crawlo 1.2.2__py3-none-any.whl → 1.2.4__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 (222) 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 +81 -81
  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 +144 -142
  12. crawlo/commands/list.py +155 -155
  13. crawlo/commands/run.py +323 -292
  14. crawlo/commands/startproject.py +420 -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 +251 -252
  19. crawlo/core/__init__.py +2 -2
  20. crawlo/core/engine.py +354 -354
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +143 -143
  23. crawlo/crawler.py +1110 -1027
  24. crawlo/data/__init__.py +6 -0
  25. crawlo/data/user_agents.py +108 -0
  26. crawlo/downloader/__init__.py +266 -266
  27. crawlo/downloader/aiohttp_downloader.py +220 -220
  28. crawlo/downloader/cffi_downloader.py +256 -256
  29. crawlo/downloader/httpx_downloader.py +259 -259
  30. crawlo/downloader/hybrid_downloader.py +212 -213
  31. crawlo/downloader/playwright_downloader.py +402 -402
  32. crawlo/downloader/selenium_downloader.py +472 -472
  33. crawlo/event.py +11 -11
  34. crawlo/exceptions.py +81 -81
  35. crawlo/extension/__init__.py +37 -37
  36. crawlo/extension/health_check.py +141 -141
  37. crawlo/extension/log_interval.py +57 -57
  38. crawlo/extension/log_stats.py +81 -81
  39. crawlo/extension/logging_extension.py +43 -43
  40. crawlo/extension/memory_monitor.py +104 -104
  41. crawlo/extension/performance_profiler.py +133 -133
  42. crawlo/extension/request_recorder.py +107 -107
  43. crawlo/filters/__init__.py +154 -154
  44. crawlo/filters/aioredis_filter.py +280 -280
  45. crawlo/filters/memory_filter.py +269 -269
  46. crawlo/items/__init__.py +23 -23
  47. crawlo/items/base.py +21 -21
  48. crawlo/items/fields.py +52 -53
  49. crawlo/items/items.py +104 -104
  50. crawlo/middleware/__init__.py +21 -21
  51. crawlo/middleware/default_header.py +131 -131
  52. crawlo/middleware/download_delay.py +104 -104
  53. crawlo/middleware/middleware_manager.py +135 -135
  54. crawlo/middleware/offsite.py +114 -115
  55. crawlo/middleware/proxy.py +367 -366
  56. crawlo/middleware/request_ignore.py +86 -87
  57. crawlo/middleware/response_code.py +163 -164
  58. crawlo/middleware/response_filter.py +136 -137
  59. crawlo/middleware/retry.py +124 -124
  60. crawlo/mode_manager.py +211 -211
  61. crawlo/network/__init__.py +21 -21
  62. crawlo/network/request.py +338 -338
  63. crawlo/network/response.py +359 -359
  64. crawlo/pipelines/__init__.py +21 -21
  65. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  66. crawlo/pipelines/console_pipeline.py +39 -39
  67. crawlo/pipelines/csv_pipeline.py +316 -316
  68. crawlo/pipelines/database_dedup_pipeline.py +222 -224
  69. crawlo/pipelines/json_pipeline.py +218 -218
  70. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  71. crawlo/pipelines/mongo_pipeline.py +131 -131
  72. crawlo/pipelines/mysql_pipeline.py +317 -316
  73. crawlo/pipelines/pipeline_manager.py +61 -61
  74. crawlo/pipelines/redis_dedup_pipeline.py +165 -167
  75. crawlo/project.py +279 -187
  76. crawlo/queue/pqueue.py +37 -37
  77. crawlo/queue/queue_manager.py +337 -337
  78. crawlo/queue/redis_priority_queue.py +298 -298
  79. crawlo/settings/__init__.py +7 -7
  80. crawlo/settings/default_settings.py +217 -226
  81. crawlo/settings/setting_manager.py +122 -122
  82. crawlo/spider/__init__.py +639 -639
  83. crawlo/stats_collector.py +59 -59
  84. crawlo/subscriber.py +129 -130
  85. crawlo/task_manager.py +30 -30
  86. crawlo/templates/crawlo.cfg.tmpl +10 -10
  87. crawlo/templates/project/__init__.py.tmpl +3 -3
  88. crawlo/templates/project/items.py.tmpl +17 -17
  89. crawlo/templates/project/middlewares.py.tmpl +118 -118
  90. crawlo/templates/project/pipelines.py.tmpl +96 -96
  91. crawlo/templates/project/run.py.tmpl +47 -45
  92. crawlo/templates/project/settings.py.tmpl +350 -327
  93. crawlo/templates/project/settings_distributed.py.tmpl +160 -119
  94. crawlo/templates/project/settings_gentle.py.tmpl +133 -94
  95. crawlo/templates/project/settings_high_performance.py.tmpl +155 -151
  96. crawlo/templates/project/settings_simple.py.tmpl +108 -68
  97. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  98. crawlo/templates/spider/spider.py.tmpl +143 -143
  99. crawlo/tools/__init__.py +182 -182
  100. crawlo/tools/anti_crawler.py +268 -268
  101. crawlo/tools/authenticated_proxy.py +240 -240
  102. crawlo/tools/data_validator.py +180 -180
  103. crawlo/tools/date_tools.py +35 -35
  104. crawlo/tools/distributed_coordinator.py +386 -386
  105. crawlo/tools/retry_mechanism.py +220 -220
  106. crawlo/tools/scenario_adapter.py +262 -262
  107. crawlo/utils/__init__.py +35 -35
  108. crawlo/utils/batch_processor.py +259 -260
  109. crawlo/utils/controlled_spider_mixin.py +439 -439
  110. crawlo/utils/date_tools.py +290 -290
  111. crawlo/utils/db_helper.py +343 -343
  112. crawlo/utils/enhanced_error_handler.py +356 -359
  113. crawlo/utils/env_config.py +105 -105
