crawlo 1.1.6__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 -40
  8. crawlo/commands/__init__.py +14 -13
  9. crawlo/commands/check.py +594 -594
  10. crawlo/commands/genspider.py +151 -151
  11. crawlo/commands/help.py +133 -0
  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 -110
  87. crawlo/templates/project/pipelines.py.tmpl +96 -97
  88. crawlo/templates/project/run.py.tmpl +46 -252
  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-1.1.6.dist-info → crawlo-1.1.9.dist-info}/METADATA +626 -401
  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-1.1.6.dist-info/RECORD +0 -189
  188. {crawlo-1.1.6.dist-info → crawlo-1.1.9.dist-info}/WHEEL +0 -0
  189. {crawlo-1.1.6.dist-info → crawlo-1.1.9.dist-info}/entry_points.txt +0 -0
  190. {crawlo-1.1.6.dist-info → crawlo-1.1.9.dist-info}/top_level.txt +0 -0
@@ -1,111 +1,110 @@
1
- # -*- coding: UTF-8 -*-
2
- """
3
- {{project_name}}.middlewares
4
- ============================
5
- 自定义中间件,用于在请求/响应/异常处理过程中插入自定义逻辑。
6
-
7
- 这是一个简单的示例中间件,您可以根据需要添加更多中间件。
8
- """
9
-
10
- import random
11
- from crawlo import Request, Response
12
- from crawlo.utils.log import get_logger
13
- from crawlo.exceptions import IgnoreRequest
14
-
15
-
16
- class ExampleMiddleware:
17
- """
18
- 示例中间件,演示如何处理请求、响应和异常。
19
-
20
- 此中间件会:
21
- 1. 为请求添加随机 User-Agent
22
- 2. 记录请求和响应信息
23
- 3. 处理异常情况
24
- """
25
-
26
- def __init__(self):
27
- self.logger = get_logger(self.__class__.__name__)
28
- self.user_agents = [
29
- 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36',
30
- 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36',
31
- 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:135.0) Gecko/20100101 Firefox/135.0',
32
- 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:135.0) Gecko/20100101 Firefox/135.0',
33
- ]
34
-
35
- def process_request(self, request, spider):
36
- """
37
- 在请求被下载器执行前调用。
38
-
39
- Args:
40
- request: 请求对象
41
- spider: 爬虫实例
42
-
43
- Returns:
44
- None: 继续处理请求
45
- Response: 返回响应对象(短路处理)
46
- Request: 返回新请求对象(替换原请求)
47
- """
48
- # 为请求添加随机 User-Agent
49
- if 'User-Agent' not in request.headers:
50
- ua = random.choice(self.user_agents)
51
- request.headers['User-Agent'] = ua
52
- self.logger.debug(f"为请求 {request.url} 设置 User-Agent: {ua[:50]}...")
53
-
54
- return None
55
-
56
- def process_response(self, request, response, spider):
57
- """
58
- 在响应被 Spider 处理前调用。
59
-
60
- Args:
61
- request: 原始请求对象
62
- response: 响应对象
63
- spider: 爬虫实例
64
-
65
- Returns:
66
- Response: 处理后的响应对象
67
- """
68
- # 记录响应信息
69
- self.logger.info(f"收到响应: {request.url} - 状态码: {response.status_code}")
70
-
71
- # 可以在这里处理特殊状态码
72
- if response.status_code == 403:
73
- self.logger.warning(f"访问被拒绝: {request.url}")
74
-
75
- return response
76
-
77
- def process_exception(self, request, exception, spider):
78
- """
79
- 在下载或处理过程中发生异常时调用。
80
-
81
- Args:
82
- request: 请求对象
83
- exception: 异常对象
84
- spider: 爬虫实例
85
-
86
- Returns:
87
- None: 异常将继续传播
88
- Response: 返回响应对象(处理异常)
89
- Request: 返回新请求对象(重试请求)
90
- """
91
- self.logger.error(f"请求异常: {request.url} - {exception}")
92
- return None
93
-
94
-
95
- # ======================== 使用说明 ========================
96
- #
97
- # settings.py 中启用中间件:
98
- # MIDDLEWARES = [
99
- # '{{project_name}}.middlewares.ExampleMiddleware',
100
- # ]
101
- #
102
- # 您可以根据需要添加更多中间件,例如:
103
- # 1. 请求处理中间件(修改请求头、设置代理等)
104
- # 2. 响应处理中间件(解析、过滤等)
105
