crawlo 1.3.2__py3-none-any.whl → 1.3.3__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of crawlo might be problematic. Click here for more details.

Files changed (219) hide show
  1. crawlo/__init__.py +63 -63
  2. crawlo/__version__.py +1 -1
  3. crawlo/cli.py +75 -75
  4. crawlo/commands/__init__.py +14 -14
  5. crawlo/commands/check.py +594 -594
  6. crawlo/commands/genspider.py +151 -151
  7. crawlo/commands/help.py +138 -138
  8. crawlo/commands/list.py +155 -155
  9. crawlo/commands/run.py +322 -314
  10. crawlo/commands/startproject.py +436 -436
  11. crawlo/commands/stats.py +187 -187
  12. crawlo/commands/utils.py +196 -196
  13. crawlo/config.py +312 -312
  14. crawlo/config_validator.py +277 -277
  15. crawlo/core/__init__.py +2 -2
  16. crawlo/core/engine.py +365 -365
  17. crawlo/core/processor.py +40 -40
  18. crawlo/core/scheduler.py +256 -256
  19. crawlo/crawler.py +1166 -1168
  20. crawlo/data/__init__.py +5 -5
  21. crawlo/data/user_agents.py +194 -194
  22. crawlo/downloader/__init__.py +273 -273
  23. crawlo/downloader/aiohttp_downloader.py +226 -226
  24. crawlo/downloader/cffi_downloader.py +245 -245
  25. crawlo/downloader/httpx_downloader.py +259 -259
  26. crawlo/downloader/hybrid_downloader.py +212 -212
  27. crawlo/downloader/playwright_downloader.py +402 -402
  28. crawlo/downloader/selenium_downloader.py +472 -472
  29. crawlo/event.py +11 -11
  30. crawlo/exceptions.py +81 -81
  31. crawlo/extension/__init__.py +39 -39
  32. crawlo/extension/health_check.py +141 -141
  33. crawlo/extension/log_interval.py +57 -57
  34. crawlo/extension/log_stats.py +81 -81
  35. crawlo/extension/logging_extension.py +52 -45
  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/filters/__init__.py +154 -154
  40. crawlo/filters/aioredis_filter.py +234 -234
  41. crawlo/filters/memory_filter.py +269 -269
  42. crawlo/items/__init__.py +23 -23
  43. crawlo/items/base.py +21 -21
  44. crawlo/items/fields.py +52 -52
  45. crawlo/items/items.py +104 -104
  46. crawlo/middleware/__init__.py +21 -21
  47. crawlo/middleware/default_header.py +132 -132
  48. crawlo/middleware/download_delay.py +104 -104
  49. crawlo/middleware/middleware_manager.py +135 -135
  50. crawlo/middleware/offsite.py +123 -123
  51. crawlo/middleware/proxy.py +386 -386
  52. crawlo/middleware/request_ignore.py +86 -86
  53. crawlo/middleware/response_code.py +163 -163
  54. crawlo/middleware/response_filter.py +136 -136
  55. crawlo/middleware/retry.py +124 -124
  56. crawlo/middleware/simple_proxy.py +65 -65
  57. crawlo/mode_manager.py +187 -187
  58. crawlo/network/__init__.py +21 -21
  59. crawlo/network/request.py +379 -379
  60. crawlo/network/response.py +359 -359
  61. crawlo/pipelines/__init__.py +21 -21
  62. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  63. crawlo/pipelines/console_pipeline.py +39 -39
  64. crawlo/pipelines/csv_pipeline.py +316 -316
  65. crawlo/pipelines/database_dedup_pipeline.py +222 -222
  66. crawlo/pipelines/json_pipeline.py +218 -218
  67. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  68. crawlo/pipelines/mongo_pipeline.py +131 -131
  69. crawlo/pipelines/mysql_pipeline.py +318 -318
  70. crawlo/pipelines/pipeline_manager.py +75 -75
  71. crawlo/pipelines/redis_dedup_pipeline.py +166 -166
  72. crawlo/project.py +325 -297
  73. crawlo/queue/pqueue.py +37 -37
  74. crawlo/queue/queue_manager.py +379 -379
  75. crawlo/queue/redis_priority_queue.py +306 -306
  76. crawlo/settings/__init__.py +7 -7
