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

(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()

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。

(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()

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。

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)