crawlo 1.1.2__py3-none-any.whl → 1.1.3__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 (113) hide show
  1. crawlo/__init__.py +34 -34
  2. crawlo/__version__.py +1 -1
  3. crawlo/cli.py +40 -40
  4. crawlo/commands/__init__.py +13 -13
  5. crawlo/commands/check.py +594 -594
  6. crawlo/commands/genspider.py +151 -151
  7. crawlo/commands/list.py +155 -155
  8. crawlo/commands/run.py +285 -285
  9. crawlo/commands/startproject.py +196 -196
  10. crawlo/commands/stats.py +188 -188
  11. crawlo/commands/utils.py +186 -186
  12. crawlo/config.py +279 -279
  13. crawlo/core/__init__.py +2 -2
  14. crawlo/core/engine.py +171 -171
  15. crawlo/core/enhanced_engine.py +189 -189
  16. crawlo/core/processor.py +40 -40
  17. crawlo/core/scheduler.py +166 -162
  18. crawlo/crawler.py +1027 -1027
  19. crawlo/downloader/__init__.py +242 -242
  20. crawlo/downloader/aiohttp_downloader.py +212 -212
  21. crawlo/downloader/cffi_downloader.py +251 -251
  22. crawlo/downloader/httpx_downloader.py +259 -257
  23. crawlo/event.py +11 -11
  24. crawlo/exceptions.py +82 -78
  25. crawlo/extension/__init__.py +31 -31
  26. crawlo/extension/log_interval.py +49 -49
  27. crawlo/extension/log_stats.py +44 -44
  28. crawlo/extension/logging_extension.py +34 -34
  29. crawlo/filters/__init__.py +154 -154
  30. crawlo/filters/aioredis_filter.py +242 -242
  31. crawlo/filters/memory_filter.py +269 -269
  32. crawlo/items/__init__.py +23 -23
  33. crawlo/items/base.py +21 -21
  34. crawlo/items/fields.py +53 -53
  35. crawlo/items/items.py +104 -104
  36. crawlo/middleware/__init__.py +21 -21
  37. crawlo/middleware/default_header.py +32 -32
  38. crawlo/middleware/download_delay.py +28 -28
  39. crawlo/middleware/middleware_manager.py +135 -135
  40. crawlo/middleware/proxy.py +248 -248
  41. crawlo/middleware/request_ignore.py +30 -30
  42. crawlo/middleware/response_code.py +18 -18
  43. crawlo/middleware/response_filter.py +26 -26
  44. crawlo/middleware/retry.py +125 -125
  45. crawlo/mode_manager.py +200 -200
  46. crawlo/network/__init__.py +21 -21
  47. crawlo/network/request.py +311 -311
  48. crawlo/network/response.py +271 -269
  49. crawlo/pipelines/__init__.py +22 -13
  50. crawlo/pipelines/bloom_dedup_pipeline.py +157 -0
  51. crawlo/pipelines/console_pipeline.py +39 -39
  52. crawlo/pipelines/csv_pipeline.py +316 -316
  53. crawlo/pipelines/database_dedup_pipeline.py +225 -0
  54. crawlo/pipelines/json_pipeline.py +218 -218
  55. crawlo/pipelines/memory_dedup_pipeline.py +116 -0
  56. crawlo/pipelines/mongo_pipeline.py +116 -116
  57. crawlo/pipelines/mysql_pipeline.py +195 -195
  58. crawlo/pipelines/pipeline_manager.py +56 -56
  59. crawlo/pipelines/redis_dedup_pipeline.py +163 -0
  60. crawlo/project.py +153 -153
  61. crawlo/queue/pqueue.py +37 -37
  62. crawlo/queue/queue_manager.py +307 -303
  63. crawlo/queue/redis_priority_queue.py +208 -191
  64. crawlo/settings/__init__.py +7 -7
  65. crawlo/settings/default_settings.py +245 -226
  66. crawlo/settings/setting_manager.py +99 -99
  67. crawlo/spider/__init__.py +639 -639
  68. crawlo/stats_collector.py +59 -59
  69. crawlo/subscriber.py +106 -106
  70. crawlo/task_manager.py +30 -30
  71. crawlo/templates/crawlo.cfg.tmpl +10 -10
  72. crawlo/templates/project/__init__.py.tmpl +3 -3
  73. crawlo/templates/project/items.py.tmpl +17 -17
  74. crawlo/templates/project/middlewares.py.tmpl +86 -86
  75. crawlo/templates/project/pipelines.py.tmpl +341 -335
  76. crawlo/templates/project/run.py.tmpl +251 -238
  77. crawlo/templates/project/settings.py.tmpl +250 -247
  78. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  79. crawlo/templates/spider/spider.py.tmpl +177 -177
  80. crawlo/utils/__init__.py +7 -7
  81. crawlo/utils/controlled_spider_mixin.py +439 -335
  82. crawlo/utils/date_tools.py +233 -233
  83. crawlo/utils/db_helper.py +343 -343
  84. crawlo/utils/func_tools.py +82 -82
  85. crawlo/utils/large_scale_config.py +286 -286
  86. crawlo/utils/large_scale_helper.py +343 -343
  87. crawlo/utils/log.py +128 -128
  88. crawlo/utils/queue_helper.py +175 -175
  89. crawlo/utils/request.py +267 -267
  90. crawlo/utils/request_serializer.py +219 -219
  91. crawlo/utils/spider_loader.py +62 -62
  92. crawlo/utils/system.py +11 -11
  93. crawlo/utils/tools.py +4 -4
  94. crawlo/utils/url.py +39 -39
  95. {crawlo-1.1.2.dist-info → crawlo-1.1.3.dist-info}/METADATA +635 -567
  96. crawlo-1.1.3.dist-info/RECORD +113 -0
  97. examples/__init__.py +7 -7
  98. examples/controlled_spider_example.py +205 -0
  99. tests/__init__.py +7 -7
  100. tests/test_final_validation.py +153 -153
  101. tests/test_proxy_health_check.py +32 -32
  102. tests/test_proxy_middleware_integration.py +136 -136
  103. tests/test_proxy_providers.py +56 -56
  104. tests/test_proxy_stats.py +19 -19
  105. tests/test_proxy_strategies.py +59 -59
  106. tests/test_redis_config.py +28 -28
  107. tests/test_redis_queue.py +224 -224
  108. tests/test_request_serialization.py +70 -70
  109. tests/test_scheduler.py +241 -241
  110. crawlo-1.1.2.dist-info/RECORD +0 -108
  111. {crawlo-1.1.2.dist-info → crawlo-1.1.3.dist-info}/WHEEL +0 -0
  112. {crawlo-1.1.2.dist-info → crawlo-1.1.3.dist-info}/entry_points.txt +0 -0
  113. {crawlo-1.1.2.dist-info → crawlo-1.1.3.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