crawlo 1.4.1__tar.gz → 1.4.2__tar.gz

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 (318) hide show
  1. {crawlo-1.4.1/crawlo.egg-info → crawlo-1.4.2}/PKG-INFO +1 -1
  2. crawlo-1.4.2/crawlo/__version__.py +1 -0
  3. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/run.py +1 -1
  4. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/downloader/aiohttp_downloader.py +7 -2
  5. {crawlo-1.4.1 → crawlo-1.4.2/crawlo.egg-info}/PKG-INFO +1 -1
  6. crawlo-1.4.1/crawlo/__version__.py +0 -1
  7. {crawlo-1.4.1 → crawlo-1.4.2}/LICENSE +0 -0
  8. {crawlo-1.4.1 → crawlo-1.4.2}/MANIFEST.in +0 -0
  9. {crawlo-1.4.1 → crawlo-1.4.2}/README.md +0 -0
  10. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/__init__.py +0 -0
  11. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/cli.py +0 -0
  12. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/__init__.py +0 -0
  13. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/check.py +0 -0
  14. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/genspider.py +0 -0
  15. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/help.py +0 -0
  16. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/list.py +0 -0
  17. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/startproject.py +0 -0
  18. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/stats.py +0 -0
  19. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/utils.py +0 -0
  20. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/config.py +0 -0
  21. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/config_validator.py +0 -0
  22. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/core/__init__.py +0 -0
  23. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/core/engine.py +0 -0
  24. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/core/processor.py +0 -0
  25. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/core/scheduler.py +0 -0
  26. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/crawler.py +0 -0
  27. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/data/__init__.py +0 -0
  28. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/data/user_agents.py +0 -0
  29. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/downloader/__init__.py +0 -0
  30. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/downloader/cffi_downloader.py +0 -0
  31. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/downloader/httpx_downloader.py +0 -0
  32. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/downloader/hybrid_downloader.py +0 -0
  33. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/downloader/playwright_downloader.py +0 -0
  34. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/downloader/selenium_downloader.py +0 -0
  35. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/event.py +0 -0
  36. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/exceptions.py +0 -0
  37. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/extension/__init__.py +0 -0
  38. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/extension/health_check.py +0 -0
  39. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/extension/log_interval.py +0 -0
  40. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/extension/log_stats.py +0 -0
  41. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/extension/logging_extension.py +0 -0
  42. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/extension/memory_monitor.py +0 -0
  43. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/extension/performance_profiler.py +0 -0
  44. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/extension/request_recorder.py +0 -0
  45. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/factories/__init__.py +0 -0
  46. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/factories/base.py +0 -0
  47. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/factories/crawler.py +0 -0
  48. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/factories/registry.py +0 -0
  49. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/filters/__init__.py +0 -0
  50. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/filters/aioredis_filter.py +0 -0
  51. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/filters/memory_filter.py +0 -0
  52. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/framework.py +0 -0
  53. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/initialization/__init__.py +0 -0
  54. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/initialization/built_in.py +0 -0
  55. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/initialization/context.py +0 -0
  56. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/initialization/core.py +0 -0
  57. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/initialization/phases.py +0 -0
  58. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/initialization/registry.py +0 -0
  59. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/items/__init__.py +0 -0
  60. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/items/base.py +0 -0
  61. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/items/fields.py +0 -0
  62. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/items/items.py +0 -0
  63. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/logging/__init__.py +0 -0
  64. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/logging/config.py +0 -0
  65. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/logging/factory.py +0 -0