  77. crawlo/settings/default_settings.py +225 -225
  78. crawlo/settings/setting_manager.py +198 -198
  79. crawlo/spider/__init__.py +639 -639
  80. crawlo/stats_collector.py +59 -59
  81. crawlo/subscriber.py +129 -129
  82. crawlo/task_manager.py +30 -30
  83. crawlo/templates/crawlo.cfg.tmpl +10 -10
  84. crawlo/templates/project/__init__.py.tmpl +3 -3
  85. crawlo/templates/project/items.py.tmpl +17 -17
  86. crawlo/templates/project/middlewares.py.tmpl +118 -118
  87. crawlo/templates/project/pipelines.py.tmpl +96 -96
  88. crawlo/templates/project/settings.py.tmpl +266 -266
  89. crawlo/templates/project/settings_distributed.py.tmpl +179 -179
  90. crawlo/templates/project/settings_gentle.py.tmpl +60 -60
  91. crawlo/templates/project/settings_high_performance.py.tmpl +130 -130
  92. crawlo/templates/project/settings_minimal.py.tmpl +34 -34
  93. crawlo/templates/project/settings_simple.py.tmpl +101 -101
  94. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  95. crawlo/templates/run.py.tmpl +38 -38
  96. crawlo/templates/spider/spider.py.tmpl +143 -143
  97. crawlo/tools/__init__.py +200 -200
  98. crawlo/tools/anti_crawler.py +268 -268
  99. crawlo/tools/authenticated_proxy.py +240 -240
  100. crawlo/tools/data_formatter.py +225 -225
  101. crawlo/tools/data_validator.py +180 -180
  102. crawlo/tools/date_tools.py +289 -289
  103. crawlo/tools/distributed_coordinator.py +388 -388
  104. crawlo/tools/encoding_converter.py +127 -127
  105. crawlo/tools/request_tools.py +82 -82
  106. crawlo/tools/retry_mechanism.py +224 -224
  107. crawlo/tools/scenario_adapter.py +262 -262
  108. crawlo/tools/text_cleaner.py +232 -232
  109. crawlo/utils/__init__.py +34 -34
  110. crawlo/utils/batch_processor.py +259 -259
  111. crawlo/utils/controlled_spider_mixin.py +439 -439
  112. crawlo/utils/db_helper.py +343 -343
  113. crawlo/utils/enhanced_error_handler.py +356 -356
  114. crawlo/utils/env_config.py +142 -142
  115. crawlo/utils/error_handler.py +123 -123
  116. crawlo/utils/func_tools.py +82 -82
  117. crawlo/utils/large_scale_config.py +286 -286
  118. crawlo/utils/large_scale_helper.py +344 -344
  119. crawlo/utils/log.py +199 -146
  120. crawlo/utils/performance_monitor.py +285 -285
  121. crawlo/utils/queue_helper.py +175 -175
  122. crawlo/utils/redis_connection_pool.py +351 -351
  123. crawlo/utils/redis_key_validator.py +198 -198
  124. crawlo/utils/request.py +267 -267
  125. crawlo/utils/request_serializer.py +218 -218
  126. crawlo/utils/spider_loader.py +61 -61
  127. crawlo/utils/system.py +11 -11
  128. crawlo/utils/tools.py +4 -4
  129. crawlo/utils/url.py +39 -39
  130. {crawlo-1.3.2.dist-info → crawlo-1.3.3.dist-info}/METADATA +1020 -1020
  131. crawlo-1.3.3.dist-info/RECORD +219 -0
  132. examples/__init__.py +7 -7
  133. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  134. tests/__init__.py +7 -7
  135. tests/advanced_tools_example.py +275 -275
  136. tests/authenticated_proxy_example.py +107 -107
  137. tests/cleaners_example.py +160 -160
  138. tests/config_validation_demo.py +142 -142
  139. tests/controlled_spider_example.py +205 -205
  140. tests/date_tools_example.py +180 -180
  141. tests/debug_pipelines.py +66 -66
  142. tests/dynamic_loading_example.py +523 -523
  143. tests/dynamic_loading_test.py +104 -104
  144. tests/env_config_example.py +133 -133
  145. tests/error_handling_example.py +171 -171
  146. tests/redis_key_validation_demo.py +130 -130
  147. tests/request_params_example.py +150 -150
