()
107
+ demo_combined_usage()
108
+
109
+ print("=== 在爬虫中使用Request参数 ===\n")
110
+ print("在爬虫项目中,您可以这样使用Request参数:")
111
+ print("""
112
+ from crawlo import Spider, Request
113
+
114
+ class ExampleSpider(Spider):
115
+ def start_requests(self):
116
+ # GET请求带参数
117
+ yield Request(
118
+ url="https://api.example.com/articles",
119
+ method="GET",
120
+ get_params={"page": 1, "limit": 20},
121
+ callback=self.parse_articles
122
+ )
123
+
124
+ # POST请求带表单数据
125
+ yield Request(
126
+ url="https://api.example.com/login",
127
+ method="POST",
128
+ form_data={"username": "user", "password": "pass"},
129
+ callback=self.parse_login
130
+ )
131
+
132
+ # POST请求带JSON数据
133
+ yield Request(
134
+ url="https://api.example.com/users",
135
+ method="POST",
136
+ json_body={"name": "John", "email": "john@example.com"},
137
+ callback=self.parse_user
138
+ )
139
+
140
+ async def parse_articles(self, response):
141
+ # 处理文章列表
142
+ pass
143
+
144
+ async def parse_login(self, response):
145
+ # 处理登录响应
146
+ pass
147
+
148
+ async def parse_user(self, response):
149
+ # 处理用户创建响应
150
+ pass
151
151
  """)
@@ -1,145 +1,145 @@
1
- #!/usr/bin/python
2
- # -*- coding:UTF-8 -*-
3
- """
4
- Response 改进功能使用示例
5
- """
6
- from crawlo.network.response import Response
7
-
8
-
9
- def demo_response_improvements():
10
- """演示Response改进功能"""
11
- print("=== Response 改进功能演示 ===\n")
12
-
13
- # 创建一个示例HTML响应
14
- html_content = """
15
- <html>
16
- <head>
17
- <title>Crawlo框架示例页面</title>
18
- </head>
19
- <body>
20
- <div class="container">
21
- <h1>产品列表</h1>
22
- <div class="product-list">
23
- <div class="product-item" data-id="1">
24
- <h2>产品A</h2>
25
- <p class="price">¥99.99</p>
26
- <p class="description">这是产品A的描述信息</p>
27
- <a href="/product/1" class="details-link">查看详情</a>
28
- </div>
29
- <div class="product-item" data-id="2">
30
- <h2>产品B</h2>
31
- <p class="price">¥149.99</p>
32
- <p class="description">这是产品B的描述信息</p>
33
- <a href="/product/2" class="details-link">查看详情</a>
34
- </div>
35
- <div class="product-item" data-id="3">
36
- <h2>产品C</h2>
37
- <p class="price">¥199.99</p>
38
- <p class="description">这是产品C的描述信息</p>
39
- <a href="/product/3" class="details-link">查看详情</a>
40
- </div>
41
- </div>
42
- <div class="pagination">
43
- <a href="/page/1" class="page-link">1</a>
44
- <a href="/page/2" class="page-link active">2</a>
45
- <a href="/page/3" class="page-link">3</a>
46
- </div>
47
- </div>
48
- </body>
49
- </html>
50
- """
51
-
52
- # 创建Response对象
53
- response = Response(
54
- url="https://example.com/products",
55
- body=html_content.encode('utf-8'),
56
- headers={"content-type": "text/html; charset=utf-8"}
57
- )
58
-
59
- # 1. 演示 extract_text 方法(支持CSS和XPath)
60
- print("1. 提取文本内容:")
61
- title = response.extract_text('title')
62
- print(f" 页面标题: {title}")
63
-
64
- # 使用CSS选择器提取第一个产品名称
65
- first_product_name = response.extract_text('.product-item:first-child h2')
66
- print(f" 第一个产品名称 (CSS): {first_product_name}")
67
-
68
- # 使用XPath选择器
69
- first_product_name_xpath = response.extract_text('//div[@class="product-item"][1]/h2')
70
- print(f" 第一个产品名称 (XPath): {first_product_name_xpath}")
71
-
72
- # 使用默认值处理不存在的元素
73