  66. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/logging/manager.py +0 -0
  67. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/middleware/__init__.py +0 -0
  68. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/middleware/default_header.py +0 -0
  69. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/middleware/download_delay.py +0 -0
  70. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/middleware/middleware_manager.py +0 -0
  71. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/middleware/offsite.py +0 -0
  72. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/middleware/proxy.py +0 -0
  73. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/middleware/request_ignore.py +0 -0
  74. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/middleware/response_code.py +0 -0
  75. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/middleware/response_filter.py +0 -0
  76. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/middleware/retry.py +0 -0
  77. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/middleware/simple_proxy.py +0 -0
  78. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/mode_manager.py +0 -0
  79. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/network/__init__.py +0 -0
  80. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/network/request.py +0 -0
  81. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/network/response.py +0 -0
  82. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/pipelines/__init__.py +0 -0
  83. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/pipelines/bloom_dedup_pipeline.py +0 -0
  84. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/pipelines/console_pipeline.py +0 -0
  85. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/pipelines/csv_pipeline.py +0 -0
  86. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/pipelines/database_dedup_pipeline.py +0 -0
  87. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/pipelines/json_pipeline.py +0 -0
  88. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/pipelines/memory_dedup_pipeline.py +0 -0
  89. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/pipelines/mongo_pipeline.py +0 -0
  90. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/pipelines/mysql_pipeline.py +0 -0
  91. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/pipelines/pipeline_manager.py +0 -0
  92. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/pipelines/redis_dedup_pipeline.py +0 -0
  93. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/project.py +0 -0
  94. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/queue/__init__.py +0 -0
  95. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/queue/pqueue.py +0 -0
  96. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/queue/queue_manager.py +0 -0
  97. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/queue/redis_priority_queue.py +0 -0
  98. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/settings/__init__.py +0 -0
  99. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/settings/default_settings.py +0 -0
  100. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/settings/setting_manager.py +0 -0
  101. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/spider/__init__.py +0 -0
  102. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/stats_collector.py +0 -0
  103. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/subscriber.py +0 -0
  104. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/task_manager.py +0 -0
  105. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/crawlo.cfg.tmpl +0 -0
  106. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/project/__init__.py.tmpl +0 -0
  107. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/project/items.py.tmpl +0 -0
  108. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/project/middlewares.py.tmpl +0 -0
  109. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/project/pipelines.py.tmpl +0 -0
  110. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/project/settings.py.tmpl +0 -0
  111. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/project/settings_distributed.py.tmpl +0 -0
  112. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/project/settings_gentle.py.tmpl +0 -0
  113. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/project/settings_high_performance.py.tmpl +0 -0
  114. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/project/settings_minimal.py.tmpl +0 -0
  115. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/project/settings_simple.py.tmpl +0 -0
  116. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/project/spiders/__init__.py.tmpl +0 -0
  117. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/run.py.tmpl +0 -0
  118. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/spider/spider.py.tmpl +0 -0
  119. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/templates/spiders_init.py.tmpl +0 -0
  120. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/tools/__init__.py +0 -0
  121. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/tools/anti_crawler.py +0 -0
  122. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/tools/authenticated_proxy.py +0 -0
  123. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/tools/data_formatter.py +0 -0
  124. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/tools/data_validator.py +0 -0
  125. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/tools/date_tools.py +0 -0
