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
@@ -1,154 +1,154 @@
1
- #!/usr/bin/python
2
- # -*- coding:UTF-8 -*-
3
- """
4
- Crawlo Filters Module
5
- ====================
6
- 提供多种请求去重过滤器实现。
7
-
8
- 过滤器类型:
9
- - MemoryFilter: 基于内存的高效去重,适合单机模式
10
- - AioRedisFilter: 基于Redis的分布式去重,适合分布式模式
11
- - MemoryFileFilter: 内存+文件持久化,适合需要重启恢复的场景
12
-
13
- 核心接口:
14
- - BaseFilter: 所有过滤器的基类
15
- - requested(): 检查请求是否重复的主要方法
16
- """
17
- from abc import ABC, abstractmethod
18
- from typing import Optional
19
-
20
- from crawlo.utils.request import request_fingerprint
21
-
22
-
23
- class BaseFilter(ABC):
24
- """
25
- 请求去重过滤器基类
26
-
27
- 提供统一的去重接口和统计功能。
28
- 所有过滤器实现都应该继承此类。
29
- """
30
-
31
- def __init__(self, logger, stats, debug: bool = False):
32
- """
33
- 初始化过滤器
34
-
35
- :param logger: 日志器实例
36
- :param stats: 统计信息存储
37
- :param debug: 是否启用调试日志
38
- """
39
- self.logger = logger
40
- self.stats = stats
41
- self.debug = debug
42
- self._request_count = 0
43
- self._duplicate_count = 0
44
-
45
- @classmethod
46
- def create_instance(cls, *args, **kwargs) -> 'BaseFilter':
47
- return cls(*args, **kwargs)
48
-
49
- def requested(self, request) -> bool:
50
- """
51
- 检查请求是否重复(主要接口)
52
-
53
- :param request: 请求对象
54
- :return: True 表示重复,False 表示新请求
55
- """
56
- self._request_count += 1
57
- fp = request_fingerprint(request)
58
-
59
- if fp in self:
60
- self._duplicate_count += 1
61
- self.log_stats(request)
62
- return True
63
-
64
- self.add_fingerprint(fp)
65
- return False
66
-
67
- @abstractmethod
68
- def add_fingerprint(self, fp: str) -> None:
69
- """
70
- 添加请求指纹(子类必须实现)
71
-
72
- :param fp: 请求指纹字符串
73
- """
74
- pass
75
-
76
- @abstractmethod
77
- def __contains__(self, item: str) -> bool:
78
- """
79
- 检查指纹是否存在(支持 in 操作符)
80
-
81
- :param item: 要检查的指纹
82
- :return: 是否已存在
83
- """
84
- pass
85
-
86
- def log_stats(self, request) -> None:
87
- """
88
- 记录统计信息
89
-
90
- :param request: 重复的请求对象
91
- """
92
- if self.debug:
93
- self.logger.debug(f'Filtered duplicate request: {request}')
94
- self.stats.inc_value(f'{self}/filtered_count')
95
-
96
- def get_stats(self) -> dict:
97
- """
98
- 获取过滤器统计信息
99
-
100
- :return: 统计信息字典
101
- """
102
- return {
103
- 'total_requests': self._request_count,
104
- 'duplicate_requests': self._duplicate_count,
105
- 'unique_requests': self._request_count - self._duplicate_count,
106
- 'duplicate_rate': f"{self._duplicate_count / max(1, self._request_count) * 100:.2f}%"
107
- }
108
-
109
- def reset_stats(self) -> None:
110
- """重置统计信息"""
111
- self._request_count = 0
112
- self._duplicate_count = 0
113
-
114
- def close(self) -> None:
115
- """关闭过滤器并清理资源"""
116
- pass
117
-
118
- def __str__(self) -> str:
119
- return f'{self.__class__.__name__}'
120
-
121
-
122
- # 导出所有可用的过滤器
123
- __all__ = ['BaseFilter']
124
-
125
- # 动态导入具体实现
126
- try:
127
- from .memory_filter import MemoryFilter, MemoryFileFilter
128
- __all__.extend(['MemoryFilter', 'MemoryFileFilter'])
129
- except ImportError:
130
- MemoryFilter = None
131
- MemoryFileFilter = None
132
-
133
- try:
134
- from .aioredis_filter import AioRedisFilter
135
- __all__.append('AioRedisFilter')
136
- except ImportError:
137
- AioRedisFilter = None
138
-
139
- # 提供便捷的过滤器映射
140
- FILTER_MAP = {
141
- 'memory': MemoryFilter,
142
- 'memory_file': MemoryFileFilter,
143
- 'redis': AioRedisFilter,
144
- 'aioredis': AioRedisFilter, # 别名
145
- }
146
-
147
- # 过滤掉不可用的过滤器
148
- FILTER_MAP = {k: v for k, v in FILTER_MAP.items() if v is not None}
149
-
150
- def get_filter_class(name: str):
151
- """根据名称获取过滤器类"""
152
- if name in FILTER_MAP:
153
- return FILTER_MAP[name]
154