- non_exist = response.extract_text('.non-exist', default='未找到')
74
- print(f" 不存在的元素: {non_exist}")
75
-
76
- print()
77
-
78
- # 2. 演示 extract_texts 方法(提取多个元素的文本)
79
- print("2. 提取多个元素的文本:")
80
- # 提取所有产品名称
81
- product_names = response.extract_texts('.product-item h2')
82
- print(f" 所有产品名称: {product_names}")
83
-
84
- # 提取所有价格
85
- prices = response.extract_texts('.price')
86
- print(f" 所有价格: {prices}")
87
-
88
- # 使用XPath提取所有产品名称
89
- product_names_xpath = response.extract_texts('//div[@class="product-item"]/h2')
90
- print(f" 所有产品名称 (XPath): {product_names_xpath}")
91
-
92
- print()
93
-
94
- # 3. 演示 extract_attr 方法(提取元素属性)
95
- print("3. 提取元素属性:")
96
- # 提取第一个产品项的data-id属性
97
- first_product_id = response.extract_attr('.product-item', 'data-id')
98
- print(f" 第一个产品ID: {first_product_id}")
99
-
100
- # 提取详情链接的href属性
101
- first_detail_link = response.extract_attr('.details-link', 'href')
102
- print(f" 第一个详情链接: {first_detail_link}")
103
-
104
- # 提取不存在属性的默认值
105
- non_exist_attr = response.extract_attr('.product-item', 'non-exist', default='默认值')
106
- print(f" 不存在的属性: {non_exist_attr}")
107
-
108
- print()
109
-
110
- # 4. 演示 extract_attrs 方法(提取多个元素的属性)
111
- print("4. 提取多个元素的属性:")
112
- # 提取所有产品项的data-id属性
113
- product_ids = response.extract_attrs('.product-item', 'data-id')
114
- print(f" 所有产品ID: {product_ids}")
115
-
116
- # 提取所有详情链接的href属性
117
- detail_links = response.extract_attrs('.details-link', 'href')
118
- print(f" 所有详情链接: {detail_links}")
119
-
120
- # 提取分页链接的href属性
121
- page_links = response.extract_attrs('.page-link', 'href')
122
- print(f" 分页链接: {page_links}")
123
-
124
- print()
125
-
126
- # 5. 演示复杂文本提取
127
- print("5. 复杂文本提取:")
128
- # 提取所有产品描述
129
- descriptions = response.extract_texts('.description')
130
- print(f" 所有产品描述: {descriptions}")
131
-
132
- print()
133
-
134
- # 6. 边界情况处理
135
- print("6. 边界情况处理:")
136
- # 空响应测试
137
- empty_response = Response(url="https://example.com/empty", body=b"")
138
- empty_text = empty_response.extract_text('title', default='默认标题')
139
- print(f" 空响应默认值: {empty_text}")
140
-
141
- print("\n=== 演示完成 ===")
142
-
143
-
144
- if __name__ == '__main__':
1
+ #!/usr/bin/python
2
+ # -*- coding:UTF-8 -*-
3
+ """
4
+ Response 改进功能使用示例
5
+ """
6
+ from crawlo.network.response import Response
7
+
8
+
9
+ def demo_response_improvements():
10
+ """演示Response改进功能"""
11
+ print("=== Response 改进功能演示 ===\n")
12
+
13
+ # 创建一个示例HTML响应
14
+ html_content = """
15
+ <html>
16
+ <head>
17
+ <title>Crawlo框架示例页面</title>
18
+ </head>
19
+ <body>
20
+ <div class="container">
21
+ <h1>产品列表</h1>
22
+ <div class="product-list">
23
+ <div class="product-item" data-id="1">
24
+ <h2>产品A</h2>
25
+ <p class="price">¥99.99</p>
26
+ <p class="description">这是产品A的描述信息</p>
27
+ <a href="/product/1" class="details-link">查看详情</a>
28
+ </div>
29
+ <div class="product-item" data-id="2">
30
+ <h2>产品B</h2>
31
+ <p class="price">¥149.99</p>
32
+ <p class="description">这是产品B的描述信息</p>
33
+ <a href="/product/2" class="details-link">查看详情</a>
34
+ </div>
35
+ <div class="product-item" data-id="3">
36
+ <h2>产品C</h2>
37
+ <p class="price">¥199.99</p>
38
+ <p class="description">这是产品C的描述信息</p>
39
+ <a href="/product/3" class="details-link">查看详情</a>
