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
tests/test_scheduler.py CHANGED
@@ -1,242 +1,242 @@
1
- #!/usr/bin/env python3
2
- # -*- coding: utf-8 -*-
3
- """
4
- 测试修复后的 Scheduler 分布式队列功能
5
- """
6
- import asyncio
7
- import sys
8
- from unittest.mock import Mock
9
- from crawlo.core.scheduler import Scheduler
10
- from crawlo.network.request import Request
11
- from crawlo.utils.log import get_logger
12
-
13
-
14
- class MockCrawler:
15
- """模拟 Crawler 对象"""
16
- def __init__(self, use_redis=True):
17
- self.settings = MockSettings(use_redis)
18
- self.stats = Mock()
19
-
20
-
21
- class MockSettings:
22
- """模拟 Settings 对象"""
23
- def __init__(self, use_redis=True):
24
- self.use_redis = use_redis
25
-
26
- def get(self, key, default=None):
27
- config = {
28
- 'FILTER_CLASS': 'crawlo.filters.memory_filter.MemoryFilter',
29
- 'LOG_LEVEL': 'INFO',
30
- 'DEPTH_PRIORITY': 1,
31
- 'SCHEDULER_MAX_QUEUE_SIZE': 100,
32
- 'SCHEDULER_QUEUE_NAME': 'test:crawlo:requests',
33
- 'FILTER_DEBUG': False,
34
- 'PROJECT_NAME': 'test',
35
- }
36
- if self.use_redis:
37
- config['REDIS_URL'] = 'redis://localhost:6379/0'
38
-
39
- return config.get(key, default)
40
-
41
- def get_int(self, key, default=0):
42
- value = self.get(key, default)
43
- return int(value) if value is not None else default
44
-
45
- def get_bool(self, key, default=False):
46
- value = self.get(key, default)
47
- if isinstance(value, bool):
48
- return value
49
- if isinstance(value, str):
50
- return value.lower() in ('true', '1', 'yes')
51
- return bool(value) if value is not None else default
52
-
53
-
54
- class MockFilter:
55
- """模拟去重过滤器"""
56
- def __init__(self):
57
- self.seen = set()
58
-
59
- @classmethod
60
- def create_instance(cls, crawler):
61
- return cls()
62
-
63
- async def requested(self, request):
64
- if request.url in self.seen:
65
- return True
66
- self.seen.add(request.url)
67
- return False
68
-
69
- def log_stats(self, request):
70
- pass
71
-
72
-
73
- async def test_memory_scheduler():
74
- """测试内存调度器"""
75
- print("🔍 测试内存调度器...")
76
-
77
- crawler = MockCrawler(use_redis=False)
78
- scheduler = Scheduler.create_instance(crawler)
79
-
80
- # 模拟去重过滤器
81
- scheduler.dupe_filter = MockFilter()
82
-
83
- scheduler.open()
84
-
85
- # 测试入队
86
- request1 = Request(url="https://example1.com")
87
- request2 = Request(url="https://example2.com")
88
-
89
- success1 = await scheduler.enqueue_request(request1)
90
- success2 = await scheduler.enqueue_request(request2)
91
-
92
- print(f" 📤 入队结果: {success1}, {success2}")
93
- print(f" 📊 队列大小: {len(scheduler)}")
94
-
95
- # 测试出队
96
- req1 = await scheduler.next_request()
97
- req2 = await scheduler.next_request()
98
-
99
- print(f" 📥 出队结果: {req1.url if req1 else None}, {req2.url if req2 else None}")
100
- print(f" 📊 剩余大小: {len(scheduler)}")
101
-
102
- await scheduler.close()
103
- print(" ✅ 内存调度器测试完成")
104
-
105
-
106
- async def test_redis_scheduler():
107
- """测试 Redis 调度器"""
108
- print("🔍 测试 Redis 调度器...")
