python之爬虫_并发（串行、多线程、多进程、异步IO）
并发
在编写爬虫时，性能的消耗主要在IO请求中，当单进程单线程模式下请求URL时必然会引起等待，从而使得请求整体变慢
import requests def fetch_async(url): response = requests.get(url) return response url_list = ['http://www.github.com', 'http://www.bing.com'] for url in url_list: fetch_async(url)
from concurrent.futures import ThreadPoolExecutor import requests def fetch_async(url): response = requests.get(url) return response url_list = ['http://www.github.com', 'http://www.bing.com'] pool = ThreadPoolExecutor(5) for url in url_list: pool.submit(fetch_async, url) pool.shutdown(wait=True)
from concurrent.futures import ThreadPoolExecutor import requests def fetch_async(url): response = requests.get(url) return response def callback(future): print(future.result()) url_list = ['http://www.github.com', 'http://www.bing.com'] pool = ThreadPoolExecutor(5) for url in url_list: v = pool.submit(fetch_async, url) v.add_done_callback(callback) pool.shutdown(wait=True)
from concurrent.futures import ProcessPoolExecutor import requests def fetch_async(url): response = requests.get(url) return response url_list = ['http://www.github.com', 'http://www.bing.com'] pool = ProcessPoolExecutor(5) for url in url_list: pool.submit(fetch_async, url) pool.shutdown(wait=True)
from concurrent.futures import ProcessPoolExecutor import requests def fetch_async(url): response = requests.get(url) return response def callback(future): print(future.result()) url_list = ['http://www.github.com', 'http://www.bing.com'] pool = ProcessPoolExecutor(5) for url in url_list: v = pool.submit(fetch_async, url) v.add_done_callback(callback) pool.shutdown(wait=True)
异步IO
通过上述代码均可以完成对请求性能的提高，对于多线程和多进行的缺点是在IO阻塞时会造成了线程和进程的浪费，所以异步IO回事首选：
以下优先级：Twisted > gevent+requests > asyncio+aiohttp
import asyncio @asyncio.coroutine def func1(): print('before...func1......') yield from asyncio.sleep(5) print('end...func1......') tasks = [func1(), func1()] loop = asyncio.get_event_loop() loop.run_until_complete(asyncio.gather(*tasks)) loop.close()
import asyncio @asyncio.coroutine def fetch_async(host, url='/'): print(host, url) reader, writer = yield from asyncio.open_connection(host, 80) request_header_content = """GET %s HTTP/1.0\r\nHost: %s\r\n\r\n""" % (url, host,) request_header_content = bytes(request_header_content, encoding='utf-8') writer.write(request_header_content) yield from writer.drain() text = yield from reader.read() print(host, url, text) writer.close() tasks = [ fetch_async('www.cnblogs.com', '/wupeiqi/'), fetch_async('dig.chouti.com', '/pic/show?nid=4073644713430508&lid=10273091') ] loop = asyncio.get_event_loop() results = loop.run_until_complete(asyncio.gather(*tasks)) loop.close()
import aiohttp import asyncio @asyncio.coroutine def fetch_async(url): print(url) response = yield from aiohttp.request('GET', url) # data = yield from response.read() # print(url, data) print(url, response) response.close() tasks = [fetch_async('http://www.google.com/'), fetch_async('http://www.chouti.com/')] event_loop = asyncio.get_event_loop() results = event_loop.run_until_complete(asyncio.gather(*tasks)) event_loop.close()
import asyncio import requests @asyncio.coroutine def fetch_async(func, *args): loop = asyncio.get_event_loop() future = loop.run_in_executor(None, func, *args) response = yield from future print(response.url, response.content) tasks = [ fetch_async(requests.get, 'http://www.cnblogs.com/wupeiqi/'), fetch_async(requests.get, 'http://dig.chouti.com/pic/show?nid=4073644713430508&lid=10273091') ] loop = asyncio.get_event_loop() results = loop.run_until_complete(asyncio.gather(*tasks)) loop.close()
import gevent import requests from gevent import monkey monkey.patch_all() def fetch_async(method, url, req_kwargs): print(method, url, req_kwargs) response = requests.request(method=method, url=url, **req_kwargs) print(response.url, response.content) # ##### 发送请求 ##### gevent.joinall([ gevent.spawn(fetch_async, method='get', url='https://www.python.org/', req_kwargs={}), gevent.spawn(fetch_async, method='get', url='https://www.yahoo.com/', req_kwargs={}), gevent.spawn(fetch_async, method='get', url='https://github.com/', req_kwargs={}), ]) # ##### 发送请求（协程池控制最大协程数量） ##### # from gevent.pool import Pool # pool = Pool(None) # gevent.joinall([ # pool.spawn(fetch_async, method='get', url='https://www.python.org/', req_kwargs={}), # pool.spawn(fetch_async, method='get', url='https://www.yahoo.com/', req_kwargs={}), # pool.spawn(fetch_async, method='get', url='https://www.github.com/', req_kwargs={}), # ])
