I am opening a file which has 100,000 URL's. I need to send an HTTP request to each URL and print the status code. I am using Python 2.6, and so far looked at the many confusing ways Python implements threading/concurrency. I have even looked at the python concurrence library, but cannot figure out how to write this program correctly. Has anyone come across a similar problem? I guess generally I need to know how to perform thousands of tasks in Python as fast as possible - I suppose that means 'concurrently'.


当前回答

对于您的情况,线程可能会做的技巧,因为您可能会花费大部分时间等待响应。标准库中有一些有用的模块,如Queue,可能会有所帮助。

我以前做过类似的并行下载文件的事情,对我来说已经足够好了,但它不是你所说的那种规模。

如果您的任务对cpu的限制更大,您可能需要考虑multiprocessing模块,它将允许您利用更多的cpu /内核/线程(更多的进程不会相互阻塞,因为锁定是每个进程)

其他回答

创建epoll对象, 打开许多客户端TCP套接字, 调整他们的发送缓冲区比请求头多一点, 发送一个请求头-它应该是即时的,只是放置到缓冲区, 在epoll对象中注册套接字 在epoll obect上做。poll, 从.poll中读取每个套接字的前3个字节, 将它们写入sys。Stdout后面跟着\n(不刷新), 关闭客户端套接字。

限制同时打开的套接字数量-在创建套接字时处理错误。只有当另一个套接字关闭时才创建新的套接字。 调整操作系统限制。 尝试分成几个(不是很多)进程:这可能有助于更有效地使用CPU。

这个扭曲的异步web客户端运行得相当快。

#!/usr/bin/python2.7

from twisted.internet import reactor
from twisted.internet.defer import Deferred, DeferredList, DeferredLock
from twisted.internet.defer import inlineCallbacks
from twisted.web.client import Agent, HTTPConnectionPool
from twisted.web.http_headers import Headers
from pprint import pprint
from collections import defaultdict
from urlparse import urlparse
from random import randrange
import fileinput

pool = HTTPConnectionPool(reactor)
pool.maxPersistentPerHost = 16
agent = Agent(reactor, pool)
locks = defaultdict(DeferredLock)
codes = {}

def getLock(url, simultaneous = 1):
    return locks[urlparse(url).netloc, randrange(simultaneous)]

@inlineCallbacks
def getMapping(url):
    # Limit ourselves to 4 simultaneous connections per host
    # Tweak this number, but it should be no larger than pool.maxPersistentPerHost 
    lock = getLock(url,4)
    yield lock.acquire()
    try:
        resp = yield agent.request('HEAD', url)
        codes[url] = resp.code
    except Exception as e:
        codes[url] = str(e)
    finally:
        lock.release()


dl = DeferredList(getMapping(url.strip()) for url in fileinput.input())
dl.addCallback(lambda _: reactor.stop())

reactor.run()
pprint(codes)

(工具)

Apache Bench是您所需要的全部。—用于测量HTTP web服务器性能的命令行计算机程序

给你一篇不错的博客文章:https://www.petefreitag.com/item/689.cfm(来自Pete Freitag)

下面是一个“异步”解决方案,它不使用asyncio,而是使用asyncio使用的低级机制(在Linux上):select()。(或者asyncio可能使用poll或epoll,但这是类似的原理。)

它是对PyCurl示例的稍微修改版本。

(为了简单起见,它多次请求相同的URL,但您可以轻松地修改它以检索一系列不同的URL。)

(另一个轻微的修改可以使这个检索相同的URL作为一个无限循环。提示:将while url和句柄更改为while句柄,将while nprocessed<nurls更改为while 1。)

import pycurl,io,gzip,signal, time, random
signal.signal(signal.SIGPIPE, signal.SIG_IGN)  # NOTE! We should ignore SIGPIPE when using pycurl.NOSIGNAL - see the libcurl tutorial for more info

NCONNS = 2  # Number of concurrent GET requests
url    = 'example.com'
urls   = [url for i in range(0x7*NCONNS)]  # Copy the same URL over and over

# Check args
nurls  = len(urls)
NCONNS = min(NCONNS, nurls)
print("\x1b[32m%s \x1b[0m(compiled against 0x%x)" % (pycurl.version, pycurl.COMPILE_LIBCURL_VERSION_NUM))
print(f'\x1b[37m{nurls} \x1b[91m@ \x1b[92m{NCONNS}\x1b[0m')

# Pre-allocate a list of curl objects
m         = pycurl.CurlMulti()
m.handles = []
for i in range(NCONNS):
  c = pycurl.Curl()
  c.setopt(pycurl.FOLLOWLOCATION,  1)
  c.setopt(pycurl.MAXREDIRS,       5)
  c.setopt(pycurl.CONNECTTIMEOUT,  30)
  c.setopt(pycurl.TIMEOUT,         300)
  c.setopt(pycurl.NOSIGNAL,        1)
  m.handles.append(c)

handles    = m.handles  # MUST make a copy?!
nprocessed = 0
while nprocessed<nurls:

  while urls and handles:  # If there is an url to process and a free curl object, add to multi stack
    url   = urls.pop(0)
    c     = handles.pop()
    c.buf = io.BytesIO()
    c.url = url  # store some info
    c.t0  = time.perf_counter()
    c.setopt(pycurl.URL,        c.url)
    c.setopt(pycurl.WRITEDATA,  c.buf)
    c.setopt(pycurl.HTTPHEADER, [f'user-agent: {random.randint(0,(1<<256)-1):x}', 'accept-encoding: gzip, deflate', 'connection: keep-alive', 'keep-alive: timeout=10, max=1000'])
    m.add_handle(c)

  while 1:  # Run the internal curl state machine for the multi stack
    ret, num_handles = m.perform()
    if ret!=pycurl.E_CALL_MULTI_PERFORM:  break

  while 1:  # Check for curl objects which have terminated, and add them to the handles
    nq, ok_list, ko_list = m.info_read()
    for c in ok_list:
      m.remove_handle(c)
      t1 = time.perf_counter()
      reply = gzip.decompress(c.buf.getvalue())
      print(f'\x1b[33mGET  \x1b[32m{t1-c.t0:.3f}  \x1b[37m{len(reply):9,}  \x1b[0m{reply[:32]}...')  # \x1b[35m{psutil.Process(os.getpid()).memory_info().rss:,} \x1b[0mbytes')
      handles.append(c)
    for c, errno, errmsg in ko_list:
      m.remove_handle(c)
      print('\x1b[31mFAIL {c.url} {errno} {errmsg}')
      handles.append(c)
    nprocessed = nprocessed + len(ok_list) + len(ko_list)
    if nq==0: break

  m.select(1.0)  # Currently no more I/O is pending, could do something in the meantime (display a progress bar, etc.). We just call select() to sleep until some more data is available.

for c in m.handles:
  c.close()
m.close()

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。