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

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。

其他回答

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。

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

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)

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。

自从2010年这篇文章发布以来,事情发生了很大的变化,我还没有尝试过所有其他的答案,但我尝试了一些,我发现使用python3.6对我来说这是最好的。

在AWS上运行时,我每秒可以获取大约150个独特的域名。

import concurrent.futures
import requests
import time

out = []
CONNECTIONS = 100
TIMEOUT = 5

tlds = open('../data/sample_1k.txt').read().splitlines()
urls = ['http://{}'.format(x) for x in tlds[1:]]

def load_url(url, timeout):
    ans = requests.head(url, timeout=timeout)
    return ans.status_code

with concurrent.futures.ThreadPoolExecutor(max_workers=CONNECTIONS) as executor:
    future_to_url = (executor.submit(load_url, url, TIMEOUT) for url in urls)
    time1 = time.time()
    for future in concurrent.futures.as_completed(future_to_url):
        try:
            data = future.result()
        except Exception as exc:
            data = str(type(exc))
        finally:
            out.append(data)

            print(str(len(out)),end="\r")

    time2 = time.time()

print(f'Took {time2-time1:.2f} s')