import grequests request_list = [ grequests.get('http://httpbin.org/delay/1', timeout=0.001), grequests.get('http://fakedomain/'), grequests.get('http://httpbin.org/status/500') ] # ##### 执行并获取响应列表 ##### # response_list = grequests.map(request_list) # print(response_list) # ##### 执行并获取响应列表（处理异常） ##### # def exception_handler(request, exception): # print(request,exception) # print("Request failed") # response_list = grequests.map(request_list, exception_handler=exception_handler) # print(response_list)
from tornado.httpclient import AsyncHTTPClient from tornado.httpclient import HTTPRequest from tornado import ioloop def handle_response(response): """ 处理返回值内容（需要维护计数器，来停止IO循环），调用 ioloop.IOLoop.current().stop() :param response: :return: """ if response.error: print("Error:", response.error) else: print(response.body) def func(): url_list = [ 'http://www.baidu.com', 'http://www.bing.com', ] for url in url_list: print(url) http_client = AsyncHTTPClient() http_client.fetch(HTTPRequest(url), handle_response) ioloop.IOLoop.current().add_callback(func) ioloop.IOLoop.current().start()
from twisted.web.client import getPage, defer from twisted.internet import reactor def all_done(arg): reactor.stop() def callback(contents): print(contents) deferred_list = [] url_list = ['http://www.bing.com', 'http://www.baidu.com', ] for url in url_list: deferred = getPage(bytes(url, encoding='utf8')) deferred.addCallback(callback) deferred_list.append(deferred) dlist = defer.DeferredList(deferred_list) dlist.addBoth(all_done) reactor.run()
from twisted.internet import reactor from twisted.web.client import getPage import urllib.parse def one_done(arg): print(arg) reactor.stop() post_data = urllib.parse.urlencode({'check_data': 'adf'}) post_data = bytes(post_data, encoding='utf8') headers = {b'Content-Type': b'application/x-www-form-urlencoded'} response = getPage(bytes('http://dig.chouti.com/login', encoding='utf8'), method=bytes('POST', encoding='utf8'), postdata=post_data, cookies={}, headers=headers) response.addBoth(one_done) reactor.run()
以上均是Python内置以及第三方模块提供异步IO请求模块，使用简便大大提高效率，而对于异步IO请求的本质则是【非阻塞Socket】+【IO多路复用】：
import socket import select class Request(object): def __init__(self,sock,info): self.sock = sock self.info = info def fileno(self): return self.sock.fileno() class AsyncRequest(object): def __init__(self): self.sock_list = [] self.conn_list = [] def add_request(self,req_info): """ 创建请求 :req_info:{"host":"www.baidu.com","port":80,"path":"/"} :return: """ sock = socket.socket() sock.setblocking(False) try: sock.connect((req_info["host"],req_info["port"])) except BlockingIOError as e: pass obj = Request(sock,req_info) self.sock_list.append(obj) self.conn_list.append(obj) def run(self): """ 开始事件循环，检测：连接成功？数据是否返回？ :return: """ while True: # select.select([socket对象]) # 可以是任何对象，对象一定要fileno方法 # 执行 对象.fileno() # select.select([Request对象]) r,w,e = select.select(self.sock_list,self.conn_list,[],0.05) # w，是否连接成功 for obj in w: # 检查obj是哪个字典 data = bytes("GET {url} HTTP/1.1\r\nhost:{host}\r\n\r\n".format(url=obj.info["path"],host=obj.info["host"]),encoding="utf-8") obj.sock.send(data) self.conn_list.remove(obj) # 数据返回，接收到数据 for obj in r: response = obj.sock.recv(8096) print(obj.info["host"],response) obj.info["callback"](response) # for func in obj.info["callback"]: # func(response) self.sock_list.remove(obj) # 所有的请求已返回 if not self.sock_list: break def done1(response): print(response) def done2(response): print(123,response) url_list = [ {"host":"www.baidu.com","port":80,"path":"/","callback":done1,}, {"host":"www.cnblogs.com","port":80,"path":"/index.html","callback":done2,}, {"host":"www.bing.com","port":80,"path":"/","callback":done2,}, ] qinbing = AsyncRequest() for item in url_list: qinbing.add_request(item) qinbing.run()