  114. crawlo/utils/error_handler.py +123 -125
  115. crawlo/utils/func_tools.py +82 -82
  116. crawlo/utils/large_scale_config.py +286 -286
  117. crawlo/utils/large_scale_helper.py +344 -343
  118. crawlo/utils/log.py +128 -128
  119. crawlo/utils/performance_monitor.py +285 -284
  120. crawlo/utils/queue_helper.py +175 -175
  121. crawlo/utils/redis_connection_pool.py +334 -334
  122. crawlo/utils/redis_key_validator.py +198 -199
  123. crawlo/utils/request.py +267 -267
  124. crawlo/utils/request_serializer.py +218 -219
  125. crawlo/utils/spider_loader.py +61 -62
  126. crawlo/utils/system.py +11 -11
  127. crawlo/utils/tools.py +4 -4
  128. crawlo/utils/url.py +39 -39
  129. {crawlo-1.2.2.dist-info → crawlo-1.2.4.dist-info}/METADATA +764 -692
  130. crawlo-1.2.4.dist-info/RECORD +206 -0
  131. examples/__init__.py +7 -7
  132. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  133. tests/__init__.py +7 -7
  134. tests/advanced_tools_example.py +275 -275
  135. tests/authenticated_proxy_example.py +236 -236
  136. tests/cleaners_example.py +160 -160
  137. tests/config_validation_demo.py +102 -102
  138. tests/controlled_spider_example.py +205 -205
  139. tests/date_tools_example.py +180 -180
  140. tests/dynamic_loading_example.py +523 -523
  141. tests/dynamic_loading_test.py +104 -104
  142. tests/env_config_example.py +133 -133
  143. tests/error_handling_example.py +171 -171
  144. tests/redis_key_validation_demo.py +130 -130
  145. tests/response_improvements_example.py +144 -144
  146. tests/test_advanced_tools.py +148 -148
  147. tests/test_all_redis_key_configs.py +145 -145
  148. tests/test_authenticated_proxy.py +141 -141
  149. tests/test_cleaners.py +54 -54
  150. tests/test_comprehensive.py +146 -146
  151. tests/test_config_validator.py +193 -193
  152. tests/test_crawlo_proxy_integration.py +172 -172
  153. tests/test_date_tools.py +123 -123
  154. tests/test_default_header_middleware.py +158 -158
  155. tests/test_double_crawlo_fix.py +207 -207
  156. tests/test_double_crawlo_fix_simple.py +124 -124
  157. tests/test_download_delay_middleware.py +221 -221
  158. tests/test_downloader_proxy_compatibility.py +268 -268
  159. tests/test_dynamic_downloaders_proxy.py +124 -124
  160. tests/test_dynamic_proxy.py +92 -92
  161. tests/test_dynamic_proxy_config.py +146 -146
  162. tests/test_dynamic_proxy_real.py +109 -109
  163. tests/test_edge_cases.py +303 -303
  164. tests/test_enhanced_error_handler.py +270 -270
  165. tests/test_env_config.py +121 -121
  166. tests/test_error_handler_compatibility.py +112 -112
  167. tests/test_final_validation.py +153 -153
  168. tests/test_framework_env_usage.py +103 -103
  169. tests/test_integration.py +356 -356
  170. tests/test_item_dedup_redis_key.py +122 -122
  171. tests/test_offsite_middleware.py +221 -221
  172. tests/test_parsel.py +29 -29
  173. tests/test_performance.py +327 -327
  174. tests/test_proxy_api.py +264 -264
  175. tests/test_proxy_health_check.py +32 -32
  176. tests/test_proxy_middleware.py +121 -121
  177. tests/test_proxy_middleware_enhanced.py +216 -216
  178. tests/test_proxy_middleware_integration.py +136 -136
  179. tests/test_proxy_providers.py +56 -56
  180. tests/test_proxy_stats.py +19 -19
  181. tests/test_proxy_strategies.py +59 -59
  182. tests/test_queue_manager_double_crawlo.py +173 -173
  183. tests/test_queue_manager_redis_key.py +176 -176
  184. tests/test_real_scenario_proxy.py +195 -195
  185. tests/test_redis_config.py +28 -28
  186. tests/test_redis_connection_pool.py +294 -294
  187. tests/test_redis_key_naming.py +181 -181
  188. tests/test_redis_key_validator.py +123 -123
  189. tests/test_redis_queue.py +224 -224
  190. tests/test_request_ignore_middleware.py +182 -182
  191. tests/test_request_serialization.py +70 -70
  192. tests/test_response_code_middleware.py +349 -349
  193. tests/test_response_filter_middleware.py +427 -427
  194. tests/test_response_improvements.py +152 -152
  195. tests/test_retry_middleware.py +241 -241
  196. tests/test_scheduler.py +241 -241
  197. tests/test_simple_response.py +61 -61
  198. tests/test_telecom_spider_redis_key.py +205 -205
  199. tests/test_template_content.py +87 -87
  200. tests/test_template_redis_key.py +134 -134
  201. tests/test_tools.py +153 -153
  202. tests/tools_example.py +257 -257
  203. crawlo-1.2.2.dist-info/RECORD +0 -220
  204. examples/aiohttp_settings.py +0 -42
  205. examples/curl_cffi_settings.py +0 -41
  206. examples/default_header_middleware_example.py +0 -107
  207. examples/default_header_spider_example.py +0 -129
  208. examples/download_delay_middleware_example.py +0 -160
  209. examples/httpx_settings.py +0 -42
  210. examples/multi_downloader_proxy_example.py +0 -81
  211. examples/offsite_middleware_example.py +0 -55
  212. examples/offsite_spider_example.py +0 -107
  213. examples/proxy_spider_example.py +0 -166
  214. examples/request_ignore_middleware_example.py +0 -51
  215. examples/request_ignore_spider_example.py +0 -99