  126. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/tools/distributed_coordinator.py +0 -0
  127. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/tools/encoding_converter.py +0 -0
  128. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/tools/network_diagnostic.py +0 -0
  129. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/tools/request_tools.py +0 -0
  130. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/tools/retry_mechanism.py +0 -0
  131. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/tools/scenario_adapter.py +0 -0
  132. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/tools/text_cleaner.py +0 -0
  133. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/__init__.py +0 -0
  134. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/batch_processor.py +0 -0
  135. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/class_loader.py +0 -0
  136. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/controlled_spider_mixin.py +0 -0
  137. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/db_helper.py +0 -0
  138. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/enhanced_error_handler.py +0 -0
  139. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/env_config.py +0 -0
  140. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/error_handler.py +0 -0
  141. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/fingerprint.py +0 -0
  142. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/func_tools.py +0 -0
  143. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/large_scale_config.py +0 -0
  144. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/large_scale_helper.py +0 -0
  145. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/log.py +0 -0
  146. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/performance_monitor.py +0 -0
  147. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/queue_helper.py +0 -0
  148. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/redis_connection_pool.py +0 -0
  149. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/redis_key_validator.py +0 -0
  150. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/request.py +0 -0
  151. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/request_serializer.py +0 -0
  152. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/spider_loader.py +0 -0
  153. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/system.py +0 -0
  154. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/tools.py +0 -0
  155. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/url.py +0 -0
  156. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo.egg-info/SOURCES.txt +0 -0
  157. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo.egg-info/dependency_links.txt +0 -0
  158. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo.egg-info/entry_points.txt +0 -0
  159. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo.egg-info/requires.txt +0 -0
  160. {crawlo-1.4.1 → crawlo-1.4.2}/crawlo.egg-info/top_level.txt +0 -0
  161. {crawlo-1.4.1 → crawlo-1.4.2}/examples/__init__.py +0 -0
  162. {crawlo-1.4.1 → crawlo-1.4.2}/examples/test_project/__init__.py +0 -0
  163. {crawlo-1.4.1 → crawlo-1.4.2}/examples/test_project/run.py +0 -0
  164. {crawlo-1.4.1 → crawlo-1.4.2}/examples/test_project/test_project/__init__.py +0 -0
  165. {crawlo-1.4.1 → crawlo-1.4.2}/examples/test_project/test_project/items.py +0 -0
  166. {crawlo-1.4.1 → crawlo-1.4.2}/examples/test_project/test_project/middlewares.py +0 -0
  167. {crawlo-1.4.1 → crawlo-1.4.2}/examples/test_project/test_project/pipelines.py +0 -0
  168. {crawlo-1.4.1 → crawlo-1.4.2}/examples/test_project/test_project/settings.py +0 -0
  169. {crawlo-1.4.1 → crawlo-1.4.2}/examples/test_project/test_project/spiders/__init__.py +0 -0
  170. {crawlo-1.4.1 → crawlo-1.4.2}/examples/test_project/test_project/spiders/of_week_dis.py +0 -0
  171. {crawlo-1.4.1 → crawlo-1.4.2}/pyproject.toml +0 -0
  172. {crawlo-1.4.1 → crawlo-1.4.2}/requirements.txt +0 -0
  173. {crawlo-1.4.1 → crawlo-1.4.2}/setup.cfg +0 -0
  174. {crawlo-1.4.1 → crawlo-1.4.2}/tests/__init__.py +0 -0
  175. {crawlo-1.4.1 → crawlo-1.4.2}/tests/advanced_tools_example.py +0 -0
  176. {crawlo-1.4.1 → crawlo-1.4.2}/tests/authenticated_proxy_example.py +0 -0
  177. {crawlo-1.4.1 → crawlo-1.4.2}/tests/baidu_performance_test.py +0 -0
  178. {crawlo-1.4.1 → crawlo-1.4.2}/tests/baidu_test.py +0 -0
  179. {crawlo-1.4.1 → crawlo-1.4.2}/tests/cleaners_example.py +0 -0
  180. {crawlo-1.4.1 → crawlo-1.4.2}/tests/comprehensive_framework_test.py +0 -0
  181. {crawlo-1.4.1 → crawlo-1.4.2}/tests/comprehensive_test.py +0 -0
  182. {crawlo-1.4.1 → crawlo-1.4.2}/tests/comprehensive_testing_summary.md +0 -0
  183. {crawlo-1.4.1 → crawlo-1.4.2}/tests/config_validation_demo.py +0 -0
  184. {crawlo-1.4.1 → crawlo-1.4.2}/tests/controlled_spider_example.py +0 -0
  185. {crawlo-1.4.1 → crawlo-1.4.2}/tests/date_tools_example.py +0 -0
  186. {crawlo-1.4.1 → crawlo-1.4.2}/tests/debug_configure.py +0 -0
  187. {crawlo-1.4.1 → crawlo-1.4.2}/tests/debug_framework_logger.py +0 -0
  188. {crawlo-1.4.1 → crawlo-1.4.2}/tests/debug_log_config.py +0 -0
  189. {crawlo-1.4.1 → crawlo-1.4.2}/tests/debug_log_levels.py +0 -0
  190. {crawlo-1.4.1 → crawlo-1.4.2}/tests/debug_pipelines.py +0 -0
  191. {crawlo-1.4.1 → crawlo-1.4.2}/tests/detailed_log_test.py +0 -0
  192. {crawlo-1.4.1 → crawlo-1.4.2}/tests/distributed_test.py +0 -0
  193. {crawlo-1.4.1 → crawlo-1.4.2}/tests/distributed_test_debug.py +0 -0