- # 3. 异常处理中间件(重试、记录等)
106
- #
107
- # 每个中间件可以实现以下方法:
108
- # - process_request: 处理请求
109
- # - process_response: 处理响应
110
- # - process_exception: 处理异常
1
+ # -*- coding: UTF-8 -*-
2
+ """
3
+ {{project_name}}.middlewares
4
+ ============================
5
+ 自定义中间件,用于在请求/响应/异常处理过程中插入自定义逻辑。
6
+
7
+ 这是一个简单的示例中间件,您可以根据需要添加更多中间件。
8
+ """
9
+
10
+ import random
11
+ from crawlo import Request, Response
12
+ from crawlo.utils.log import get_logger
13
+
14
+
15
+ class ExampleMiddleware:
16
+ """
17
+ 示例中间件,演示如何处理请求、响应和异常。
18
+
19
+ 此中间件会:
20
+ 1. 为请求添加随机 User-Agent
21
+ 2. 记录请求和响应信息
22
+ 3. 处理异常情况
23
+ """
24
+
25
+ def __init__(self):
26
+ self.logger = get_logger(self.__class__.__name__)
27
+ self.user_agents = [
28
+ 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36',
29
+ 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36',
30
+ 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:135.0) Gecko/20100101 Firefox/135.0',
31
+ 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:135.0) Gecko/20100101 Firefox/135.0',
32
+ ]
33
+
34
+ def process_request(self, request, spider):
35
+ """
36
+ 在请求被下载器执行前调用。
37
+
38
+ Args:
39
+ request: 请求对象
40
+ spider: 爬虫实例
41
+
42
+ Returns:
43
+ None: 继续处理请求
44
+ Response: 返回响应对象(短路处理)
45
+ Request: 返回新请求对象(替换原请求)
46
+ """
47
+ # 为请求添加随机 User-Agent
48
+ if 'User-Agent' not in request.headers:
49
+ ua = random.choice(self.user_agents)
50
+ request.headers['User-Agent'] = ua
51
+ self.logger.debug(f"为请求 {request.url} 设置 User-Agent: {ua[:50]}...")
52
+
53
+ return None
54
+
55
+ def process_response(self, request, response, spider):
56
+ """
57
+ 在响应被 Spider 处理前调用。
58
+
59
+ Args:
60
+ request: 原始请求对象
61
+ response: 响应对象
62
+ spider: 爬虫实例
63
+
64
+ Returns:
65
+ Response: 处理后的响应对象
66
+ """
67
+ # 记录响应信息
68
+ self.logger.info(f"收到响应: {request.url} - 状态码: {response.status_code}")
69
+
70
+ # 可以在这里处理特殊状态码
71
+ if response.status_code == 403:
72
+ self.logger.warning(f"访问被拒绝: {request.url}")
73
+
74
+ return response
75
+
76
+ def process_exception(self, request, exception, spider):
77
+ """
78
+ 在下载或处理过程中发生异常时调用。
79
+
80
+ Args:
81
+ request: 请求对象
82
+ exception: 异常对象
83
+ spider: 爬虫实例
84
+
85
+ Returns:
86
+ None: 异常将继续传播
87
+ Response: 返回响应对象(处理异常)
88
+ Request: 返回新请求对象(重试请求)
89
+ """
90
+ self.logger.error(f"请求异常: {request.url} - {exception}")
91
+ return None
92
+
93
+
94
+ # ======================== 使用说明 ========================
95
+ #
96
+ # 在 settings.py 中启用中间件:
97
+ # MIDDLEWARES = [
98
+ # '{{project_name}}.middlewares.ExampleMiddleware',
99
+ # ]
100
+ #
101
+ # 您可以根据需要添加更多中间件,例如:
102
+ # 1. 请求处理中间件(修改请求头、设置代理等)
103
+ # 2. 响应处理中间件(解析、过滤等)
104
+ # 3. 异常处理中间件(重试、记录等)
105
+ #
106
+ # 每个中间件可以实现以下方法:
107
+ # - process_request: 处理请求
108
+ # - process_response: 处理响应
109
+ # - process_exception: 处理异常
111
110
  # ======================== 使用说明 ========================
@@ -1,98 +1,97 @@
1
- # -*- coding: UTF-8 -*-
2
- """
3
- {{project_name}}.pipelines
4
- ==========================
5
- 数据管道,用于处理 Spider 返回的 Item。
6
- 例如:清理、验证、去重、保存到数据库等。
7
-
8
- 这是一个简单的示例管道,您可以根据需要添加更多管道。
9
- """
10
-
11
- import json
12
- from datetime import datetime
13
- from crawlo.exceptions import DropItem
14
- from crawlo.utils.log import get_logger
15
-
16
-
17
- class ExamplePipeline:
18
- """
19
- 示例管道,演示如何处理数据项。
20
-
21
- 此管道会:
22
- 1. 验证必要字段
23
- 2. 清理数据
24
- 3. 添加时间戳
25
- 4. 记录处理日志
26
- """
27
-
28
- def __init__(self):