109
-
110
- try:
111
- crawler = MockCrawler(use_redis=True)
112
- scheduler = Scheduler.create_instance(crawler)
113
-
114
- # 模拟去重过滤器
115
- scheduler.dupe_filter = MockFilter()
116
-
117
- scheduler.open()
118
-
119
- # 测试入队
120
- request1 = Request(url="https://redis-test1.com", priority=5)
121
- request2 = Request(url="https://redis-test2.com", priority=3)
122
- request3 = Request(url="https://redis-test3.com", priority=8)
123
-
124
- success1 = await scheduler.enqueue_request(request1)
125
- success2 = await scheduler.enqueue_request(request2)
126
- success3 = await scheduler.enqueue_request(request3)
127
-
128
- print(f" 📤 入队结果: {success1}, {success2}, {success3}")
129
- print(f" 📊 队列大小: {len(scheduler)}")
130
-
131
- # 等待一小段时间让 Redis 操作完成
132
- await asyncio.sleep(0.5)
133
-
134
- # 测试出队(应该按优先级排序)
135
- req1 = await scheduler.next_request()
136
- req2 = await scheduler.next_request()
137
- req3 = await scheduler.next_request()
138
-
139
- print(" 📥 出队结果(按优先级):")
140
- if req1:
141
- print(f" {req1.url} (优先级: {getattr(req1, 'priority', 0)})")
142
- if req2:
143
- print(f" {req2.url} (优先级: {getattr(req2, 'priority', 0)})")
144
- if req3:
145
- print(f" {req3.url} (优先级: {getattr(req3, 'priority', 0)})")
146
-
147
- print(f" 📊 剩余大小: {len(scheduler)}")
148
-
149
- await scheduler.close()
150
- print(" ✅ Redis 调度器测试完成")
151
-
152
- except Exception as e:
153
- print(f" ❌ Redis 调度器测试失败: {e}")
154
- import traceback
155
- traceback.print_exc()
156
-
157
-
158
- async def test_concurrent_redis():
159
- """测试并发 Redis 操作"""
160
- print("🔍 测试并发 Redis 操作...")
161
-
162
- async def producer(scheduler, name, count):
163
- """生产者"""
164
- for i in range(count):
165
- request = Request(url=f"https://{name}-{i}.com", priority=i % 10)
166
- await scheduler.enqueue_request(request)
167
- await asyncio.sleep(0.01)
168
- print(f" ✅ 生产者 {name} 完成 ({count} 个请求)")
169
-
170
- async def consumer(scheduler, name, count):
171
- """消费者"""
172
- consumed = 0
173
- for _ in range(count):
174
- request = await scheduler.next_request()
175
- if request:
176
- consumed += 1
177
- await asyncio.sleep(0.005)
178
- else:
179
- break
180
- print(f" ✅ 消费者 {name} 处理了 {consumed} 个请求")
181
-
182
- try:
183
- crawler = MockCrawler(use_redis=True)
184
- scheduler = Scheduler.create_instance(crawler)
185
- scheduler.dupe_filter = MockFilter()
186
- scheduler.open()
187
-
188
- # 并发运行生产者和消费者
189
- tasks = [
190
- producer(scheduler, "producer-1", 5),
191
- producer(scheduler, "producer-2", 5),
192
- consumer(scheduler, "consumer-1", 3),
193
- consumer(scheduler, "consumer-2", 3),
194
- consumer(scheduler, "consumer-3", 4),
195
- ]
196
-
197
- await asyncio.gather(*tasks, return_exceptions=True)
198
-
199
- print(f" 📊 最终队列大小: {len(scheduler)}")
200
-
201
- await scheduler.close()
202
- print(" ✅ 并发测试完成")
203
-
204
- except Exception as e:
205
- print(f" ❌ 并发测试失败: {e}")
206
- import traceback
207
- traceback.print_exc()
208
-
209
-
210
- async def main():
211
- """主测试函数"""
212
- print("🚀 开始测试修复后的 Scheduler...")
213
- print("=" * 50)
214
-
215
- try:
216
- # 1. 测试内存调度器
217
- await test_memory_scheduler()
218
- print()
219
-
220
- # 2. 测试 Redis 调度器
221
- await test_redis_scheduler()
222
- print()
223
-
224
- # 3. 测试并发操作
225
- await test_concurrent_redis()
226
-
227
- print("=" * 50)
228
- print("🎉 所有 Scheduler 测试完成!")