  194. {crawlo-1.4.1 → crawlo-1.4.2}/tests/dynamic_loading_example.py +0 -0
  195. {crawlo-1.4.1 → crawlo-1.4.2}/tests/dynamic_loading_test.py +0 -0
  196. {crawlo-1.4.1 → crawlo-1.4.2}/tests/env_config_example.py +0 -0
  197. {crawlo-1.4.1 → crawlo-1.4.2}/tests/error_handling_example.py +0 -0
  198. {crawlo-1.4.1 → crawlo-1.4.2}/tests/final_command_test_report.md +0 -0
  199. {crawlo-1.4.1 → crawlo-1.4.2}/tests/final_comprehensive_test.py +0 -0
  200. {crawlo-1.4.1 → crawlo-1.4.2}/tests/final_log_test.py +0 -0
  201. {crawlo-1.4.1 → crawlo-1.4.2}/tests/final_validation_test.py +0 -0
  202. {crawlo-1.4.1 → crawlo-1.4.2}/tests/fix_log_test.py +0 -0
  203. {crawlo-1.4.1 → crawlo-1.4.2}/tests/framework_performance_test.py +0 -0
  204. {crawlo-1.4.1 → crawlo-1.4.2}/tests/log_buffering_test.py +0 -0
  205. {crawlo-1.4.1 → crawlo-1.4.2}/tests/log_generation_timing_test.py +0 -0
  206. {crawlo-1.4.1 → crawlo-1.4.2}/tests/optimized_performance_test.py +0 -0
  207. {crawlo-1.4.1 → crawlo-1.4.2}/tests/performance_comparison.py +0 -0
  208. {crawlo-1.4.1 → crawlo-1.4.2}/tests/queue_blocking_test.py +0 -0
  209. {crawlo-1.4.1 → crawlo-1.4.2}/tests/queue_test.py +0 -0
  210. {crawlo-1.4.1 → crawlo-1.4.2}/tests/redis_key_validation_demo.py +0 -0
  211. {crawlo-1.4.1 → crawlo-1.4.2}/tests/request_params_example.py +0 -0
  212. {crawlo-1.4.1 → crawlo-1.4.2}/tests/response_improvements_example.py +0 -0
  213. {crawlo-1.4.1 → crawlo-1.4.2}/tests/scrapy_comparison/ofweek_scrapy.py +0 -0
  214. {crawlo-1.4.1 → crawlo-1.4.2}/tests/scrapy_comparison/scrapy_test.py +0 -0
  215. {crawlo-1.4.1 → crawlo-1.4.2}/tests/simple_command_test.py +0 -0
  216. {crawlo-1.4.1 → crawlo-1.4.2}/tests/simple_crawlo_test.py +0 -0
  217. {crawlo-1.4.1 → crawlo-1.4.2}/tests/simple_log_test.py +0 -0
  218. {crawlo-1.4.1 → crawlo-1.4.2}/tests/simple_log_test2.py +0 -0
  219. {crawlo-1.4.1 → crawlo-1.4.2}/tests/simple_optimization_test.py +0 -0
  220. {crawlo-1.4.1 → crawlo-1.4.2}/tests/simple_queue_type_test.py +0 -0
  221. {crawlo-1.4.1 → crawlo-1.4.2}/tests/simple_spider_test.py +0 -0
  222. {crawlo-1.4.1 → crawlo-1.4.2}/tests/simple_test.py +0 -0
  223. {crawlo-1.4.1 → crawlo-1.4.2}/tests/spider_log_timing_test.py +0 -0
  224. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_advanced_tools.py +0 -0
  225. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_all_commands.py +0 -0
  226. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_all_pipeline_fingerprints.py +0 -0
  227. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_all_redis_key_configs.py +0 -0
  228. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_authenticated_proxy.py +0 -0
  229. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_batch_processor.py +0 -0
  230. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_cleaners.py +0 -0
  231. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_component_factory.py +0 -0
  232. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_comprehensive.py +0 -0
  233. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_config_consistency.py +0 -0
  234. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_config_merge.py +0 -0
  235. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_config_validator.py +0 -0
  236. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_controlled_spider_mixin.py +0 -0
  237. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_crawlo_proxy_integration.py +0 -0
  238. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_date_tools.py +0 -0
  239. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_dedup_fix.py +0 -0
  240. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_default_header_middleware.py +0 -0
  241. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_distributed.py +0 -0
  242. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_double_crawlo_fix.py +0 -0
  243. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_double_crawlo_fix_simple.py +0 -0
  244. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_download_delay_middleware.py +0 -0
  245. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_downloader_proxy_compatibility.py +0 -0
  246. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_dynamic_downloaders_proxy.py +0 -0
  247. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_dynamic_proxy.py +0 -0
  248. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_dynamic_proxy_config.py +0 -0
  249. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_dynamic_proxy_real.py +0 -0
  250. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_edge_cases.py +0 -0
  251. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_enhanced_error_handler.py +0 -0
  252. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_enhanced_error_handler_comprehensive.py +0 -0
  253. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_env_config.py +0 -0
  254. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_error_handler_compatibility.py +0 -0
  255. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_factories.py +0 -0
  256. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_final_validation.py +0 -0
  257. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_fingerprint_consistency.py +0 -0
  258. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_fingerprint_simple.py +0 -0
  259. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_framework_env_usage.py +0 -0