import select import socket import time class AsyncTimeoutException(TimeoutError): """ 请求超时异常类 """ def __init__(self, msg): self.msg = msg super(AsyncTimeoutException, self).__init__(msg) class HttpContext(object): """封装请求和相应的基本数据""" def __init__(self, sock, host, port, method, url, data, callback, timeout=5): """ sock: 请求的客户端socket对象 host: 请求的主机名 port: 请求的端口 port: 请求的端口 method: 请求方式 url: 请求的URL data: 请求时请求体中的数据 callback: 请求完成后的回调函数 timeout: 请求的超时时间 """ 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): """当前请求是否已经超时""" current_time = time.time() if (self.__start_time + self.timeout) < current_time: return True def fileno(self): """请求sockect对象的文件描述符，用于select监听""" return self.sock.fileno() def write(self, data): """在buffer中写入响应内容""" self.__buffer.append(data) def finish(self, exc=None): """在buffer中写入响应内容完成，执行请求的回调函数""" 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): """创建一个要请求""" client = socket.socket() client.setblocking(False) try: client.connect((host, port)) except BlockingIOError as e: pass # print('已经向远程发送连接的请求') req = HttpContext(client, host, port, method, url, data, callback, timeout) self.connections.append(req) self.fds.append(req) def check_conn_timeout(self): """检查所有的请求，是否有已经连接超时，如果有则终止""" timeout_list = [] for context in self.connections: if context.is_timeout(): timeout_list.append(context) for context in timeout_list: context.finish(AsyncTimeoutException('请求超时')) self.fds.remove(context) self.connections.remove(context) def running(self): """事件循环，用于检测请求的socket是否已经就绪，从而执行相关操作""" 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: # 已经连接成功远程服务器，开始向远程发送请求数据 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对象，内部封装了请求相关信息 :param response: 请求响应内容 :param ex: 是否出现异常（如果有异常则值为异常对象；否则值为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()
尝试使用selector模块写上面的模块
# -*- coding:utf-8 -*- import selectors import socket class MySock(): def __init__(self,sock,host,port,method,url,data,callback,timeout=5): self.sock = sock self.host = host self.port = port self.url = url self.data = data self.method = method self.callback = callback self.timeout = timeout self.__buffer = [] def fileno(self): return self.sock.fileno() def send_request(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 def write(self,data): self.__buffer.append(data) def finish(self): self.sock.close() if self.callback: response = b''.join(self.__buffer) self.callback(self,response) def __str__(self): return self.host class Test(): def __init__(self): self.sel = selectors.DefaultSelector() def add_request(self,host,port,method,url,data="",callback=None,timeout=5): sock = socket.socket() sock.setblocking(False) try: sock.connect((host,port)) except BlockingIOError as e: pass obj = MySock(sock,host,port,method,url,data,callback=callback,timeout=timeout) self.sel.register(obj,selectors.EVENT_WRITE,self.crawl) def crawl(self,fileobj,mask): data = fileobj.send_request() fileobj.sock.sendall(bytes(data,encoding="utf-8")) self.sel.unregister(fileobj) self.sel.register(fileobj,selectors.EVENT_READ,self.read) def read(self,fileobj,mask): sock = fileobj.sock while True: try: data = sock.recv(8096) if not data: self.sel.unregister(fileobj) fileobj.finish() break else: fileobj.write(data) except BlockingIOError as e: break def run(self): while True: try: events = self.sel.select() # 检测所有的fileobj，是否有完成wait data的 for sel_obj, mask in events: callback = sel_obj.data # callback=accpet callback(sel_obj.fileobj, mask) # accpet(server_fileobj,1) except OSError as e: # print("完成") break if __name__ == '__main__': def callback_func(fileobj,response): print(response) print(fileobj) # print(response.decode("utf-8")) t = Test() url_list = [ {'host': 'www.taiyingshi.com', 'port': 80, 'method': 'GET', 'url': '/', 'data': '', 'timeout': 5, 'callback': callback_func}, {'host': 'www.msj1.com', 'port': 80, 'method': 'GET', 'url': '/', 'data': '', 'timeout': 5, 'callback': callback_func}, ] for item in url_list: t.add_request(**item) t.run()