  148. tests/response_improvements_example.py +144 -144
  149. tests/test_advanced_tools.py +148 -148
  150. tests/test_all_redis_key_configs.py +145 -145
  151. tests/test_authenticated_proxy.py +141 -141
  152. tests/test_cleaners.py +54 -54
  153. tests/test_comprehensive.py +146 -146
  154. tests/test_config_consistency.py +80 -80
  155. tests/test_config_merge.py +152 -152
  156. tests/test_config_validator.py +182 -182
  157. tests/test_crawlo_proxy_integration.py +108 -108
  158. tests/test_date_tools.py +123 -123
  159. tests/test_default_header_middleware.py +158 -158
  160. tests/test_distributed.py +65 -65
  161. tests/test_double_crawlo_fix.py +207 -207
  162. tests/test_double_crawlo_fix_simple.py +124 -124
  163. tests/test_download_delay_middleware.py +221 -221
  164. tests/test_downloader_proxy_compatibility.py +268 -268
  165. tests/test_dynamic_downloaders_proxy.py +124 -124
  166. tests/test_dynamic_proxy.py +92 -92
  167. tests/test_dynamic_proxy_config.py +146 -146
  168. tests/test_dynamic_proxy_real.py +109 -109
  169. tests/test_edge_cases.py +303 -303
  170. tests/test_enhanced_error_handler.py +270 -270
  171. tests/test_env_config.py +121 -121
  172. tests/test_error_handler_compatibility.py +112 -112
  173. tests/test_final_validation.py +153 -153
  174. tests/test_framework_env_usage.py +103 -103
  175. tests/test_integration.py +169 -169
  176. tests/test_item_dedup_redis_key.py +122 -122
  177. tests/test_mode_consistency.py +51 -51
  178. tests/test_offsite_middleware.py +221 -221
  179. tests/test_parsel.py +29 -29
  180. tests/test_performance.py +327 -327
  181. tests/test_proxy_api.py +264 -264
  182. tests/test_proxy_health_check.py +32 -32
  183. tests/test_proxy_middleware.py +121 -121
  184. tests/test_proxy_middleware_enhanced.py +216 -216
  185. tests/test_proxy_middleware_integration.py +136 -136
  186. tests/test_proxy_middleware_refactored.py +184 -184
  187. tests/test_proxy_providers.py +56 -56
  188. tests/test_proxy_stats.py +19 -19
  189. tests/test_proxy_strategies.py +59 -59
  190. tests/test_queue_manager_double_crawlo.py +173 -173
  191. tests/test_queue_manager_redis_key.py +176 -176
  192. tests/test_random_user_agent.py +72 -72
  193. tests/test_real_scenario_proxy.py +195 -195
  194. tests/test_redis_config.py +28 -28
  195. tests/test_redis_connection_pool.py +294 -294
  196. tests/test_redis_key_naming.py +181 -181
  197. tests/test_redis_key_validator.py +123 -123
  198. tests/test_redis_queue.py +224 -224
  199. tests/test_request_ignore_middleware.py +182 -182
  200. tests/test_request_params.py +111 -111
  201. tests/test_request_serialization.py +70 -70
  202. tests/test_response_code_middleware.py +349 -349
  203. tests/test_response_filter_middleware.py +427 -427
  204. tests/test_response_improvements.py +152 -152
  205. tests/test_retry_middleware.py +241 -241
  206. tests/test_scheduler.py +252 -252
  207. tests/test_scheduler_config_update.py +133 -133
  208. tests/test_simple_response.py +61 -61
  209. tests/test_telecom_spider_redis_key.py +205 -205
  210. tests/test_template_content.py +87 -87
  211. tests/test_template_redis_key.py +134 -134
  212. tests/test_tools.py +159 -159
  213. tests/test_user_agents.py +96 -96
  214. tests/tools_example.py +260 -260
  215. tests/verify_distributed.py +117 -117
  216. crawlo-1.3.2.dist-info/RECORD +0 -219
  217. {crawlo-1.3.2.dist-info → crawlo-1.3.3.dist-info}/WHEEL +0 -0
