crawlo 1.4.6__py3-none-any.whl → 1.4.7__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 (374) hide show
  1. crawlo/__init__.py +90 -89
  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 +186 -186
  7. crawlo/commands/help.py +140 -138
  8. crawlo/commands/list.py +155 -155
  9. crawlo/commands/run.py +379 -341
  10. crawlo/commands/startproject.py +460 -460
  11. crawlo/commands/stats.py +187 -187
  12. crawlo/commands/utils.py +196 -196
  13. crawlo/config.py +320 -312
  14. crawlo/config_validator.py +277 -277
  15. crawlo/core/__init__.py +52 -52
  16. crawlo/core/engine.py +451 -438
  17. crawlo/core/processor.py +47 -47
  18. crawlo/core/scheduler.py +290 -291
  19. crawlo/crawler.py +698 -657
  20. crawlo/data/__init__.py +5 -5
  21. crawlo/data/user_agents.py +194 -194
  22. crawlo/downloader/__init__.py +280 -276
  23. crawlo/downloader/aiohttp_downloader.py +233 -233
  24. crawlo/downloader/cffi_downloader.py +250 -247
  25. crawlo/downloader/httpx_downloader.py +265 -259
  26. crawlo/downloader/hybrid_downloader.py +212 -212
  27. crawlo/downloader/playwright_downloader.py +425 -402
  28. crawlo/downloader/selenium_downloader.py +486 -472
  29. crawlo/event.py +45 -11
  30. crawlo/exceptions.py +215 -82
  31. crawlo/extension/__init__.py +65 -64
  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 +53 -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 +104 -103
  42. crawlo/factories/registry.py +84 -84
  43. crawlo/factories/utils.py +135 -0
  44. crawlo/filters/__init__.py +170 -153
  45. crawlo/filters/aioredis_filter.py +348 -264
  46. crawlo/filters/memory_filter.py +261 -276
  47. crawlo/framework.py +306 -292
  48. crawlo/initialization/__init__.py +44 -44
  49. crawlo/initialization/built_in.py +391 -434
  50. crawlo/initialization/context.py +141 -141
  51. crawlo/initialization/core.py +240 -194
  52. crawlo/initialization/phases.py +230 -149
  53. crawlo/initialization/registry.py +143 -145
  54. crawlo/initialization/utils.py +49 -0
  55. crawlo/interfaces.py +23 -23
  56. crawlo/items/__init__.py +23 -23
  57. crawlo/items/base.py +23 -23
  58. crawlo/items/fields.py +52 -52
  59. crawlo/items/items.py +104 -104
  60. crawlo/logging/__init__.py +42 -46
  61. crawlo/logging/config.py +277 -197
  62. crawlo/logging/factory.py +175 -171
  63. crawlo/logging/manager.py +104 -112
  64. crawlo/middleware/__init__.py +87 -24
  65. crawlo/middleware/default_header.py +132 -132
  66. crawlo/middleware/download_delay.py +104 -104
  67. crawlo/middleware/middleware_manager.py +142 -142
  68. crawlo/middleware/offsite.py +123 -123
  69. crawlo/middleware/proxy.py +209 -209
  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/mode_manager.py +287 -253
  75. crawlo/network/__init__.py +21 -21
  76. crawlo/network/request.py +375 -379
  77. crawlo/network/response.py +569 -664
  78. crawlo/pipelines/__init__.py +53 -22
  79. crawlo/pipelines/base_pipeline.py +452 -0
  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 +140 -132
  87. crawlo/pipelines/mysql_pipeline.py +469 -476
  88. crawlo/pipelines/pipeline_manager.py +100 -100
  89. crawlo/pipelines/redis_dedup_pipeline.py +155 -156
  90. crawlo/project.py +347 -347
  91. crawlo/queue/__init__.py +10 -0
  92. crawlo/queue/pqueue.py +38 -38
  93. crawlo/queue/queue_manager.py +591 -525
  94. crawlo/queue/redis_priority_queue.py +519 -370
  95. crawlo/settings/__init__.py +7 -7
