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
@@ -1,116 +1,115 @@
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
-
8
- import re
9
- from urllib.parse import urlparse
10
-
11
- from crawlo.utils.log import get_logger
12
- from crawlo.exceptions import IgnoreRequestError
13
-
14
-
15
- class OffsiteMiddleware:
16
- """
17
- OffsiteMiddleware 中间件
18
- 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
19
- """
20
-
21
- def __init__(self, stats, log_level, allowed_domains=None):
22
- self.logger = get_logger(self.__class__.__name__, log_level)
23
- self.stats = stats
24
- self.allowed_domains = allowed_domains or []
25
-
26
- @classmethod
27
- def create_instance(cls, crawler):
28
- """
29
- 创建中间件实例
30
- 从爬虫设置中获取允许的域名列表
31
- """
32
- # 从爬虫设置中获取允许的域名
33
- allowed_domains = crawler.settings.get_list('ALLOWED_DOMAINS')
34
-
35
- # 如果没有配置允许的域名,则禁用此中间件
36
- if not allowed_domains:
37
- from crawlo.exceptions import NotConfiguredError
38
- raise NotConfiguredError("未配置ALLOWED_DOMAINS,OffsiteMiddleware已禁用")
39
-
40
- o = cls(
41
- stats=crawler.stats,
42
- log_level=crawler.settings.get('LOG_LEVEL'),
43
- allowed_domains=allowed_domains
44
- )
45
-
46
- # 编译域名正则表达式以提高性能
47
- o._compile_domains()
48
-
49
- crawler.logger.info(f"OffsiteMiddleware已启用,允许的域名: {allowed_domains}")
50
- return o
51
-
52
- def _compile_domains(self):
53
- """
54
- 编译域名正则表达式
55
- """
56
- self._domain_regexes = []
57
- for domain in self.allowed_domains:
58
- # 转义域名中的特殊字符
59
- escaped_domain = re.escape(domain)
60
- # 创建匹配域名的正则表达式(支持子域名)
61
- regex = re.compile(r'(^|.*\.)' + escaped_domain + '$', re.IGNORECASE)
62
- self._domain_regexes.append(regex)
63
-
64
- def _is_offsite_request(self, request):
65
- """
66
- 判断请求是否为站外请求
67
- """
68
- try:
69
- parsed_url = urlparse(request.url)
70
- hostname = parsed_url.hostname
71
-
72
- if not hostname:
73
- return True # 无效URL
74
-
75
- # 检查是否匹配允许的域名
76
- for regex in self._domain_regexes:
77
- if regex.match(hostname):
78
- return False # 匹配允许的域名
79
-
80
- return True # 不匹配任何允许的域名
81
- except Exception:
82
- # URL解析失败,视为站外请求
83
- return True
84
-
85
- async def process_request(self, request, spider):
86
- """
87
- 处理请求,过滤站外请求
88
- """
89
- if self._is_offsite_request(request):
90
- # 记录被过滤的请求
91
- self.stats.inc_value('offsite_request_count')
92
-
93
- # 记录被过滤的域名
94
- try:
95
- parsed_url = urlparse(request.url)
96
- hostname = parsed_url.hostname or "unknown"
97
- self.stats.inc_value(f'offsite_request_count/{hostname}')
98
- except:
99
- self.stats.inc_value('offsite_request_count/invalid_url')
100
-
101
- self.logger.debug(f"过滤站外请求: {request.url}")
102
-
103
- # 抛出异常以忽略该请求
104
- raise IgnoreRequestError(f"站外请求被过滤: {request.url}")
105
-
106
- return None
107
-
108
- def process_exception(self, request, exception, spider):
109
- """
110
- 处理异常
111
- """
112
- # 如果是IgnoreRequestError且是我们产生的,则处理它
113
- if isinstance(exception, IgnoreRequestError) and "站外请求被过滤" in str(exception):
114
- self.logger.debug(f"已过滤站外请求: {request.url}")
115
- 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
+ # 从爬虫设置中获取允许的域名
32
+ allowed_domains = crawler.settings.get_list('ALLOWED_DOMAINS')
33
+
34
+ # 如果没有配置允许的域名,则禁用此中间件
35
+ if not allowed_domains:
36
+ from crawlo.exceptions import NotConfiguredError
37
+ raise NotConfiguredError("未配置ALLOWED_DOMAINS,OffsiteMiddleware已禁用")
38
+
39
+ o = cls(
40
+ stats=crawler.stats,
41
+ log_level=crawler.settings.get('LOG_LEVEL'),
42
+ allowed_domains=allowed_domains
43
+ )
44
+
45
+ # 编译域名正则表达式以提高性能
46
+ o._compile_domains()
47
+
48
+ crawler.logger.info(f"OffsiteMiddleware已启用,允许的域名: {allowed_domains}")
49
+ return o
50
+
51
+ def _compile_domains(self):
52
+ """
53
+ 编译域名正则表达式
54
+ """
55
+ self._domain_regexes = []
56
+ for domain in self.allowed_domains:
57
+ # 转义域名中的特殊字符
58
+ escaped_domain = re.escape(domain)
59
+ # 创建匹配域名的正则表达式(支持子域名)
60
+ regex = re.compile(r'(^|.*\.)' + escaped_domain + '$', re.IGNORECASE)
61
+ self._domain_regexes.append(regex)
62
+
63
+ def _is_offsite_request(self, request):
64
+ """
65
+ 判断请求是否为站外请求
66
+ """
67
+ try:
68
+ parsed_url = urlparse(request.url)
69
+ hostname = parsed_url.hostname
70
+
71
+ if not hostname:
72
+ return True # 无效URL
73
+
74
+ # 检查是否匹配允许的域名
75
+ for regex in self._domain_regexes:
76
+ if regex.match(hostname):
77
+ return False # 匹配允许的域名
78
+
79
+ return True # 不匹配任何允许的域名
80
+ except Exception:
81
+ # URL解析失败,视为站外请求
82
+ return True
83
+
84
+ async def process_request(self, request, spider):
85
+ """
86
+ 处理请求,过滤站外请求
87
+ """
88
+ if self._is_offsite_request(request):
89
+ # 记录被过滤的请求
90
+ self.stats.inc_value('offsite_request_count')
91
+
92
+ # 记录被过滤的域名
93
+ try:
94
+ parsed_url = urlparse(request.url)
95
+ hostname = parsed_url.hostname or "unknown"
96
+ self.stats.inc_value(f'offsite_request_count/{hostname}')
97
+ except:
98
+ self.stats.inc_value('offsite_request_count/invalid_url')
99
+
100
+ self.logger.debug(f"过滤站外请求: {request.url}")
101
+
102
+ # 抛出异常以忽略该请求
103
+ raise IgnoreRequestError(f"站外请求被过滤: {request.url}")
104
+
105
+ return None
106
+
107
+ def process_exception(self, request, exception, spider):
108
+ """
109
+ 处理异常
110
+ """
111
+ # 如果是IgnoreRequestError且是我们产生的,则处理它
112
+ if isinstance(exception, IgnoreRequestError) and "站外请求被过滤" in str(exception):
113
+ self.logger.debug(f"已过滤站外请求: {request.url}")
114
+ return True # 表示异常已被处理
116
115
  return None