crawlo 1.1.0__py3-none-any.whl → 1.1.1__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 +33 -24
- crawlo/__version__.py +1 -1
- crawlo/cli.py +40 -40
- crawlo/commands/__init__.py +13 -13
- crawlo/commands/check.py +594 -155
- crawlo/commands/genspider.py +125 -110
- crawlo/commands/list.py +147 -119
- crawlo/commands/run.py +285 -170
- crawlo/commands/startproject.py +111 -101
- crawlo/commands/stats.py +188 -167
- crawlo/core/__init__.py +2 -2
- crawlo/core/engine.py +158 -158
- crawlo/core/processor.py +40 -40
- crawlo/core/scheduler.py +57 -57
- crawlo/crawler.py +494 -492
- crawlo/downloader/__init__.py +78 -78
- crawlo/downloader/aiohttp_downloader.py +199 -199
- crawlo/downloader/cffi_downloader.py +242 -277
- crawlo/downloader/httpx_downloader.py +246 -246
- crawlo/event.py +11 -11
- crawlo/exceptions.py +78 -78
- crawlo/extension/__init__.py +31 -31
- crawlo/extension/log_interval.py +49 -49
- crawlo/extension/log_stats.py +44 -44
- crawlo/extension/logging_extension.py +34 -34
- crawlo/filters/__init__.py +37 -37
- crawlo/filters/aioredis_filter.py +150 -150
- crawlo/filters/memory_filter.py +202 -202
- crawlo/items/__init__.py +23 -23
- crawlo/items/base.py +21 -21
- crawlo/items/fields.py +53 -53
- crawlo/items/items.py +104 -104
- crawlo/middleware/__init__.py +21 -21
- crawlo/middleware/default_header.py +32 -32
- crawlo/middleware/download_delay.py +28 -28
- crawlo/middleware/middleware_manager.py +135 -135
- crawlo/middleware/proxy.py +245 -245
- crawlo/middleware/request_ignore.py +30 -30
- crawlo/middleware/response_code.py +18 -18
- crawlo/middleware/response_filter.py +26 -26
- crawlo/middleware/retry.py +90 -90
- crawlo/network/__init__.py +7 -7
- crawlo/network/request.py +203 -203
- crawlo/network/response.py +166 -166
- crawlo/pipelines/__init__.py +13 -13
- crawlo/pipelines/console_pipeline.py +39 -39
- crawlo/pipelines/mongo_pipeline.py +116 -116
- crawlo/pipelines/mysql_batch_pipline.py +272 -272
- crawlo/pipelines/mysql_pipeline.py +195 -195
- crawlo/pipelines/pipeline_manager.py +56 -56
- crawlo/project.py +153 -0
- crawlo/settings/__init__.py +7 -7
- crawlo/settings/default_settings.py +166 -168
- crawlo/settings/setting_manager.py +99 -99
- crawlo/spider/__init__.py +129 -129
- crawlo/stats_collector.py +59 -59
- crawlo/subscriber.py +106 -106
- crawlo/task_manager.py +27 -27
- 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 +75 -75
- crawlo/templates/project/pipelines.py.tmpl +63 -63
- crawlo/templates/project/settings.py.tmpl +54 -54
- crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
- crawlo/templates/spider/spider.py.tmpl +31 -31
- crawlo/utils/__init__.py +7 -7
- crawlo/utils/date_tools.py +233 -233