  96. crawlo/settings/default_settings.py +284 -277
  97. crawlo/settings/setting_manager.py +219 -219
  98. crawlo/spider/__init__.py +657 -657
  99. crawlo/stats_collector.py +81 -81
  100. crawlo/subscriber.py +129 -129
  101. crawlo/task_manager.py +138 -138
  102. crawlo/templates/crawlo.cfg.tmpl +10 -10
  103. crawlo/templates/project/__init__.py.tmpl +2 -4
  104. crawlo/templates/project/items.py.tmpl +13 -17
  105. crawlo/templates/project/middlewares.py.tmpl +38 -38
  106. crawlo/templates/project/pipelines.py.tmpl +35 -36
  107. crawlo/templates/project/settings.py.tmpl +109 -111
  108. crawlo/templates/project/settings_distributed.py.tmpl +156 -159
  109. crawlo/templates/project/settings_gentle.py.tmpl +170 -176
  110. crawlo/templates/project/settings_high_performance.py.tmpl +171 -177
  111. crawlo/templates/project/settings_minimal.py.tmpl +98 -100
  112. crawlo/templates/project/settings_simple.py.tmpl +168 -174
  113. crawlo/templates/project/spiders/__init__.py.tmpl +9 -9
  114. crawlo/templates/run.py.tmpl +23 -23
  115. crawlo/templates/spider/spider.py.tmpl +32 -40
  116. crawlo/templates/spiders_init.py.tmpl +5 -10
  117. crawlo/tools/__init__.py +86 -189
  118. crawlo/tools/date_tools.py +289 -289
  119. crawlo/tools/distributed_coordinator.py +384 -384
  120. crawlo/tools/scenario_adapter.py +262 -262
  121. crawlo/tools/text_cleaner.py +232 -232
  122. crawlo/utils/__init__.py +50 -50
  123. crawlo/utils/batch_processor.py +276 -259
  124. crawlo/utils/config_manager.py +442 -0
  125. crawlo/utils/controlled_spider_mixin.py +439 -439
  126. crawlo/utils/db_helper.py +250 -250
  127. crawlo/utils/error_handler.py +410 -410
  128. crawlo/utils/fingerprint.py +121 -121
  129. crawlo/utils/func_tools.py +82 -82
  130. crawlo/utils/large_scale_helper.py +344 -344
  131. crawlo/utils/leak_detector.py +335 -0
  132. crawlo/utils/log.py +79 -79
  133. crawlo/utils/misc.py +81 -81
  134. crawlo/utils/mongo_connection_pool.py +157 -0
  135. crawlo/utils/mysql_connection_pool.py +197 -0
  136. crawlo/utils/performance_monitor.py +285 -285
  137. crawlo/utils/queue_helper.py +175 -175
  138. crawlo/utils/redis_checker.py +91 -0
  139. crawlo/utils/redis_connection_pool.py +578 -388
  140. crawlo/utils/redis_key_validator.py +198 -198
  141. crawlo/utils/request.py +278 -256
  142. crawlo/utils/request_serializer.py +225 -225
  143. crawlo/utils/resource_manager.py +337 -0
  144. crawlo/utils/selector_helper.py +137 -137
  145. crawlo/utils/singleton.py +70 -0
  146. crawlo/utils/spider_loader.py +201 -201
  147. crawlo/utils/text_helper.py +94 -94
  148. crawlo/utils/{url.py → url_utils.py} +39 -39
  149. crawlo-1.4.7.dist-info/METADATA +689 -0
  150. crawlo-1.4.7.dist-info/RECORD +347 -0
  151. examples/__init__.py +7 -7
  152. tests/__init__.py +7 -7
  153. tests/advanced_tools_example.py +217 -275
  154. tests/authenticated_proxy_example.py +110 -110
  155. tests/baidu_performance_test.py +108 -108
  156. tests/baidu_test.py +59 -59
  157. tests/bug_check_test.py +250 -250
  158. tests/cleaners_example.py +160 -160
  159. tests/comprehensive_framework_test.py +212 -212
  160. tests/comprehensive_test.py +81 -81
  161. tests/comprehensive_testing_summary.md +186 -186
  162. tests/config_validation_demo.py +142 -142
  163. tests/controlled_spider_example.py +205 -205
  164. tests/date_tools_example.py +180 -180
  165. tests/debug_configure.py +69 -69
  166. tests/debug_framework_logger.py +84 -84
