crawlo 1.1.4__py3-none-any.whl → 1.1.6__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 -34
  2. crawlo/__version__.py +1 -1
  3. crawlo/cleaners/__init__.py +61 -0
  4. crawlo/cleaners/data_formatter.py +226 -0
  5. crawlo/cleaners/encoding_converter.py +126 -0
  6. crawlo/cleaners/text_cleaner.py +233 -0
  7. crawlo/cli.py +40 -40
  8. crawlo/commands/__init__.py +13 -13
  9. crawlo/commands/check.py +594 -594
  10. crawlo/commands/genspider.py +151 -151
  11. crawlo/commands/list.py +155 -155
  12. crawlo/commands/run.py +292 -285
  13. crawlo/commands/startproject.py +419 -196
  14. crawlo/commands/stats.py +188 -188
  15. crawlo/commands/utils.py +186 -186
  16. crawlo/config.py +312 -279
  17. crawlo/config_validator.py +253 -0
  18. crawlo/core/__init__.py +2 -2
  19. crawlo/core/engine.py +346 -172
  20. crawlo/core/processor.py +40 -40
  21. crawlo/core/scheduler.py +137 -166
  22. crawlo/crawler.py +1027 -1027
  23. crawlo/downloader/__init__.py +266 -242
  24. crawlo/downloader/aiohttp_downloader.py +220 -212
  25. crawlo/downloader/cffi_downloader.py +256 -251
  26. crawlo/downloader/httpx_downloader.py +259 -259
  27. crawlo/downloader/hybrid_downloader.py +214 -0
  28. crawlo/downloader/playwright_downloader.py +403 -0
  29. crawlo/downloader/selenium_downloader.py +473 -0
  30. crawlo/event.py +11 -11
  31. crawlo/exceptions.py +81 -81
  32. crawlo/extension/__init__.py +37 -37
  33. crawlo/extension/health_check.py +141 -141
  34. crawlo/extension/log_interval.py +57 -57
  35. crawlo/extension/log_stats.py +81 -81
  36. crawlo/extension/logging_extension.py +43 -43
  37. crawlo/extension/memory_monitor.py +104 -88
  38. crawlo/extension/performance_profiler.py +133 -117
  39. crawlo/extension/request_recorder.py +107 -107
  40. crawlo/filters/__init__.py +154 -154
  41. crawlo/filters/aioredis_filter.py +281 -242
  42. crawlo/filters/memory_filter.py +269 -269
  43. crawlo/items/__init__.py +23 -23
  44. crawlo/items/base.py +21 -21
  45. crawlo/items/fields.py +53 -53
  46. crawlo/items/items.py +104 -104
  47. crawlo/middleware/__init__.py +21 -21
  48. crawlo/middleware/default_header.py +32 -32
  49. crawlo/middleware/download_delay.py +28 -28
  50. crawlo/middleware/middleware_manager.py +135 -135
  51. crawlo/middleware/proxy.py +272 -248
  52. crawlo/middleware/request_ignore.py +30 -30
  53. crawlo/middleware/response_code.py +18 -18
  54. crawlo/middleware/response_filter.py +26 -26
  55. crawlo/middleware/retry.py +124 -124
  56. crawlo/mode_manager.py +212 -201
  57. crawlo/network/__init__.py +21 -21
  58. crawlo/network/request.py +338 -311
  59. crawlo/network/response.py +360 -271
  60. crawlo/pipelines/__init__.py +21 -21
  61. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  62. crawlo/pipelines/console_pipeline.py +39 -39
  63. crawlo/pipelines/csv_pipeline.py +316 -316
  64. crawlo/pipelines/database_dedup_pipeline.py +224 -224
  65. crawlo/pipelines/json_pipeline.py +218 -218
  66. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  67. crawlo/pipelines/mongo_pipeline.py +131 -131
  68. crawlo/pipelines/mysql_pipeline.py +316 -316
  69. crawlo/pipelines/pipeline_manager.py +61 -56
  70. crawlo/pipelines/redis_dedup_pipeline.py +167 -162