29
- self.logger = get_logger(self.__class__.__name__)
30
- self.item_count = 0
31
-
32
- def process_item(self, item, spider):
33
- """
34
- 处理数据项。
35
-
36
- Args:
37
- item: 要处理的数据项
38
- spider: 爬虫实例
39
-
40
- Returns:
41
- 处理后的数据项
42
-
43
- Raises:
44
- DropItem: 如果数据项无效则抛出此异常
45
- """
46
- # 验证必要字段
47
- if not item.get('title') or not item.get('url'):
48
- raise DropItem("缺少必要字段: title 或 url")
49
-
50
- # 数据清理
51
- item['title'] = str(item['title']).strip()
52
-
53
- # 添加处理时间戳
54
- item['processed_at'] = datetime.now().isoformat()
55
-
56
- # 计数器
57
- self.item_count += 1
58
-
59
- # 记录日志
60
- self.logger.info(f"处理第 {self.item_count} 个数据项: {item['title']}")
61
-
62
- return item
63
-
64
- def open_spider(self, spider):
65
- """
66
- 爬虫启动时调用。
67
-
68
- Args:
69
- spider: 爬虫实例
70
- """
71
- self.logger.info(f"管道已启动,准备处理爬虫 '{spider.name}' 的数据")
72
-
73
- def close_spider(self, spider):
74
- """
75
- 爬虫关闭时调用。
76
-
77
- Args:
78
- spider: 爬虫实例
79
- """
80
- self.logger.info(f"管道已关闭,共处理了 {self.item_count} 个数据项")
81
-
82
-
83
- # ======================== 使用说明 ========================
84
- #
85
- # settings.py 中启用管道:
86
- # PIPELINES = [
87
- # '{{project_name}}.pipelines.ExamplePipeline',
88
- # ]
89
- #
90
- # 您可以根据需要添加更多管道,例如:
91
- # 1. 数据验证管道
92
- # 2. 去重管道
93
- # 3. 数据存储管道(数据库、文件等)
94
- # 4. 数据转换管道
95
- #
96
- # 每个管道都应该实现 process_item 方法,
97
- # 可选实现 open_spider 和 close_spider 方法。
1
+ # -*- coding: UTF-8 -*-
2
+ """
3
+ {{project_name}}.pipelines
4
+ ==========================
5
+ 数据管道,用于处理 Spider 返回的 Item。
6
+ 例如:清理、验证、去重、保存到数据库等。
7
+
8
+ 这是一个简单的示例管道,您可以根据需要添加更多管道。
9
+ """
10
+
11
+ from datetime import datetime
12
+ from crawlo.exceptions import DropItem
13
+ from crawlo.utils.log import get_logger
14
+
15
+
16
+ class ExamplePipeline:
17
+ """
18
+ 示例管道,演示如何处理数据项。
19
+
20
+ 此管道会:
21
+ 1. 验证必要字段
22
+ 2. 清理数据
23
+ 3. 添加时间戳
24
+ 4. 记录处理日志
25
+ """
26
+
27
+ def __init__(self):
28
+ self.logger = get_logger(self.__class__.__name__)
29
+ self.item_count = 0
30
+
31
+ def process_item(self, item, spider):
32
+ """
33
+ 处理数据项。
34
+
35
+ Args:
36
+ item: 要处理的数据项
37
+ spider: 爬虫实例
38
+
39
+ Returns:
40
+ 处理后的数据项
41
+
42
+ Raises:
43
+ DropItem: 如果数据项无效则抛出此异常
44
+ """
45
+ # 验证必要字段
46
+ if not item.get('title') or not item.get('url'):
47
+ raise DropItem("缺少必要字段: title url")
48
+
49
+ # 数据清理
50
+ item['title'] = str(item['title']).strip()
51
+
52
+ # 添加处理时间戳
53
+ item['processed_at'] = datetime.now().isoformat()
54
+
55
+ # 计数器
56
+ self.item_count += 1
57
+
58
+ # 记录日志
59
+ self.logger.info(f"处理第 {self.item_count} 个数据项: {item['title']}")
60
+
61
+ return item
62
+
63
+ def open_spider(self, spider):
64
+ """
65
+ 爬虫启动时调用。
66
+
67
+ Args:
68
+ spider: 爬虫实例
69
+ """
70
+ self.logger.info(f"管道已启动,准备处理爬虫 '{spider.name}' 的数据")
71
+
72
+ def close_spider(self, spider):
73
+ """
74
+ 爬虫关闭时调用。
75
+
76
+ Args:
77
+ spider: 爬虫实例
78
+ """
79
+ self.logger.info(f"管道已关闭,共处理了 {self.item_count} 个数据项")
80
+
81
+
82
+ # ======================== 使用说明 ========================
83
+ #
84
+ # 在 settings.py 中启用管道:
85
+ # PIPELINES = [
86
+ # '{{project_name}}.pipelines.ExamplePipeline',
87
+ # ]
88
+ #
89
+ # 您可以根据需要添加更多管道,例如:
90
+ # 1. 数据验证管道
91
+ # 2. 去重管道
92
+ # 3. 数据存储管道(数据库、文件等)
93
+ # 4. 数据转换管道
94
+ #
95
+ # 每个管道都应该实现 process_item 方法,
96
+ # 可选实现 open_spider 和 close_spider 方法。
98
97
  # ======================== 使用说明 ========================