crawlo 1.1.4__py3-none-any.whl → 1.1.5__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 (186) hide show
  1. crawlo/__init__.py +61 -34
  2. crawlo/__version__.py +1 -1
  3. crawlo/cleaners/__init__.py +61 -0
  4. crawlo/cleaners/data_formatter.py +226 -0
  5. crawlo/cleaners/encoding_converter.py +126 -0
  6. crawlo/cleaners/text_cleaner.py +233 -0
  7. crawlo/cli.py +40 -40
  8. crawlo/commands/__init__.py +13 -13
  9. crawlo/commands/check.py +594 -594
  10. crawlo/commands/genspider.py +151 -151
  11. crawlo/commands/list.py +155 -155
  12. crawlo/commands/run.py +285 -285
  13. crawlo/commands/startproject.py +300 -196
  14. crawlo/commands/stats.py +188 -188
  15. crawlo/commands/utils.py +186 -186
  16. crawlo/config.py +309 -279
  17. crawlo/config_validator.py +253 -0
  18. crawlo/core/__init__.py +2 -2
  19. crawlo/core/engine.py +346 -172
  20. crawlo/core/processor.py +40 -40
  21. crawlo/core/scheduler.py +137 -166
  22. crawlo/crawler.py +1027 -1027
  23. crawlo/downloader/__init__.py +266 -242
  24. crawlo/downloader/aiohttp_downloader.py +220 -212
  25. crawlo/downloader/cffi_downloader.py +256 -251
  26. crawlo/downloader/httpx_downloader.py +259 -259
  27. crawlo/downloader/hybrid_downloader.py +214 -0
  28. crawlo/downloader/playwright_downloader.py +403 -0
  29. crawlo/downloader/selenium_downloader.py +473 -0
  30. crawlo/event.py +11 -11
  31. crawlo/exceptions.py +81 -81
  32. crawlo/extension/__init__.py +37 -37
  33. crawlo/extension/health_check.py +141 -141
  34. crawlo/extension/log_interval.py +57 -57
  35. crawlo/extension/log_stats.py +81 -81
  36. crawlo/extension/logging_extension.py +43 -43
  37. crawlo/extension/memory_monitor.py +104 -88
  38. crawlo/extension/performance_profiler.py +133 -117
  39. crawlo/extension/request_recorder.py +107 -107
  40. crawlo/filters/__init__.py +154 -154
  41. crawlo/filters/aioredis_filter.py +280 -242
  42. crawlo/filters/memory_filter.py +269 -269
  43. crawlo/items/__init__.py +23 -23
  44. crawlo/items/base.py +21 -21
  45. crawlo/items/fields.py +53 -53
  46. crawlo/items/items.py +104 -104
  47. crawlo/middleware/__init__.py +21 -21
  48. crawlo/middleware/default_header.py +32 -32
  49. crawlo/middleware/download_delay.py +28 -28
  50. crawlo/middleware/middleware_manager.py +135 -135
  51. crawlo/middleware/proxy.py +272 -248
  52. crawlo/middleware/request_ignore.py +30 -30
  53. crawlo/middleware/response_code.py +18 -18
  54. crawlo/middleware/response_filter.py +26 -26
  55. crawlo/middleware/retry.py +124 -124
  56. crawlo/mode_manager.py +206 -201
  57. crawlo/network/__init__.py +21 -21
  58. crawlo/network/request.py +338 -311
  59. crawlo/network/response.py +360 -271
  60. crawlo/pipelines/__init__.py +21 -21
  61. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  62. crawlo/pipelines/console_pipeline.py +39 -39
  63. crawlo/pipelines/csv_pipeline.py +316 -316
  64. crawlo/pipelines/database_dedup_pipeline.py +224 -224
  65. crawlo/pipelines/json_pipeline.py +218 -218
  66. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  67. crawlo/pipelines/mongo_pipeline.py +131 -131
  68. crawlo/pipelines/mysql_pipeline.py +316 -316
  69. crawlo/pipelines/pipeline_manager.py +56 -56
  70. crawlo/pipelines/redis_dedup_pipeline.py +166 -162
  71. crawlo/project.py +153 -153
  72. crawlo/queue/pqueue.py +37 -37
  73. crawlo/queue/queue_manager.py +320 -307
  74. crawlo/queue/redis_priority_queue.py +277 -209
  75. crawlo/settings/__init__.py +7 -7
  76. crawlo/settings/default_settings.py +216 -278
  77. crawlo/settings/setting_manager.py +99 -99
  78. crawlo/spider/__init__.py +639 -639
  79. crawlo/stats_collector.py +59 -59
  80. crawlo/subscriber.py +130 -130
  81. crawlo/task_manager.py +30 -30
  82. crawlo/templates/crawlo.cfg.tmpl +10 -10
  83. crawlo/templates/project/__init__.py.tmpl +3 -3
