ProcessPoolExecutor對multiprocessing進行了高級抽象，暴露出簡單的統一接口。
異步非阻塞 爬蟲
對於異步IO請求的本質則是【非阻塞Socket】+【IO多路復用】：
"""史上最牛逼的異步IO模塊
"""
import select
import socket
import time
class AsyncTimeoutException(TimeoutError):
"""
請求超時異常類
"""
def __init__(self, msg):
self.msg = msg
super(AsyncTimeoutException, self).__init__(msg)
class HttpContext(object):
"""封裝請求和相應的基本數據"""
def __init__(self, sock, host, port, method, url, data, callback, timeout=5):
"""
sock: 請求的客戶端socket對象
host: 請求的主機名
port: 請求的端口
port: 請求的端口
method: 請求方式
url: 請求的URL
data: 請求時請求體中的數據
callback: 請求完成后的回調函數
timeout: 請求的超時時間
"""
self.sock = sock
self.callback = callback
self.host = host
self.port = port
self.method = method
self.url = url
self.data = data
self.timeout = timeout
self.__start_time = time.time()
self.__buffer = []
def is_timeout(self):
"""當前請求是否已經超時"""
current_time = time.time()
if (self.__start_time + self.timeout) < current_time:
return True
def fileno(self):
"""請求sockect對象的文件描述符，用於select監聽"""
return self.sock.fileno()
def write(self, data):
"""在buffer中寫入響應內容"""
self.__buffer.append(data)
def finish(self, exc=None):
"""在buffer中寫入響應內容完成，執行請求的回調函數"""
if not exc:
response = b''.join(self.__buffer)
self.callback(self, response, exc)
else:
self.callback(self, None, exc)
def send_request_data(self):
content = """%s %s HTTP/1.0\r\nHost: %s\r\n\r\n%s""" % (
self.method.upper(), self.url, self.host, self.data,)
return content.encode(encoding='utf8')
class AsyncRequest(object):
def __init__(self):
self.fds = []
self.connections = []
def add_request(self, host, port, method, url, data, callback, timeout):
"""創建一個要請求"""
client = socket.socket()
client.setblocking(False)
try:
client.connect((host, port))
except BlockingIOError as e:
pass
# print('已經向遠程發送連接的請求')
req = HttpContext(client, host, port, method, url, data, callback, timeout)
self.connections.append(req)
self.fds.append(req)
def check_conn_timeout(self):
"""檢查所有的請求，是否有已經連接超時，如果有則終止"""
timeout_list = []
for context in self.connections:
if context.is_timeout():
timeout_list.append(context)
for context in timeout_list:
context.finish(AsyncTimeoutException('請求超時'))
self.fds.remove(context)
self.connections.remove(context)
def running(self):
"""事件循環，用於檢測請求的socket是否已經就緒，從而執行相關操作"""
while True:
r, w, e = select.select(self.fds, self.connections, self.fds, 0.05)
if not self.fds:
return
for context in r:
sock = context.sock
while True:
try:
data = sock.recv(8096)
if not data:
self.fds.remove(context)
context.finish()
break
else:
context.write(data)
except BlockingIOError as e:
break
except TimeoutError as e:
self.fds.remove(context)
self.connections.remove(context)
context.finish(e)
break
for context in w:
# 已經連接成功遠程服務器，開始向遠程發送請求數據
if context in self.fds:
data = context.send_request_data()
context.sock.sendall(data)
self.connections.remove(context)
self.check_conn_timeout()
if __name__ == '__main__':
def callback_func(context, response, ex):
"""
:param context: HttpContext對象，內部封裝了請求相關信息
:param response: 請求響應內容
:param ex: 是否出現異常（如果有異常則值為異常對象；否則值為None）
:return:
"""
print(context, response, ex)
obj = AsyncRequest()
url_list = [
{'host': 'www.google.com', 'port': 80, 'method': 'GET', 'url': '/', 'data': '', 'timeout': 5,
'callback': callback_func},
{'host': 'www.baidu.com', 'port': 80, 'method': 'GET', 'url': '/', 'data': '', 'timeout': 5,
'callback': callback_func},
{'host': 'www.bing.com', 'port': 80, 'method': 'GET', 'url': '/', 'data': '', 'timeout': 5,
'callback': callback_func},
]
for item in url_list:
print(item)
obj.add_request(**item)
obj.running()