- crawlo/utils/db_helper.py +343 -343
- crawlo/utils/func_tools.py +82 -82
- crawlo/utils/log.py +128 -128
- crawlo/utils/pqueue.py +173 -173
- crawlo/utils/request.py +267 -267
- crawlo/utils/spider_loader.py +62 -62
- crawlo/utils/system.py +11 -11
- crawlo/utils/tools.py +4 -4
- crawlo/utils/url.py +39 -39
- crawlo-1.1.1.dist-info/METADATA +220 -0
- crawlo-1.1.1.dist-info/RECORD +100 -0
- examples/__init__.py +7 -0
- examples/baidu_spider/__init__.py +7 -0
- examples/baidu_spider/demo.py +94 -0
- examples/baidu_spider/items.py +46 -0
- examples/baidu_spider/middleware.py +49 -0
- examples/baidu_spider/pipeline.py +55 -0
- examples/baidu_spider/run.py +27 -0
- examples/baidu_spider/settings.py +121 -0
- examples/baidu_spider/spiders/__init__.py +7 -0
- examples/baidu_spider/spiders/bai_du.py +61 -0
- examples/baidu_spider/spiders/miit.py +159 -0
- examples/baidu_spider/spiders/sina.py +79 -0
- tests/__init__.py +7 -7
- tests/test_proxy_health_check.py +32 -32
- 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
- crawlo/utils/concurrency_manager.py +0 -125
- crawlo/utils/project.py +0 -197
- crawlo-1.1.0.dist-info/METADATA +0 -49
- crawlo-1.1.0.dist-info/RECORD +0 -97
- examples/gxb/__init__.py +0 -0
- examples/gxb/items.py +0 -36
- examples/gxb/run.py +0 -16
- examples/gxb/settings.py +0 -72
- examples/gxb/spider/__init__.py +0 -2
- examples/gxb/spider/miit_spider.py +0 -180
- examples/gxb/spider/telecom_device.py +0 -129
- {crawlo-1.1.0.dist-info → crawlo-1.1.1.dist-info}/WHEEL +0 -0
- {crawlo-1.1.0.dist-info → crawlo-1.1.1.dist-info}/entry_points.txt +0 -0
- {crawlo-1.1.0.dist-info → crawlo-1.1.1.dist-info}/top_level.txt +0 -0
|
@@ -1,117 +1,117 @@
|
|
|
1
|
-
# -*- coding: utf-8 -*-
|
|
2
|
-
from typing import Optional
|
|
3
|
-
from motor.motor_asyncio import AsyncIOMotorClient
|
|
4
|
-
from pymongo.errors import PyMongoError
|
|
5
|
-
from crawlo.utils.log import get_logger
|
|
6
|
-
from crawlo.exceptions import ItemDiscard
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
class MongoPipeline:
|
|
10
|
-
def __init__(self, crawler):
|
|
11
|
-
self.crawler = crawler
|
|
12
|
-
self.settings = crawler.settings
|
|
13
|
-
self.logger = get_logger(self.__class__.__name__, self.settings.get('LOG_LEVEL'))
|
|
14
|
-
|
|
15
|
-
# 初始化连接参数
|
|
16
|
-
self.client = None
|
|
17
|
-
self.db = None
|
|
18
|
-
self.collection = None
|
|
19
|
-
|
|
20
|
-
# 配置默认值
|
|
21
|
-
self.mongo_uri = self.settings.get('MONGO_URI', 'mongodb://localhost:27017')
|
|
22
|
-
self.db_name = self.settings.get('MONGO_DATABASE', 'scrapy_db')
|
|
23
|
-
self.collection_name = self.settings.get('MONGO_COLLECTION', crawler.spider.name)
|
|
24
|
-
|
|
25
|
-
# 注册关闭事件
|
|
26
|
-
