crawlo 1.2.6__py3-none-any.whl → 1.2.7__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.
- crawlo/__init__.py +61 -61
- crawlo/__version__.py +1 -1
- crawlo/cleaners/__init__.py +60 -60
- crawlo/cleaners/data_formatter.py +225 -225
- crawlo/cleaners/encoding_converter.py +125 -125
- crawlo/cleaners/text_cleaner.py +232 -232
- crawlo/cli.py +75 -88
- crawlo/commands/__init__.py +14 -14
- crawlo/commands/check.py +594 -594
- crawlo/commands/genspider.py +151 -151
- crawlo/commands/help.py +138 -144
- crawlo/commands/list.py +155 -155
- crawlo/commands/run.py +323 -323
- crawlo/commands/startproject.py +436 -436
- crawlo/commands/stats.py +187 -187
- crawlo/commands/utils.py +186 -186
- crawlo/config.py +312 -312
- crawlo/config_validator.py +251 -251
- crawlo/core/__init__.py +2 -2
- crawlo/core/engine.py +365 -356
- crawlo/core/processor.py +40 -40
- crawlo/core/scheduler.py +251 -239
- crawlo/crawler.py +1099 -1110
- crawlo/data/__init__.py +5 -5
- crawlo/data/user_agents.py +107 -107
- crawlo/downloader/__init__.py +266 -266
- crawlo/downloader/aiohttp_downloader.py +228 -221
- crawlo/downloader/cffi_downloader.py +256 -256
- crawlo/downloader/httpx_downloader.py +259 -259
- crawlo/downloader/hybrid_downloader.py +212 -212
- crawlo/downloader/playwright_downloader.py +402 -402
- crawlo/downloader/selenium_downloader.py +472 -472
- crawlo/event.py +11 -11
- crawlo/exceptions.py +81 -81
- crawlo/extension/__init__.py +39 -38
- crawlo/extension/health_check.py +141 -141
- crawlo/extension/log_interval.py +57 -57
- crawlo/extension/log_stats.py +81 -81
- crawlo/extension/logging_extension.py +43 -43
- crawlo/extension/memory_monitor.py +104 -104
- crawlo/extension/performance_profiler.py +133 -133
- crawlo/extension/request_recorder.py +107 -107
- crawlo/filters/__init__.py +154 -154
- crawlo/filters/aioredis_filter.py +234 -234
- crawlo/filters/memory_filter.py +269 -269
- crawlo/items/__init__.py +23 -23
- crawlo/items/base.py +21 -21
- crawlo/items/fields.py +52 -52
- crawlo/items/items.py +104 -104
- crawlo/middleware/__init__.py +21 -21
- crawlo/middleware/default_header.py +131 -131
- crawlo/middleware/download_delay.py +104 -104
- crawlo/middleware/middleware_manager.py +136 -135
- crawlo/middleware/offsite.py +114 -114
- crawlo/middleware/proxy.py +367 -367
- crawlo/middleware/request_ignore.py +86 -86
- crawlo/middleware/response_code.py +163 -163
- crawlo/middleware/response_filter.py +136 -136
- crawlo/middleware/retry.py +124 -124
- crawlo/mode_manager.py +211 -211
- crawlo/network/__init__.py +21 -21
- crawlo/network/request.py +338 -338
- crawlo/network/response.py +359 -359
- crawlo/pipelines/__init__.py +21 -21
- crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
- crawlo/pipelines/console_pipeline.py +39 -39
- crawlo/pipelines/csv_pipeline.py +316 -316
- crawlo/pipelines/database_dedup_pipeline.py +222 -222
- crawlo/pipelines/json_pipeline.py +218 -218
- crawlo/pipelines/memory_dedup_pipeline.py +115 -115