  167. tests/debug_log_config.py +126 -126
  168. tests/debug_log_levels.py +63 -63
  169. tests/debug_pipelines.py +66 -66
  170. tests/detailed_log_test.py +233 -233
  171. tests/direct_selector_helper_test.py +96 -96
  172. tests/distributed_dedup_test.py +467 -0
  173. tests/distributed_test.py +66 -66
  174. tests/distributed_test_debug.py +76 -76
  175. tests/dynamic_loading_example.py +523 -523
  176. tests/dynamic_loading_test.py +104 -104
  177. tests/error_handling_example.py +171 -171
  178. tests/explain_mysql_update_behavior.py +76 -76
  179. tests/final_comprehensive_test.py +151 -151
  180. tests/final_log_test.py +260 -260
  181. tests/final_validation_test.py +182 -182
  182. tests/fix_log_test.py +142 -142
  183. tests/framework_performance_test.py +202 -202
  184. tests/log_buffering_test.py +111 -111
  185. tests/log_generation_timing_test.py +153 -153
  186. tests/monitor_redis_dedup.sh +72 -0
  187. tests/ofweek_scrapy/ofweek_scrapy/items.py +12 -12
  188. tests/ofweek_scrapy/ofweek_scrapy/middlewares.py +100 -100
  189. tests/ofweek_scrapy/ofweek_scrapy/pipelines.py +13 -13
  190. tests/ofweek_scrapy/ofweek_scrapy/settings.py +84 -84
  191. tests/ofweek_scrapy/scrapy.cfg +11 -11
  192. tests/optimized_performance_test.py +211 -211
  193. tests/performance_comparison.py +244 -244
  194. tests/queue_blocking_test.py +113 -113
  195. tests/queue_test.py +89 -89
  196. tests/redis_key_validation_demo.py +130 -130
  197. tests/request_params_example.py +150 -150
  198. tests/response_improvements_example.py +144 -144
  199. tests/scrapy_comparison/ofweek_scrapy.py +138 -138
  200. tests/scrapy_comparison/scrapy_test.py +133 -133
  201. tests/simple_cli_test.py +55 -0
  202. tests/simple_command_test.py +119 -119
  203. tests/simple_crawlo_test.py +126 -126
  204. tests/simple_follow_test.py +38 -38
  205. tests/simple_log_test2.py +137 -137
  206. tests/simple_optimization_test.py +128 -128
  207. tests/simple_queue_type_test.py +41 -41
  208. tests/simple_response_selector_test.py +94 -94
  209. tests/simple_selector_helper_test.py +154 -154
  210. tests/simple_selector_test.py +207 -207
  211. tests/simple_spider_test.py +49 -49
  212. tests/simple_url_test.py +73 -73
  213. tests/simulate_mysql_update_test.py +139 -139
  214. tests/spider_log_timing_test.py +177 -177
  215. tests/test_advanced_tools.py +148 -148
  216. tests/test_all_commands.py +230 -230
  217. tests/test_all_pipeline_fingerprints.py +133 -133
  218. tests/test_all_redis_key_configs.py +145 -145
  219. tests/test_asyncmy_usage.py +56 -56
  220. tests/test_batch_processor.py +178 -178
  221. tests/test_cleaners.py +54 -54
  222. tests/test_cli_arguments.py +119 -0
  223. tests/test_component_factory.py +174 -174
  224. tests/test_config_consistency.py +80 -80
  225. tests/test_config_merge.py +152 -152
  226. tests/test_config_validator.py +182 -182
  227. tests/test_controlled_spider_mixin.py +79 -79
  228. tests/test_crawler_process_import.py +38 -38
  229. tests/test_crawler_process_spider_modules.py +47 -47
  230. tests/test_crawlo_proxy_integration.py +114 -114
  231. tests/test_date_tools.py +123 -123
  232. tests/test_dedup_fix.py +220 -220
  233. tests/test_dedup_pipeline_consistency.py +124 -124
  234. tests/test_default_header_middleware.py +313 -313
  235. tests/test_distributed.py +65 -65
  236. tests/test_double_crawlo_fix.py +204 -204
  237. tests/test_double_crawlo_fix_simple.py +124 -124
