crawlo 1.1.8__py3-none-any.whl → 1.1.9__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 (190) 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 +65 -65
  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 +132 -132
  12. crawlo/commands/list.py +155 -155
  13. crawlo/commands/run.py +292 -292
  14. crawlo/commands/startproject.py +418 -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 +252 -252
  19. crawlo/core/__init__.py +2 -2
  20. crawlo/core/engine.py +345 -345
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +136 -136
  23. crawlo/crawler.py +1027 -1027
  24. crawlo/downloader/__init__.py +266 -266
  25. crawlo/downloader/aiohttp_downloader.py +220 -220
  26. crawlo/downloader/cffi_downloader.py +256 -256
  27. crawlo/downloader/httpx_downloader.py +259 -259
  28. crawlo/downloader/hybrid_downloader.py +213 -213
  29. crawlo/downloader/playwright_downloader.py +402 -402
  30. crawlo/downloader/selenium_downloader.py +472 -472
  31. crawlo/event.py +11 -11
  32. crawlo/exceptions.py +81 -81
  33. crawlo/extension/__init__.py +37 -37
  34. crawlo/extension/health_check.py +141 -141
  35. crawlo/extension/log_interval.py +57 -57
  36. crawlo/extension/log_stats.py +81 -81
  37. crawlo/extension/logging_extension.py +43 -43
  38. crawlo/extension/memory_monitor.py +104 -104
  39. crawlo/extension/performance_profiler.py +133 -133
  40. crawlo/extension/request_recorder.py +107 -107
  41. crawlo/filters/__init__.py +154 -154
  42. crawlo/filters/aioredis_filter.py +280 -280
  43. crawlo/filters/memory_filter.py +269 -269
  44. crawlo/items/__init__.py +23 -23
  45. crawlo/items/base.py +21 -21
  46. crawlo/items/fields.py +53 -53
  47. crawlo/items/items.py +104 -104
  48. crawlo/middleware/__init__.py +21 -21
  49. crawlo/middleware/default_header.py +32 -32
  50. crawlo/middleware/download_delay.py +28 -28
  51. crawlo/middleware/middleware_manager.py +135 -135
  52. crawlo/middleware/proxy.py +272 -272
  53. crawlo/middleware/request_ignore.py +30 -30
  54. crawlo/middleware/response_code.py +18 -18
  55. crawlo/middleware/response_filter.py +26 -26
  56. crawlo/middleware/retry.py +124 -124
  57. crawlo/mode_manager.py +211 -211
  58. crawlo/network/__init__.py +21 -21
  59. crawlo/network/request.py +338 -338
  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 +224 -224
  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 +316 -316
  70. crawlo/pipelines/pipeline_manager.py +61 -61
  71. crawlo/pipelines/redis_dedup_pipeline.py +167 -167
  72. crawlo/project.py +187 -187
  73. crawlo/queue/pqueue.py +37 -37
  74. crawlo/queue/queue_manager.py +334 -334
  75. crawlo/queue/redis_priority_queue.py +298 -298
  76. crawlo/settings/__init__.py +7 -7
  77. crawlo/settings/default_settings.py +219 -219
  78. crawlo/settings/setting_manager.py +122 -122
  79. crawlo/spider/__init__.py +639 -639
  80. crawlo/stats_collector.py +59 -59
  81. crawlo/subscriber.py +130 -130
  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 +109 -109
  87. crawlo/templates/project/pipelines.py.tmpl +96 -96
  88. crawlo/templates/project/run.py.tmpl +45 -45
  89. crawlo/templates/project/settings.py.tmpl +326 -326
  90. crawlo/templates/project/settings_distributed.py.tmpl +119 -119
  91. crawlo/templates/project/settings_gentle.py.tmpl +94 -94
  92. crawlo/templates/project/settings_high_performance.py.tmpl +151 -151
  93. crawlo/templates/project/settings_simple.py.tmpl +68 -68
  94. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  95. crawlo/templates/spider/spider.py.tmpl +141 -141
  96. crawlo/tools/__init__.py +182 -182
  97. crawlo/tools/anti_crawler.py +268 -268
  98. crawlo/tools/authenticated_proxy.py +240 -240
  99. crawlo/tools/data_validator.py +180 -180
  100. crawlo/tools/date_tools.py +35 -35
  101. crawlo/tools/distributed_coordinator.py +386 -386
  102. crawlo/tools/retry_mechanism.py +220 -220
  103. crawlo/tools/scenario_adapter.py +262 -262