  216. examples/response_code_middleware_example.py +0 -52
  217. examples/response_filter_middleware_example.py +0 -67
  218. examples/tong_hua_shun_settings.py +0 -62
  219. examples/tong_hua_shun_spider.py +0 -170
  220. {crawlo-1.2.2.dist-info → crawlo-1.2.4.dist-info}/WHEEL +0 -0
  221. {crawlo-1.2.2.dist-info → crawlo-1.2.4.dist-info}/entry_points.txt +0 -0
  222. {crawlo-1.2.2.dist-info → crawlo-1.2.4.dist-info}/top_level.txt +0 -0
@@ -1,220 +0,0 @@
1
- crawlo/__init__.py,sha256=jSOsZbDJ_Q5wZV8onSXx5LgNM7Z1q3zCROGdImBDr2I,1373
2
- crawlo/__version__.py,sha256=ZQHRX6XTb8PHUxt2yUXlITCSopFOjlI8X1fch8t4uA8,23
3
- crawlo/cli.py,sha256=DQIS3qIqLvQk_RVBc1j52to4QULfkq3DKK0fpNdiQ9k,2617
4
- crawlo/config.py,sha256=_pORwcVEgjEhrqVaApu51X0Il3TBK6w9aezGnnqYu8Y,9847
5
- crawlo/config_validator.py,sha256=M118EATR-tITzRSe2oSinV5oh2QsooMCkEJ5WS8ma_0,10155
6
- crawlo/crawler.py,sha256=24EE7zFPByeYLJnf1K_R9fhJMqaFUjBSa6TuUhlY4TI,37398
7
- crawlo/event.py,sha256=ZhoPW5CglCEuZNFEwviSCBIw0pT5O6jT98bqYrDFd3E,324
8
- crawlo/exceptions.py,sha256=YVIDnC1bKSMv3fXH_6tinWMuD9HmKHIaUfO4_fkX5sY,1247
9
- crawlo/mode_manager.py,sha256=q34nX-bMCLCKFfeYy_34VrBT86sL_K030LlLX2H3m0I,7728
10
- crawlo/project.py,sha256=MH2OYXIZdc9EJolUpUBXTcAgS7qvPP366LkOy62iP_8,6831
11
- crawlo/stats_collector.py,sha256=v4jC9BAe-23w93hWzbeMCCgQ9VuFPyxw5JV9ItbGH8w,1636
12
- crawlo/subscriber.py,sha256=Aj0kPpbBYlzOb1uViDFraoaThsQEVlqOSYUaFT3jSDs,5136
13
- crawlo/task_manager.py,sha256=PScfEB03306Txa0l38AeQ_0WVhKzeWOFyT3bnrkbHW0,849
14
- crawlo/cleaners/__init__.py,sha256=lxL-ZWDKW-DdobdgKUQ27wNmBiUhGnD0CVG6HWkX3_o,1261
15
- crawlo/cleaners/data_formatter.py,sha256=iBDHpZBZvn9O7pLkTQilE1TzYJQEc3z3f6HXoVus0f0,7808
16
- crawlo/cleaners/encoding_converter.py,sha256=G3khLlk0uBeTwIutsWxVUeSuyc1GMC1BDNJDwsU9ryg,4238
17
- crawlo/cleaners/text_cleaner.py,sha256=16e6WqIIb9qANMiK-vCEl4TvgkId19Aa2W1NMLU-jFQ,6707
18
- crawlo/commands/__init__.py,sha256=orvY6wLOBwGUEJKeF3h_T1fxj8AaQLjngBDd-3xKOE4,392
19
- crawlo/commands/check.py,sha256=jW8SgfkOS35j4VS7nRZBZdFCBX9CVFez5LR2sfP_H1U,23437
20
- crawlo/commands/genspider.py,sha256=_3GwFMYK79BuKk__5L0ljuwWwOzN80MeuhRkL4Ql11A,5201
21
- crawlo/commands/help.py,sha256=-bQRaGiV0tw4FKURDY2OXeQQuHGGlq6uzYJQ0tHB20w,5322
22
- crawlo/commands/list.py,sha256=octTk0QZhapiyM7WgCPersP2v3MesthbJeG9vMqVFOs,5936
23
- crawlo/commands/run.py,sha256=Go9hAEUMuG3GphBgemG5S5W4MF39XOxp7-E06rX-pTU,11043
24
- crawlo/commands/startproject.py,sha256=UYGelGY4dM6Zu3U4G5m8snKqbsfgszhvfpAJLl5b5tM,15772
25
- crawlo/commands/stats.py,sha256=iEKdxHoqsJuTkn8zAF9ekBVO1--8__BeD7xohYG5NwE,6252
26
- crawlo/commands/utils.py,sha256=b7yW6UlOLprR3gN9oOdhcl3fsCwWRE3-_gDxWz5xhMo,5292
27
- crawlo/core/__init__.py,sha256=JYSAn15r8yWgRK_Nc69t_8tZCyb70MiPZKssA8wrYz0,43
28
- crawlo/core/engine.py,sha256=kkNHQt1Dycb1hrEmG1m3seyX9C5qQp4GhOF-0H97t-A,14078
29
- crawlo/core/processor.py,sha256=oHLs-cno0bJGTNc9NGD2S7_2-grI3ruvggO0SY2mf3Q,1180
30
- crawlo/core/scheduler.py,sha256=LGeytsc04itdX7ulsl46MXBTyRFhBUu7UCSQzbtKZsk,5362
31
- crawlo/downloader/__init__.py,sha256=8-r4_Wc_X64FJtKzNQamwsZsc428creKeFo19VxF33o,8565
32
- crawlo/downloader/aiohttp_downloader.py,sha256=Ck4ybwpox3sC7v4IGc8RIcvmIBf9v6jAdyNGHByY1m4,8620
33
- crawlo/downloader/cffi_downloader.py,sha256=U2CMYQ8ZyKMQNNPvyI2USqI-Dclq2d7ZRgp3LxLjTFs,10966
34
- crawlo/downloader/httpx_downloader.py,sha256=MpgDeIdGqNsiSKLOEDBnr5Z0eUbhHnqVEmAuoIfJmFU,12296
35
- crawlo/downloader/hybrid_downloader.py,sha256=nn_cD4SOKj0_TE2zuLfXfJhQppeftZDL5u8DZuITwVQ,8256
36
- crawlo/downloader/playwright_downloader.py,sha256=L-TVzG7cYfuBlqW0XSZuz5C_r9fpJrmYNcoQ-cDEna4,16663
37
- crawlo/downloader/selenium_downloader.py,sha256=ho0ovIVU7e99xMT2_Clgj6SIH3GjxPx7yPN85C0_w9o,21508
38
- crawlo/extension/__init__.py,sha256=g7Nj1vm8L8n9ZmIbTzOXMYTkMSAJj4pw8TefaDyd52k,1563
39
- crawlo/extension/health_check.py,sha256=Yiu50Dkn_rIS6NnzurIoQmwDM2d-SmEetO1d5wor2Xc,5668
40
- crawlo/extension/log_interval.py,sha256=2R3XVdM1grDN8wh9TTHRB_WmQypCr5YSGvESNDnS16s,2474
41
- crawlo/extension/log_stats.py,sha256=5CpcTHj0lCtFvhBTI3pG41gkiL_hPtv5FWY87L6EVjM,2989
42
- crawlo/extension/logging_extension.py,sha256=euecjvj71aK6dElMzYCuNXiNb9jO8qQmL5QspQ1xoz8,1669
43
- crawlo/extension/memory_monitor.py,sha256=fClPchpCkVjcIiU0AJHCKDd7HEiz5B4KqNqKTRZ2hcU,4394
44
- crawlo/extension/performance_profiler.py,sha256=BjWD3LOb4VwjQJQvQtWNg7GluEwFquI1CztNfgMzy3c,5032
45
- crawlo/extension/request_recorder.py,sha256=KA_RmcfscDxP5wPdolO76yKfRj-1jmHhG3jkVGO1pbc,4181
46
- crawlo/filters/__init__.py,sha256=lX-QOCDTiTRFoiK1qrZ5HABo7LgZfcxScx_lELYEvJk,4395
47
- crawlo/filters/aioredis_filter.py,sha256=oveE9qFRtK8C9FZGRSZusRakXcAF-B2vkwbpsc0fX1E,10308
48
- crawlo/filters/memory_filter.py,sha256=FzGJPhVKfZ8P23kP6de-VSfE8oVMjjpfWzKJIdiMtZU,9529
49
- crawlo/items/__init__.py,sha256=rFpx1qFBo0Ik7bSdnXC8EVTJUOQdoJYGVdhYjaH00nk,409
50
- crawlo/items/base.py,sha256=hwGJEdFWOdaZfalFX8umRkh_HUWLEbCjvq4j70fplMQ,598
51