  238. tests/test_download_delay_middleware.py +221 -221
  239. tests/test_downloader_proxy_compatibility.py +272 -272
  240. tests/test_edge_cases.py +305 -305
  241. tests/test_encoding_core.py +56 -56
  242. tests/test_encoding_detection.py +126 -126
  243. tests/test_enhanced_error_handler.py +270 -270
  244. tests/test_enhanced_error_handler_comprehensive.py +245 -245
  245. tests/test_error_handler_compatibility.py +112 -112
  246. tests/test_factories.py +252 -252
  247. tests/test_factory_compatibility.py +196 -196
  248. tests/test_final_validation.py +153 -153
  249. tests/test_fingerprint_consistency.py +135 -135
  250. tests/test_fingerprint_simple.py +51 -51
  251. tests/test_get_component_logger.py +83 -83
  252. tests/test_hash_performance.py +99 -99
  253. tests/test_integration.py +169 -169
  254. tests/test_item_dedup_redis_key.py +122 -122
  255. tests/test_large_scale_helper.py +235 -235
  256. tests/test_logging_enhancements.py +374 -374
  257. tests/test_logging_final.py +184 -184
  258. tests/test_logging_integration.py +312 -312
  259. tests/test_logging_system.py +282 -282
  260. tests/test_middleware_debug.py +141 -141
  261. tests/test_mode_consistency.py +51 -51
  262. tests/test_multi_directory.py +67 -67
  263. tests/test_multiple_spider_modules.py +80 -80
  264. tests/test_mysql_pipeline_config.py +164 -164
  265. tests/test_mysql_pipeline_error.py +98 -98
  266. tests/test_mysql_pipeline_init_log.py +82 -82
  267. tests/test_mysql_pipeline_integration.py +132 -132
  268. tests/test_mysql_pipeline_refactor.py +143 -143
  269. tests/test_mysql_pipeline_refactor_simple.py +85 -85
  270. tests/test_mysql_pipeline_robustness.py +195 -195
  271. tests/test_mysql_pipeline_types.py +88 -88
  272. tests/test_mysql_update_columns.py +93 -93
  273. tests/test_offsite_middleware.py +244 -244
  274. tests/test_offsite_middleware_simple.py +203 -203
  275. tests/test_optimized_selector_naming.py +100 -100
  276. tests/test_parsel.py +29 -29
  277. tests/test_performance.py +327 -327
  278. tests/test_performance_monitor.py +115 -115
  279. tests/test_pipeline_fingerprint_consistency.py +86 -86
  280. tests/test_priority_behavior.py +211 -211
  281. tests/test_priority_consistency.py +151 -151
  282. tests/test_priority_consistency_fixed.py +249 -249
  283. tests/test_proxy_health_check.py +32 -32
  284. tests/test_proxy_middleware.py +217 -217
  285. tests/test_proxy_middleware_enhanced.py +212 -212
  286. tests/test_proxy_middleware_integration.py +142 -142
  287. tests/test_proxy_middleware_refactored.py +207 -207
  288. tests/test_proxy_only.py +83 -83
  289. tests/test_proxy_providers.py +56 -56
  290. tests/test_proxy_stats.py +19 -19
  291. tests/test_proxy_strategies.py +59 -59
  292. tests/test_proxy_with_downloader.py +152 -152
  293. tests/test_queue_empty_check.py +41 -41
  294. tests/test_queue_manager_double_crawlo.py +173 -173
  295. tests/test_queue_manager_redis_key.py +179 -179
  296. tests/test_queue_naming.py +154 -154
  297. tests/test_queue_type.py +106 -106
  298. tests/test_queue_type_redis_config_consistency.py +130 -130
  299. tests/test_random_headers_default.py +322 -322
  300. tests/test_random_headers_necessity.py +308 -308
  301. tests/test_random_user_agent.py +72 -72
  302. tests/test_redis_config.py +28 -28
  303. tests/test_redis_connection_pool.py +294 -294
  304. tests/test_redis_key_naming.py +181 -181
