crawlo 1.0.4__py3-none-any.whl → 1.0.6__py3-none-any.whl

crawlo/subscriber.py

@@ -1,106 +1,106 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-import asyncio
-from collections import defaultdict
-from inspect import iscoroutinefunction
-from typing import Dict, Set, Callable, Coroutine, Any, TypeAlias, List
-
-
-class ReceiverTypeError(TypeError):
-    """当订阅的接收者不是一个协程函数时抛出。"""
-    pass
-
-
-ReceiverCoroutine: TypeAlias = Callable[..., Coroutine[Any, Any, Any]]
-
-
-class Subscriber:
-    """
-    一个支持异步协程的发布/订阅（Pub/Sub）模式实现。
-
-    这个类允许你注册（订阅）协程函数来监听特定事件，并在事件发生时
-    以并发的方式异步地通知所有订阅者。
-    """
-
-    def __init__(self):
-        """初始化一个空的订阅者字典。"""
-        self._subscribers: Dict[str, Set[ReceiverCoroutine]] = defaultdict(set)
-
-    def subscribe(self, receiver: ReceiverCoroutine, *, event: str) -> None:
-        """
-        订阅一个事件。
-
-        Args:
-            receiver: 一个协程函数 (例如 async def my_func(...))。
-            event: 要订阅的事件名称。
-
-        Raises:
-            ReceiverTypeError: 如果提供的 `receiver` 不是一个协程函数。
-        """
-        if not iscoroutinefunction(receiver):
-            raise ReceiverTypeError(f"接收者 '{receiver.__qualname__}' 必须是一个协程函数。")
-        self._subscribers[event].add(receiver)
-
-    def unsubscribe(self, receiver: ReceiverCoroutine, *, event: str) -> None:
-        """
-        取消订阅一个事件。
-
-        如果事件或接收者不存在，将静默处理。
-
-        Args:
-            receiver: 要取消订阅的协程函数。
-            event: 事件名称。
-        """
-        if event in self._subscribers:
-            self._subscribers[event].discard(receiver)
-
-    async def notify(self, event: str, *args, **kwargs) -> List[Any]:
-        """
-        异步地、并发地通知所有订阅了该事件的接收者。
-
-        此方法会等待所有订阅者任务完成后再返回，并收集所有结果或异常。
-
-        Args:
-            event: 要触发的事件名称。
-            *args: 传递给接收者的位置参数。
-            **kwargs: 传递给接收者的关键字参数。
-
-        Returns:
-            一个列表，包含每个订阅者任务的返回结果或在执行期间捕获的异常。
-        """
-        receivers = self._subscribers.get(event, set())
-        if not receivers:
-            return []
-
-        tasks = [asyncio.create_task(receiver(*args, **kwargs)) for receiver in receivers]
-
-        # 并发执行所有任务并返回结果列表（包括异常）
-        return await asyncio.gather(*tasks, return_exceptions=True)
-
-# #!/usr/bin/python
-# # -*- coding:UTF-8 -*-
-# import asyncio
-# from collections import defaultdict
-# from inspect import iscoroutinefunction
-# from typing import Dict, Set, Callable, Coroutine
-#
-# from crawlo.exceptions import ReceiverTypeError
-#
-#
-# class Subscriber:
-#
-#     def __init__(self):
-#         self._subscribers: Dict[str, Set[Callable[..., Coroutine]]] = defaultdict(set)
-#
-#     def subscribe(self, receiver: Callable[..., Coroutine], *, event: str) -> None:
-#         if not iscoroutinefunction(receiver):
-#             raise ReceiverTypeError(f"{receiver.__qualname__} must be a coroutine function")
-#         self._subscribers[event].add(receiver)
-#
-#     def unsubscribe(self, receiver: Callable[..., Coroutine], *, event: str) -> None:
-#         self._subscribers[event].discard(receiver)
-#
-#     async def notify(self, event: str, *args, **kwargs) -> None:
-#         for receiver in self._subscribers[event]:
-#             # 不能 await
-#             asyncio.create_task(receiver(*args, **kwargs))
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+import asyncio
+from collections import defaultdict
+from inspect import iscoroutinefunction
+from typing import Dict, Set, Callable, Coroutine, Any, TypeAlias, List
+
+
+class ReceiverTypeError(TypeError):
+    """当订阅的接收者不是一个协程函数时抛出。"""
+    pass
+
+
+ReceiverCoroutine: TypeAlias = Callable[..., Coroutine[Any, Any, Any]]
+
+
+class Subscriber:
+    """
+    一个支持异步协程的发布/订阅（Pub/Sub）模式实现。
+
+    这个类允许你注册（订阅）协程函数来监听特定事件，并在事件发生时
+    以并发的方式异步地通知所有订阅者。
+    """
+
+    def __init__(self):
+        """初始化一个空的订阅者字典。"""
+        self._subscribers: Dict[str, Set[ReceiverCoroutine]] = defaultdict(set)
+
+    def subscribe(self, receiver: ReceiverCoroutine, *, event: str) -> None:
+        """
+        订阅一个事件。
+
+        Args:
+            receiver: 一个协程函数 (例如 async def my_func(...))。
+            event: 要订阅的事件名称。
+
+        Raises:
+            ReceiverTypeError: 如果提供的 `receiver` 不是一个协程函数。
+        """
+        if not iscoroutinefunction(receiver):
+            raise ReceiverTypeError(f"接收者 '{receiver.__qualname__}' 必须是一个协程函数。")
+        self._subscribers[event].add(receiver)
+
+    def unsubscribe(self, receiver: ReceiverCoroutine, *, event: str) -> None:
+        """
+        取消订阅一个事件。
+
+        如果事件或接收者不存在，将静默处理。
+
+        Args:
+            receiver: 要取消订阅的协程函数。
+            event: 事件名称。
+        """
+        if event in self._subscribers:
+            self._subscribers[event].discard(receiver)
+
+    async def notify(self, event: str, *args, **kwargs) -> List[Any]:
+        """
+        异步地、并发地通知所有订阅了该事件的接收者。
+
+        此方法会等待所有订阅者任务完成后再返回，并收集所有结果或异常。
+
+        Args:
+            event: 要触发的事件名称。
+            *args: 传递给接收者的位置参数。
+            **kwargs: 传递给接收者的关键字参数。
+
+        Returns:
+            一个列表，包含每个订阅者任务的返回结果或在执行期间捕获的异常。
+        """
+        receivers = self._subscribers.get(event, set())
+        if not receivers:
+            return []
+
+        tasks = [asyncio.create_task(receiver(*args, **kwargs)) for receiver in receivers]
+
+        # 并发执行所有任务并返回结果列表（包括异常）
+        return await asyncio.gather(*tasks, return_exceptions=True)
+
+# #!/usr/bin/python
+# # -*- coding:UTF-8 -*-
+# import asyncio
+# from collections import defaultdict
+# from inspect import iscoroutinefunction
+# from typing import Dict, Set, Callable, Coroutine
+#
+# from crawlo.exceptions import ReceiverTypeError
+#
+#
+# class Subscriber:
+#
+#     def __init__(self):
+#         self._subscribers: Dict[str, Set[Callable[..., Coroutine]]] = defaultdict(set)
+#
+#     def subscribe(self, receiver: Callable[..., Coroutine], *, event: str) -> None:
+#         if not iscoroutinefunction(receiver):
+#             raise ReceiverTypeError(f"{receiver.__qualname__} must be a coroutine function")
+#         self._subscribers[event].add(receiver)
+#
+#     def unsubscribe(self, receiver: Callable[..., Coroutine], *, event: str) -> None:
+#         self._subscribers[event].discard(receiver)
+#
+#     async def notify(self, event: str, *args, **kwargs) -> None:
+#         for receiver in self._subscribers[event]:
+#             # 不能 await
+#             asyncio.create_task(receiver(*args, **kwargs))

