crawlo 1.1.0__py3-none-any.whl → 1.1.2__py3-none-any.whl

crawlo/stats_collector.py

@@ -1,59 +1,59 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-"""
-# @Time    :    2025-05-17 09:57
-# @Author  :   crawl-coder
-# @Desc    :   统计信息收集器
-"""
-from pprint import pformat
-from crawlo.utils.log import get_logger
-
-
-class StatsCollector(object):
-
-    def __init__(self, crawler):
-        self.crawler = crawler
-        self._dump = self.crawler.settings.get_bool('STATS_DUMP')
-        self._stats = {}
-        self.logger = get_logger(self.__class__.__name__, "INFO")
-
-    def inc_value(self, key, count=1, start=0):
-        self._stats[key] = self._stats.setdefault(key, start) + count
-
-    def get_value(self, key, default=None):
-        return self._stats.get(key, default)
-
-    def get_stats(self):
-        return self._stats
-
-    def set_stats(self, stats):
-        self._stats = stats
-
-    def clear_stats(self):
-        self._stats.clear()
-
-    def close_spider(self, spider, reason):
-        self._stats['reason'] = reason
-
-        # 首选：使用 spider.name
-        # 次选：使用实例的类名
-        # 最后：使用一个完全未知的占位符
-        spider_name = (
-                getattr(spider, 'name', None) or
-                spider.__class__.__name__ or
-                '<Unknown>'
-        )
-
-        self._stats['spider_name'] = spider_name
-
-        if self._dump:
-            self.logger.info(f'{spider_name} stats: \n{pformat(self._stats)}')
-
-    def __getitem__(self, item):
-        return self._stats[item]
-
-    def __setitem__(self, key, value):
-        self._stats[key] = value
-
-    def __delitem__(self, key):
-        del self._stats[key]
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+# @Time    :    2025-05-17 09:57
+# @Author  :   crawl-coder
+# @Desc    :   统计信息收集器
+"""
+from pprint import pformat
+from crawlo.utils.log import get_logger
+
+
+class StatsCollector(object):
+
+    def __init__(self, crawler):
+        self.crawler = crawler
+        self._dump = self.crawler.settings.get_bool('STATS_DUMP')
+        self._stats = {}
+        self.logger = get_logger(self.__class__.__name__, "INFO")
+
+    def inc_value(self, key, count=1, start=0):
+        self._stats[key] = self._stats.setdefault(key, start) + count
+
+    def get_value(self, key, default=None):
+        return self._stats.get(key, default)
+
+    def get_stats(self):
+        return self._stats
+
+    def set_stats(self, stats):
+        self._stats = stats
+
+    def clear_stats(self):
+        self._stats.clear()
+
+    def close_spider(self, spider, reason):
+        self._stats['reason'] = reason
+
+        # 首选：使用 spider.name
+        # 次选：使用实例的类名
+        # 最后：使用一个完全未知的占位符
+        spider_name = (
+                getattr(spider, 'name', None) or
+                spider.__class__.__name__ or
+                '<Unknown>'
+        )
+
+        self._stats['spider_name'] = spider_name
+
+        if self._dump:
+            self.logger.info(f'{spider_name} stats: \n{pformat(self._stats)}')
+
+    def __getitem__(self, item):
+        return self._stats[item]
+
+    def __setitem__(self, key, value):
+        self._stats[key] = value
+
+    def __delitem__(self, key):
+        del self._stats[key]

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 +1,30 @@
-#!/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)
+
+    async def create_task(self, coroutine) -> Task:
+        # 等待信号量，控制并发数
+        await self.semaphore.acquire()
+        
+        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

@@ -1,11 +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/
+# 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

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

crawlo/templates/project/items.py.tmpl

@@ -1,18 +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()
+# -*- 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

@@ -1,76 +1,87 @@
-# -*- 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
+# -*- 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。
+"""
+
+import random
+from crawlo import Request, Response
+from crawlo.utils.log import get_logger
+from crawlo.exceptions import IgnoreRequest
+
+
+class RandomUserAgentMiddleware:
+    """随机 User-Agent 中间件。"""
+    
+    def __init__(self):
+        self.logger = get_logger(self.__class__.__name__)
+        self.user_agents = [
+            'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36',
+            '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',
+            'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:135.0) Gecko/20100101 Firefox/135.0',
+            'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:135.0) Gecko/20100101 Firefox/135.0',
+        ]
+    
+    def process_request(self, request, spider):
+        if 'User-Agent' not in request.headers:
+            ua = random.choice(self.user_agents)
+            request.headers['User-Agent'] = ua
+        return None
+
+
+class CustomDownloaderMiddleware:
+    """自定义下载器中间件示例。"""
+
+    def __init__(self):
+        self.logger = get_logger(self.__class__.__name__)
+
+    def process_request(self, request, spider):
+        """在请求被下载器执行前调用。"""
+        # 示例：添加自定义请求头
+        # request.headers['Custom-Header'] = 'Custom-Value'
+        # 示例：设置代理
+        # request.meta['proxy'] = 'http://proxy.example.com:8080'
+        return None
+
+    def process_response(self, request, response, spider):
+        """在响应被 Spider 处理前调用。"""
+        # 示例：检查响应状态
+        if response.status_code == 403:
+            self.logger.warning(f"访问被拒绝: {request.url}")
+        return response
+
+    def process_exception(self, request, exception, spider):
+        """在下载或处理过程中发生异常时调用。"""
+        self.logger.error(f"请求异常: {request.url} - {exception}")
+        return None
+
+
+class CustomSpiderMiddleware:
+    """
+Spider 中间件示例。
+    """
+
+    def __init__(self):
+        self.logger = get_logger(self.__class__.__name__)
+
+    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
+
+    def process_spider_exception(self, response, exception, spider):
+        """在 Spider 的 parse 方法抛出异常时调用。"""
+        self.logger.error(f"Spider 异常: {response.url} - {exception}")
+        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