  104. crawlo/utils/__init__.py +35 -35
  105. crawlo/utils/batch_processor.py +260 -260
  106. crawlo/utils/controlled_spider_mixin.py +439 -439
  107. crawlo/utils/date_tools.py +290 -290
  108. crawlo/utils/db_helper.py +343 -343
  109. crawlo/utils/enhanced_error_handler.py +359 -359
  110. crawlo/utils/env_config.py +105 -105
  111. crawlo/utils/error_handler.py +125 -125
  112. crawlo/utils/func_tools.py +82 -82
  113. crawlo/utils/large_scale_config.py +286 -286
  114. crawlo/utils/large_scale_helper.py +343 -343
  115. crawlo/utils/log.py +128 -128
  116. crawlo/utils/performance_monitor.py +284 -284
  117. crawlo/utils/queue_helper.py +175 -175
  118. crawlo/utils/redis_connection_pool.py +334 -334
  119. crawlo/utils/redis_key_validator.py +199 -199
  120. crawlo/utils/request.py +267 -267
  121. crawlo/utils/request_serializer.py +219 -219
  122. crawlo/utils/spider_loader.py +62 -62
  123. crawlo/utils/system.py +11 -11
  124. crawlo/utils/tools.py +4 -4
  125. crawlo/utils/url.py +39 -39
  126. {crawlo-1.1.8.dist-info → crawlo-1.1.9.dist-info}/METADATA +626 -626
  127. crawlo-1.1.9.dist-info/RECORD +190 -0
  128. examples/__init__.py +7 -7
  129. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  130. tests/__init__.py +7 -7
  131. tests/advanced_tools_example.py +275 -275
  132. tests/authenticated_proxy_example.py +236 -236
  133. tests/cleaners_example.py +160 -160
  134. tests/config_validation_demo.py +102 -102
  135. tests/controlled_spider_example.py +205 -205
  136. tests/date_tools_example.py +180 -180
  137. tests/dynamic_loading_example.py +523 -523
  138. tests/dynamic_loading_test.py +104 -104
  139. tests/env_config_example.py +133 -133
  140. tests/error_handling_example.py +171 -171
  141. tests/redis_key_validation_demo.py +130 -130
  142. tests/response_improvements_example.py +144 -144
  143. tests/test_advanced_tools.py +148 -148
  144. tests/test_all_redis_key_configs.py +145 -145
  145. tests/test_authenticated_proxy.py +141 -141
  146. tests/test_cleaners.py +54 -54
  147. tests/test_comprehensive.py +146 -146
  148. tests/test_config_validator.py +193 -193
  149. tests/test_date_tools.py +123 -123
  150. tests/test_double_crawlo_fix.py +207 -207
  151. tests/test_double_crawlo_fix_simple.py +124 -124
  152. tests/test_dynamic_downloaders_proxy.py +124 -124
  153. tests/test_dynamic_proxy.py +92 -92
  154. tests/test_dynamic_proxy_config.py +146 -146
  155. tests/test_dynamic_proxy_real.py +109 -109
  156. tests/test_edge_cases.py +303 -303
  157. tests/test_enhanced_error_handler.py +270 -270
  158. tests/test_env_config.py +121 -121
  159. tests/test_error_handler_compatibility.py +112 -112
  160. tests/test_final_validation.py +153 -153
  161. tests/test_framework_env_usage.py +103 -103
  162. tests/test_integration.py +356 -356
  163. tests/test_item_dedup_redis_key.py +122 -122
  164. tests/test_parsel.py +29 -29
  165. tests/test_performance.py +327 -327
  166. tests/test_proxy_health_check.py +32 -32
  167. tests/test_proxy_middleware_integration.py +136 -136
  168. tests/test_proxy_providers.py +56 -56
  169. tests/test_proxy_stats.py +19 -19
  170. tests/test_proxy_strategies.py +59 -59
  171. tests/test_queue_manager_double_crawlo.py +230 -230
  172. tests/test_queue_manager_redis_key.py +176 -176
  173. tests/test_redis_config.py +28 -28
  174. tests/test_redis_connection_pool.py +294 -294
  175. tests/test_redis_key_naming.py +181 -181
  176. tests/test_redis_key_validator.py +123 -123
  177. tests/test_redis_queue.py +224 -224
  178. tests/test_request_serialization.py +70 -70
  179. tests/test_response_improvements.py +152 -152
  180. tests/test_scheduler.py +241 -241
  181. tests/test_simple_response.py +61 -61
  182. tests/test_telecom_spider_redis_key.py +205 -205
  183. tests/test_template_content.py +87 -87
  184. tests/test_template_redis_key.py +134 -134
  185. tests/test_tools.py +153 -153
  186. tests/tools_example.py +257 -257