229
-
230
- except Exception as e:
231
- print("=" * 50)
232
- print(f"❌ 测试失败: {e}")
233
- import traceback
234
- traceback.print_exc()
235
-
236
-
237
- if __name__ == "__main__":
238
- # 设置日志级别避免过多输出
239
- import logging
240
- logging.getLogger('crawlo').setLevel(logging.WARNING)
241
-
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ """
4
+ 测试修复后的 Scheduler 分布式队列功能
5
+ """
6
+ import asyncio
7
+ import sys
8
+ from unittest.mock import Mock
9
+ from crawlo.core.scheduler import Scheduler
10
+ from crawlo.network.request import Request
11
+ from crawlo.utils.log import get_logger
12
+
13
+
14
+ class MockCrawler:
15
+ """模拟 Crawler 对象"""
16
+ def __init__(self, use_redis=True):
17
+ self.settings = MockSettings(use_redis)
18
+ self.stats = Mock()
19
+
20
+
21
+ class MockSettings:
22
+ """模拟 Settings 对象"""
23
+ def __init__(self, use_redis=True):
24
+ self.use_redis = use_redis
25
+
26
+ def get(self, key, default=None):
27
+ config = {
28
+ 'FILTER_CLASS': 'crawlo.filters.memory_filter.MemoryFilter',
29
+ 'LOG_LEVEL': 'INFO',
30
+ 'DEPTH_PRIORITY': 1,
31
+ 'SCHEDULER_MAX_QUEUE_SIZE': 100,
32
+ 'SCHEDULER_QUEUE_NAME': 'test:crawlo:requests',
33
+ 'FILTER_DEBUG': False,
34
+ 'PROJECT_NAME': 'test',
35
+ }
36
+ if self.use_redis:
37
+ config['REDIS_URL'] = 'redis://localhost:6379/0'
38
+
39
+ return config.get(key, default)
40
+
41
+ def get_int(self, key, default=0):
42
+ value = self.get(key, default)
43
+ return int(value) if value is not None else default
44
+
45
+ def get_bool(self, key, default=False):
46
+ value = self.get(key, default)
47
+ if isinstance(value, bool):
48
+ return value
49
+ if isinstance(value, str):
50
+ return value.lower() in ('true', '1', 'yes')
51
+ return bool(value) if value is not None else default
52
+
53
+
54
+ class MockFilter:
55
+ """模拟去重过滤器"""
56
+ def __init__(self):
57
+ self.seen = set()
58
+
59
+ @classmethod
60
+ def create_instance(cls, crawler):
61
+ return cls()
62
+
63
+ async def requested(self, request):
64
+ if request.url in self.seen:
65
+ return True
66
+ self.seen.add(request.url)
67
+ return False
68
+
69
+ def log_stats(self, request):
70
+ pass
71
+
72
+
73
+ async def test_memory_scheduler():
74
+ """测试内存调度器"""
75
+ print("🔍 测试内存调度器...")
76
+
77
+ crawler = MockCrawler(use_redis=False)
78
+ scheduler = Scheduler.create_instance(crawler)
79
+
80
+ # 模拟去重过滤器
81
+ scheduler.dupe_filter = MockFilter()
82
+
83
+ scheduler.open()
84
+
85
+ # 测试入队
86
+ request1 = Request(url="https://example1.com")
87
+ request2 = Request(url="https://example2.com")
88
+
89
+ success1 = await scheduler.enqueue_request(request1)
90
+ success2 = await scheduler.enqueue_request(request2)
91
+
92
+ print(f" 📤 入队结果: {success1}, {success2}")
93
+ print(f" 📊 队列大小: {len(scheduler)}")
94
+
95
+ # 测试出队
96
+ req1 = await scheduler.next_request()
97
+ req2 = await scheduler.next_request()
98
+
99
+ print(f" 📥 出队结果: {req1.url if req1 else None}, {req2.url if req2 else None}")
100
+ print(f" 📊 剩余大小: {len(scheduler)}")
101
+
102
+ await scheduler.close()
103
+ print(" ✅ 内存调度器测试完成")
104
+
105
+
106
+ async def test_redis_scheduler():
107
+ """测试 Redis 调度器"""
108
+ print("🔍 测试 Redis 调度器...")