  71. crawlo/project.py +188 -153
  72. crawlo/queue/pqueue.py +37 -37
  73. crawlo/queue/queue_manager.py +334 -307
  74. crawlo/queue/redis_priority_queue.py +299 -209
  75. crawlo/settings/__init__.py +7 -7
  76. crawlo/settings/default_settings.py +219 -278
  77. crawlo/settings/setting_manager.py +123 -100
  78. crawlo/spider/__init__.py +639 -639
  79. crawlo/stats_collector.py +59 -59
  80. crawlo/subscriber.py +130 -130
  81. crawlo/task_manager.py +30 -30
  82. crawlo/templates/crawlo.cfg.tmpl +10 -10
  83. crawlo/templates/project/__init__.py.tmpl +3 -3
  84. crawlo/templates/project/items.py.tmpl +17 -17
  85. crawlo/templates/project/middlewares.py.tmpl +110 -110
  86. crawlo/templates/project/pipelines.py.tmpl +97 -97
  87. crawlo/templates/project/run.py.tmpl +251 -251
  88. crawlo/templates/project/settings.py.tmpl +326 -279
  89. crawlo/templates/project/settings_distributed.py.tmpl +120 -0
  90. crawlo/templates/project/settings_gentle.py.tmpl +95 -0
  91. crawlo/templates/project/settings_high_performance.py.tmpl +152 -0
  92. crawlo/templates/project/settings_simple.py.tmpl +69 -0
  93. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  94. crawlo/templates/spider/spider.py.tmpl +141 -141
  95. crawlo/tools/__init__.py +183 -0
  96. crawlo/tools/anti_crawler.py +269 -0
  97. crawlo/tools/authenticated_proxy.py +241 -0
  98. crawlo/tools/data_validator.py +181 -0
  99. crawlo/tools/date_tools.py +36 -0
  100. crawlo/tools/distributed_coordinator.py +387 -0
  101. crawlo/tools/retry_mechanism.py +221 -0
  102. crawlo/tools/scenario_adapter.py +263 -0
  103. crawlo/utils/__init__.py +35 -7
  104. crawlo/utils/batch_processor.py +261 -0
  105. crawlo/utils/controlled_spider_mixin.py +439 -439
  106. crawlo/utils/date_tools.py +290 -233
  107. crawlo/utils/db_helper.py +343 -343
  108. crawlo/utils/enhanced_error_handler.py +360 -0
  109. crawlo/utils/env_config.py +106 -0
  110. crawlo/utils/error_handler.py +126 -0
  111. crawlo/utils/func_tools.py +82 -82
  112. crawlo/utils/large_scale_config.py +286 -286
  113. crawlo/utils/large_scale_helper.py +343 -343
  114. crawlo/utils/log.py +128 -128
  115. crawlo/utils/performance_monitor.py +285 -0
  116. crawlo/utils/queue_helper.py +175 -175
  117. crawlo/utils/redis_connection_pool.py +335 -0
  118. crawlo/utils/redis_key_validator.py +200 -0
  119. crawlo/utils/request.py +267 -267
  120. crawlo/utils/request_serializer.py +219 -219
  121. crawlo/utils/spider_loader.py +62 -62
  122. crawlo/utils/system.py +11 -11
  123. crawlo/utils/tools.py +4 -4
  124. crawlo/utils/url.py +39 -39
  125. {crawlo-1.1.4.dist-info → crawlo-1.1.6.dist-info}/METADATA +401 -403
  126. crawlo-1.1.6.dist-info/RECORD +189 -0
  127. examples/__init__.py +7 -7
  128. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +82 -0
  129. tests/__init__.py +7 -7
  130. tests/advanced_tools_example.py +276 -0
  131. tests/authenticated_proxy_example.py +237 -0
  132. tests/cleaners_example.py +161 -0
  133. tests/config_validation_demo.py +103 -0
  134. {examples → tests}/controlled_spider_example.py +205 -205
  135. tests/date_tools_example.py +181 -0
  136. tests/dynamic_loading_example.py +524 -0