crawler.subscriber.subscribe(self.spider_closed, event='spider_closed')
|
|
27
|
-
|
|
28
|
-
@classmethod
|
|
29
|
-
def from_crawler(cls, crawler):
|
|
30
|
-
return cls(crawler)
|
|
31
|
-
|
|
32
|
-
async def _ensure_connection(self):
|
|
33
|
-
"""确保连接已建立"""
|
|
34
|
-
if self.client is None:
|
|
35
|
-
self.client = AsyncIOMotorClient(self.mongo_uri)
|
|
36
|
-
self.db = self.client[self.db_name]
|
|
37
|
-
self.collection = self.db[self.collection_name]
|
|
38
|
-
self.logger.info(f"MongoDB连接建立 (集合: {self.collection_name})")
|
|
39
|
-
|
|
40
|
-
async def process_item(self, item, spider) -> Optional[dict]:
|
|
41
|
-
"""处理item的核心方法"""
|
|
42
|
-
try:
|
|
43
|
-
await self._ensure_connection()
|
|
44
|
-
|
|
45
|
-
item_dict = dict(item)
|
|
46
|
-
result = await self.collection.insert_one(item_dict)
|
|
47
|
-
|
|
48
|
-
# 统计计数
|
|
49
|
-
self.crawler.stats.inc_value('mongodb/inserted')
|
|
50
|
-
self.logger.debug(f"插入文档ID: {result.inserted_id}")
|
|
51
|
-
|
|
52
|
-
return item
|
|
53
|
-
|
|
54
|
-
except Exception as e:
|
|
55
|
-
self.crawler.stats.inc_value('mongodb/failed')
|
|
56
|
-
self.logger.error(f"MongoDB插入失败: {e}")
|
|
57
|
-
raise ItemDiscard(f"MongoDB操作失败: {e}")
|
|
58
|
-
|
|
59
|
-
async def spider_closed(self):
|
|
60
|
-
"""关闭爬虫时清理资源"""
|
|
61
|
-
if self.client:
|
|
62
|
-
self.client.close()
|
|
63
|
-
self.logger.info("MongoDB连接已关闭")
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
class MongoPoolPipeline:
|
|
67
|
-
def __init__(self, crawler):
|
|
68
|
-
self.crawler = crawler
|
|
69
|
-
self.settings = crawler.settings
|
|
70
|
-
self.logger = get_logger(self.__class__.__name__, self.settings.get('LOG_LEVEL'))
|
|
71
|
-
|
|
72
|
-
# 连接池配置
|
|
73
|
-
self.client = AsyncIOMotorClient(
|
|
74
|
-
self.settings.get('MONGO_URI', 'mongodb://localhost:27017'),
|
|
75
|
-
maxPoolSize=self.settings.getint('MONGO_MAX_POOL_SIZE', 100),
|
|
76
|
-
minPoolSize=self.settings.getint('MONGO_MIN_POOL_SIZE', 10),
|
|
77
|
-
connectTimeoutMS=5000,
|
|
78
|
-
socketTimeoutMS=30000
|
|
79
|
-
)
|
|
80
|
-
|
|
81
|
-
self.db = self.client[self.settings.get('MONGO_DATABASE', 'scrapy_db')]
|
|
82
|
-
self.collection = self.db[self.settings.get('MONGO_COLLECTION', crawler.spider.name)]
|
|
83
|
-
|
|
84
|
-
crawler.subscriber.subscribe(self.spider_closed, event='spider_closed')
|
|
85
|
-
self.logger.info(f"MongoDB连接池已初始化 (集合: {self.collection.name})")
|
|
86
|
-
|
|
87
|
-
@classmethod
|
|
88
|
-
def create_instance(cls, crawler):
|
|
89
|
-
return cls(crawler)
|
|
90
|
-
|
|
91
|
-
async def process_item(self, item, spider) -> Optional[dict]:
|
|
92
|
-
"""处理item方法(带重试机制)"""
|
|
93
|
-
try:
|
|
94
|
-
item_dict = dict(item)
|
|
95
|
-
|
|
96
|
-
# 带重试的插入操作
|