- raise ValueError(f"未知的过滤器类型: {name}。可用类型: {list(FILTER_MAP.keys())}")
1
+ #!/usr/bin/python
2
+ # -*- coding:UTF-8 -*-
3
+ """
4
+ Crawlo Filters Module
5
+ ====================
6
+ 提供多种请求去重过滤器实现。
7
+
8
+ 过滤器类型:
9
+ - MemoryFilter: 基于内存的高效去重,适合单机模式
10
+ - AioRedisFilter: 基于Redis的分布式去重,适合分布式模式
11
+ - MemoryFileFilter: 内存+文件持久化,适合需要重启恢复的场景
12
+
13
+ 核心接口:
14
+ - BaseFilter: 所有过滤器的基类
15
+ - requested(): 检查请求是否重复的主要方法
16
+ """
17
+ from abc import ABC, abstractmethod
18
+ from typing import Optional
19
+
20
+ from crawlo.utils.request import request_fingerprint
21
+
22
+
23
+ class BaseFilter(ABC):
24
+ """
25
+ 请求去重过滤器基类
26
+
27
+ 提供统一的去重接口和统计功能。
28
+ 所有过滤器实现都应该继承此类。
29
+ """
30
+
31
+ def __init__(self, logger, stats, debug: bool = False):
32
+ """
33
+ 初始化过滤器
34
+
35
+ :param logger: 日志器实例
36
+ :param stats: 统计信息存储
37
+ :param debug: 是否启用调试日志
38
+ """
39
+ self.logger = logger
40
+ self.stats = stats
41
+ self.debug = debug
42
+ self._request_count = 0
43
+ self._duplicate_count = 0
44
+
45
+ @classmethod
46
+ def create_instance(cls, *args, **kwargs) -> 'BaseFilter':
47
+ return cls(*args, **kwargs)
48
+
49
+ def requested(self, request) -> bool:
50
+ """
51
+ 检查请求是否重复(主要接口)
52
+
53
+ :param request: 请求对象
54
+ :return: True 表示重复,False 表示新请求
55
+ """
56
+ self._request_count += 1
57
+ fp = request_fingerprint(request)
58
+
59
+ if fp in self:
60
+ self._duplicate_count += 1
61
+ self.log_stats(request)
62
+ return True
63
+
64
+ self.add_fingerprint(fp)
65
+ return False
66
+
67
+ @abstractmethod
68
+ def add_fingerprint(self, fp: str) -> None:
69
+ """
70
+ 添加请求指纹(子类必须实现)
71
+
72
+ :param fp: 请求指纹字符串
73
+ """
74
+ pass
75
+
76
+ @abstractmethod
77
+ def __contains__(self, item: str) -> bool:
78
+ """
79
+ 检查指纹是否存在(支持 in 操作符)
80
+
81
+ :param item: 要检查的指纹
82
+ :return: 是否已存在
83
+ """
84
+ pass
85
+
86
+ def log_stats(self, request) -> None:
87
+ """
88
+ 记录统计信息
89
+
90
+ :param request: 重复的请求对象
91
+ """
92
+ if self.debug:
93
+ self.logger.debug(f'Filtered duplicate request: {request}')
94
+ self.stats.inc_value(f'{self}/filtered_count')
95
+
96
+ def get_stats(self) -> dict:
97
+ """
98
+ 获取过滤器统计信息
99
+
100
+ :return: 统计信息字典
101
+ """
102
+ return {
103
+ 'total_requests': self._request_count,
104
+ 'duplicate_requests': self._duplicate_count,
105
+ 'unique_requests': self._request_count - self._duplicate_count,
106
+ 'duplicate_rate': f"{self._duplicate_count / max(1, self._request_count) * 100:.2f}%"
107
+ }
108
+
109
+ def reset_stats(self) -> None:
110
+ """重置统计信息"""
111
+ self._request_count = 0
112
+ self._duplicate_count = 0
113
+
114
+ def close(self) -> None:
115
+ """关闭过滤器并清理资源"""
116
+ pass
117
+
118
+ def __str__(self) -> str:
119
+ return f'{self.__class__.__name__}'
120
+
121
+
122
+ # 导出所有可用的过滤器
123
+ __all__ = ['BaseFilter']
124
+
125
+ # 动态导入具体实现
126
+ try:
127
+ from .memory_filter import MemoryFilter, MemoryFileFilter
128
+ __all__.extend(['MemoryFilter', 'MemoryFileFilter'])
129
+ except ImportError:
130
+ MemoryFilter = None
131
+ MemoryFileFilter = None
132
+
133
+ try:
134
+ from .aioredis_filter import AioRedisFilter
135
+ __all__.append('AioRedisFilter')
136
+ except ImportError:
137
+ AioRedisFilter = None
138
+
139
+ # 提供便捷的过滤器映射
140
+ FILTER_MAP = {
141
+ 'memory': MemoryFilter,
142
+ 'memory_file': MemoryFileFilter,
143
+ 'redis': AioRedisFilter,
144
+ 'aioredis': AioRedisFilter, # 别名
145
+ }
146
+
147
+ # 过滤掉不可用的过滤器
148
+ FILTER_MAP = {k: v for k, v in FILTER_MAP.items() if v is not None}
149
+
150
+ def get_filter_class(name: str):
151
+ """根据名称获取过滤器类"""
152
+ if name in FILTER_MAP:
153
+ return FILTER_MAP[name]
154
+ raise ValueError(f"未知的过滤器类型: {name}。可用类型: {list(FILTER_MAP.keys())}")