- crawlo/pipelines/mongo_pipeline.py +131 -131
- crawlo/pipelines/mysql_pipeline.py +317 -317
- crawlo/pipelines/pipeline_manager.py +62 -61
- crawlo/pipelines/redis_dedup_pipeline.py +166 -165
- crawlo/project.py +314 -279
- crawlo/queue/pqueue.py +37 -37
- crawlo/queue/queue_manager.py +377 -376
- crawlo/queue/redis_priority_queue.py +306 -306
- crawlo/settings/__init__.py +7 -7
- crawlo/settings/default_settings.py +219 -215
- crawlo/settings/setting_manager.py +122 -122
- crawlo/spider/__init__.py +639 -639
- crawlo/stats_collector.py +59 -59
- crawlo/subscriber.py +129 -129
- crawlo/task_manager.py +30 -30
- crawlo/templates/crawlo.cfg.tmpl +10 -10
- crawlo/templates/project/__init__.py.tmpl +3 -3
- crawlo/templates/project/items.py.tmpl +17 -17
- crawlo/templates/project/middlewares.py.tmpl +118 -118
- crawlo/templates/project/pipelines.py.tmpl +96 -96
- crawlo/templates/project/settings.py.tmpl +288 -288
- crawlo/templates/project/settings_distributed.py.tmpl +157 -157
- crawlo/templates/project/settings_gentle.py.tmpl +100 -100
- crawlo/templates/project/settings_high_performance.py.tmpl +134 -134
- crawlo/templates/project/settings_simple.py.tmpl +98 -98
- crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
- crawlo/templates/run.py.tmpl +45 -45
- crawlo/templates/spider/spider.py.tmpl +143 -143
- crawlo/tools/__init__.py +182 -182
- crawlo/tools/anti_crawler.py +268 -268
- crawlo/tools/authenticated_proxy.py +240 -240
- crawlo/tools/data_validator.py +180 -180
- crawlo/tools/date_tools.py +35 -35
- crawlo/tools/distributed_coordinator.py +386 -386
- crawlo/tools/retry_mechanism.py +220 -220
- crawlo/tools/scenario_adapter.py +262 -262
- crawlo/utils/__init__.py +35 -35
- crawlo/utils/batch_processor.py +259 -259
- crawlo/utils/controlled_spider_mixin.py +439 -439
- crawlo/utils/date_tools.py +290 -290
- crawlo/utils/db_helper.py +343 -343
- crawlo/utils/enhanced_error_handler.py +356 -356
- crawlo/utils/env_config.py +143 -106
- crawlo/utils/error_handler.py +123 -123
- crawlo/utils/func_tools.py +82 -82
- crawlo/utils/large_scale_config.py +286 -286
- crawlo/utils/large_scale_helper.py +344 -344
- crawlo/utils/log.py +128 -128
- crawlo/utils/performance_monitor.py +285 -285
- crawlo/utils/queue_helper.py +175 -175
- crawlo/utils/redis_connection_pool.py +351 -351
- crawlo/utils/redis_key_validator.py +198 -198
- crawlo/utils/request.py +267 -267
- crawlo/utils/request_serializer.py +218 -218
- crawlo/utils/spider_loader.py +61 -61
- crawlo/utils/system.py +11 -11
- crawlo/utils/tools.py +4 -4
- crawlo/utils/url.py +39 -39
- {crawlo-1.2.6.dist-info → crawlo-1.2.7.dist-info}/METADATA +764 -764
- crawlo-1.2.7.dist-info/RECORD +209 -0
- examples/__init__.py +7 -7
- tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
- tests/__init__.py +7 -7
- tests/advanced_tools_example.py +275 -275
- tests/authenticated_proxy_example.py +236 -236
- tests/cleaners_example.py +160 -160
- tests/config_validation_demo.py +102 -102
- tests/controlled_spider_example.py +205 -205