109
+
110
+ try:
111
+ crawler = MockCrawler(use_redis=True)
112
+ scheduler = Scheduler.create_instance(crawler)
113
+
114
+ # 模拟去重过滤器
115
+ scheduler.dupe_filter = MockFilter()
116
+
117
+ scheduler.open()
118
+
119
+ # 测试入队
120
+ request1 = Request(url="https://redis-test1.com", priority=5)
121
+ request2 = Request(url="https://redis-test2.com", priority=3)
122
+ request3 = Request(url="https://redis-test3.com", priority=8)
123
+
124
+ success1 = await scheduler.enqueue_request(request1)
125
+ success2 = await scheduler.enqueue_request(request2)
126
+ success3 = await scheduler.enqueue_request(request3)
127
+
128
+ print(f" 📤 入队结果: {success1}, {success2}, {success3}")
129
+ print(f" 📊 队列大小: {len(scheduler)}")
130
+
131
+ # 等待一小段时间让 Redis 操作完成
132
+ await asyncio.sleep(0.5)
133
+
134
+ # 测试出队(应该按优先级排序)
135
+ req1 = await scheduler.next_request()
136
+ req2 = await scheduler.next_request()
137
+ req3 = await scheduler.next_request()
138
+
139
+ print(" 📥 出队结果(按优先级):")
140
+ if req1:
141
+ print(f" {req1.url} (优先级: {getattr(req1, 'priority', 0)})")
142
+ if req2:
143
+ print(f" {req2.url} (优先级: {getattr(req2, 'priority', 0)})")
144
+ if req3:
145
+ print(f" {req3.url} (优先级: {getattr(req3, 'priority', 0)})")
146
+
147
+ print(f" 📊 剩余大小: {len(scheduler)}")
148
+
149
+ await scheduler.close()
150
+ print(" ✅ Redis 调度器测试完成")
151
+
152
+ except Exception as e:
153
+ print(f" ❌ Redis 调度器测试失败: {e}")
154
+ import traceback
155
+ traceback.print_exc()
156
+
157
+
158
+ async def test_concurrent_redis():
159
+ """测试并发 Redis 操作"""
160
+ print("🔍 测试并发 Redis 操作...")
161
+
162
+ async def producer(scheduler, name, count):
163
+ """生产者"""
164
+ for i in range(count):
165
+ request = Request(url=f"https://{name}-{i}.com", priority=i % 10)
166
+ await scheduler.enqueue_request(request)
167
+ await asyncio.sleep(0.01)
168
+ print(f" ✅ 生产者 {name} 完成 ({count} 个请求)")
169
+
170
+ async def consumer(scheduler, name, count):
171
+ """消费者"""
172
+ consumed = 0
173
+ for _ in range(count):
174
+ request = await scheduler.next_request()
175
+ if request:
176
+ consumed += 1
177
+ await asyncio.sleep(0.005)
178
+ else:
179
+ break
180
+ print(f" ✅ 消费者 {name} 处理了 {consumed} 个请求")
181
+
182
+ try:
183
+ crawler = MockCrawler(use_redis=True)
184
+ scheduler = Scheduler.create_instance(crawler)
185
+ scheduler.dupe_filter = MockFilter()
186
+ scheduler.open()
187
+
188
+ # 并发运行生产者和消费者
189
+ tasks = [
190
+ producer(scheduler, "producer-1", 5),
191
+ producer(scheduler, "producer-2", 5),
192
+ consumer(scheduler, "consumer-1", 3),
193
+ consumer(scheduler, "consumer-2", 3),
194
+ consumer(scheduler, "consumer-3", 4),
195
+ ]
196
+
197
+ await asyncio.gather(*tasks, return_exceptions=True)
198
+
199
+ print(f" 📊 最终队列大小: {len(scheduler)}")
200
+
201
+ await scheduler.close()
202
+ print(" ✅ 并发测试完成")
203
+
204
+ except Exception as e:
205
+ print(f" ❌ 并发测试失败: {e}")
206
+ import traceback
207
+ traceback.print_exc()
208
+
209
+
210
+ async def main():
211
+ """主测试函数"""
212
+ print("🚀 开始测试修复后的 Scheduler...")
213
+ print("=" * 50)
214
+
215
+ try:
216
+ # 1. 测试内存调度器
217
+ await test_memory_scheduler()
218
+ print()
219
+
220
+ # 2. 测试 Redis 调度器
221
+ await test_redis_scheduler()
222
+ print()
223
+
224
+ # 3. 测试并发操作
225
+ await test_concurrent_redis()
226
+
227
+ print("=" * 50)
228
+ print("🎉 所有 Scheduler 测试完成!")