crawlo/task_manager.py

@@ -1,27 +1,27 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-import asyncio
-from asyncio import Task, Future, Semaphore
-from typing import Set, Final
-
-
-class TaskManager:
-
-    def __init__(self, total_concurrency: int = 8):
-        self.current_task: Final[Set] = set()
-        self.semaphore: Semaphore = Semaphore(total_concurrency)
-
-    def create_task(self, coroutine) -> Task:
-        task = asyncio.create_task(coroutine)
-        self.current_task.add(task)
-
-        def done_callback(_future: Future) -> None:
-            self.current_task.remove(task)
-            self.semaphore.release()
-
-        task.add_done_callback(done_callback)
-
-        return task
-
-    def all_done(self) -> bool:
-        return len(self.current_task) == 0
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+import asyncio
+from asyncio import Task, Future, Semaphore
+from typing import Set, Final
+
+
+class TaskManager:
+
+    def __init__(self, total_concurrency: int = 8):
+        self.current_task: Final[Set] = set()
+        self.semaphore: Semaphore = Semaphore(total_concurrency)
+
+    def create_task(self, coroutine) -> Task:
+        task = asyncio.create_task(coroutine)
+        self.current_task.add(task)
+
+        def done_callback(_future: Future) -> None:
+            self.current_task.remove(task)
+            self.semaphore.release()
+
+        task.add_done_callback(done_callback)
+
+        return task
+
+    def all_done(self) -> bool:
+        return len(self.current_task) == 0