- tests/date_tools_example.py +180 -180
- tests/dynamic_loading_example.py +523 -523
- tests/dynamic_loading_test.py +104 -104
- tests/env_config_example.py +133 -133
- tests/error_handling_example.py +171 -171
- tests/redis_key_validation_demo.py +130 -130
- tests/response_improvements_example.py +144 -144
- tests/test_advanced_tools.py +148 -148
- tests/test_all_redis_key_configs.py +145 -145
- tests/test_authenticated_proxy.py +141 -141
- tests/test_cleaners.py +54 -54
- tests/test_comprehensive.py +146 -146
- tests/test_config_consistency.py +81 -0
- tests/test_config_validator.py +193 -193
- tests/test_crawlo_proxy_integration.py +172 -172
- tests/test_date_tools.py +123 -123
- tests/test_default_header_middleware.py +158 -158
- tests/test_double_crawlo_fix.py +207 -207
- tests/test_double_crawlo_fix_simple.py +124 -124
- tests/test_download_delay_middleware.py +221 -221
- tests/test_downloader_proxy_compatibility.py +268 -268
- tests/test_dynamic_downloaders_proxy.py +124 -124
- tests/test_dynamic_proxy.py +92 -92
- tests/test_dynamic_proxy_config.py +146 -146
- tests/test_dynamic_proxy_real.py +109 -109
- tests/test_edge_cases.py +303 -303
- tests/test_enhanced_error_handler.py +270 -270
- tests/test_env_config.py +121 -121
- tests/test_error_handler_compatibility.py +112 -112
- tests/test_final_validation.py +153 -153
- tests/test_framework_env_usage.py +103 -103
- tests/test_integration.py +356 -356
- tests/test_item_dedup_redis_key.py +122 -122
- tests/test_mode_consistency.py +52 -0
- tests/test_offsite_middleware.py +221 -221
- tests/test_parsel.py +29 -29
- tests/test_performance.py +327 -327
- tests/test_proxy_api.py +264 -264
- tests/test_proxy_health_check.py +32 -32
- tests/test_proxy_middleware.py +121 -121
- tests/test_proxy_middleware_enhanced.py +216 -216
- tests/test_proxy_middleware_integration.py +136 -136
- tests/test_proxy_providers.py +56 -56
- tests/test_proxy_stats.py +19 -19
- tests/test_proxy_strategies.py +59 -59
- tests/test_queue_manager_double_crawlo.py +173 -173
- tests/test_queue_manager_redis_key.py +176 -176
- tests/test_real_scenario_proxy.py +195 -195
- tests/test_redis_config.py +28 -28
- tests/test_redis_connection_pool.py +294 -294
- tests/test_redis_key_naming.py +181 -181
- tests/test_redis_key_validator.py +123 -123
- tests/test_redis_queue.py +224 -224
- tests/test_request_ignore_middleware.py +182 -182
- tests/test_request_serialization.py +70 -70
- tests/test_response_code_middleware.py +349 -349
- tests/test_response_filter_middleware.py +427 -427
- tests/test_response_improvements.py +152 -152
- tests/test_retry_middleware.py +241 -241
- tests/test_scheduler.py +252 -241
- tests/test_scheduler_config_update.py +134 -0
- tests/test_simple_response.py +61 -61
- tests/test_telecom_spider_redis_key.py +205 -205
- tests/test_template_content.py +87 -87
- tests/test_template_redis_key.py +134 -134
- tests/test_tools.py +153 -153
- tests/tools_example.py +257 -257