40
+ </div>
41
+ </div>
42
+ <div class="pagination">
43
+ <a href="/page/1" class="page-link">1</a>
44
+ <a href="/page/2" class="page-link active">2</a>
45
+ <a href="/page/3" class="page-link">3</a>
46
+ </div>
47
+ </div>
48
+ </body>
49
+ </html>
50
+ """
51
+
52
+ # 创建Response对象
53
+ response = Response(
54
+ url="https://example.com/products",
55
+ body=html_content.encode('utf-8'),
56
+ headers={"content-type": "text/html; charset=utf-8"}
57
+ )
58
+
59
+ # 1. 演示 extract_text 方法(支持CSS和XPath)
60
+ print("1. 提取文本内容:")
61
+ title = response.extract_text('title')
62
+ print(f" 页面标题: {title}")
63
+
64
+ # 使用CSS选择器提取第一个产品名称
65
+ first_product_name = response.extract_text('.product-item:first-child h2')
66
+ print(f" 第一个产品名称 (CSS): {first_product_name}")
67
+
68
+ # 使用XPath选择器
69
+ first_product_name_xpath = response.extract_text('//div[@class="product-item"][1]/h2')
70
+ print(f" 第一个产品名称 (XPath): {first_product_name_xpath}")
71
+
72
+ # 使用默认值处理不存在的元素
73
+ non_exist = response.extract_text('.non-exist', default='未找到')
74
+ print(f" 不存在的元素: {non_exist}")
75
+
76
+ print()
77
+
78
+ # 2. 演示 extract_texts 方法(提取多个元素的文本)
79
+ print("2. 提取多个元素的文本:")
80
+ # 提取所有产品名称
81
+ product_names = response.extract_texts('.product-item h2')
82
+ print(f" 所有产品名称: {product_names}")
83
+
84
+ # 提取所有价格
85
+ prices = response.extract_texts('.price')
86
+ print(f" 所有价格: {prices}")
87
+
88
+ # 使用XPath提取所有产品名称
89
+ product_names_xpath = response.extract_texts('//div[@class="product-item"]/h2')
90
+ print(f" 所有产品名称 (XPath): {product_names_xpath}")
91
+
92
+ print()
93
+
94
+ # 3. 演示 extract_attr 方法(提取元素属性)
95
+ print("3. 提取元素属性:")
96
+ # 提取第一个产品项的data-id属性
97
+ first_product_id = response.extract_attr('.product-item', 'data-id')
98
+ print(f" 第一个产品ID: {first_product_id}")
99
+
100
+ # 提取详情链接的href属性
101
+ first_detail_link = response.extract_attr('.details-link', 'href')
102
+ print(f" 第一个详情链接: {first_detail_link}")
103
+
104
+ # 提取不存在属性的默认值
105
+ non_exist_attr = response.extract_attr('.product-item', 'non-exist', default='默认值')
106
+ print(f" 不存在的属性: {non_exist_attr}")
107
+
108
+ print()
109
+
110
+ # 4. 演示 extract_attrs 方法(提取多个元素的属性)
111
+ print("4. 提取多个元素的属性:")
112
+ # 提取所有产品项的data-id属性
113
+ product_ids = response.extract_attrs('.product-item', 'data-id')
114
+ print(f" 所有产品ID: {product_ids}")
115
+
116
+ # 提取所有详情链接的href属性
117
+ detail_links = response.extract_attrs('.details-link', 'href')
118
+ print(f" 所有详情链接: {detail_links}")
119
+
120
+ # 提取分页链接的href属性
121
+ page_links = response.extract_attrs('.page-link', 'href')
122
+ print(f" 分页链接: {page_links}")
123
+
124
+ print()
125
+
126
+ # 5. 演示复杂文本提取
127
+ print("5. 复杂文本提取:")
128
+ # 提取所有产品描述
129
+ descriptions = response.extract_texts('.description')
130
+ print(f" 所有产品描述: {descriptions}")
131
+
132
+ print()
133
+
134
+ # 6. 边界情况处理
135
+ print("6. 边界情况处理:")
136
+ # 空响应测试
137
+ empty_response = Response(url="https://example.com/empty", body=b"")
138
+ empty_text = empty_response.extract_text('title', default='默认标题')
139
+ print(f" 空响应默认值: {empty_text}")
140
+
141
+ print("\n=== 演示完成 ===")
142
+
143
+
144
+ if __name__ == '__main__':
145
145
  demo_response_improvements()