  218. {crawlo-1.3.2.dist-info → crawlo-1.3.3.dist-info}/entry_points.txt +0 -0
  219. {crawlo-1.3.2.dist-info → crawlo-1.3.3.dist-info}/top_level.txt +0 -0
@@ -1,124 +1,124 @@
1
- #!/usr/bin/python
2
- # -*- coding:UTF-8 -*-
3
- """
4
- OffsiteMiddleware 中间件
5
- 用于过滤掉不在指定域名范围内的请求
6
- """
7
- import re
8
- from urllib.parse import urlparse
9
-
10
- from crawlo.utils.log import get_logger
11
- from crawlo.exceptions import IgnoreRequestError
12
-
13
-
14
- class OffsiteMiddleware:
15
- """
16
- OffsiteMiddleware 中间件
17
- 用于过滤掉不在指定域名范围内的请求,防止爬虫爬取到不相关的网站
18
- """
19
-
20
- def __init__(self, stats, log_level, allowed_domains=None):
21
- self.logger = get_logger(self.__class__.__name__, log_level)
22
- self.stats = stats
23
- self.allowed_domains = allowed_domains or []
24
-
25
- @classmethod
26
- def create_instance(cls, crawler):
27
- """
28
- 创建中间件实例
29
- 从爬虫设置中获取允许的域名列表
30
- """
31
- # 优先使用 Spider 实例的 allowed_domains,回退到全局设置中的 ALLOWED_DOMAINS
32
- allowed_domains = []
33
-
34
- # 检查当前爬虫实例是否有 allowed_domains 属性
35
- if hasattr(crawler, 'spider') and crawler.spider and hasattr(crawler.spider, 'allowed_domains'):
36
- allowed_domains = getattr(crawler.spider, 'allowed_domains', [])
37
-
38
- # 如果 Spider 实例没有设置 allowed_domains,则从全局设置中获取
39
- if not allowed_domains:
40
- allowed_domains = crawler.settings.get_list('ALLOWED_DOMAINS')
41
-
42
- # 如果没有配置允许的域名,则禁用此中间件
43
- if not allowed_domains:
44
- from crawlo.exceptions import NotConfiguredError
45
- raise NotConfiguredError("未配置ALLOWED_DOMAINS,OffsiteMiddleware已禁用")
46
-
47
- o = cls(
48
- stats=crawler.stats,
49
- log_level=crawler.settings.get('LOG_LEVEL'),
50
- allowed_domains=allowed_domains
51
- )
52
-
53
- # 编译域名正则表达式以提高性能
54
- o._compile_domains()
55
-
56
- # 使用中间件自己的logger而不是crawler.logger
57
- o.logger.info(f"OffsiteMiddleware已启用,允许的域名: {allowed_domains}")
58
- return o
59
-
60
- def _compile_domains(self):
61
- """
62
- 编译域名正则表达式
63
- """
64
- self._domain_regexes = []
65
- for domain in self.allowed_domains:
66
- # 转义域名中的特殊字符
67
- escaped_domain = re.escape(domain)
68
- # 创建匹配域名的正则表达式(支持子域名)
69
- regex = re.compile(r'(^|.*\.)' + escaped_domain + '$', re.IGNORECASE)
70
- self._domain_regexes.append(regex)
71
-
72
- def _is_offsite_request(self, request):
73
- """
74
- 判断请求是否为站外请求
75
- """
76
- try:
77
- parsed_url = urlparse(request.url)
78
- hostname = parsed_url.hostname
79
-
80
- if not hostname:
81
- return True # 无效URL
82
-
83
- # 检查是否匹配允许的域名
84
- for regex in self._domain_regexes:
85
- if regex.match(hostname):
86
- return False # 匹配允许的域名
87
-
88
- return True # 不匹配任何允许的域名
89
- except Exception:
90
- # URL解析失败,视为站外请求
91
- return True
92
-
93
- async def process_request(self, request, spider):
94
- """
95
- 处理请求,过滤站外请求
96
- """
97
- if self._is_offsite_request(request):
98
- # 记录被过滤的请求
99
- self.stats.inc_value('offsite_request_count')
100
-
101
- # 记录被过滤的域名
102
- try:
103
- parsed_url = urlparse(request.url)
104
- hostname = parsed_url.hostname or "unknown"
105
- self.stats.inc_value(f'offsite_request_count/{hostname}')
106
- except:
107
- self.stats.inc_value('offsite_request_count/invalid_url')
108
-
109
- self.logger.debug(f"过滤站外请求: {request.url}")
110
-
111
- # 抛出异常以忽略该请求
112
- raise IgnoreRequestError(f"站外请求被过滤: {request.url}")
113
-
114
- return None
115
-
116
- def process_exception(self, request, exception, spider):
117
- """
118
- 处理异常
119
- """
120
- # 如果是IgnoreRequestError且是我们产生的,则处理它
121
- if isinstance(exception, IgnoreRequestError) and "站外请求被过滤" in str(exception):
122