- crawlo-1.2.6.dist-info/RECORD +0 -206
- {crawlo-1.2.6.dist-info → crawlo-1.2.7.dist-info}/WHEEL +0 -0
- {crawlo-1.2.6.dist-info → crawlo-1.2.7.dist-info}/entry_points.txt +0 -0
- {crawlo-1.2.6.dist-info → crawlo-1.2.7.dist-info}/top_level.txt +0 -0
crawlo/pipelines/__init__.py
CHANGED
|
@@ -1,22 +1,22 @@
|
|
|
1
|
-
#!/usr/bin/python
|
|
2
|
-
# -*- coding:UTF-8 -*-
|
|
3
|
-
from crawlo.items import Item
|
|
4
|
-
|
|
5
|
-
|
|
6
|
-
class BasePipeline:
|
|
7
|
-
|
|
8
|
-
def process_item(self, item: Item, spider):
|
|
9
|
-
raise NotImplementedError
|
|
10
|
-
|
|
11
|
-
@classmethod
|
|
12
|
-
def create_instance(cls, crawler):
|
|
13
|
-
return cls()
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
# 导出去重管道
|
|
17
|
-
from .memory_dedup_pipeline import MemoryDedupPipeline
|
|
18
|
-
from .redis_dedup_pipeline import RedisDedupPipeline
|
|
19
|
-
from .bloom_dedup_pipeline import BloomDedupPipeline
|
|
20
|
-
from .database_dedup_pipeline import DatabaseDedupPipeline
|
|
21
|
-
|
|
1
|
+
#!/usr/bin/python
|
|
2
|
+
# -*- coding:UTF-8 -*-
|
|
3
|
+
from crawlo.items import Item
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
class BasePipeline:
|
|
7
|
+
|
|
8
|
+
def process_item(self, item: Item, spider):
|
|
9
|
+
raise NotImplementedError
|
|
10
|
+
|
|
11
|
+
@classmethod
|
|
12
|
+
def create_instance(cls, crawler):
|
|
13
|
+
return cls()
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
# 导出去重管道
|
|
17
|
+
from .memory_dedup_pipeline import MemoryDedupPipeline
|
|
18
|
+
from .redis_dedup_pipeline import RedisDedupPipeline
|
|
19
|
+
from .bloom_dedup_pipeline import BloomDedupPipeline
|
|
20
|
+
from .database_dedup_pipeline import DatabaseDedupPipeline
|
|
21
|
+
|
|
22
22
|
__all__ = ['BasePipeline', 'MemoryDedupPipeline', 'RedisDedupPipeline', 'BloomDedupPipeline', 'DatabaseDedupPipeline']
|
|
@@ -1,157 +1,157 @@
|
|
|
1
|
-
#!/usr/bin/python
|
|
2
|
-
# -*- coding:UTF-8 -*-
|
|
3
|
-
"""
|
|
4
|
-
基于 Bloom Filter 的数据项去重管道
|
|
5
|
-
=============================
|
|
6
|
-
提供大规模数据采集场景下的高效去重功能,使用概率性数据结构节省内存。
|
|
7
|
-
|
|
8
|
-
特点:
|
|
9
|
-
- 内存效率高: 相比传统集合节省大量内存
|
|
10
|
-
- 高性能: 快速的插入和查找操作
|
|
11
|
-
- 可扩展: 支持自定义容量和误判率
|
|
12
|
-
- 适用性广: 特别适合大规模数据采集
|
|
13
|
-
|
|
14
|
-
注意: Bloom Filter 有误判率,可能会错误地丢弃一些未见过的数据项。
|
|
15
|
-
"""
|
|
16
|
-
|
|
17
|
-
import hashlib
|
|
18
|
-
try:
|
|
19
|
-
from pybloom_live import BloomFilter
|
|
20
|
-
BLOOM_FILTER_AVAILABLE = True
|
|
21
|
-
except ImportError:
|
|
22
|
-
# 如果没有安装 pybloom_live,使用简单的替代方案
|
|
23
|
-
BLOOM_FILTER_AVAILABLE = False
|
|
24
|
-
|
|
25
|
-
class BloomFilter:
|
|
26
|
-
def __init__(self, capacity, error_rate):
|
|
27
|
-
self._data = set()
|
|
28
|
-
|
|
29
|
-
def add(self, item):
|
|
30
|
-
if item in self._data:
|
|
31
|
-
return False
|
|
32
|
-
else:
|
|
33
|
-
self._data.add(item)
|
|
34
|
-
return True
|
|
35
|
-
|
|
36
|
-
def __contains__(self, item):
|
|
37
|
-
return item in self._data
|
|
38
|
-
|
|
39
|
-
from crawlo import Item
|
|
40
|
-
from crawlo.spider import Spider