  137. tests/dynamic_loading_test.py +105 -0
  138. tests/env_config_example.py +134 -0
  139. tests/error_handling_example.py +172 -0
  140. tests/redis_key_validation_demo.py +131 -0
  141. tests/response_improvements_example.py +145 -0
  142. tests/test_advanced_tools.py +149 -0
  143. tests/test_all_redis_key_configs.py +146 -0
  144. tests/test_authenticated_proxy.py +142 -0
  145. tests/test_cleaners.py +55 -0
  146. tests/test_comprehensive.py +147 -0
  147. tests/test_config_validator.py +194 -0
  148. tests/test_date_tools.py +124 -0
  149. tests/test_double_crawlo_fix.py +208 -0
  150. tests/test_double_crawlo_fix_simple.py +125 -0
  151. tests/test_dynamic_downloaders_proxy.py +125 -0
  152. tests/test_dynamic_proxy.py +93 -0
  153. tests/test_dynamic_proxy_config.py +147 -0
  154. tests/test_dynamic_proxy_real.py +110 -0
  155. tests/test_edge_cases.py +304 -0
  156. tests/test_enhanced_error_handler.py +271 -0
  157. tests/test_env_config.py +122 -0
  158. tests/test_error_handler_compatibility.py +113 -0
  159. tests/test_final_validation.py +153 -153
  160. tests/test_framework_env_usage.py +104 -0
  161. tests/test_integration.py +357 -0
  162. tests/test_item_dedup_redis_key.py +123 -0
  163. tests/test_parsel.py +30 -0
  164. tests/test_performance.py +328 -0
  165. tests/test_proxy_health_check.py +32 -32
  166. tests/test_proxy_middleware_integration.py +136 -136
  167. tests/test_proxy_providers.py +56 -56
  168. tests/test_proxy_stats.py +19 -19
  169. tests/test_proxy_strategies.py +59 -59
  170. tests/test_queue_manager_double_crawlo.py +231 -0
  171. tests/test_queue_manager_redis_key.py +177 -0
  172. tests/test_redis_config.py +28 -28
  173. tests/test_redis_connection_pool.py +295 -0
  174. tests/test_redis_key_naming.py +182 -0
  175. tests/test_redis_key_validator.py +124 -0
  176. tests/test_redis_queue.py +224 -224
  177. tests/test_request_serialization.py +70 -70
  178. tests/test_response_improvements.py +153 -0
  179. tests/test_scheduler.py +241 -241
  180. tests/test_simple_response.py +62 -0
  181. tests/test_telecom_spider_redis_key.py +206 -0
  182. tests/test_template_content.py +88 -0
  183. tests/test_template_redis_key.py +135 -0
  184. tests/test_tools.py +154 -0
  185. tests/tools_example.py +258 -0
  186. crawlo/core/enhanced_engine.py +0 -190
  187. crawlo-1.1.4.dist-info/RECORD +0 -117
  188. {crawlo-1.1.4.dist-info → crawlo-1.1.6.dist-info}/WHEEL +0 -0
  189. {crawlo-1.1.4.dist-info → crawlo-1.1.6.dist-info}/entry_points.txt +0 -0
  190. {crawlo-1.1.4.dist-info → crawlo-1.1.6.dist-info}/top_level.txt +0 -0
@@ -1,111 +1,111 @@
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
- # 在 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
+ 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
+ # 在 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
111
111
  # ======================== 使用说明 ========================
@@ -1,98 +1,98 @@
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
- # 在 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
+ 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
+ # 在 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。
98
98
  # ======================== 使用说明 ========================