- crawlo/items/fields.py,sha256=fpS0vlRPpZYjTaMDgI9Q8z_YQqruwf6fi4Dgm6R2oEk,1854
52
- crawlo/items/items.py,sha256=OmVEvMmgofMU95GkaiWkfNQ2fjsH2fY9sw3SKcmUhLs,3478
53
- crawlo/middleware/__init__.py,sha256=PSwpRLdBUopaQzBp1S0zK_TZbrRagQ4yzvgyLy4tBk8,570
54
- crawlo/middleware/default_header.py,sha256=PHz_VWRZga1gqkpTGY_lDoG2c_ktt03dDacVKUzNu_I,5348
55
- crawlo/middleware/download_delay.py,sha256=2iWnJFtWDlqDy5MsAob8TPiJQoiz9v21yatkBI0eptg,3542
56
- crawlo/middleware/middleware_manager.py,sha256=G9R9SnDVey_zS2k1zm_358EPHDxRWfP953I4QavL7P0,6348
57
- crawlo/middleware/offsite.py,sha256=Y1SQaNjZOmWPNCHy884X0hfwVR31sIdJ1ofv83n0NDU,4142
58
- crawlo/middleware/proxy.py,sha256=eHeEDaCm72cpipXM7b-KO3i8ScYMsPuu5byLZUFuHhY,15604
59
- crawlo/middleware/request_ignore.py,sha256=cjjwtACdbH4Me0NF7RwYn6cJQNlrJktO_ZaRE5OjiF8,2665
60
- crawlo/middleware/response_code.py,sha256=Nk5fQtgyzZVOfFvFcgF442rk9hXBm9ixzTh4nH8BhSM,5099
61
- crawlo/middleware/response_filter.py,sha256=tUe5Hc2N8p5_4kO8pdDa6sChUBkP2Mk7XAo762ScZOk,4386
62
- crawlo/middleware/retry.py,sha256=D_v4-8grofGsLkGJIhLKklMbdHO0gtij7DIS4G52NJc,4248
63
- crawlo/network/__init__.py,sha256=bvEnpEUBZJ79URfNZbsHhsBKna54hM2-x_BV8eotTA4,418
64
- crawlo/network/request.py,sha256=amZdRvDJvFpx82thtWwv6uo5uv9vtCwbvw3jAc3sCrY,12633
65
- crawlo/network/response.py,sha256=QwJhL3xJfPVy_gwtGrg61oAgaqCoCmjyj1Ug7Zju7Pg,13060
66
- crawlo/pipelines/__init__.py,sha256=FDe2Pr5tiHtV8hFlheElRO_O1aVKvSWlkTcAl9BXAKA,637
67
- crawlo/pipelines/bloom_dedup_pipeline.py,sha256=n0Ay7MtIEJ8L4Otiha4zRvI9toFUSNFugTNubi-Q3aw,5798
68
- crawlo/pipelines/console_pipeline.py,sha256=bwe5hZgaVSWmh3R8XpOaaeAjJme-Ttrpo6G6f1cnLIg,1287
69
- crawlo/pipelines/csv_pipeline.py,sha256=qbXZoqq4FIR9QkUGpC0ryWzmqGJSrM2bxmWLM4I1nXM,12490
70
- crawlo/pipelines/database_dedup_pipeline.py,sha256=6_zKtCNgFBPJyTI3Mk4l75fMQ2UQQGKFfNTpZqGs_zI,8224
71
- crawlo/pipelines/json_pipeline.py,sha256=wrCsh8YInmcPLAkhPrHObMx89VZfhf-c7qRrYsTixPE,8585
72
- crawlo/pipelines/memory_dedup_pipeline.py,sha256=oQcBODO-I2p6B7Nm_klXvuhzSMIHP-JWwC4_o6Gkgcc,3954
73
- crawlo/pipelines/mongo_pipeline.py,sha256=PohTKTGw3QRvuP-T6SrquwW3FAHSno8jQ2D2cH_d75U,5837
74
- crawlo/pipelines/mysql_pipeline.py,sha256=RRKMuO-7BTomyRFYCmDpfvjBTcU4SGdjGDV4wBeKWck,13796
75
- crawlo/pipelines/pipeline_manager.py,sha256=g7lQBllYpKLymDWShjsR4SsXG41XnzD5mUR0UDBt0ZQ,2419
76
- crawlo/pipelines/redis_dedup_pipeline.py,sha256=U2mms0XBkTgC8_DywIigGboChjUH_l0-cfo_ioYQNsI,6333
77
- crawlo/queue/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
78
- crawlo/queue/pqueue.py,sha256=qTFOuvEXsYEZbm0ULjsOeZo0XtSsZ-SHpx7nFEtmluE,1095
79
- crawlo/queue/queue_manager.py,sha256=wdQq0UYJcmyw9JPXiro2GP3q58vtjeIV3ouWyFmuhBc,13211
80
- crawlo/queue/redis_priority_queue.py,sha256=oVvGjkcMpRqJEEBbRlAL16TKcp38Gg9YMdZCUQa7wFI,13081
81
- crawlo/settings/__init__.py,sha256=NgYFLfk_Bw7h6KSoepJn_lMBSqVbCHebjKxaE3_eMgw,130
82
- crawlo/settings/default_settings.py,sha256=_s5mXXYFhZ6Yx_8ATALDmrOOb-4e8iAiaGyi7LNYJss,9385
83
- crawlo/settings/setting_manager.py,sha256=uqgm2uZQp7Wx1hMSf2FnA0dh6f4jzZ13NQbRvIfYwsQ,3829
84
- crawlo/spider/__init__.py,sha256=xAH6NfE_6K2aY_VSL9DoGjcmMHJDd5Nxr7TG1Y8vQAE,21091
85
- crawlo/templates/crawlo.cfg.tmpl,sha256=lwiUVe5sFixJgHFEjn1OtbAeyWsECOrz37uheuVtulk,240
86
- crawlo/templates/project/__init__.py.tmpl,sha256=aQnHaOjMSkTviOC8COUX0fKymuyf8lx2tGduxkMkXEE,61
87
- crawlo/templates/project/items.py.tmpl,sha256=8_3DBA8HrS2XbfHzsMZNJiZbFY6fDJUUMFoFti_obJk,314
88
- crawlo/templates/project/middlewares.py.tmpl,sha256=fxHqi-Sjec5GiHJciprOU-6SAUTzM728NlZckIqf9hM,4278
89
- crawlo/templates/project/pipelines.py.tmpl,sha256=j9oqEhCezmmHlBhMWgYtlgup4jhWnMlv6AEiAOHODkg,2704
90
- crawlo/templates/project/run.py.tmpl,sha256=yOxpPkyffXLwa7NDx2Y96c8U-QN81_3mqZSuB526DNs,1271
91
- crawlo/templates/project/settings.py.tmpl,sha256=1481CdB6VdDzNXyYe0a5Qn5z-UJ0ELIELuSVbExnrOg,12167
92
- crawlo/templates/project/settings_distributed.py.tmpl,sha256=Nli-qR-UB4TXAq4mXjx17y-yAv46NwwpcVidjGeM00A,4321
93
- crawlo/templates/project/settings_gentle.py.tmpl,sha256=ljXf9vKV2c-cN8yvf5U4UWsPWrMVmJUfbXladIdS2mg,3320
94
- crawlo/templates/project/settings_high_performance.py.tmpl,sha256=3wf8fFYZ5EVE2742JlcwwrPF794vEIEmbxFSbqyGnJQ,5434
95
- crawlo/templates/project/settings_simple.py.tmpl,sha256=UKfSEZFAXDywswwws9SvR5vBMng2maJ37DJMfK0nAmI,2365
96
- crawlo/templates/project/spiders/__init__.py.tmpl,sha256=zMbePipgLsctQUEnda4WkHz8rDLUX--rc8ruI6zkpWc,111
97
- crawlo/templates/spider/spider.py.tmpl,sha256=KvU-9YpN6MifDE7XzejjyyQS7RUjLDLZ8zqJcLwSsu0,5198
98
- crawlo/tools/__init__.py,sha256=6BcoEE7t119VzdwqnULrWnYDNpXu86FHkWgx_WL1-Sk,3853
99
- crawlo/tools/anti_crawler.py,sha256=LwLC6BkxDSkxc5H1hQ6kY9j7O0PZGAMPZECr7gbqw2M,9431
100
- crawlo/tools/authenticated_proxy.py,sha256=ULCK0Cc9F2rGhRqu6kzKBdxzK9v2n1CsatSQ_PMxpAg,7272
101
- crawlo/tools/data_validator.py,sha256=bLWnkpFdclJuqjtSAgMI5nznN4vAuPwE1YaiFWKWenM,5490
102
- crawlo/tools/date_tools.py,sha256=dNm06OwJYQ7KeVkZoFcfFhMwJPsHlB3JJfSplOA0XfY,635
103