  187. crawlo-1.1.8.dist-info/RECORD +0 -190
  188. {crawlo-1.1.8.dist-info → crawlo-1.1.9.dist-info}/WHEEL +0 -0
  189. {crawlo-1.1.8.dist-info → crawlo-1.1.9.dist-info}/entry_points.txt +0 -0
  190. {crawlo-1.1.8.dist-info → crawlo-1.1.9.dist-info}/top_level.txt +0 -0
@@ -1,135 +1,135 @@
1
- #!/usr/bin/python
2
- # -*- coding:UTF-8 -*-
3
- from pprint import pformat
4
- from types import MethodType
5
- from asyncio import create_task
6
- from collections import defaultdict
7
- from typing import List, Dict, Callable, Optional
8
-
9
- from crawlo import Request, Response
10
- from crawlo.utils.log import get_logger
11
- from crawlo.project import load_class
12
- from crawlo.middleware import BaseMiddleware
13
- from crawlo.project import common_call
14
- from crawlo.event import ignore_request, response_received
15
- from crawlo.exceptions import MiddlewareInitError, InvalidOutputError, RequestMethodError, IgnoreRequestError, \
16
- NotConfiguredError
17
-
18
-
19
- class MiddlewareManager:
20
-
21
- def __init__(self, crawler):
22
- self.crawler = crawler
23
- self.logger = get_logger(self.__class__.__name__, crawler.settings.get('LOG_LEVEL'))
24
- self.middlewares: List = []
25
- self.methods: Dict[str, List[MethodType]] = defaultdict(list)
26
- middlewares = self.crawler.settings.get_list('MIDDLEWARES')
27
- self._add_middleware(middlewares)
28
- self._add_method()
29
-
30
- self.download_method: Callable = crawler.engine.downloader.download
31
- self._stats = crawler.stats
32
-
33
- async def _process_request(self, request: Request):
34
- for method in self.methods['process_request']:
35
- result = await common_call(method, request, self.crawler.spider)
36
- if result is None:
37
- continue
38
- if isinstance(result, (Request, Response)):
39
- return result
40
- raise InvalidOutputError(
41
- f"{method.__self__.__class__.__name__}. must return None or Request or Response, got {type(result).__name__}"
42
- )
43
- return await self.download_method(request)
44
-
45
- async def _process_response(self, request: Request, response: Response):
46
- for method in reversed(self.methods['process_response']):
47
- try:
48
- response = await common_call(method, request, response, self.crawler.spider)
49
- except IgnoreRequestError as exp:
50
- create_task(self.crawler.subscriber.notify(ignore_request, exp, request, self.crawler.spider))
51
- if isinstance(response, Request):
52
- return response
53
- if isinstance(response, Response):
54
- continue
55
- raise InvalidOutputError(
56
- f"{method.__self__.__class__.__name__}. must return Request or Response, got {type(response).__name__}"
57
- )
58
- return response
59
-
60
- async def _process_exception(self, request: Request, exp: Exception):
61
- for method in self.methods['process_exception']:
62
- response = await common_call(method, request, exp, self.crawler.spider)
63
- if response is None:
64
- continue
65
- if isinstance(response, (Request, Response)):
66
- return response
67
- if response:
68
- break
69
- raise InvalidOutputError(
70
- f"{method.__self__.__class__.__name__}. must return None or Request or Response, got {type(response).__name__}"
71
- )
72
- else:
73
- raise exp
74
-
75
- async def download(self, request) -> Optional[Response]:
76
- """ called in the download method. """
77
- try:
78
- response = await self._process_request(request)
79
- except KeyError:
80
- raise RequestMethodError(f"{request.method.lower()} is not supported")
81
- except IgnoreRequestError as exp:
82
- create_task(self.crawler.subscriber.notify(ignore_request, exp, request, self.crawler.spider))
83
- response = await self._process_exception(request, exp)
84
- except Exception as exp:
85
- self._stats.inc_value(f'download_error/{exp.__class__.__name__}')
86
- response = await self._process_exception(request, exp)
87
- else:
88
- create_task(self.crawler.subscriber.notify(response_received, response, self.crawler.spider))
89