|
97
|
-
for attempt in range(3):
|
|
98
|
-
try:
|
|
99
|
-
result = await self.collection.insert_one(item_dict)
|
|
100
|
-
self.crawler.stats.inc_value('mongodb/insert_success')
|
|
101
|
-
self.logger.debug(f"插入成功 [attempt {attempt + 1}]: {result.inserted_id}")
|
|
102
|
-
return item
|
|
103
|
-
except PyMongoError as e:
|
|
104
|
-
if attempt == 2: # 最后一次尝试仍失败
|
|
105
|
-
raise
|
|
106
|
-
self.logger.warning(f"插入重试中 [attempt {attempt + 1}]: {e}")
|
|
107
|
-
|
|
108
|
-
except Exception as e:
|
|
109
|
-
self.crawler.stats.inc_value('mongodb/insert_failed')
|
|
110
|
-
self.logger.error(f"MongoDB操作最终失败: {e}")
|
|
111
|
-
raise ItemDiscard(f"MongoDB操作失败: {e}")
|
|
112
|
-
|
|
113
|
-
async def spider_closed(self):
|
|
114
|
-
"""资源清理"""
|
|
115
|
-
if hasattr(self, 'client'):
|
|
116
|
-
self.client.close()
|
|
1
|
+
# -*- coding: utf-8 -*-
|
|
2
|
+
from typing import Optional
|
|
3
|
+
from motor.motor_asyncio import AsyncIOMotorClient
|
|
4
|
+
from pymongo.errors import PyMongoError
|
|
5
|
+
from crawlo.utils.log import get_logger
|
|
6
|
+
from crawlo.exceptions import ItemDiscard
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
class MongoPipeline:
|
|
10
|
+
def __init__(self, crawler):
|
|
11
|
+
self.crawler = crawler
|
|
12
|
+
self.settings = crawler.settings
|
|
13
|
+
self.logger = get_logger(self.__class__.__name__, self.settings.get('LOG_LEVEL'))
|
|
14
|
+
|
|
15
|
+
# 初始化连接参数
|
|
16
|
+
self.client = None
|
|
17
|
+
self.db = None
|
|
18
|
+
self.collection = None
|
|
19
|
+
|
|
20
|
+
# 配置默认值
|
|
21
|
+
self.mongo_uri = self.settings.get('MONGO_URI', 'mongodb://localhost:27017')
|
|
22
|
+
self.db_name = self.settings.get('MONGO_DATABASE', 'scrapy_db')
|
|
23
|
+
self.collection_name = self.settings.get('MONGO_COLLECTION', crawler.spider.name)
|
|
24
|
+
|
|
25
|
+
# 注册关闭事件
|
|
26
|
+
crawler.subscriber.subscribe(self.spider_closed, event='spider_closed')
|
|
27
|
+
|
|
28
|
+
@classmethod
|
|
29
|
+
def from_crawler(cls, crawler):
|
|
30
|
+
return cls(crawler)
|
|
31
|
+
|
|
32
|
+
async def _ensure_connection(self):
|
|
33
|
+
"""确保连接已建立"""
|
|
34
|
+
if self.client is None:
|
|
35
|
+
self.client = AsyncIOMotorClient(self.mongo_uri)
|
|
36
|
+
self.db = self.client[self.db_name]
|
|
37
|
+
self.collection = self.db[self.collection_name]
|
|
38
|
+
self.logger.info(f"MongoDB连接建立 (集合: {self.collection_name})")
|
|
39
|
+
|
|
40
|
+
async def process_item(self, item, spider) -> Optional[dict]:
|
|
41
|
+
"""处理item的核心方法"""
|
|
42
|
+
try:
|
|
43
|
+
await self._ensure_connection()
|
|
44
|
+
|
|
45
|
+
item_dict = dict(item)
|
|
46
|
+
result = await self.collection.insert_one(item_dict)
|
|
47
|
+
|
|
48
|
+
# 统计计数
|
|
49
|
+