- crawlo/tools/distributed_coordinator.py,sha256=QM4ECyhTba9jtV7-AkOuT_lDJObeKVeBsRLZZFS_A7Y,12863
104
- crawlo/tools/retry_mechanism.py,sha256=VbHo9-pT8ADbwyPuKcRfeUo4BtVZQy6yvrSvugoiZRA,8021
105
- crawlo/tools/scenario_adapter.py,sha256=pzysL1B2uQ1ZSEncVHd9Hv2viHNgaxP44YAUcDcppfw,9660
106
- crawlo/utils/__init__.py,sha256=5unISyKR7pZdj7EwP5tadGYKvyb_W1uoC52YzqSbxis,592
107
- crawlo/utils/batch_processor.py,sha256=wnpWL41Su6gSvbzNgRWv7sRxKzBFV0J27V9gC3WsLJc,9155
108
- crawlo/utils/controlled_spider_mixin.py,sha256=os5v8eFX08Nbqm48W-xWdY04LboqDgOgOL-93IX9zvg,16914
109
- crawlo/utils/date_tools.py,sha256=gsgHweZFOzeW-K91wRlBEg_XLKBCXl7UZJfnjI_W-J0,9197
110
- crawlo/utils/db_helper.py,sha256=ZqOt1d3mErVv4TOvoWlov0niUxORB9aHByTmMoNFIDw,10902
111
- crawlo/utils/enhanced_error_handler.py,sha256=o6oxCtWFcAGslON3FZNRgxvHutd9z0tqbc0R5kmF_lk,14265
112
- crawlo/utils/env_config.py,sha256=9hJ4T-ufAzWPZugytgLMZStZxD17JaE900S8xpGoyn0,2974
113
- crawlo/utils/error_handler.py,sha256=7AHwZHJD-CTq0DNOwbDjUvzdbushDI_xWJiwe4KzBeQ,4411
114
- crawlo/utils/func_tools.py,sha256=y-TYP9H3X67MS_foWy9Z2LIS6GP7Y4Cy3T168ulq3Jc,2451
115
- crawlo/utils/large_scale_config.py,sha256=lsraHTAQx3sMPjTnCBY_SVIpkuIBUb3zD9eFvmccOOM,8440
116
- crawlo/utils/large_scale_helper.py,sha256=ZazAI7KV3V-3hzc4a3BWxTXfEO2XIEBMzxTLM9S1l_Q,12500
117
- crawlo/utils/log.py,sha256=YD2FfXuuE2MC9ZdQQZ0H7KysE7l_LHZqQepaTPlcApo,4133
118
- crawlo/utils/performance_monitor.py,sha256=ku_QAx3MX8U-Dfd5fqMr-YV5j1srYJbtF_5jdVJx6tY,9879
119
- crawlo/utils/queue_helper.py,sha256=gFmkh1jKlIcN1rmo2Jl6vYcLP5ByUWlfHO9eNlZPBLs,4918
120
- crawlo/utils/redis_connection_pool.py,sha256=rGaKcn2YVeP_bA38svkl3A-lU3DpfX6x0TzdaxWvIlo,10665
121
- crawlo/utils/redis_key_validator.py,sha256=5lft8SPbHkBf9NdrQaW13R-fXLJoMBkJlc1w38wuPmU,5836
122
- crawlo/utils/request.py,sha256=ejdKpTwc-HE04HQybafhOVywzz57IV3pY0YMkSLyGUo,9065
123
- crawlo/utils/request_serializer.py,sha256=bZhuonZV2AdB_X0aje7sDljqWAIrEzUYwEaxXytaWsg,8784
124
- crawlo/utils/spider_loader.py,sha256=V0CBTicJBYBZafhwLfDEfuEc_hJ2mSoiptT6qKufI9U,2249
125
- crawlo/utils/system.py,sha256=24zGmtHNhDFMGVo7ftMV-Pqg6_5d63zsyNey9udvJJk,248
126
- crawlo/utils/tools.py,sha256=uy7qw5Z1BIhyEgiHENvtM7WoGCJxlS8EX3PmOA7ouCo,275
127
- crawlo/utils/url.py,sha256=RKe_iqdjafsNcp-P2GVLYpsL1qbxiuZLiFc-SqOQkcs,1521
128
- examples/__init__.py,sha256=NkRbV8_S1tb8S2AW6BE2U6P2-eGOPwMR1k0YQAwQpSE,130
129
- examples/aiohttp_settings.py,sha256=xEagH-6lGmUaWBiGJ1gqtHTDw60PzR9q1qzkpMrd_oc,1058
130
- examples/curl_cffi_settings.py,sha256=0oLNQ2MI-hf8t7ibYmbXw68v3yd_Xu9j9j4_3RNsvGQ,1027
131
- examples/default_header_middleware_example.py,sha256=1hUPu-Zw4okWLox2pD8FTV7MQqYgRjDus5mVsGODinQ,4599
132
- examples/default_header_spider_example.py,sha256=JIkG81aqXhGi-TKeFGl8s4ewMhdhwss-QBODj5il3VI,4723
133
- examples/download_delay_middleware_example.py,sha256=utIsjO6in9vqiDZ59fhV8It62rx9_9DMyJXbdbh8kSE,4855
134
- examples/httpx_settings.py,sha256=cOYrH4PlsrfSD6r8z9ErjU_2cPLWifXIvu8YfmVSRxg,1036
135
- examples/multi_downloader_proxy_example.py,sha256=mje7W5GsCbLvXClQ724n9AFgZbJMgQ80hMh-N5fzQv0,2576
136
- examples/offsite_middleware_example.py,sha256=X6GqLG6J1iDjs04CVwh-XvTv7sW0r2o6OyBX3xxBV7U,2069
137
- examples/offsite_spider_example.py,sha256=01LPOkNZEAlMwXuK2jI8fqUNkgm_CDmrNQRzL8RCE5A,3172
138
- examples/proxy_spider_example.py,sha256=CvreU4UhLXnFFDffKthJAgO6ebzOvwHQbXBNQfw8rOY,5495
139
- examples/request_ignore_middleware_example.py,sha256=O9YdM6-ivsBMyXmMAhw2kI9j3VmSXf0cftBnPsJGEQA,2023
140
- examples/request_ignore_spider_example.py,sha256=S6Y50w7wrL8l5vemq4lm13_0SONHBIs3pN3_6LfR0Hw,3169
141
- examples/response_code_middleware_example.py,sha256=AvR4RuCK4wL7yUd0qoOB5ScBbdYefUa95SmBr_Pv9pQ,2082
142
- examples/response_filter_middleware_example.py,sha256=9QDqzDkcfSF8WVyUNgu-ybj6x43OXI_Xl1v2gVHqWhE,2651
143
- examples/tong_hua_shun_settings.py,sha256=3YYojtVvxm3JqRkR-hNL9WDR3AeoIZW3iikRnM4C6OU,1926
144
- examples/tong_hua_shun_spider.py,sha256=5ToQOv01LS0GlmMVknwIY2CpUZ0vTq-sBUP6t8aOfqg,6690
145
- tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md,sha256=4W6HlT9Uc3cyu77T9pfbkrMxpAZ-xq_L9MU-GbukLV0,3427
146
- tests/__init__.py,sha256=409aRX8hsPffiZCVjOogtxwhACzBp8G2UTJyUQSxhK0,136
147
- tests/advanced_tools_example.py,sha256=1_iitECKCuWUYMNNGo61l3lmwMRrWdA8F_Xw56UaGZY,9340
148
- tests/authenticated_proxy_example.py,sha256=b307_RybOtxXVQK0ITboLvHmOTwIN4yTF9aup4dYF7Q,8477
149
- tests/cleaners_example.py,sha256=tEGf-x8CNlXpKurgmNxTmmPjQa45dRUSBjnOJVGGSeU,5330
150
- tests/config_validation_demo.py,sha256=ah4cLZnozMdwKzACOoa5R52dWfya282WyulCGjadioM,3218
151
- tests/controlled_spider_example.py,sha256=2SAQKoREGHe-OzVaSkGpopCcrou6QXmeW7rLdmsyopw,7981
152
- tests/date_tools_example.py,sha256=XI3iFEzeo7Nb5YepK8WHytIaBegtxWVSISpqQgpV6M8,5042
153
- tests/dynamic_loading_example.py,sha256=7LdeQZFevrb-U1_dgr4oX3aYo2Da4HvE_0KIf1fw4Ew,18786
154
- tests/dynamic_loading_test.py,sha256=dzDW7b66HeDsIYsYgvNRihE3V6b6gEbUGQpp-eJbcIM,3413
155
- tests/env_config_example.py,sha256=_ZRDh_LR23ZKpy9E--y_KM0QIOiZF5vRT98QTn52TY8,4951