- # self.crawler.stats.inc_value('response_received_count')
90
- if isinstance(response, Response):
91
- response = await self._process_response(request, response)
92
- if isinstance(response, Request):
93
- await self.crawler.engine.enqueue_request(request)
94
- return None
95
- return response
96
-
97
- @classmethod
98
- def create_instance(cls, *args, **kwargs):
99
- return cls(*args, **kwargs)
100
-
101
- def _add_middleware(self, middlewares):
102
- enabled_middlewares = [m for m in middlewares if self._validate_middleware(m)]
103
- if enabled_middlewares:
104
- self.logger.info(f'enabled middleware:\n {pformat(enabled_middlewares)}')
105
-
106
- def _validate_middleware(self, middleware):
107
- middleware_cls = load_class(middleware)
108
- if not hasattr(middleware_cls, 'create_instance'):
109
- raise MiddlewareInitError(
110
- f"Middleware init failed, must inherit from `BaseMiddleware` or have a `create_instance` method"
111
- )
112
- try:
113
- instance = middleware_cls.create_instance(self.crawler)
114
- self.middlewares.append(instance)
115
- return True
116
- except NotConfiguredError:
117
- return False
118
-
119
- def _add_method(self):
120
- for middleware in self.middlewares:
121
- if hasattr(middleware, 'process_request'):
122
- if self._validate_middleware_method(method_name='process_request', middleware=middleware):
123
- self.methods['process_request'].append(middleware.process_request)
124
- if hasattr(middleware, 'process_response'):
125
- if self._validate_middleware_method(method_name='process_response', middleware=middleware):
126
- self.methods['process_response'].append(middleware.process_response)
127
- if hasattr(middleware, 'process_exception'):
128
- if self._validate_middleware_method(method_name='process_exception', middleware=middleware):
129
- self.methods['process_exception'].append(middleware.process_exception)
130
-
131
- @staticmethod
132
- def _validate_middleware_method(method_name, middleware) -> bool:
133
- method = getattr(type(middleware), method_name)
134
- base_method = getattr(BaseMiddleware, method_name)
135
- return False if method == base_method else True
1
+ #!/usr/bin/python
2
+ # -*- coding:UTF-8 -*-
3
+ from pprint import pformat
4
+ from types import MethodType
5
+ from asyncio import create_task
6
+ from collections import defaultdict
7
+ from typing import List, Dict, Callable, Optional
8
+
9
+ from crawlo import Request, Response
10
+ from crawlo.utils.log import get_logger
11
+ from crawlo.project import load_class
12
+ from crawlo.middleware import BaseMiddleware
13
+ from crawlo.project import common_call
14
+ from crawlo.event import ignore_request, response_received
15
+ from crawlo.exceptions import MiddlewareInitError, InvalidOutputError, RequestMethodError, IgnoreRequestError, \
16
+ NotConfiguredError
17
+
18
+
19
+ class MiddlewareManager:
20
+
21
+ def __init__(self, crawler):
22
+ self.crawler = crawler
23
+ self.logger = get_logger(self.__class__.__name__, crawler.settings.get('LOG_LEVEL'))
24
+ self.middlewares: List = []
25
+ self.methods: Dict[str, List[MethodType]] = defaultdict(list)
26
+ middlewares = self.crawler.settings.get_list('MIDDLEWARES')
27
+ self._add_middleware(middlewares)
28
+ self._add_method()
29
+
30
+ self.download_method: Callable = crawler.engine.downloader.download
31
+ self._stats = crawler.stats
32
+
33
+ async def _process_request(self, request: Request):
34
+ for method in self.methods['process_request']:
35
+ result = await common_call(method, request, self.crawler.spider)
36
+ if result is None:
37
+ continue
38
+ if isinstance(result, (Request, Response)):
39
+ return result
40
+ raise InvalidOutputError(
41
+ f"{method.__self__.__class__.__name__}. must return None or Request or Response, got {type(result).__name__}"
42
+ )
43
+ return await self.download_method(request)
44
+
45
+ async def _process_response(self, request: Request, response: Response):
46
+ for method in reversed(self.methods['process_response']):