- self.logger.debug(f"已过滤站外请求: {request.url}")
123
- return True # 表示异常已被处理
1
+ #!/usr/bin/python
2
+ # -*- coding:UTF-8 -*-
3
+ """
4
+ OffsiteMiddleware 中间件
5
+ 用于过滤掉不在指定域名范围内的请求
6
+ """
7
+ import re
8
+ from urllib.parse import urlparse
9
+
10
+ from crawlo.utils.log import get_logger
11
+ from crawlo.exceptions import IgnoreRequestError
12
+
13
+
14
+ class OffsiteMiddleware:
15
+ """
16
+ OffsiteMiddleware 中间件
17
+ 用于过滤掉不在指定域名范围内的请求,防止爬虫爬取到不相关的网站
18
+ """
19
+
20
+ def __init__(self, stats, log_level, allowed_domains=None):
21
+ self.logger = get_logger(self.__class__.__name__, log_level)
22
+ self.stats = stats
23
+ self.allowed_domains = allowed_domains or []
24
+
25
+ @classmethod
26
+ def create_instance(cls, crawler):
27
+ """
28
+ 创建中间件实例
29
+ 从爬虫设置中获取允许的域名列表
30
+ """
31
+ # 优先使用 Spider 实例的 allowed_domains,回退到全局设置中的 ALLOWED_DOMAINS
32
+ allowed_domains = []
33
+
34
+ # 检查当前爬虫实例是否有 allowed_domains 属性
35
+ if hasattr(crawler, 'spider') and crawler.spider and hasattr(crawler.spider, 'allowed_domains'):
36
+ allowed_domains = getattr(crawler.spider, 'allowed_domains', [])
37
+
38
+ # 如果 Spider 实例没有设置 allowed_domains,则从全局设置中获取
39
+ if not allowed_domains:
40
+ allowed_domains = crawler.settings.get_list('ALLOWED_DOMAINS')
41
+
42
+ # 如果没有配置允许的域名,则禁用此中间件
43
+ if not allowed_domains:
44
+ from crawlo.exceptions import NotConfiguredError
45
+ raise NotConfiguredError("未配置ALLOWED_DOMAINS,OffsiteMiddleware已禁用")
46
+
47
+ o = cls(
48
+ stats=crawler.stats,
49
+ log_level=crawler.settings.get('LOG_LEVEL'),
50
+ allowed_domains=allowed_domains
51
+ )
52
+
53
+ # 编译域名正则表达式以提高性能
54
+ o._compile_domains()
55
+
56
+ # 使用中间件自己的logger而不是crawler.logger
57
+ o.logger.debug(f"OffsiteMiddleware 已启用,允许的域名: {allowed_domains}")
58
+ return o
59
+
60
+ def _compile_domains(self):
61
+ """
62
+ 编译域名正则表达式
63
+ """
64
+ self._domain_regexes = []
65
+ for domain in self.allowed_domains:
66
+ # 转义域名中的特殊字符
67
+ escaped_domain = re.escape(domain)
68
+ # 创建匹配域名的正则表达式(支持子域名)
69
+ regex = re.compile(r'(^|.*\.)' + escaped_domain + '$', re.IGNORECASE)
70
+ self._domain_regexes.append(regex)
71
+
72
+ def _is_offsite_request(self, request):
73
+ """
74
+ 判断请求是否为站外请求
75
+ """
76
+ try:
77
+ parsed_url = urlparse(request.url)
78
+ hostname = parsed_url.hostname
79
+
80
+ if not hostname:
81
+ return True # 无效URL
82
+
83
+ # 检查是否匹配允许的域名
84
+ for regex in self._domain_regexes:
85
+ if regex.match(hostname):
86
+ return False # 匹配允许的域名
87
+
88
+ return True # 不匹配任何允许的域名
89
+ except Exception:
90
+ # URL解析失败,视为站外请求
91
+ return True
92
+
93
+ async def process_request(self, request, spider):
94
+ """
95
+ 处理请求,过滤站外请求
96
+ """
97
+ if self._is_offsite_request(request):
98
+ # 记录被过滤的请求
99
+ self.stats.inc_value('offsite_request_count')
100
+
101
+ # 记录被过滤的域名
102
+ try:
103
+ parsed_url = urlparse(request.url)
104
+ hostname = parsed_url.hostname or "unknown"
105
+ self.stats.inc_value(f'offsite_request_count/{hostname}')
106
+ except:
107
+ self.stats.inc_value('offsite_request_count/invalid_url')
108
+
109
+ self.logger.debug(f"过滤站外请求: {request.url}")
110
+
111
+ # 抛出异常以忽略该请求
112
+ raise IgnoreRequestError(f"站外请求被过滤: {request.url}")
113
+
114
+ return None
115
+
116
+ def process_exception(self, request, exception, spider):
117
+ """
118
+ 处理异常
119
+ """
120
+ # 如果是IgnoreRequestError且是我们产生的,则处理它
121
+ if isinstance(exception, IgnoreRequestError) and "站外请求被过滤" in str(exception):
122
+ self.logger.debug(f"已过滤站外请求: {request.url}")
123
+ return True # 表示异常已被处理
124
124
  return None