156
- tests/error_handling_example.py,sha256=sqvSoogDefyDoEBz3AVPG4pe49gRqBxT5BDFkijmYaA,5332
157
- tests/redis_key_validation_demo.py,sha256=R0ZTJJSeMB-ptVfzwegw7bw83FDDcR2XUNnUZqstSPE,4475
158
- tests/response_improvements_example.py,sha256=t1cbG3nesp82bqog4_ku1GvQzNbhRyWa5EaKTmOPrSk,5402
159
- tests/test_advanced_tools.py,sha256=HT_TcwfFzli-CavIJSqQqnCxnBn5FDMX09zL7AJ5tNY,5398
160
- tests/test_all_redis_key_configs.py,sha256=Uk91dnGwGaGsdukpvbTiXd4NnrsOa-THWD2cwSZkqag,5805
161
- tests/test_authenticated_proxy.py,sha256=lnvmQwuf0zaZP_E05EzcNFR2VJbwTkLjOmZGNoJKaC4,4339
162
- tests/test_cleaners.py,sha256=qyd20RNuBHIVHz7X5JjLwlIZedn7yHZ4uB3X78BpaF4,1819
163
- tests/test_comprehensive.py,sha256=dvRJeeVYc1cgXK9Y171hH9Y847zZpWSAFFH-EI3UepQ,5182
164
- tests/test_config_validator.py,sha256=Ec1h8Mw-fVz1d9JoATIWZb0nTc8pYjhTCSjPm3tvkTQ,6825
165
- tests/test_crawlo_proxy_integration.py,sha256=O0wK1u73qOuahRHWBXeDuMk5y1qMBMHLVVBYVP3U5SM,5576
166
- tests/test_date_tools.py,sha256=pcLDyhLrZ_jh-PhPm4CvLZEgNeH9kLMPKN5zacHwuWM,4053
167
- tests/test_default_header_middleware.py,sha256=v-ei_1EY7cvFSsySrQPXF5-DmyGsq2yzjYhhrwFMOXs,6003
168
- tests/test_double_crawlo_fix.py,sha256=qkJugMiEM2KQFHZ_Iza7Y0cER8p-Mecr57zjwHdsaSE,8033
169
- tests/test_double_crawlo_fix_simple.py,sha256=aPQQRex7ShxC_QJyjRkgelbn0Lnl3fFTwsPH5OglpwM,4807
170
- tests/test_download_delay_middleware.py,sha256=Idc6KzhL3hY3aDKgn1j_v5-mLIHz7dTnV5c4tJVZh5Q,9107
171
- tests/test_downloader_proxy_compatibility.py,sha256=DU19UnjhS3jdP1lfoF098bptKF4jpaowc4G274SgV8c,8915
172
- tests/test_dynamic_downloaders_proxy.py,sha256=t_aWpxOHi4h3_fg2ImtIq7IIJ0r3PTHtnXiopPe2ZlM,4450
173
- tests/test_dynamic_proxy.py,sha256=zi7Ocbhc9GL1zCs0XhmG2NvBBeIZ2d2hPJVh18lH4Y0,3172
174
- tests/test_dynamic_proxy_config.py,sha256=C_9CEjCJtrr0SxIXCyLDhSIi88ujF7UAT1F-FAphd0w,5853
175
- tests/test_dynamic_proxy_real.py,sha256=krWnbFIH26mWNPhOfPMmx3ZxJfOreZxMZFGwVb_8-K8,3511
176
- tests/test_edge_cases.py,sha256=kd5irijfGB0MkL-eukmc-WFm_xfbzQ30tPq-FMJaxsg,10856
177
- tests/test_enhanced_error_handler.py,sha256=cROcikmLvL11NgjCj-fGfVlKV3sLq7VN4DY_9U54IBU,8705
178
- tests/test_env_config.py,sha256=Qu1sDeADs69dSr1x0QmEe8nJrMHneE_4JClt-N901e8,4867
179
- tests/test_error_handler_compatibility.py,sha256=xJ43cmCwfBGh-qBwCGiMDPPlfNDLw4ZrmlrHN9IojkU,4241
180
- tests/test_final_validation.py,sha256=UNHMOkcOBx9jPdnYuYCF4Cx5GlXakBeHybOP27lpbAg,5078
181
- tests/test_framework_env_usage.py,sha256=bFb_ptdLeX2obdJWEqEHPWweiWR-wR2BpvEaJMQK7h4,4201
182
- tests/test_integration.py,sha256=l-G_z_btCtK0W4VvP1yNJFaZIZtKXDTeD1Ns2C-v6Nw,11677
183
- tests/test_item_dedup_redis_key.py,sha256=GIdyFBm56EbFzTvgnYcimgQFoMgvEZW8z1KFVUu3HJ4,3877
184
- tests/test_offsite_middleware.py,sha256=1DYktO_D-hiLEB6dBnc0iOvnWimqOdE6kimnS8aof_s,7764
185
- tests/test_parsel.py,sha256=wuZqRFIm9xx1tt6o3Xi_OjvwhT_MPmHiUEj2ax06zlo,701
186
- tests/test_performance.py,sha256=cjmWwIXBsHibgVyjyIt30iiXSDVse2HD6lFb0YlZsAQ,11613
187
- tests/test_proxy_api.py,sha256=SOBedDX8JTl3iPhluaCyybvA6B6k1poYkN7hY9gNpho,11029
188
- tests/test_proxy_health_check.py,sha256=_tDlxa_6TdL3M5RLkHF82roXJ8WIuG5hELBp2GADyKQ,1123
189
- tests/test_proxy_middleware.py,sha256=EdQAfwwAJIBxw9JmUFTDEu_pdxapaTlcJr7KcrY6-AY,4021
190
- tests/test_proxy_middleware_enhanced.py,sha256=QR-p26F63N7MxNjZ2QJUeerh_xdnCDejkrGPIh7Fh4U,7035
191
- tests/test_proxy_middleware_integration.py,sha256=mTPK_XvbmLCV_QoVZzA3ybWOOX61493Ew78WfTp-bYQ,4441
192
- tests/test_proxy_providers.py,sha256=u_R2fhab90vqvQEaOAztpAOe9tJXvUMIdoDxmStmXJ4,1749
193
- tests/test_proxy_stats.py,sha256=ES00CEoDITYPFBGPk8pecFzD3ItYIv6NSpcqNd8-kvo,526
194
- tests/test_proxy_strategies.py,sha256=9Z1pXmTNyw-eIhGXlf2abZbJx6igLohYq-_3hldQ5uE,1868
195
- tests/test_queue_manager_double_crawlo.py,sha256=5oPn3xnAXcZ2ZJweLTYEKDM-sQXQ0MZJdtjqD_Zmlrc,6995
196
- tests/test_queue_manager_redis_key.py,sha256=tvy3qkmB6XNpnJ4SOgjKvxE83hltCdL5Z32CupQ2VZ0,6454
197
- tests/test_real_scenario_proxy.py,sha256=dhlQcbiGd-zp2L9EJ12q7HfDxuEAyi_SxBSoXH6YyZM,8490
198
- tests/test_redis_config.py,sha256=Kbl3PURGNM1BUIspakEOA-ZOl2xxTHb_8KbftwjYOsg,921
199
- tests/test_redis_connection_pool.py,sha256=wLPmJ94jUajpShNrnnl4pTbX9ZIGqCEZgzzecasAC4s,9471
200
- tests/test_redis_key_naming.py,sha256=44A174UkKdj2ipjJa4N0RWIN8CYun6w08yylg8Yu9ac,6957
201
- tests/test_redis_key_validator.py,sha256=Yw0EsDQuI3Gzt_s86BubBP2VU_s7fyI-TthEX5J5C-o,4427
202
- tests/test_redis_queue.py,sha256=5LTc86A5qqF5VbmkvkF2OnLAxlJ7ClfJPw0dODxekFk,6846
203
- tests/test_request_ignore_middleware.py,sha256=QN81wgG_W_XfXCF9LvJNxCNwbOH6_tZnLIwLDTK2K5Q,6229
204
- tests/test_request_serialization.py,sha256=Jf7Kr7edL0ENwxh8ABa1W_O3dWyqNlvoSfQM1Mykpys,2359
205
- tests/test_response_code_middleware.py,sha256=wSe525bm-bk_iWMjPDzUu1LfOQrwJY8_MLKAspq2dzk,12193
206
- tests/test_response_filter_middleware.py,sha256=YWrGzJ7wmftTjJXcNTtJl3b3EdJsO4oR22ZLWwgErhg,16327
207
- tests/test_response_improvements.py,sha256=vNqHKyoEoYeEGAUiRzdsff2V6yvJ9QnDwGg7gmN38Ow,6028