47
+ try:
48
+ response = await common_call(method, request, response, self.crawler.spider)
49
+ except IgnoreRequestError as exp:
50
+ create_task(self.crawler.subscriber.notify(ignore_request, exp, request, self.crawler.spider))
51
+ if isinstance(response, Request):
52
+ return response
53
+ if isinstance(response, Response):
54
+ continue
55
+ raise InvalidOutputError(
56
+ f"{method.__self__.__class__.__name__}. must return Request or Response, got {type(response).__name__}"
57
+ )
58
+ return response
59
+
60
+ async def _process_exception(self, request: Request, exp: Exception):
61
+ for method in self.methods['process_exception']:
62
+ response = await common_call(method, request, exp, self.crawler.spider)
63
+ if response is None:
64
+ continue
65
+ if isinstance(response, (Request, Response)):
66
+ return response
67
+ if response:
68
+ break
69
+ raise InvalidOutputError(
70
+ f"{method.__self__.__class__.__name__}. must return None or Request or Response, got {type(response).__name__}"
71
+ )
72
+ else:
73
+ raise exp
74
+
75
+ async def download(self, request) -> Optional[Response]:
76
+ """ called in the download method. """
77
+ try:
78
+ response = await self._process_request(request)
79
+ except KeyError:
80
+ raise RequestMethodError(f"{request.method.lower()} is not supported")
81
+ except IgnoreRequestError as exp:
82
+ create_task(self.crawler.subscriber.notify(ignore_request, exp, request, self.crawler.spider))
83
+ response = await self._process_exception(request, exp)
84
+ except Exception as exp:
85
+ self._stats.inc_value(f'download_error/{exp.__class__.__name__}')
86
+ response = await self._process_exception(request, exp)
87
+ else:
88
+ create_task(self.crawler.subscriber.notify(response_received, response, self.crawler.spider))
89
+ # self.crawler.stats.inc_value('response_received_count')
90
+ if isinstance(response, Response):
91
+ response = await self._process_response(request, response)
92
+ if isinstance(response, Request):
93
+ await self.crawler.engine.enqueue_request(request)
94
+ return None
95
+ return response
96
+
97
+ @classmethod
98
+ def create_instance(cls, *args, **kwargs):
99
+ return cls(*args, **kwargs)
100
+
101
+ def _add_middleware(self, middlewares):
102
+ enabled_middlewares = [m for m in middlewares if self._validate_middleware(m)]
103
+ if enabled_middlewares:
104
+ self.logger.info(f'enabled middleware:\n {pformat(enabled_middlewares)}')
105
+
106
+ def _validate_middleware(self, middleware):
107
+ middleware_cls = load_class(middleware)
108
+ if not hasattr(middleware_cls, 'create_instance'):
109
+ raise MiddlewareInitError(
110
+ f"Middleware init failed, must inherit from `BaseMiddleware` or have a `create_instance` method"
111
+ )
112
+ try:
113
+ instance = middleware_cls.create_instance(self.crawler)
114
+ self.middlewares.append(instance)
115
+ return True
116
+ except NotConfiguredError:
117
+ return False
118
+
119
+ def _add_method(self):
120
+ for middleware in self.middlewares:
121
+ if hasattr(middleware, 'process_request'):
122
+ if self._validate_middleware_method(method_name='process_request', middleware=middleware):
123
+ self.methods['process_request'].append(middleware.process_request)
124
+ if hasattr(middleware, 'process_response'):
125
+ if self._validate_middleware_method(method_name='process_response', middleware=middleware):
126
+ self.methods['process_response'].append(middleware.process_response)
127
+ if hasattr(middleware, 'process_exception'):
128
+ if self._validate_middleware_method(method_name='process_exception', middleware=middleware):
129
+ self.methods['process_exception'].append(middleware.process_exception)
130
+
131
+ @staticmethod
132
+ def _validate_middleware_method(method_name, middleware) -> bool:
133
+ method = getattr(type(middleware), method_name)
134
+ base_method = getattr(BaseMiddleware, method_name)
135
+ return False if method == base_method else True