  305. tests/test_redis_key_validator.py +123 -123
  306. tests/test_redis_queue.py +224 -224
  307. tests/test_redis_queue_name_fix.py +175 -175
  308. tests/test_redis_queue_type_fallback.py +129 -129
  309. tests/test_request_ignore_middleware.py +182 -182
  310. tests/test_request_params.py +111 -111
  311. tests/test_request_serialization.py +70 -70
  312. tests/test_response_code_middleware.py +349 -349
  313. tests/test_response_filter_middleware.py +427 -427
  314. tests/test_response_follow.py +104 -104
  315. tests/test_response_improvements.py +152 -152
  316. tests/test_response_selector_methods.py +92 -92
  317. tests/test_response_url_methods.py +70 -70
  318. tests/test_response_urljoin.py +86 -86
  319. tests/test_retry_middleware.py +333 -333
  320. tests/test_retry_middleware_realistic.py +273 -273
  321. tests/test_scheduler.py +252 -252
  322. tests/test_scheduler_config_update.py +133 -133
  323. tests/test_scrapy_style_encoding.py +112 -112
  324. tests/test_selector_helper.py +100 -100
  325. tests/test_selector_optimizations.py +146 -146
  326. tests/test_simple_response.py +61 -61
  327. tests/test_spider_loader.py +49 -49
  328. tests/test_spider_loader_comprehensive.py +69 -69
  329. tests/test_spider_modules.py +84 -84
  330. tests/test_spiders/test_spider.py +9 -9
  331. tests/test_telecom_spider_redis_key.py +205 -205
  332. tests/test_template_content.py +87 -87
  333. tests/test_template_redis_key.py +134 -134
  334. tests/test_tools.py +159 -159
  335. tests/test_user_agent_randomness.py +176 -176
  336. tests/test_user_agents.py +96 -96
  337. tests/untested_features_report.md +138 -138
  338. tests/verify_debug.py +51 -51
  339. tests/verify_distributed.py +117 -117
  340. tests/verify_log_fix.py +111 -111
  341. tests/verify_mysql_warnings.py +109 -109
  342. crawlo/logging/async_handler.py +0 -181
  343. crawlo/logging/monitor.py +0 -153
  344. crawlo/logging/sampler.py +0 -167
  345. crawlo/tools/authenticated_proxy.py +0 -241
  346. crawlo/tools/data_formatter.py +0 -226
  347. crawlo/tools/data_validator.py +0 -181
  348. crawlo/tools/encoding_converter.py +0 -127
  349. crawlo/tools/network_diagnostic.py +0 -365
  350. crawlo/tools/request_tools.py +0 -83
  351. crawlo/tools/retry_mechanism.py +0 -224
  352. crawlo/utils/env_config.py +0 -143
  353. crawlo/utils/large_scale_config.py +0 -287
  354. crawlo/utils/system.py +0 -11
  355. crawlo/utils/tools.py +0 -5
  356. crawlo-1.4.6.dist-info/METADATA +0 -329
  357. crawlo-1.4.6.dist-info/RECORD +0 -361
  358. tests/env_config_example.py +0 -134
  359. tests/ofweek_scrapy/ofweek_scrapy/spiders/ofweek_spider.py +0 -162
  360. tests/test_authenticated_proxy.py +0 -142
  361. tests/test_comprehensive.py +0 -147
  362. tests/test_dynamic_downloaders_proxy.py +0 -125
  363. tests/test_dynamic_proxy.py +0 -93
  364. tests/test_dynamic_proxy_config.py +0 -147
  365. tests/test_dynamic_proxy_real.py +0 -110
  366. tests/test_env_config.py +0 -122
  367. tests/test_framework_env_usage.py +0 -104
  368. tests/test_large_scale_config.py +0 -113
  369. tests/test_proxy_api.py +0 -265
  370. tests/test_real_scenario_proxy.py +0 -196
  371. tests/tools_example.py +0 -261
  372. {crawlo-1.4.6.dist-info → crawlo-1.4.7.dist-info}/WHEEL +0 -0
  373. {crawlo-1.4.6.dist-info → crawlo-1.4.7.dist-info}/entry_points.txt +0 -0
  374. {crawlo-1.4.6.dist-info → crawlo-1.4.7.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()