|
|
41
|
-
from crawlo.utils.log import get_logger
|
|
42
|
-
from crawlo.exceptions import DropItem
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
class BloomDedupPipeline:
|
|
46
|
-
"""基于 Bloom Filter 的数据项去重管道"""
|
|
47
|
-
|
|
48
|
-
def __init__(
|
|
49
|
-
self,
|
|
50
|
-
capacity: int = 1000000,
|
|
51
|
-
error_rate: float = 0.001,
|
|
52
|
-
log_level: str = "INFO"
|
|
53
|
-
):
|
|
54
|
-
"""
|
|
55
|
-
初始化 Bloom Filter 去重管道
|
|
56
|
-
|
|
57
|
-
:param capacity: 预期存储的元素数量
|
|
58
|
-
:param error_rate: 误判率 (例如 0.001 表示 0.1%)
|
|
59
|
-
:param log_level: 日志级别
|
|
60
|
-
"""
|
|
61
|
-
self.logger = get_logger(self.__class__.__name__, log_level)
|
|
62
|
-
|
|
63
|
-
# 初始化 Bloom Filter
|
|
64
|
-
try:
|
|
65
|
-
self.bloom_filter = BloomFilter(capacity=capacity, error_rate=error_rate)
|
|
66
|
-
self.logger.info(f"Bloom Filter 去重管道初始化完成 (容量: {capacity}, 误判率: {error_rate})")
|
|
67
|
-
except Exception as e:
|
|
68
|
-
self.logger.error(f"Bloom Filter 初始化失败: {e}")
|
|
69
|
-
raise RuntimeError(f"Bloom Filter 初始化失败: {e}")
|
|
70
|
-
|
|
71
|
-
self.capacity = capacity
|
|
72
|
-
self.error_rate = error_rate
|
|
73
|
-
self.dropped_count = 0
|
|
74
|
-
self.added_count = 0
|
|
75
|
-
|
|
76
|
-
@classmethod
|
|
77
|
-
def from_crawler(cls, crawler):
|
|
78
|
-
"""从爬虫配置创建管道实例"""
|
|
79
|
-
settings = crawler.settings
|
|
80
|
-
|
|
81
|
-
return cls(
|
|
82
|
-
capacity=settings.getint('BLOOM_FILTER_CAPACITY', 1000000),
|
|
83
|
-
error_rate=settings.getfloat('BLOOM_FILTER_ERROR_RATE', 0.001),
|
|
84
|
-
log_level=settings.get('LOG_LEVEL', 'INFO')
|
|
85
|
-
)
|
|
86
|
-
|
|
87
|
-
def process_item(self, item: Item, spider: Spider) -> Item:
|
|
88
|
-
"""
|
|
89
|
-
处理数据项,进行去重检查
|
|
90
|
-
|
|
91
|
-
:param item: 要处理的数据项
|
|
92
|
-
:param spider: 爬虫实例
|
|
93
|
-
:return: 处理后的数据项或抛出 DropItem 异常
|
|
94
|
-
"""
|
|
95
|
-
try:
|
|
96
|
-
# 生成数据项指纹
|
|
97
|
-
fingerprint = self._generate_item_fingerprint(item)
|
|
98
|
-
|
|
99
|
-
# 检查指纹是否已存在
|
|
100
|
-
if fingerprint in self.bloom_filter:
|
|
101
|
-
# 如果可能已存在(Bloom Filter 可能有误判),丢弃这个数据项
|
|
102
|
-
self.dropped_count += 1
|
|
103
|
-
self.logger.debug(f"可能丢弃重复数据项: {fingerprint[:20]}...")
|
|
104
|
-
raise DropItem(f"可能重复的数据项: {fingerprint}")
|
|
105
|
-
else:
|
|
106
|
-
# 添加指纹到 Bloom Filter
|
|
107
|
-
self.bloom_filter.add(fingerprint)
|
|
108
|
-
self.added_count += 1
|
|
109
|
-
self.logger.debug(f"处理新数据项: {fingerprint[:20]}...")
|
|
110
|
-
return item
|
|
111
|
-
|
|
112
|
-
except Exception as e:
|
|
113
|
-
self.logger.error(f"处理数据项时出错: {e}")
|
|
114
|
-
# 在错误时继续处理,避免丢失数据
|
|
115
|
-
return item
|
|
116
|
-
|
|
117
|
-
def _generate_item_fingerprint(self, item: Item) -> str:
|
|
118
|
-
"""
|
|
119
|
-
生成数据项指纹
|
|
120
|
-
|
|
121
|
-
基于数据项的所有字段生成唯一指纹,用于去重判断。
|
|
122
|
-
|
|
123
|
-
:param item: 数据项
|
|
124
|
-
:return: 指纹字符串
|
|
125
|
-
"""
|
|
126
|
-
# 将数据项转换为可序列化的字典
|
|
127
|
-
try:
|
|
128
|
-
item_dict = item.to_dict()
|
|
129
|
-
except AttributeError:
|
|
130
|
-
# 兼容没有to_dict方法的Item实现
|
|
131
|
-
item_dict = dict(item)
|
|
132
|
-
|
|
133
|
-
# 对字典进行排序以确保一致性
|
|
134
|
-
sorted_items = sorted(item_dict.items())
|
|
135
|
-
|
|
136
|
-
# 生成指纹字符串
|
|
137
|
-
fingerprint_string = '|'.join([f"{k}={v}" for k, v in sorted_items if v is not None])
|
|
138
|
-
|
|
139
|
-
# 使用 SHA256 生成固定长度的指纹
|
|
140
|
-
return hashlib.sha256(fingerprint_string.encode('utf-8')).hexdigest()
|
|
141
|
-
|
|
142
|
-
def close_spider(self, spider: Spider) -> None:
|
|
143
|
-
"""
|
|
144
|
-
爬虫关闭时的清理工作
|
|
145
|
-
|
|
146
|
-
:param spider: 爬虫实例
|
|
147
|
-
"""
|
|
148
|
-
self.logger.info(f"爬虫 {spider.name} 关闭:")
|
|
149
|
-
self.logger.info(f" - 处理的数据项数: {self.added_count}")
|
|
150
|
-
self.logger.info(f" - 可能丢弃的重复数据项: {self.dropped_count}")
|
|
151
|
-
|
|
152
|
-
if BLOOM_FILTER_AVAILABLE:
|
|
153
|
-
# 注意:Bloom Filter 无法准确统计元素数量
|
|
154
|
-
self.logger.info(f" - Bloom Filter 容量: {self.capacity}")
|
|
155
|
-
self.logger.info(f" - Bloom Filter 误判率: {self.error_rate}")
|
|
156
|
-
else:
|
|
1
|
+
#!/usr/bin/python
|
|
2
|
+
# -*- coding:UTF-8 -*-
|
|
3
|
+
"""
|
|
4
|
+
基于 Bloom Filter 的数据项去重管道
|
|
5
|
+
=============================
|
|
6
|
+
提供大规模数据采集场景下的高效去重功能,使用概率性数据结构节省内存。
|
|
7
|
+
|
|
8
|
+
特点:
|
|
9
|
+
- 内存效率高: 相比传统集合节省大量内存
|
|
10
|
+
- 高性能: 快速的插入和查找操作
|
|
11
|
+
- 可扩展: 支持自定义容量和误判率
|
|
12
|
+
- 适用性广: 特别适合大规模数据采集
|
|
13
|
+
|
|
14
|
+
注意: Bloom Filter 有误判率,可能会错误地丢弃一些未见过的数据项。
|
|
15
|
+
"""
|
|
16
|
+
|
|
17
|
+
import hashlib
|
|
18
|
+
try:
|
|
19
|
+
from pybloom_live import BloomFilter
|
|
20
|
+
BLOOM_FILTER_AVAILABLE = True
|
|
21
|
+
except ImportError:
|
|
22
|
+
# 如果没有安装 pybloom_live,使用简单的替代方案
|
|
23
|
+
BLOOM_FILTER_AVAILABLE = False
|
|
24
|
+
|
|
25
|
+
class BloomFilter:
|
|
26
|
+
def __init__(self, capacity, error_rate):
|
|
27
|
+
self._data = set()
|
|
28
|
+
|
|
29
|
+
def add(self, item):
|
|
30
|
+
if item in self._data:
|
|
31
|
+
return False
|
|
32
|
+
else:
|
|
33
|
+
self._data.add(item)
|
|
34
|
+
return True
|
|
35
|
+
|
|
36
|
+
def __contains__(self, item):
|
|
37
|
+
return item in self._data
|
|
38
|
+
|
|
39
|
+
from crawlo import Item
|
|
40
|
+
from crawlo.spider import Spider
|
|
41
|
+
from crawlo.utils.log import get_logger
|
|
42
|
+
from crawlo.exceptions import DropItem
|
|
43
|
+
|
|
44
|
+
|
|
45
|
+
class BloomDedupPipeline:
|
|
46
|
+
"""基于 Bloom Filter 的数据项去重管道"""
|
|
47
|
+
|
|
48
|
+
def __init__(
|
|
49
|
+
self,
|
|
50
|
+
capacity: int = 1000000,
|
|
51
|
+
error_rate: float = 0.001,
|
|
52
|
+
log_level: str = "INFO"
|
|
53
|
+
):
|
|
54
|
+
"""
|
|
55
|
+
初始化 Bloom Filter 去重管道
|
|
56
|
+
|
|
57
|
+
:param capacity: 预期存储的元素数量
|
|
58
|
+
:param error_rate: 误判率 (例如 0.001 表示 0.1%)
|
|
59
|
+
:param log_level: 日志级别
|
|
60
|
+
"""
|
|
61
|
+
self.logger = get_logger(self.__class__.__name__, log_level)
|
|
62
|
+
|
|
63
|
+
# 初始化 Bloom Filter
|
|
64
|
+
try:
|
|
65
|
+
self.bloom_filter = BloomFilter(capacity=capacity, error_rate=error_rate)
|
|
66
|
+
