pip install requests-threads

使用实例使用async/await - send 100个并发请求

from requests_threads import AsyncSession

session = AsyncSession(n=100)

async def _main():
    rs = []
    for _ in range(100):
        rs.append(await session.get('http://httpbin.org/get'))
    print(rs)

if __name__ == '__main__':
    session.run(_main)

此示例仅适用于Python 3。您还可以提供自己的asyncio事件循环!

使用实例Twisted

from twisted.internet.defer import inlineCallbacks
from twisted.internet.task import react
from requests_threads import AsyncSession

session = AsyncSession(n=100)

@inlineCallbacks
def main(reactor):
    responses = []
    for i in range(100):
        responses.append(session.get('http://httpbin.org/get'))

    for response in responses:
        r = yield response
        print(r)

if __name__ == '__main__':
    react(main)

这个例子在Python 2和Python 3上都可以运行。

也许这对我的回购有帮助，一个基本的例子， 用python编写快速异步HTTP请求

我发现使用tornado包是最快和最简单的方法来实现这一点:

from tornado import ioloop, httpclient, gen


def main(urls):
    """
    Asynchronously download the HTML contents of a list of URLs.
    :param urls: A list of URLs to download.
    :return: List of response objects, one for each URL.
    """

    @gen.coroutine
    def fetch_and_handle():
        httpclient.AsyncHTTPClient.configure(None, defaults=dict(user_agent='MyUserAgent'))
        http_client = httpclient.AsyncHTTPClient()
        waiter = gen.WaitIterator(*[http_client.fetch(url, raise_error=False, method='HEAD')
                                    for url in urls])
        results = []
        # Wait for the jobs to complete
        while not waiter.done():
            try:
                response = yield waiter.next()
            except httpclient.HTTPError as e:
                print(f'Non-200 HTTP response returned: {e}')
                continue
            except Exception as e:
                print(f'An unexpected error occurred querying: {e}')
                continue
            else:
                print(f'URL \'{response.request.url}\' has status code <{response.code}>')
                results.append(response)
        return results

    loop = ioloop.IOLoop.current()
    web_pages = loop.run_sync(fetch_and_handle)

    return web_pages

my_urls = ['url1.com', 'url2.com', 'url100000.com']
responses = main(my_urls)
print(responses[0])

线程绝对不是这里的答案。它们将提供进程和内核瓶颈，以及吞吐量限制，如果总体目标是“最快的方式”，这些限制是不可接受的。

稍微扭曲一点，它的异步HTTP客户端会给你更好的结果。

我知道这是一个老问题，但在Python 3.7中，您可以使用asyncio和aiohttp来做到这一点。

import asyncio
import aiohttp
from aiohttp import ClientSession, ClientConnectorError

async def fetch_html(url: str, session: ClientSession, **kwargs) -> tuple:
    try:
        resp = await session.request(method="GET", url=url, **kwargs)
    except ClientConnectorError:
        return (url, 404)
    return (url, resp.status)

async def make_requests(urls: set, **kwargs) -> None:
    async with ClientSession() as session:
        tasks = []
        for url in urls:
            tasks.append(
                fetch_html(url=url, session=session, **kwargs)
            )
        results = await asyncio.gather(*tasks)

    for result in results:
        print(f'{result[1]} - {str(result[0])}')

if __name__ == "__main__":
    import pathlib
    import sys

    assert sys.version_info >= (3, 7), "Script requires Python 3.7+."
    here = pathlib.Path(__file__).parent

    with open(here.joinpath("urls.txt")) as infile:
        urls = set(map(str.strip, infile))

    asyncio.run(make_requests(urls=urls))

你可以阅读更多关于它的内容，并在这里看到一个例子。

一个解决方案:

from twisted.internet import reactor, threads
from urlparse import urlparse
import httplib
import itertools


concurrent = 200
finished=itertools.count(1)
reactor.suggestThreadPoolSize(concurrent)

def getStatus(ourl):
    url = urlparse(ourl)
    conn = httplib.HTTPConnection(url.netloc)   
    conn.request("HEAD", url.path)
    res = conn.getresponse()
    return res.status

def processResponse(response,url):
    print response, url
    processedOne()

def processError(error,url):
    print "error", url#, error
    processedOne()

def processedOne():
    if finished.next()==added:
        reactor.stop()

def addTask(url):
    req = threads.deferToThread(getStatus, url)
    req.addCallback(processResponse, url)
    req.addErrback(processError, url)   

added=0
for url in open('urllist.txt'):
    added+=1
    addTask(url.strip())

try:
    reactor.run()
except KeyboardInterrupt:
    reactor.stop()

Testtime:

[kalmi@ubi1:~] wc -l urllist.txt
10000 urllist.txt
[kalmi@ubi1:~] time python f.py > /dev/null 

real    1m10.682s
user    0m16.020s
sys 0m10.330s
[kalmi@ubi1:~] head -n 6 urllist.txt
http://www.google.com
http://www.bix.hu
http://www.godaddy.com
http://www.google.com
http://www.bix.hu
http://www.godaddy.com
[kalmi@ubi1:~] python f.py | head -n 6
200 http://www.bix.hu
200 http://www.bix.hu
200 http://www.bix.hu
200 http://www.bix.hu
200 http://www.bix.hu
200 http://www.bix.hu

Pingtime:

bix.hu is ~10 ms away from me
godaddy.com: ~170 ms
google.com: ~30 ms

考虑使用风车，虽然风车可能不能做那么多线程。

您可以在5台机器上使用手卷Python脚本，每台机器使用端口40000-60000连接出站，打开100,000个端口连接。

另外，使用一个线程良好的QA应用程序(如OpenSTA)做一个示例测试可能会有所帮助，以了解每个服务器可以处理多少。

另外，试着在LWP::ConnCache类中使用简单的Perl。这样您可能会获得更好的性能(更多的连接)。