  260. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_framework_logger.py +0 -0
  261. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_framework_startup.py +0 -0
  262. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_get_component_logger.py +0 -0
  263. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_hash_performance.py +0 -0
  264. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_integration.py +0 -0
  265. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_item_dedup_redis_key.py +0 -0
  266. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_large_scale_config.py +0 -0
  267. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_large_scale_helper.py +0 -0
  268. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_logging_system.py +0 -0
  269. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_mode_change.py +0 -0
  270. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_mode_consistency.py +0 -0
  271. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_offsite_middleware.py +0 -0
  272. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_offsite_middleware_simple.py +0 -0
  273. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_parsel.py +0 -0
  274. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_performance.py +0 -0
  275. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_performance_monitor.py +0 -0
  276. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_pipeline_fingerprint_consistency.py +0 -0
  277. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_proxy_api.py +0 -0
  278. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_proxy_health_check.py +0 -0
  279. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_proxy_middleware.py +0 -0
  280. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_proxy_middleware_enhanced.py +0 -0
  281. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_proxy_middleware_integration.py +0 -0
  282. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_proxy_middleware_refactored.py +0 -0
  283. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_proxy_providers.py +0 -0
  284. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_proxy_stats.py +0 -0
  285. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_proxy_strategies.py +0 -0
  286. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_queue_empty_check.py +0 -0
  287. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_queue_manager_double_crawlo.py +0 -0
  288. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_queue_manager_redis_key.py +0 -0
  289. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_queue_naming.py +0 -0
  290. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_queue_type.py +0 -0
  291. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_random_user_agent.py +0 -0
  292. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_real_scenario_proxy.py +0 -0
  293. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_redis_config.py +0 -0
  294. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_redis_connection_pool.py +0 -0
  295. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_redis_key_naming.py +0 -0
  296. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_redis_key_validator.py +0 -0
  297. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_redis_queue.py +0 -0
  298. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_redis_queue_name_fix.py +0 -0
  299. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_request_ignore_middleware.py +0 -0
  300. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_request_params.py +0 -0
  301. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_request_serialization.py +0 -0
  302. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_response_code_middleware.py +0 -0
  303. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_response_filter_middleware.py +0 -0
  304. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_response_improvements.py +0 -0
  305. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_retry_middleware.py +0 -0
  306. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_scheduler.py +0 -0
  307. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_scheduler_config_update.py +0 -0
  308. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_simple_response.py +0 -0
  309. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_telecom_spider_redis_key.py +0 -0
  310. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_template_content.py +0 -0
  311. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_template_redis_key.py +0 -0
  312. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_tools.py +0 -0
  313. {crawlo-1.4.1 → crawlo-1.4.2}/tests/test_user_agents.py +0 -0
  314. {crawlo-1.4.1 → crawlo-1.4.2}/tests/tools_example.py +0 -0
  315. {crawlo-1.4.1 → crawlo-1.4.2}/tests/untested_features_report.md +0 -0
  316. {crawlo-1.4.1 → crawlo-1.4.2}/tests/verify_debug.py +0 -0
  317. {crawlo-1.4.1 → crawlo-1.4.2}/tests/verify_distributed.py +0 -0
  318. {crawlo-1.4.1 → crawlo-1.4.2}/tests/verify_log_fix.py +0 -0
{crawlo-1.4.1/crawlo.egg-info → crawlo-1.4.2}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: crawlo
3
- Version: 1.4.1
3
+ Version: 1.4.2
4
4
  Summary: Crawlo 是一款基于异步IO的高性能Python爬虫框架，支持分布式抓取。
5
5
  Home-page: https://github.com/crawl-coder/Crawlo.git
6
6
  Author: crawl-coder
crawlo-1.4.2/crawlo/__version__.py ADDED
@@ -0,0 +1 @@
1
+ __version__ = '1.4.2'