229
+
230
+ except Exception as e:
231
+ print("=" * 50)
232
+ print(f"❌ 测试失败: {e}")
233
+ import traceback
234
+ traceback.print_exc()
235
+
236
+
237
+ if __name__ == "__main__":
238
+ # 设置日志级别避免过多输出
239
+ import logging
240
+ logging.getLogger('crawlo').setLevel(logging.WARNING)
241
+
242
242
  asyncio.run(main())
@@ -1,108 +0,0 @@
1
- crawlo/__init__.py,sha256=esOolburYDjtF43D5N9Kh6TSQW2yKcz888ilhBSinBc,825
2
- crawlo/__version__.py,sha256=5SgGjThsHu_ITn8V83BvCziqCwxdXxTQqcC3KQMHPfM,22
3
- crawlo/cli.py,sha256=CtR2Pfa7SyRxEKPaXqt-6E6K5Vq5z3rfdAI95UO4cbU,1166
4
- crawlo/config.py,sha256=i0Amz6wNPgv_aVcdCBRRlcwuZLSa87cH9OEmTQvB97Q,8329
5
- crawlo/crawler.py,sha256=v6i5tjgSOtbMoqiw1qdgKx1cY4kcVcd5l5bUTWtJNNU,36461
6
- crawlo/event.py,sha256=7-y6HNv_EIJSYQNzsj0mVK-Gg4ON3wdQeMdQjfFJPlw,313
7
- crawlo/exceptions.py,sha256=pthF1lJlJHyRZm-mE6NAo5WzK3GYJqmRqIuIlK1Odx8,1129
8
- crawlo/mode_manager.py,sha256=WIxrq9S3EAH0D71LH1AxvcqXomeABqoXgtUN4A--DKY,6702
9
- crawlo/project.py,sha256=xWN2eTAjf_Pza-wWvvV4JjScQRWxe9hXlztX81ccUMc,5182
10
- crawlo/stats_collector.py,sha256=NkO09CB-220qz5rxFcD_dedGfr2VPFrDo4hya0Zh8Qc,1577
11
- crawlo/subscriber.py,sha256=3d4eYtkSgPj-18-mTZM6RQLSil-ux13FUcmfFxr3sMk,3730
12
- crawlo/task_manager.py,sha256=19InAxS9oJ9EMj20Aw2urN-v6BeC22dkgPuW-B9-4UI,819
13
- crawlo/commands/__init__.py,sha256=AMYjXG7ulE8dPVmgWVo0uqXsaCYUUZYmmu2-7kFzH1M,342
14
- crawlo/commands/check.py,sha256=172OiAxnX5wwSlszUsyPgMZwAoIbGDTdfhtRz309ilc,22843
15
- crawlo/commands/genspider.py,sha256=-jGJdfXLsefX_H1ydQ2wirdu6p6wmhClzVXY_0L-1aE,5050
16
- crawlo/commands/list.py,sha256=yByqQeZBgvjewOKxpnOobpeJ7Hnbs-CWsoyITqZu2ZY,5781
17
- crawlo/commands/run.py,sha256=8Qngjsl8Q4RBdO39a__wKGsheY2PFuPit2hds_jwEbM,10524
18
- crawlo/commands/startproject.py,sha256=bzNgpkKzUEggY2m7Iw810mSPe8wOPFBqSCO0jZX3z_g,7138
19
- crawlo/commands/stats.py,sha256=6pAgkEi8MBnCer2rWmKpaTYr1jaM6HeMG9owAvEzJyY,6064
20
- crawlo/commands/utils.py,sha256=nohMvUU2zLvX0XzXk6KeCNxP0EvSWj9DiVLxM_7tD5o,5106
21
- crawlo/core/__init__.py,sha256=PnFyJdVNHBoPmV1sW0AHQXijeoSTQ8cMYrbNM1JK8kA,41
22
- crawlo/core/engine.py,sha256=8Dcew1XyxChW5Fz1wFEWpJlPrQb2hKDWKul8e61S-Q0,6662
23
- crawlo/core/enhanced_engine.py,sha256=9I9Uxdy2oAz8zDGTzEiytuKu__VDVmIN8zwZKfrD8bw,6254
24
- crawlo/core/processor.py,sha256=qmCqAeqhwYu-UE86evYesaGt9qpuSIfH-ZIZKcXFCZc,1140
25
- crawlo/core/scheduler.py,sha256=iNZl47PvurnLLXRZN8Jfj1un6YP2q9m5n56X3Eb7_A8,5615
26
- crawlo/downloader/__init__.py,sha256=tl0mE54reR-PuJYSsXsKP2VY5uzvq4lITxZwKKjNzPs,7663