crawlo/templates/crawlo.cfg.tmpl

@@ -0,0 +1,11 @@
+# crawlo.cfg
+# 项目的配置文件。
+
+[settings]
+# 指定 settings 模块的导入路径
+default = {{project_name}}.settings
+
+[deploy]
+# （可选）用于部署配置
+# url = http://localhost:6800/
+# project = {{project_name}}

crawlo/templates/project/__init__.py.tmpl

@@ -0,0 +1,4 @@
+# -*- coding: UTF-8 -*-
+"""
+{{project_name}} 项目包
+"""

crawlo/templates/project/items.py.tmpl

@@ -0,0 +1,18 @@
+# -*- coding: UTF-8 -*-
+"""
+{{project_name}}.items
+======================
+定义你抓取的数据结构。
+"""
+
+from crawlo.items import Item, Field
+
+
+class ExampleItem(Item):
+    """
+    一个示例数据项。
+    """
+    # name = Field()
+    # price = Field()
+    # description = Field()
+    pass

crawlo/templates/project/middlewares.py.tmpl

@@ -0,0 +1,76 @@
+# -*- coding: UTF-8 -*-
+"""
+{{project_name}}.middlewares
+============================
+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。
+"""
+
+# 示例：下载器中间件
+class CustomDownloaderMiddleware:
+    """
+    下载器中间件示例。
+    """
+
+    def process_request(self, request, spider):
+        """
+        在请求被下载器执行前调用。
+        """
+        # request.headers['User-Agent'] = 'Custom UA'
+        # return None  # 继续处理
+        # return request  # 修改并返回
+        # return Response(...)  # 返回一个响应，停止下载
+        pass
+
+    def process_response(self, request, response, spider):
+        """
+        在响应被 Spider 处理前调用。
+        """
+        # return response  # 继续处理
+        # return request  # 重试请求
+        pass
+
+    def process_exception(self, request, exception, spider):
+        """
+        在下载或处理过程中发生异常时调用。
+        """
+        # return None  # 继续抛出异常
+        # return request  # 重试
+        # return Response(...) # 返回一个响应
+        pass
+
+
+# 示例：Spider 中间件
+class CustomSpiderMiddleware:
+    """
+    Spider 中间件示例。
+    """
+
+    def process_spider_input(self, response, spider):
+        """
+        在 Spider 的 parse 方法被调用前调用。
+        """
+        # 可以用来验证响应
+        pass
+
+    def process_spider_output(self, response, result, spider):
+        """
+        在 Spider 的 parse 方法返回结果后调用。
+        """
+        # 可以用来过滤或修改结果
+        # for item in result:
+        #     yield item
+        pass
+
+    def process_spider_exception(self, response, exception, spider):
+        """
+        在 Spider 的 parse 方法抛出异常时调用。
+        """
+        pass
+
+    def process_start_requests(self, start_requests, spider):
+        """
+        在 Spider 的 start_requests 生成器被消费时调用。
+        """
+        # for request in start_requests:
+        #     yield request
+        pass

crawlo/templates/project/pipelines.py.tmpl

@@ -0,0 +1,64 @@
+# -*- coding: UTF-8 -*-
+"""
+{{project_name}}.pipelines
+==========================
+数据管道，用于处理 Spider 返回的 Item。
+例如：清理、验证、去重、保存到数据库等。
+"""
+
+class PrintItemPipeline:
+    """
+    一个简单的管道，用于打印 Item。
+    """
+
+    def process_item(self, item, spider):
+        print(f"Pipeline received item: {dict(item)}")
+        return item
+
+
+class DuplicatesPipeline:
+    """
+    一个去重管道示例。
+    """
+    def __init__(self):
+        self.seen = set()
+
+    def process_item(self, item, spider):
+        identifier = item.get('id') or item.get('url')
+        if identifier in self.seen:
+            spider.logger.debug(f"Duplicate item found: {identifier}")
+            raise DropItem(f"Duplicate item: {identifier}")
+        self.seen.add(identifier)
+        return item
+
+
+# class MySQLPipeline:
+#     """
+#     将 Item 保存到 MySQL 的管道示例。
+#     """
+#     def __init__(self, mysql_uri, mysql_user, mysql_password, mysql_db):
+#         self.mysql_uri = mysql_uri
+#         self.mysql_user = mysql_user
+#         self.mysql_password = mysql_password
+#         self.mysql_db = mysql_db
+#         self.connection = None
+#
+#     @classmethod
+#     def from_settings(cls, settings):
+#         return cls(
+#             mysql_uri=settings.get('MYSQL_HOST'),
+#             mysql_user=settings.get('MYSQL_USER'),
+#             mysql_password=settings.get('MYSQL_PASSWORD'),
+#             mysql_db=settings.get('MYSQL_DB')
+#         )
+#
+#     def open_spider(self, spider):
+#         self.connection = pymysql.connect(...)
+#
+#     def close_spider(self, spider):
+#         if self.connection:
+#             self.connection.close()
+#
+#     def process_item(self, item, spider):
+#         # 执行 SQL 插入
+#         return item