  84. crawlo/templates/project/items.py.tmpl +17 -17
  85. crawlo/templates/project/middlewares.py.tmpl +110 -110
  86. crawlo/templates/project/pipelines.py.tmpl +97 -97
  87. crawlo/templates/project/run.py.tmpl +251 -251
  88. crawlo/templates/project/settings.py.tmpl +326 -279
  89. crawlo/templates/project/settings_distributed.py.tmpl +120 -0
  90. crawlo/templates/project/settings_gentle.py.tmpl +95 -0
  91. crawlo/templates/project/settings_high_performance.py.tmpl +152 -0
  92. crawlo/templates/project/settings_simple.py.tmpl +69 -0
  93. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  94. crawlo/templates/spider/spider.py.tmpl +141 -141
  95. crawlo/tools/__init__.py +183 -0
  96. crawlo/tools/anti_crawler.py +269 -0
  97. crawlo/tools/authenticated_proxy.py +241 -0
  98. crawlo/tools/data_validator.py +181 -0
  99. crawlo/tools/date_tools.py +36 -0
  100. crawlo/tools/distributed_coordinator.py +387 -0
  101. crawlo/tools/retry_mechanism.py +221 -0
  102. crawlo/tools/scenario_adapter.py +263 -0
  103. crawlo/utils/__init__.py +35 -7
  104. crawlo/utils/batch_processor.py +261 -0
  105. crawlo/utils/controlled_spider_mixin.py +439 -439
  106. crawlo/utils/date_tools.py +290 -233
  107. crawlo/utils/db_helper.py +343 -343
  108. crawlo/utils/enhanced_error_handler.py +360 -0
  109. crawlo/utils/env_config.py +106 -0
  110. crawlo/utils/error_handler.py +126 -0
  111. crawlo/utils/func_tools.py +82 -82
  112. crawlo/utils/large_scale_config.py +286 -286
  113. crawlo/utils/large_scale_helper.py +343 -343
  114. crawlo/utils/log.py +128 -128
  115. crawlo/utils/performance_monitor.py +285 -0
  116. crawlo/utils/queue_helper.py +175 -175
  117. crawlo/utils/redis_connection_pool.py +335 -0
  118. crawlo/utils/redis_key_validator.py +200 -0
  119. crawlo/utils/request.py +267 -267
  120. crawlo/utils/request_serializer.py +219 -219
  121. crawlo/utils/spider_loader.py +62 -62
  122. crawlo/utils/system.py +11 -11
  123. crawlo/utils/tools.py +4 -4
  124. crawlo/utils/url.py +39 -39
  125. {crawlo-1.1.4.dist-info → crawlo-1.1.5.dist-info}/METADATA +401 -403
  126. crawlo-1.1.5.dist-info/RECORD +185 -0
  127. examples/__init__.py +7 -7
  128. tests/__init__.py +7 -7
  129. tests/advanced_tools_example.py +276 -0
  130. tests/authenticated_proxy_example.py +237 -0
  131. tests/cleaners_example.py +161 -0
  132. tests/config_validation_demo.py +103 -0
  133. {examples → tests}/controlled_spider_example.py +205 -205
  134. tests/date_tools_example.py +181 -0
  135. tests/dynamic_loading_example.py +524 -0
  136. tests/dynamic_loading_test.py +105 -0
  137. tests/env_config_example.py +134 -0
  138. tests/error_handling_example.py +172 -0
  139. tests/redis_key_validation_demo.py +131 -0
  140. tests/response_improvements_example.py +145 -0
  141. tests/test_advanced_tools.py +149 -0
  142. tests/test_all_redis_key_configs.py +146 -0
  143. tests/test_authenticated_proxy.py +142 -0
  144. tests/test_cleaners.py +55 -0
  145. tests/test_comprehensive.py +147 -0
  146. tests/test_config_validator.py +194 -0
  147. tests/test_date_tools.py +124 -0
  148. tests/test_dynamic_downloaders_proxy.py +125 -0
  149. tests/test_dynamic_proxy.py +93 -0
  150. tests/test_dynamic_proxy_config.py +147 -0
  151. tests/test_dynamic_proxy_real.py +110 -0
  152. tests/test_edge_cases.py +304 -0
  153. tests/test_enhanced_error_handler.py +271 -0
  154. tests/test_env_config.py +122 -0
  155. tests/test_error_handler_compatibility.py +113 -0
  156. tests/test_final_validation.py +153 -153
  157. tests/test_framework_env_usage.py +104 -0
  158. tests/test_integration.py +357 -0
  159. tests/test_item_dedup_redis_key.py +123 -0
  160. tests/test_parsel.py +30 -0
  161. tests/test_performance.py +328 -0
  162. tests/test_proxy_health_check.py +32 -32