208
- tests/test_retry_middleware.py,sha256=RmSYSf0GagGPGAVi5TXJWc0bZlmAI_hwFr2FYhvuKrk,8097
209
- tests/test_scheduler.py,sha256=elAPFh-Ph49bbJQlTBEsRwzhoX82EdryqQbpc_wsobU,7683
210
- tests/test_simple_response.py,sha256=_ui2PuVZvJcAuLY7HZ8xcsy_tDBimgBqX0ukj3kE5J0,1549
211
- tests/test_telecom_spider_redis_key.py,sha256=SUCUK_CgHgl1wj59o2a1g4qJpLUyW4reXv-5Bjuk6Ko,7675
212
- tests/test_template_content.py,sha256=URwjlAzMCdUN0sW_OupUcuSNMxp1OKgW79JOpkLPXnw,2965
213
- tests/test_template_redis_key.py,sha256=dOFutic8CL3tOzGbYhWbMrYiXZ8R3fhNoF5VKax5Iy0,4946
214
- tests/test_tools.py,sha256=fgzXL2L7eBV_nGjeMxH8IMhfc0dviQ80XgzZkJp_4dA,5266
215
- tests/tools_example.py,sha256=uXNS4xXJ-OD_xInAn2zjKLG_nlbgVGXZLoJtfhaG9lI,7926
216
- crawlo-1.2.2.dist-info/METADATA,sha256=Kd8W53gp0eac7V4kT-IGgdpQ68iHd22tmiV4En9v8xs,20484
217
- crawlo-1.2.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
218
- crawlo-1.2.2.dist-info/entry_points.txt,sha256=5HoVoTSPxI8SCa5B7pQYxLSrkOdiunyO9tqNsLMv52g,43
219
- crawlo-1.2.2.dist-info/top_level.txt,sha256=keG_67pbZ_wZL2dmDRA9RMaNHTaV_x_oxZ9DKNgwvR0,22
220
- crawlo-1.2.2.dist-info/RECORD,,
@@ -1,42 +0,0 @@
1
- #!/usr/bin/env python
2
- # -*- coding: utf-8 -*-
3
- """
4
- aiohttp下载器配置示例
5
- """
6
-
7
- # 基础配置
8
- SETTINGS = {
9
- # 下载器配置
10
- 'DOWNLOADER': 'crawlo.downloader.aiohttp_downloader.AioHttpDownloader',
11
- 'DOWNLOADER_TYPE': 'aiohttp',
12
-
13
- # aiohttp特定配置
14
- 'AIOHTTP_AUTO_DECOMPRESS': True,
15
- 'AIOHTTP_FORCE_CLOSE': False,
16
-
17
- # 代理配置
18
- 'PROXY_ENABLED': True,
19
- 'PROXY_API_URL': 'http://test.proxy.api:8080/proxy/getitem/',
20
- 'PROXY_EXTRACTOR': 'proxy',
21
- 'PROXY_REFRESH_INTERVAL': 60,
22
- 'PROXY_POOL_SIZE': 5,
23
-
24
- # 通用下载配置
25
- 'DOWNLOAD_TIMEOUT': 30,
26
- 'CONNECTION_POOL_LIMIT': 100,
27
- 'CONNECTION_POOL_LIMIT_PER_HOST': 20,
28
- 'DOWNLOAD_MAXSIZE': 10 * 1024 * 1024, # 10MB
29
- 'VERIFY_SSL': True,
30
-
31
- # 日志配置
32
- 'LOG_LEVEL': 'INFO',
33
- }
34
-
35
- def get_settings():
36
- """获取配置"""
37
- return SETTINGS
38
-
39
- if __name__ == "__main__":
40
- print("aiohttp下载器配置:")
41
- for key, value in SETTINGS.items():
42
- print(f" {key}: {value}")
@@ -1,41 +0,0 @@
1
- #!/usr/bin/env python
2
- # -*- coding: utf-8 -*-
3
- """
4
- curl-cffi下载器配置示例
5
- """
6
-
7
- # 基础配置
8
- SETTINGS = {
9
- # 下载器配置
10
- 'DOWNLOADER': 'crawlo.downloader.cffi_downloader.CurlCffiDownloader',
11
- 'DOWNLOADER_TYPE': 'curl_cffi',
12
-
13
- # curl-cffi特定配置
14
- 'CURL_BROWSER_TYPE': 'chrome',
15
-
16
- # 代理配置
17
- 'PROXY_ENABLED': True,
18
- 'PROXY_API_URL': 'http://test.proxy.api:8080/proxy/getitem/',
19
- 'PROXY_EXTRACTOR': 'proxy',
20
- 'PROXY_REFRESH_INTERVAL': 60,
21
- 'PROXY_POOL_SIZE': 5,
22
-
23
- # 通用下载配置
24
- 'DOWNLOAD_TIMEOUT': 30,
25
- 'CONNECTION_POOL_LIMIT': 100,
26
- 'CONNECTION_POOL_LIMIT_PER_HOST': 20,
27
- 'DOWNLOAD_MAXSIZE': 10 * 1024 * 1024, # 10MB
28
- 'VERIFY_SSL': True,
29
-
30
- # 日志配置
31
- 'LOG_LEVEL': 'INFO',
32
- }
33
-
34
- def get_settings():
35
- """获取配置"""
36
- return SETTINGS
37
-
38
- if __name__ == "__main__":
39
- print("curl-cffi下载器配置:")
40
- for key, value in SETTINGS.items():
41
- print(f" {key}: {value}")
@@ -1,107 +0,0 @@
1
- #!/usr/bin/env python
2
- # -*- coding: utf-8 -*-
3
- """
4
- DefaultHeaderMiddleware 使用示例
5
- 展示如何配置和使用DefaultHeaderMiddleware来添加默认请求头,支持随机更换功能
6
- """
7
-
8
- # 基础配置
9
- SETTINGS = {
10
- # 默认请求头配置
11
- 'DEFAULT_REQUEST_HEADERS': {
12
- 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
13
- 'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
14
- 'Accept-Encoding': 'gzip, deflate, br',
15
- 'Connection': 'keep-alive',
16
- 'Upgrade-Insecure-Requests': '1',
17
- },
18
-
19
- # 固定User-Agent(优先级高于随机User-Agent)
20
- # 'USER_AGENT': 'Custom User Agent String',
21
-
22
- # 自定义User-Agent列表(可选,如果不配置将使用内置列表)
23
- # 'USER_AGENTS': [
24
- # 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36',
25
- # 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36',
26
- # ],
27
-
28
- # 启用随机User-Agent功能
29
- 'RANDOM_USER_AGENT_ENABLED': True,
30
-
31
- # 指定User-Agent设备类型(可选值: "desktop", "mobile", "all")
32
- 'USER_AGENT_DEVICE_TYPE': 'all',
33
-
34
- # 随机请求头配置(启用RANDOMNESS时使用)
35
- 'RANDOM_HEADERS': {
36
- 'Accept': [
37
- 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
38
- 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
39
- 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8'
40
- ],
41
- 'Accept-Language': [
42
- 'zh-CN,zh;q=0.9,en;q=0.8',
43
- 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
44
- 'zh-TW,zh;q=0.9,en-US;q=0.8,en;q=0.7'
45
- ],
46
- 'Cache-Control': 'no-cache' # 固定值
47
- },
48
-
49
- # 启用随机性功能(用于随机请求头)
50
- 'RANDOMNESS': True,
51
-
52
- # 中间件配置(DefaultHeaderMiddleware已默认启用)
53
- 'MIDDLEWARES': [
54
- # === 请求预处理阶段 ===
55
- 'crawlo.middleware.request_ignore.RequestIgnoreMiddleware', # 1. 忽略无效请求
56
- 'crawlo.middleware.download_delay.DownloadDelayMiddleware', # 2. 控制请求频率
57
- 'crawlo.middleware.default_header.DefaultHeaderMiddleware', # 3. 添加默认请求头