crawlo/templates/project/settings.py.tmpl

@@ -0,0 +1,54 @@
+# -*- coding: UTF-8 -*-
+"""自动创建的 settings.py 文件"""
+
+PROJECT_NAME = '{{project_name}}'
+VERSION = '1.0'
+
+# ============================== 网络请求配置 ==============================
+DOWNLOADER = "crawlo.downloader.aiohttp_downloader.AioHttpDownloader"
+DOWNLOAD_TIMEOUT = 60
+VERIFY_SSL = True
+USE_SESSION = True
+
+DOWNLOAD_DELAY = 1.0
+RANDOMNESS = True
+
+MAX_RETRY_TIMES = 3
+RETRY_HTTP_CODES = [408, 429, 500, 502, 503, 504, 522, 524]
+IGNORE_HTTP_CODES = [403, 404]
+
+CONNECTION_POOL_LIMIT = 100
+
+# ============================== 并发与调度 ==============================
+CONCURRENCY = 8
+MAX_RUNNING_SPIDERS = 3
+
+# ============================== 数据存储 ==============================
+MYSQL_HOST = '127.0.0.1'
+MYSQL_PORT = 3306
+MYSQL_USER = 'root'
+MYSQL_PASSWORD = '123456'
+MYSQL_DB = '{{project_name}}'
+MYSQL_TABLE = 'crawled_data'
+
+# ============================== 去重过滤 ==============================
+FILTER_CLASS = 'crawlo.filters.memory_filter.MemoryFilter'
+
+# ============================== 中间件 & 管道 ==============================
+MIDDLEWARES = [
+    'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
+    'crawlo.middleware.download_delay.DownloadDelayMiddleware',
+    'crawlo.middleware.default_header.DefaultHeaderMiddleware',
+    'crawlo.middleware.proxy.ProxyMiddleware',
+    'crawlo.middleware.retry.RetryMiddleware',
+    'crawlo.middleware.response_code.ResponseCodeMiddleware',
+    'crawlo.middleware.response_filter.ResponseFilterMiddleware',
+]
+
+PIPELINES = [
+    'crawlo.pipelines.console_pipeline.ConsolePipeline',
+]
+
+# ============================== 日志 ==============================
+LOG_LEVEL = 'INFO'
+LOG_FILE = f'logs/{{{{project_name}}}}.log'

crawlo/templates/project/spiders/__init__.py.tmpl

@@ -0,0 +1,6 @@
+# -*- coding: UTF-8 -*-
+"""
+{{project_name}}.spiders
+========================
+存放所有的爬虫。
+"""

crawlo/templates/spider/spider.py.tmpl

@@ -0,0 +1,32 @@
+# -*- coding: UTF-8 -*-
+"""
+{{project_name}}.spiders.{{spider_name}}
+=======================================
+由 `crawlo genspider` 命令生成的爬虫。
+"""
+
+from crawlo.spider import Spider
+
+
+class {{class_name}}(Spider):
+    """
+    爬虫：{{spider_name}}
+    """
+    name = '{{spider_name}}'
+    allowed_domains = ['{{domain}}']
+    start_urls = ['https://{{domain}}/']
+
+    def parse(self, response):
+        """
+        解析响应的主方法。
+        """
+        # TODO: 在这里编写你的解析逻辑
+
+        # 示例：提取数据
+        # item = {{item_class}}()
+        # item['title'] = response.xpath('//title/text()').get()
+        # yield item
+
+        # 示例：提取链接并跟进
+        # for href in response.xpath('//a/@href').getall():
+        #     yield response.follow(href, callback=self.parse)

crawlo/utils/__init__.py

@@ -1,7 +1,7 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-"""
-# @Time    :    2025-02-05 13:57
-# @Author  :   oscar
-# @Desc    :   None
-"""
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+# @Time    :    2025-02-05 13:57
+# @Author  :   oscar
+# @Desc    :   None
+"""