27
- crawlo/downloader/aiohttp_downloader.py,sha256=UKupGYPOWrscAVsjhFgKYElTa9tbEeltqV7nuWqjIeE,8005
28
- crawlo/downloader/cffi_downloader.py,sha256=-GVfSIhi1Ip56suSiGf8jnUE2EBF1P56vw0uxLh_T6I,10440
29
- crawlo/downloader/httpx_downloader.py,sha256=FJcdE3BoxUYFQDPm3quaveSjweAKfAQRaeJm1hQViLg,12003
30
- crawlo/extension/__init__.py,sha256=PEBbMxi6ULBZ9ivEJ4T7IH_R376BQJ6Rz_D9Ce-Cqbs,1133
31
- crawlo/extension/log_interval.py,sha256=S-hSoiz9GdmgHrac4vDQ52fleoBcH-kzdPUD8YRAons,1922
32
- crawlo/extension/log_stats.py,sha256=VinABjzuFa-JmNXSX86gQ_3Oyx1y3vUhpWTEu9HRRqg,1677
33
- crawlo/extension/logging_extension.py,sha256=Jce2HHc9ejsIWQitkHZuhnLbT_1MIfcvywfzYkkJ5eY,1202
34
- crawlo/filters/__init__.py,sha256=XC_Q4ykZtSNYizYlAcehVwBBNO3lZ2zuWwafzXiuWyQ,4241
35
- crawlo/filters/aioredis_filter.py,sha256=3vbPOY3L_H7TUgL8K6AtaP6QDtoIg5xpE70Kxpil6dM,8376
36
- crawlo/filters/memory_filter.py,sha256=VJO0UFRYGxmV8dj4G1subsQ-FtvPcGLbvd7IVtqXnOs,9260
37
- crawlo/items/__init__.py,sha256=bqekZrRlDhxfWie0UbCs656TptYseoe9QJ67I4E7Elk,386
38
- crawlo/items/base.py,sha256=tAYrPJgblp3ZEihDXvappdYc6pGdim6x2_9QSmMKI2o,577
39
- crawlo/items/fields.py,sha256=wMlakQTsEwyrlLzMt1gI4pScLQZMqd3E1xcfH4dbSqk,1801
40
- crawlo/items/items.py,sha256=e-3nXI9ckD64vcDxxQiAU6ufbtJMs09gbZQcYjxgwHY,3374
41
- crawlo/middleware/__init__.py,sha256=ldaGFNbiJnK9Fx12Vdf9fDNfzXxoETtShp5r-vodtw0,549
42
- crawlo/middleware/default_header.py,sha256=i_Uj07JObyeZFxL7ZAZmvZsHvA1HGtkNab1sA0d-nWI,1067
43
- crawlo/middleware/download_delay.py,sha256=2M-TchDA7MwyTfYy0Hzh_bW9wlHlpiP-oQlys7crTj0,966
44
- crawlo/middleware/middleware_manager.py,sha256=j1hkWRFB5rnC5SnB7oXWE5eUNv8blS9krDIDM5fIDs8,6213
45
- crawlo/middleware/proxy.py,sha256=m2ZZ50En9hUtgrqSqA6hItGT74xMqccHFPhZshutIco,9811
46
- crawlo/middleware/request_ignore.py,sha256=QI2z4fUnJ-4xvPTZAmsL-GqR4RFHS1xq9iDr5KFrMco,997
47
- crawlo/middleware/response_code.py,sha256=tmef2QVl3JCiTMii6VQkASlOY2OyqmOPoOfNxIK1eF8,659
48
- crawlo/middleware/response_filter.py,sha256=ep8ZxDlfIefi9YqK8dPASEp5TTDRo9QEY_jMceC411s,837
49
- crawlo/middleware/retry.py,sha256=pH4fdW71DwQzMY7APutX7yqtvSTAoznYeM3ux2EOT7E,4146
50
- crawlo/network/__init__.py,sha256=BLPERYPo22g1BXrW--wUnlolrdFUmOPjgOB8XQQJlck,397
51
- crawlo/network/request.py,sha256=5bzXJJWcAgGngNos-k4eIh9QaJdnGw0_SLgdrNt_0-4,11103
52
- crawlo/network/response.py,sha256=M0iG8ggcEpFzN7aAinKwVbxHAhANLYj8Zp4-FwaTpYo,9812
53
- crawlo/pipelines/__init__.py,sha256=Tvs9FQ_2qz8GcmoEqLrz_YFZrRpL3gGIssiI5Ce9b5I,254
54