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/run.py RENAMED
@@ -23,7 +23,7 @@ from crawlo.crawler import CrawlerProcess
23
23
  from crawlo.project import get_settings, _find_project_root
24
24
  # 使用新的统一初始化系统
25
25
  from crawlo.initialization import initialize_framework
26
- from crawlo.initialization import get_framework_initializer
26
+ from crawlo.core import get_framework_initializer
27
27
  from crawlo.utils.log import get_logger
28
28
 
29
29
  # 延迟获取logger，确保在日志系统配置之后获取
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/downloader/aiohttp_downloader.py RENAMED
@@ -55,8 +55,13 @@ class AioHttpDownloader(DownloaderBase):
55
55
  family=0, # 允许IPv4和IPv6
56
56
  )
57
57
 
58
- # 超时控制
59
- timeout = ClientTimeout(total=timeout_secs)
58
+ # 超时控制 - 增加更多超时设置
59
+ timeout = ClientTimeout(
60
+ total=timeout_secs,
61
+ connect=timeout_secs/2, # 连接超时
62
+ sock_read=timeout_secs, # 读取超时
63
+ sock_connect=timeout_secs/2 # socket连接超时
64
+ )
60
65
 
61
66
  # 请求追踪
62
67
  trace_config = TraceConfig()
{crawlo-1.4.1 → crawlo-1.4.2/crawlo.egg-info}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: crawlo
3
- Version: 1.4.1
3
+ Version: 1.4.2
4
4
  Summary: Crawlo 是一款基于异步IO的高性能Python爬虫框架，支持分布式抓取。
5
5
  Home-page: https://github.com/crawl-coder/Crawlo.git
6
6
  Author: crawl-coder
crawlo-1.4.1/crawlo/__version__.py DELETED
@@ -1 +0,0 @@
1
- __version__ = '1.4.1'
{crawlo-1.4.1 → crawlo-1.4.2}/LICENSE RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/MANIFEST.in RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/README.md RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/__init__.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/cli.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/check.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/help.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/list.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/stats.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/commands/utils.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/config.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/core/__init__.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/core/engine.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/core/processor.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/core/scheduler.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/crawler.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/data/__init__.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/event.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/exceptions.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/factories/base.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/framework.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/items/__init__.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/items/base.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/items/fields.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/items/items.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/logging/config.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/logging/factory.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/logging/manager.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/mode_manager.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/network/request.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/project.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/queue/__init__.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/queue/pqueue.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/spider/__init__.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/stats_collector.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/subscriber.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/task_manager.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/tools/__init__.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/__init__.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/db_helper.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/log.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/request.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/system.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/tools.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/crawlo/utils/url.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/examples/__init__.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/pyproject.toml RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/requirements.txt RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/setup.cfg RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/tests/__init__.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/tests/baidu_test.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/tests/cleaners_example.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/tests/debug_configure.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/tests/debug_log_config.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/tests/debug_log_levels.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/tests/debug_pipelines.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/tests/distributed_test.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/tests/final_log_test.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/tests/fix_log_test.py RENAMED
File without changes
{crawlo-1.4.1 → crawlo-1.4.2}/tests/queue_test.py RENAMED
File without changes