Scrapy框架将快速和专业地解决您的问题。它还将缓存所有请求，以便稍后可以重新运行失败的请求。

将该脚本保存为quotes_spider.py。

# quote_spiders.py
import json
import string
import scrapy
from scrapy.crawler import CrawlerProcess
from scrapy.item import Item, Field

class TextCleaningPipeline(object):
    def _clean_text(self, text):
        text = text.replace('“', '').replace('”', '')
        table = str.maketrans({key: None for key in string.punctuation})
        clean_text = text.translate(table)
        return clean_text.lower()

    def process_item(self, item, spider):
        item['text'] = self._clean_text(item['text'])
        return item

class JsonWriterPipeline(object):
    def open_spider(self, spider):
        self.file = open(spider.settings['JSON_FILE'], 'a')

    def close_spider(self, spider):
        self.file.close()

    def process_item(self, item, spider):
        line = json.dumps(dict(item)) + "\n"
        self.file.write(line)
        return item

class QuoteItem(Item):
    text = Field()
    author = Field()
    tags = Field()
    spider = Field()

class QuoteSpider(scrapy.Spider):
    name = "quotes"

    def start_requests(self):
        urls = [
            'http://quotes.toscrape.com/page/1/',
            'http://quotes.toscrape.com/page/2/',
            # ...
        ]
        for url in urls:
            yield scrapy.Request(url=url, callback=self.parse)

    def parse(self, response):
        for quote in response.css('div.quote'):
            item = QuoteItem()
            item['text'] = quote.css('span.text::text').get()
            item['author'] = quote.css('small.author::text').get()
            item['tags'] = quote.css('div.tags a.tag::text').getall()
            item['spider'] = self.name
            yield item

if __name__ == '__main__':
    settings = dict()
    settings['USER_AGENT'] = 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)'
    settings['HTTPCACHE_ENABLED'] = True
    settings['CONCURRENT_REQUESTS'] = 20
    settings['CONCURRENT_REQUESTS_PER_DOMAIN'] = 20
    settings['JSON_FILE'] = 'items.jl'
    settings['ITEM_PIPELINES'] = dict()
    settings['ITEM_PIPELINES']['__main__.TextCleaningPipeline'] = 800
    settings['ITEM_PIPELINES']['__main__.JsonWriterPipeline'] = 801

    process = CrawlerProcess(settings=settings)
    process.crawl(QuoteSpider)
    process.start()

紧随其后的是

$ pip install Scrapy
$ python quote_spiders.py 

为了微调scraper，相应地调整CONCURRENT_REQUESTS和CONCURRENT_REQUESTS_PER_DOMAIN设置。

最简单的方法是使用Python的内置线程库。它们不是“真正的”/内核线程。它们有问题(比如序列化)，但足够好了。你需要一个队列和线程池。这里有一个选项，但是编写自己的选项很简单。您无法并行处理所有100,000个调用，但可以同时发出100个(或左右)调用。

使用线程池是一个很好的选择，这将使这相当容易。不幸的是，python并没有一个标准库来简化线程池。但这里有一个不错的图书馆，你应该开始: http://www.chrisarndt.de/projects/threadpool/

来自他们网站的代码示例:

pool = ThreadPool(poolsize)
requests = makeRequests(some_callable, list_of_args, callback)
[pool.putRequest(req) for req in requests]
pool.wait()

希望这能有所帮助。

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。

使用grequests，它是requests + Gevent模块的组合。

GRequests允许您使用带有Gevent的Requests来轻松地生成异步HTTP请求。

用法很简单:

import grequests

urls = [
   'http://www.heroku.com',
   'http://tablib.org',
   'http://httpbin.org',
   'http://python-requests.org',
   'http://kennethreitz.com'
]

创建一组未发送的请求:

>>> rs = (grequests.get(u) for u in urls)

同时发送:

>>> grequests.map(rs)
[<Response [200]>, <Response [200]>, <Response [200]>, <Response [200]>, <Response [200]>]

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