self.crawler.stats.inc_value('mongodb/inserted')
|
|
50
|
+
self.logger.debug(f"插入文档ID: {result.inserted_id}")
|
|
51
|
+
|
|
52
|
+
return item
|
|
53
|
+
|
|
54
|
+
except Exception as e:
|
|
55
|
+
self.crawler.stats.inc_value('mongodb/failed')
|
|
56
|
+
self.logger.error(f"MongoDB插入失败: {e}")
|
|
57
|
+
raise ItemDiscard(f"MongoDB操作失败: {e}")
|
|
58
|
+
|
|
59
|
+
async def spider_closed(self):
|
|
60
|
+
"""关闭爬虫时清理资源"""
|
|
61
|
+
if self.client:
|
|
62
|
+
self.client.close()
|
|
63
|
+
self.logger.info("MongoDB连接已关闭")
|
|
64
|
+
|
|
65
|
+
|
|
66
|
+
class MongoPoolPipeline:
|
|
67
|
+
def __init__(self, crawler):
|
|
68
|
+
self.crawler = crawler
|
|
69
|
+
self.settings = crawler.settings
|
|
70
|
+
self.logger = get_logger(self.__class__.__name__, self.settings.get('LOG_LEVEL'))
|
|
71
|
+
|
|
72
|
+
# 连接池配置
|
|
73
|
+
self.client = AsyncIOMotorClient(
|
|
74
|
+
self.settings.get('MONGO_URI', 'mongodb://localhost:27017'),
|
|
75
|
+
maxPoolSize=self.settings.getint('MONGO_MAX_POOL_SIZE', 100),
|
|
76
|
+
minPoolSize=self.settings.getint('MONGO_MIN_POOL_SIZE', 10),
|
|
77
|
+
connectTimeoutMS=5000,
|
|
78
|
+
socketTimeoutMS=30000
|
|
79
|
+
)
|
|
80
|
+
|
|
81
|
+
self.db = self.client[self.settings.get('MONGO_DATABASE', 'scrapy_db')]
|
|
82
|
+
self.collection = self.db[self.settings.get('MONGO_COLLECTION', crawler.spider.name)]
|
|
83
|
+
|
|
84
|
+
crawler.subscriber.subscribe(self.spider_closed, event='spider_closed')
|
|
85
|
+
self.logger.info(f"MongoDB连接池已初始化 (集合: {self.collection.name})")
|
|
86
|
+
|
|
87
|
+
@classmethod
|
|
88
|
+
def create_instance(cls, crawler):
|
|
89
|
+
return cls(crawler)
|
|
90
|
+
|
|
91
|
+
async def process_item(self, item, spider) -> Optional[dict]:
|
|
92
|
+
"""处理item方法(带重试机制)"""
|
|
93
|
+
try:
|
|
94
|
+
item_dict = dict(item)
|
|
95
|
+
|
|
96
|
+
# 带重试的插入操作
|
|
97
|
+
for attempt in range(3):
|
|
98
|
+
try:
|
|
99
|
+
result = await self.collection.insert_one(item_dict)
|
|
100
|
+
self.crawler.stats.inc_value('mongodb/insert_success')
|
|
101
|
+
self.logger.debug(f"插入成功 [attempt {attempt + 1}]: {result.inserted_id}")
|
|
102
|
+
return item
|
|
103
|
+
except PyMongoError as e:
|
|
104
|
+
if attempt == 2: # 最后一次尝试仍失败
|
|
105
|
+
raise
|
|
106
|
+
self.logger.warning(f"插入重试中 [attempt {attempt + 1}]: {e}")
|
|
107
|
+
|
|
108
|
+
except Exception as e:
|
|
109
|
+
self.crawler.stats.inc_value('mongodb/insert_failed')
|
|
110
|
+
self.logger.error(f"MongoDB操作最终失败: {e}")
|
|
111
|
+
raise ItemDiscard(f"MongoDB操作失败: {e}")
|
|
112
|
+
|
|
113
|
+
async def spider_closed(self):
|
|
114
|
+
"""资源清理"""
|
|
115
|
+
if hasattr(self, 'client'):
|
|
116
|
+
self.client.close()
|
|
117
117
|
self.logger.info("MongoDB连接池已释放")
|