58
- 'crawlo.middleware.proxy.ProxyMiddleware', # 4. 设置代理
59
- 'crawlo.middleware.offsite.OffsiteMiddleware', # 5. 站外请求过滤
60
-
61
- # === 响应处理阶段 ===
62
- 'crawlo.middleware.retry.RetryMiddleware', # 6. 失败请求重试
63
- 'crawlo.middleware.response_code.ResponseCodeMiddleware', # 7. 处理特殊状态码
64
- 'crawlo.middleware.response_filter.ResponseFilterMiddleware', # 8. 响应内容过滤
65
- ],
66
-
67
- # 其他常用配置
68
- 'DOWNLOAD_DELAY': 1,
69
- 'CONCURRENCY': 8,
70
- 'LOG_LEVEL': 'INFO',
71
- }
72
-
73
- def get_settings():
74
- """获取配置"""
75
- return SETTINGS
76
-
77
- if __name__ == "__main__":
78
- print("DefaultHeaderMiddleware配置示例:")
79
- print("=" * 40)
80
- print("默认请求头配置:")
81
- for key, value in SETTINGS['DEFAULT_REQUEST_HEADERS'].items():
82
- print(f" {key}: {value}")
83
-
84
- print(f"\n随机User-Agent功能: {'启用' if SETTINGS['RANDOM_USER_AGENT_ENABLED'] else '禁用'}")
85
- print(f"User-Agent设备类型: {SETTINGS['USER_AGENT_DEVICE_TYPE']}")
86
-
87
- print(f"\n随机请求头功能: {'启用' if SETTINGS['RANDOMNESS'] else '禁用'}")
88
- print("随机请求头配置:")
89
- for key, value in SETTINGS['RANDOM_HEADERS'].items():
90
- if isinstance(value, list):
91
- print(f" {key}: {len(value)}个可选值")
92
- else:
93
- print(f" {key}: {value}")
94
-
95
- print("\n中间件列表:")
96
- for i, middleware in enumerate(SETTINGS['MIDDLEWARES'], 1):
97
- print(f" {i}. {middleware}")
98
-
99
- print("\n" + "=" * 40)
100
- print("DefaultHeaderMiddleware功能说明:")
101
- print("✓ 自动为所有请求添加默认请求头")
102
- print("✓ 不会覆盖请求中已存在的同名头部")
103
- print("✓ 支持随机User-Agent更换(降低被识别风险)")
104
- print("✓ 支持按设备类型选择User-Agent(桌面/移动/全部)")
105
- print("✓ 支持随机请求头更换(增加请求多样性)")
106
- print("✓ 可通过设置相关配置项来启用/禁用随机功能")
107
- print("✓ 在调试模式下会记录添加的请求头信息")
@@ -1,129 +0,0 @@
1
- #!/usr/bin/env python
2
- # -*- coding: utf-8 -*-
3
- """
4
- 使用DefaultHeaderMiddleware的爬虫示例
5
- 展示如何在实际爬虫中使用DefaultHeaderMiddleware添加默认请求头,支持随机更换功能
6
- """
7
-
8
- from crawlo.spider import Spider
9
- from crawlo.network.request import Request
10
-
11
-
12
- class HeaderExampleSpider(Spider):
13
- """
14
- 示例爬虫,演示DefaultHeaderMiddleware的使用,包括随机更换功能
15
- """
16
-
17
- # 爬虫名称
18
- name = "header_example_spider"
19
-
20
- # 自定义设置
21
- custom_settings = {
22
- # 默认请求头配置
23
- 'DEFAULT_REQUEST_HEADERS': {
24
- 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
25
- 'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
26
- 'Accept-Encoding': 'gzip, deflate, br',
27
- 'Connection': 'keep-alive',
28
- },
29
-
30
- # 启用随机User-Agent功能
31
- 'RANDOM_USER_AGENT_ENABLED': True,
32
-
33
- # 指定User-Agent设备类型(可选值: "desktop", "mobile", "all")
34
- 'USER_AGENT_DEVICE_TYPE': 'all',
35
-
36
- # 或者自定义User-Agent列表(可选,如果不配置将使用内置列表)
37
- # 'USER_AGENTS': [
38
- # 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36',
39
- # 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36',
40
- # ],
41
-
42
- # 随机请求头配置
43
- 'RANDOM_HEADERS': {
44
- 'Accept': [
45
- 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
46
- 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
47
- 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8'
48
- ],
49
- 'Accept-Language': [
50
- 'zh-CN,zh;q=0.9,en;q=0.8',
51
- 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
52
- 'zh-TW,zh;q=0.9,en-US;q=0.8,en;q=0.7'
53
- ],
54
- 'Cache-Control': 'no-cache'
55
- },
56
-
57
- # 启用随机性功能
58
- 'RANDOMNESS': True,
59
-
60
- # 请求延迟(秒)
61
- 'DOWNLOAD_DELAY': 1,
62
-
63
- # 并发数
64
- 'CONCURRENCY': 4,
65
-
66
- # 日志级别
67
- 'LOG_LEVEL': 'INFO',
68
- }
69
-
70
- def start_requests(self):
71
- """
72
- 开始请求
73
- """
74
- urls = [
75
- 'https://httpbin.org/headers', # 可以查看发送的请求头
76
- 'https://httpbin.org/user-agent', # 可以查看User-Agent
77
- ]
78
-
79
- for url in urls:
80
- yield Request(url=url, callback=self.parse_headers)
81
-
82
- async def parse_headers(self, response):
83
- """
84
- 处理响应,查看发送的请求头
85
- """
86
- self.logger.info(f"请求URL: {response.url}")
87
- self.logger.info(f"状态码: {response.status_code}")
88
-
89
- # 输出响应内容(包含请求头信息)
90
- try:
91
- import json
92
- data = json.loads(response.body.decode('utf-8'))
93
- self.logger.info("发送的请求头:")
94
- headers = data.get('headers', {})
95
- for key, value in headers.items():
96
- self.logger.info(f" {key}: {value}")
97
- except Exception as e:
98
- self.logger.warning(f"解析响应失败: {e}")
99
- self.logger.info(f"响应内容: {response.body[:200]}...")
100
-
101
-
102
- # 运行爬虫的示例代码
103
- if __name__ == "__main__":
104
- """
105
- 运行说明:
106
-
107
- 1. 确保已在项目根目录下安装了crawlo:
108
- pip install -e .
109
-
110
- 2. 运行爬虫:
111
- crawlo run header_example_spider
112
-
113
- 3. 观察日志输出:
114
- - 可以看到发送的请求头信息
115
- - 验证随机User-Agent是否正确更换
116
- - 确认随机请求头是否按预期设置
117
-
118
- DefaultHeaderMiddleware的随机功能优势:
119
- ✓ 自动为每个请求随机更换User-Agent,降低被识别为爬虫的风险
120
- ✓ 支持按设备类型选择User-Agent(桌面/移动设备)
121
- ✓ 支持随机更换其他请求头,增加请求的多样性
122
- ✓ 可配置的随机策略,灵活适应不同网站的要求
123
- ✓ 保持默认请求头的一致性,同时增加随机性
124
- """
125
- print("DefaultHeaderSpider示例")
126
- print("=" * 30)
127
- print("此爬虫演示了DefaultHeaderMiddleware的随机更换功能")
128
- print("请使用以下命令运行:")
129
- print(" crawlo run header_example_spider")