- crawlo/pipelines/console_pipeline.py,sha256=KABkR3J-rqO0Awox7lizxKR2XuHfVhWPiVRgIybwwu4,1248
55
- crawlo/pipelines/csv_pipeline.py,sha256=6FBT2AoU6iNU-5NfgWRq7-JpF9dK2nBokjxx-y4jIas,12174
56
- crawlo/pipelines/json_pipeline.py,sha256=vlu1nqbD2mtqtExt9cL5nibx1CwJM1RNqd4WGjZRHAY,8367
57
- crawlo/pipelines/mongo_pipeline.py,sha256=lv-Zn_mWdE_jVy7Nh30Lzqm3YhtLRV5rMy-m4rBWYe0,4442
58
- crawlo/pipelines/mysql_pipeline.py,sha256=6g6PGTwAyzH5VStlPAg2SdG5t1lPw1Zu-cY7x6Mz16s,7861
59
- crawlo/pipelines/pipeline_manager.py,sha256=VrbebOYiqrobtKhp5II18w-odCICdWkmRg5WPK0Emz4,2112
60
- crawlo/queue/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
61
- crawlo/queue/pqueue.py,sha256=yzF900ko2RReVNZtfk_VV3PzSXEUALI6SHf97geuu6s,1058
62
- crawlo/queue/queue_manager.py,sha256=OQ9YBbc9Y4uE_5WbQhe233FFdhaeiOhDVbqWF7ev42U,11303
63
- crawlo/queue/redis_priority_queue.py,sha256=hf7hiIiRS-2DIq1bIJbs1yLEZjuMnHwc-n2_I7PlE9A,7294
64
- crawlo/settings/__init__.py,sha256=xsukVKn_h2Hopm1Nj-bXkhbfyS62QTTvJi7fhZUwR9M,123
65
- crawlo/settings/default_settings.py,sha256=jRM_Cqt3tQ7V4mgqBTAIQY3BcfGsLkKdvW1TcbWHv48,9627
66
- crawlo/settings/setting_manager.py,sha256=SxKB1aCWh4OySM_bH9cYng9I3PAmrSP-Q8XOZEWEwbI,2899
67
- crawlo/spider/__init__.py,sha256=Z_rK23l5yt-DuwJPg8bcqodM_FIs4-iHLaKOimGumcE,20452
68
- crawlo/templates/crawlo.cfg.tmpl,sha256=9BAmwEibS5Tvy6HIcGXPb0BGeuesmibebmTW0iAEkmo,230
69
- crawlo/templates/project/__init__.py.tmpl,sha256=f3ETIXw_O6K-lkL6lXM5znMPJW1FZYGFrwDs2BnHcnQ,58
70
- crawlo/templates/project/items.py.tmpl,sha256=3h-4nuneUoCAGUzSLyLNsdgeAAUXzz4rV0QctzCkIJA,301
71
- crawlo/templates/project/middlewares.py.tmpl,sha256=Ua2vG3WXliMBSmwsbYaSwzx2lZPw9vLrG2dLqtZWGRg,3157
72
- crawlo/templates/project/pipelines.py.tmpl,sha256=-dxK7T396AVTbh0FhivLDZq4lKxw3p1-5Y6Ij4jgImE,12041
73
- crawlo/templates/project/run.py.tmpl,sha256=RQ_k_B-Pp1R853-N_58yUGjIouXa6ipBtUPQenLjswE,7519
74
- crawlo/templates/project/settings.py.tmpl,sha256=NxPvXGnomTV5NkczPIC7Tscn2vjmHUE4CYmbQB2SmDQ,7884
75
- crawlo/templates/project/spiders/__init__.py.tmpl,sha256=j_YKsw6HQMJyqlk3WUouP3bsr-XVxshRoSNakHBc00g,106
76
- crawlo/templates/spider/spider.py.tmpl,sha256=Wx1yMBsqDQvJGb9HoEVecX6XZcVrJiBj9blXYrernTo,6167
77
- crawlo/utils/__init__.py,sha256=BDORpyjMN7VGPKImnCDKSkprS-petgD7ezc9rMlBvb0,123
78
- crawlo/utils/controlled_spider_mixin.py,sha256=BpH76XxBJtYQ0rmCX6vrG-8gQXT9-LP65ibetzfqncU,12500
79
- crawlo/utils/date_tools.py,sha256=0yG0tzGb1VFgWDJJ_cow2LJfz3kj_w2MqSjmfKKESl8,6961
80
- crawlo/utils/db_helper.py,sha256=3ib5-agrlwf2t5S_QtLRYH75wvJDlYbRqRmDEbpH5Bo,10559