  163. tests/test_proxy_middleware_integration.py +136 -136
  164. tests/test_proxy_providers.py +56 -56
  165. tests/test_proxy_stats.py +19 -19
  166. tests/test_proxy_strategies.py +59 -59
  167. tests/test_queue_manager_redis_key.py +177 -0
  168. tests/test_redis_config.py +28 -28
  169. tests/test_redis_connection_pool.py +295 -0
  170. tests/test_redis_key_naming.py +182 -0
  171. tests/test_redis_key_validator.py +124 -0
  172. tests/test_redis_queue.py +224 -224
  173. tests/test_request_serialization.py +70 -70
  174. tests/test_response_improvements.py +153 -0
  175. tests/test_scheduler.py +241 -241
  176. tests/test_simple_response.py +62 -0
  177. tests/test_telecom_spider_redis_key.py +206 -0
  178. tests/test_template_content.py +88 -0
  179. tests/test_template_redis_key.py +135 -0
  180. tests/test_tools.py +154 -0
  181. tests/tools_example.py +258 -0
  182. crawlo/core/enhanced_engine.py +0 -190
  183. crawlo-1.1.4.dist-info/RECORD +0 -117
  184. {crawlo-1.1.4.dist-info → crawlo-1.1.5.dist-info}/WHEEL +0 -0
  185. {crawlo-1.1.4.dist-info → crawlo-1.1.5.dist-info}/entry_points.txt +0 -0
  186. {crawlo-1.1.4.dist-info → crawlo-1.1.5.dist-info}/top_level.txt +0 -0
crawlo/utils/url.py CHANGED
@@ -1,40 +1,40 @@
1
- from urllib.parse import urldefrag
2
- from w3lib.url import add_or_replace_parameter
3
-
4
-
5
- def escape_ajax(url: str) -> str:
6
- """
7
- 根据Google AJAX爬取规范转换URL(处理哈希片段#!):
8
- https://developers.google.com/webmasters/ajax-crawling/docs/getting-started
9
-
10
- 规则说明:
11
- 1. 仅当URL包含 `#!` 时才转换(表示这是AJAX可爬取页面)
12
- 2. 将 `#!key=value` 转换为 `?_escaped_fragment_=key%3Dvalue`
13
- 3. 保留原始查询参数(如果有)
14
-
15
- 示例:
16
- >>> escape_ajax("www.example.com/ajax.html#!key=value")
17
- 'www.example.com/ajax.html?_escaped_fragment_=key%3Dvalue'
18
- >>> escape_ajax("www.example.com/ajax.html?k1=v1#!key=value")
19
- 'www.example.com/ajax.html?k1=v1&_escaped_fragment_=key%3Dvalue'
20
- >>> escape_ajax("www.example.com/ajax.html#!")
21
- 'www.example.com/ajax.html?_escaped_fragment_='
22
-
23
- 非AJAX可爬取的URL(无#!)原样返回:
24
- >>> escape_ajax("www.example.com/ajax.html#normal")
25
- 'www.example.com/ajax.html#normal'
26
- """
27
- # 分离URL的基础部分和哈希片段
28
- de_frag, frag = urldefrag(url)
29
-
30
- # 仅处理以"!"开头的哈希片段(Google规范)
31
- if not frag.startswith("!"):
32
- return url # 不符合规则则原样返回
33
-
34
- # 调用辅助函数添加 `_escaped_fragment_` 参数
35
- return add_or_replace_parameter(de_frag, "_escaped_fragment_", frag[1:])
36
-
37
-
38
- if __name__ == '__main__':
39
- f = escape_ajax('http://example.com/page#!')
1
+ from urllib.parse import urldefrag
2
+ from w3lib.url import add_or_replace_parameter
3
+
4
+
5
+ def escape_ajax(url: str) -> str:
6
+ """
7
+ 根据Google AJAX爬取规范转换URL(处理哈希片段#!):
8
+ https://developers.google.com/webmasters/ajax-crawling/docs/getting-started
9
+
10
+ 规则说明:
11
+ 1. 仅当URL包含 `#!` 时才转换(表示这是AJAX可爬取页面)
12
+ 2. 将 `#!key=value` 转换为 `?_escaped_fragment_=key%3Dvalue`
13
+ 3. 保留原始查询参数(如果有)
14
+
15
+ 示例:
16
+ >>> escape_ajax("www.example.com/ajax.html#!key=value")
17
+ 'www.example.com/ajax.html?_escaped_fragment_=key%3Dvalue'
18
+ >>> escape_ajax("www.example.com/ajax.html?k1=v1#!key=value")
19
+ 'www.example.com/ajax.html?k1=v1&_escaped_fragment_=key%3Dvalue'
20
+ >>> escape_ajax("www.example.com/ajax.html#!")
21
+ 'www.example.com/ajax.html?_escaped_fragment_='
22
+
23
+ 非AJAX可爬取的URL(无#!)原样返回:
24
+ >>> escape_ajax("www.example.com/ajax.html#normal")
25
+ 'www.example.com/ajax.html#normal'
26
+ """
27
+ # 分离URL的基础部分和哈希片段
28
+ de_frag, frag = urldefrag(url)
29
+
30
+ # 仅处理以"!"开头的哈希片段(Google规范)
31
+ if not frag.startswith("!"):
32
+ return url # 不符合规则则原样返回
33
+
34
+ # 调用辅助函数添加 `_escaped_fragment_` 参数
35
+ return add_or_replace_parameter(de_frag, "_escaped_fragment_", frag[1:])
36
+
37
+
38
+ if __name__ == '__main__':
39
+ f = escape_ajax('http://example.com/page#!')
40
40
  print(f)