self.logger.info(f"Bloom Filter 去重管道初始化完成 (容量: {capacity}, 误判率: {error_rate})")
|
|
67
|
+
except Exception as e:
|
|
68
|
+
self.logger.error(f"Bloom Filter 初始化失败: {e}")
|
|
69
|
+
raise RuntimeError(f"Bloom Filter 初始化失败: {e}")
|
|
70
|
+
|
|
71
|
+
self.capacity = capacity
|
|
72
|
+
self.error_rate = error_rate
|
|
73
|
+
self.dropped_count = 0
|
|
74
|
+
self.added_count = 0
|
|
75
|
+
|
|
76
|
+
@classmethod
|
|
77
|
+
def from_crawler(cls, crawler):
|
|
78
|
+
"""从爬虫配置创建管道实例"""
|
|
79
|
+
settings = crawler.settings
|
|
80
|
+
|
|
81
|
+
return cls(
|
|
82
|
+
capacity=settings.getint('BLOOM_FILTER_CAPACITY', 1000000),
|
|
83
|
+
error_rate=settings.getfloat('BLOOM_FILTER_ERROR_RATE', 0.001),
|
|
84
|
+
log_level=settings.get('LOG_LEVEL', 'INFO')
|
|
85
|
+
)
|
|
86
|
+
|
|
87
|
+
def process_item(self, item: Item, spider: Spider) -> Item:
|
|
88
|
+
"""
|
|
89
|
+
处理数据项,进行去重检查
|
|
90
|
+
|
|
91
|
+
:param item: 要处理的数据项
|
|
92
|
+
:param spider: 爬虫实例
|
|
93
|
+
:return: 处理后的数据项或抛出 DropItem 异常
|
|
94
|
+
"""
|
|
95
|
+
try:
|
|
96
|
+
# 生成数据项指纹
|
|
97
|
+
fingerprint = self._generate_item_fingerprint(item)
|
|
98
|
+
|
|
99
|
+
# 检查指纹是否已存在
|
|
100
|
+
if fingerprint in self.bloom_filter:
|
|
101
|
+
# 如果可能已存在(Bloom Filter 可能有误判),丢弃这个数据项
|
|
102
|
+
self.dropped_count += 1
|
|
103
|
+
self.logger.debug(f"可能丢弃重复数据项: {fingerprint[:20]}...")
|
|
104
|
+
raise DropItem(f"可能重复的数据项: {fingerprint}")
|
|
105
|
+
else:
|
|
106
|
+
# 添加指纹到 Bloom Filter
|
|
107
|
+
self.bloom_filter.add(fingerprint)
|
|
108
|
+
self.added_count += 1
|
|
109
|
+
self.logger.debug(f"处理新数据项: {fingerprint[:20]}...")
|
|
110
|
+
return item
|
|
111
|
+
|
|
112
|
+
except Exception as e:
|
|
113
|
+
self.logger.error(f"处理数据项时出错: {e}")
|
|
114
|
+
# 在错误时继续处理,避免丢失数据
|
|
115
|
+
return item
|
|
116
|
+
|
|
117
|
+
def _generate_item_fingerprint(self, item: Item) -> str:
|
|
118
|
+
"""
|
|
119
|
+
生成数据项指纹
|
|
120
|
+
|
|
121
|
+
基于数据项的所有字段生成唯一指纹,用于去重判断。
|
|
122
|
+
|
|
123
|
+
:param item: 数据项
|
|
124
|
+
:return: 指纹字符串
|
|
125
|
+
"""
|
|
126
|
+
# 将数据项转换为可序列化的字典
|
|
127
|
+
try:
|
|
128
|
+
item_dict = item.to_dict()
|
|
129
|
+
except AttributeError:
|
|
130
|
+
# 兼容没有to_dict方法的Item实现
|
|
131
|
+
item_dict = dict(item)
|
|
132
|
+
|
|
133
|
+
# 对字典进行排序以确保一致性
|
|
134
|
+
sorted_items = sorted(item_dict.items())
|
|
135
|
+
|
|
136
|
+
# 生成指纹字符串
|
|
137
|
+
fingerprint_string = '|'.join([f"{k}={v}" for k, v in sorted_items if v is not None])
|
|
138
|
+
|
|
139
|
+
# 使用 SHA256 生成固定长度的指纹
|
|
140
|
+
return hashlib.sha256(fingerprint_string.encode('utf-8')).hexdigest()
|
|
141
|
+
|
|
142
|
+
def close_spider(self, spider: Spider) -> None:
|
|
143
|
+
"""
|
|
144
|
+
爬虫关闭时的清理工作
|
|
145
|
+
|
|
146
|
+
:param spider: 爬虫实例
|
|
147
|
+
"""
|
|
148
|
+
self.logger.info(f"爬虫 {spider.name} 关闭:")
|
|
149
|
+
self.logger.info(f" - 处理的数据项数: {self.added_count}")
|
|
150
|
+
self.logger.info(f" - 可能丢弃的重复数据项: {self.dropped_count}")
|
|
151
|
+
|
|
152
|
+
if BLOOM_FILTER_AVAILABLE:
|
|
153
|
+