81
- crawlo/utils/func_tools.py,sha256=WUZEGpWMuDDX7g-QySM7iaiC74erW2SSkZoUvDw1NjM,2369
82
- crawlo/utils/large_scale_config.py,sha256=j7wQ5ty7pQlBRygw2vhRJ7OI19RYBZKPfYMP3WeF2WI,8154
83
- crawlo/utils/large_scale_helper.py,sha256=JJqcGSI6VaVe3MSL6IWjmCp8XQIu6T4U-BvBLSttr_s,12157
84
- crawlo/utils/log.py,sha256=A3lPyhD8kD88cV23KOL-_eT8g69xGQ5L1toDB2AO0mc,4005
85
- crawlo/utils/queue_helper.py,sha256=xpUUTOqlU1xz2Pb9NKAVGo3AfAO-7Xvx8Lm1q65Dgck,4743
86
- crawlo/utils/request.py,sha256=yoLB2rY8d78vgPjIWpdhY5SalIKjyLIvTG_UH6EMdVI,8798
87
- crawlo/utils/request_serializer.py,sha256=bPoSQqE2ksiMyP3WiPB3w3UqZs4f_LgkAw4Pj0qyBDo,8565
88
- crawlo/utils/spider_loader.py,sha256=pEDUsYOTGjszA6KgjiMlYN4GS5fP4uakkhcp3JTFFQY,2187
89
- crawlo/utils/system.py,sha256=HvWV1acxou0Rn0L7pNq4CnV_GWFeU0Tmjy3_nLD8M64,237
90
- crawlo/utils/tools.py,sha256=5Uv25Wy4m_ndZY0-n-eX-t3PxvaZ6wR3-Wvx-o7_Vrs,271
91
- crawlo/utils/url.py,sha256=rlgX2VlJv6JvLmCDTsbxzMSXE6R5ZL_0dLEqprsA-JU,1482
92
- examples/__init__.py,sha256=6i631BPnS_TR_BWUjtjB5CBO-zv9kRkwQTQvSya2wHE,123
93
- tests/__init__.py,sha256=scL1IPVT1iucth7v8ffrjRdeW7QrC_Y7AMmFVMdTY1Y,129
94
- tests/test_final_validation.py,sha256=fBxf_6YcAEa_HyV_oGAXmmVHY4i6FdA4J6klCmc36hQ,4925
95
- tests/test_proxy_health_check.py,sha256=xo3QMP1YNw9hu7JDHZOYCUZmFFKLJpHSh4SbxXhCRPQ,1091
96
- tests/test_proxy_middleware_integration.py,sha256=zcl7fR9Toc-I-stSUTzKZPwcfh3kgrpjI5SbkZ6AVmE,4305
97
- tests/test_proxy_providers.py,sha256=XwWZCywTYguSsUxSm6fsbaoH1p9dKjqSIx9-sqKZehA,1693
98
- tests/test_proxy_stats.py,sha256=Til_yksrRz2yBVw-yJi5-36LhNW3vTwpXTm4BdR9PUM,507
99
- tests/test_proxy_strategies.py,sha256=ZkziozkvZd3KWOQnpHQ8Upd3WpyoX7gN0qFGluNm348,1809
100
- tests/test_redis_config.py,sha256=TqzFRojc6esGXjGhUCvSLYQDUTAgEJsty9vRVuNraMU,893
101
- tests/test_redis_queue.py,sha256=o6xViXxJcdx-1eMcG3vhAQEIm8h346HnZb7JXs7ZjwM,6622
102
- tests/test_request_serialization.py,sha256=8sVdppAsohJ5u-m1WvablCndwL-M_36YPLdGKwgeznM,2289
103
- tests/test_scheduler.py,sha256=-FOkTWzaMdr6yfO1Msu74hI_GgSfD7iRxO-cFA-9Iyk,7442
104
- crawlo-1.1.2.dist-info/METADATA,sha256=fIXPyz2xk3GN82z5693BePRT1OWvul312NOh41CBRXA,17061
105
- crawlo-1.1.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
106
- crawlo-1.1.2.dist-info/entry_points.txt,sha256=5HoVoTSPxI8SCa5B7pQYxLSrkOdiunyO9tqNsLMv52g,43
107
- crawlo-1.1.2.dist-info/top_level.txt,sha256=keG_67pbZ_wZL2dmDRA9RMaNHTaV_x_oxZ9DKNgwvR0,22
108
- crawlo-1.1.2.dist-info/RECORD,,
File without changes