一个使用tornado的异步网络库解决方案

from tornado import ioloop, httpclient

i = 0

def handle_request(response):
    print(response.code)
    global i
    i -= 1
    if i == 0:
        ioloop.IOLoop.instance().stop()

http_client = httpclient.AsyncHTTPClient()
for url in open('urls.txt'):
    i += 1
    http_client.fetch(url.strip(), handle_request, method='HEAD')
ioloop.IOLoop.instance().start()

这段代码使用非阻塞网络I/O，没有任何限制。它可以扩展到数万个打开的连接。它将在单个线程中运行，但比任何线程解决方案都要快。签出非阻塞I/O

如果您希望获得尽可能好的性能，您可能会考虑使用异步I/O而不是线程。与成千上万个操作系统线程相关的开销是不小的，Python解释器内的上下文切换甚至增加了更多的开销。线程当然可以完成工作，但我怀疑异步路由将提供更好的整体性能。

具体来说，我建议使用Twisted库中的异步web客户端(http://www.twistedmatrix.com)。它有一个公认的陡峭的学习曲线，但一旦你很好地掌握了Twisted的异步编程风格，它就很容易使用。

Twisted的异步web客户端API的HowTo可以在以下地址找到:

http://twistedmatrix.com/documents/current/web/howto/client.html

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

(下一个项目的自我提示)

Python 3解决方案只使用请求。它是最简单且快速的，不需要多处理或复杂的异步库。

最重要的方面是重用连接，特别是对于HTTPS (TLS需要额外的往返才能打开)。注意，连接是特定于子域的。如果在多个域上抓取多个页面，则可以对url列表进行排序，以最大化连接重用(它有效地按域进行排序)。

当给定足够的线程时，它将与任何异步代码一样快。(请求在等待响应时释放python GIL)。

[带有日志记录和错误处理的生产等级代码]

import logging
import requests
import time
from concurrent.futures import ThreadPoolExecutor, as_completed

# source: https://stackoverflow.com/a/68583332/5994461

THREAD_POOL = 16

# This is how to create a reusable connection pool with python requests.
session = requests.Session()
session.mount(
    'https://',
    requests.adapters.HTTPAdapter(pool_maxsize=THREAD_POOL,
                                  max_retries=3,
                                  pool_block=True)
)

def get(url):
    response = session.get(url)
    logging.info("request was completed in %s seconds [%s]", response.elapsed.total_seconds(), response.url)
    if response.status_code != 200:
        logging.error("request failed, error code %s [%s]", response.status_code, response.url)
    if 500 <= response.status_code < 600:
        # server is overloaded? give it a break
        time.sleep(5)
    return response

def download(urls):
    with ThreadPoolExecutor(max_workers=THREAD_POOL) as executor:
        # wrap in a list() to wait for all requests to complete
        for response in list(executor.map(get, urls)):
            if response.status_code == 200:
                print(response.content)

def main():
    logging.basicConfig(
        format='%(asctime)s.%(msecs)03d %(levelname)-8s %(message)s',
        level=logging.INFO,
        datefmt='%Y-%m-%d %H:%M:%S'
    )

    urls = [
        "https://httpstat.us/200",
        "https://httpstat.us/200",
        "https://httpstat.us/200",
        "https://httpstat.us/404",
        "https://httpstat.us/503"
    ]

    download(urls)

if __name__ == "__main__":
    main()

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])

一个使用tornado的异步网络库解决方案

from tornado import ioloop, httpclient

i = 0

def handle_request(response):
    print(response.code)
    global i
    i -= 1
    if i == 0:
        ioloop.IOLoop.instance().stop()

http_client = httpclient.AsyncHTTPClient()
for url in open('urls.txt'):
    i += 1
    http_client.fetch(url.strip(), handle_request, method='HEAD')
ioloop.IOLoop.instance().start()

这段代码使用非阻塞网络I/O，没有任何限制。它可以扩展到数万个打开的连接。它将在单个线程中运行，但比任何线程解决方案都要快。签出非阻塞I/O