# 注意:Bloom Filter 无法准确统计元素数量
|
|
154
|
+
self.logger.info(f" - Bloom Filter 容量: {self.capacity}")
|
|
155
|
+
self.logger.info(f" - Bloom Filter 误判率: {self.error_rate}")
|
|
156
|
+
else:
|
|
157
157
|
self.logger.warning(" - 未安装 pybloom_live,使用内存集合作为替代")
|
|
@@ -1,40 +1,40 @@
|
|
|
1
|
-
#!/usr/bin/python
|
|
2
|
-
# -*- coding:UTF-8 -*-
|
|
3
|
-
from typing import Dict, Any
|
|
4
|
-
|
|
5
|
-
from crawlo import Item
|
|
6
|
-
from crawlo.spider import Spider
|
|
7
|
-
from crawlo.utils.log import get_logger
|
|
8
|
-
|
|
9
|
-
|
|
10
|
-
class ConsolePipeline:
|
|
11
|
-
"""将Item内容输出到控制台的管道"""
|
|
12
|
-
|
|
13
|
-
def __init__(self, log_level: str = "DEBUG"):
|
|
14
|
-
self.logger = get_logger(self.__class__.__name__, log_level)
|
|
15
|
-
|
|
16
|
-
@classmethod
|
|
17
|
-
def from_crawler(cls, crawler):
|
|
18
|
-
"""从crawler实例创建管道"""
|
|
19
|
-
return cls(
|
|
20
|
-
log_level=crawler.settings.get('LOG_LEVEL', 'DEBUG')
|
|
21
|
-
)
|
|
22
|
-
|
|
23
|
-
async def process_item(self, item: Item, spider: Spider) -> Item:
|
|
24
|
-
"""处理Item并输出到日志"""
|
|
25
|
-
try:
|
|
26
|
-
item_dict = self._convert_to_serializable(item)
|
|
27
|
-
self.logger.info(f"Item processed: {item_dict}")
|
|
28
|
-
return item
|
|
29
|
-
except Exception as e:
|
|
30
|
-
self.logger.error(f"Error processing item: {e}", exc_info=True)
|
|
31
|
-
raise
|
|
32
|
-
|
|
33
|
-
@staticmethod
|
|
34
|
-
def _convert_to_serializable(item: Item) -> Dict[str, Any]:
|
|
35
|
-
"""将Item转换为可序列化的字典"""
|
|
36
|
-
try:
|
|
37
|
-
return item.to_dict()
|
|
38
|
-
except AttributeError:
|
|
39
|
-
# 兼容没有to_dict方法的Item实现
|
|
1
|
+
#!/usr/bin/python
|
|
2
|
+
# -*- coding:UTF-8 -*-
|
|
3
|
+
from typing import Dict, Any
|
|
4
|
+
|
|
5
|
+
from crawlo import Item
|
|
6
|
+
from crawlo.spider import Spider
|
|
7
|
+
from crawlo.utils.log import get_logger
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
class ConsolePipeline:
|
|
11
|
+
"""将Item内容输出到控制台的管道"""
|
|
12
|
+
|
|
13
|
+
def __init__(self, log_level: str = "DEBUG"):
|
|
14
|
+
self.logger = get_logger(self.__class__.__name__, log_level)
|
|
15
|
+
|
|
16
|
+
@classmethod
|
|
17
|
+
def from_crawler(cls, crawler):
|
|
18
|
+
"""从crawler实例创建管道"""
|
|
19
|
+
return cls(
|
|
20
|
+
log_level=crawler.settings.get('LOG_LEVEL', 'DEBUG')
|
|
21
|
+
)
|
|
22
|
+
|
|
23
|
+
async def process_item(self, item: Item, spider: Spider) -> Item:
|
|
24
|
+
"""处理Item并输出到日志"""
|
|
25
|
+
try:
|
|
26
|
+
item_dict = self._convert_to_serializable(item)
|
|
27
|
+
self.logger.info(f"Item processed: {item_dict}")
|
|
28
|
+
return item
|
|
29
|
+
except Exception as e:
|
|
30
|
+
self.logger.error(f"Error processing item: {e}", exc_info=True)
|
|
31
|
+
raise
|
|
32
|
+
|
|
33
|
+
@staticmethod
|
|
34
|
+
def _convert_to_serializable(item: Item) -> Dict[str, Any]:
|
|
35
|
+
"""将Item转换为可序列化的字典"""
|
|
36
|
+
try:
|
|
37
|
+
return item.to_dict()
|
|
38
|
+
except AttributeError:
|
|
39
|
+
# 兼容没有to_dict方法的Item实现
|
|
40
40
|
return dict(item)
|