利用Python发送 10 万个 http 请求

from threading import Thread

import sys

from queue import Queue

import requests

concurrent = 200

def doWork():

while True:

url = q.get()

status, url = getStatus(url)

doSomethingWithResult(status, url)

q.task_done()

def getStatus(ourl):

try:

res = requests.get(ourl)

return res.status_code, ourl

except:

return "error", ourl

def doSomethingWithResult(status, url):

print(status, url)

q = Queue(concurrent * 2)

for i in range(concurrent):

t = Thread(target=doWork)

t.daemon = True

t.start()

try:

for url in open("urllist.txt"):

q.put(url.strip())

q.join()

except KeyboardInterrupt:

sys.exit(1)

import concurrent.futures

import requests

out = []

CONNECTIONS = 100

TIMEOUT = 5

urls = []

with open("urllist.txt") as reader:

for url in reader:

urls.append(url.strip())

def load_url(url, timeout):

ans = requests.get(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)

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(data)

import asyncio

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 sys

assert sys.version_info >= (3, 7), "Script requires Python 3.7+."

with open("urllist.txt") as infile:

urls = set(map(str.strip, infile))

asyncio.run(make_requests(urls=urls))

import grequests

urls = []

with open("urllist.txt") as reader:

for url in reader:

urls.append(url.strip())

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

for result in grequests.map(rs):

print(result.status_code, result.url)

>>> def exception_handler(request, exception):

...    print("Request failed")

>>> reqs = [

...    grequests.get('http://httpbin.org/delay/1', timeout=0.001),

...    grequests.get('http://fakedomain/'),

...    grequests.get('http://httpbin.org/status/500')]

>>> grequests.map(reqs, exception_handler=exception_handler)

Request failed

Request failed

[None, None, <Response [500]>]