(Python) How can I apply asyncio in while loop with accumulator? - python

I have a block of codes that works well in fetching data from API requests to a specific site. The issue is that the site only gives me a limit of 50 objects for each call, and I have to make multiple calls. As a result, it takes me too long to finish the fetching work (sometimes I have to wait nearly 20 minutes). Here are my codes:
import concurrent.futures
import requests
supply = 3000
offset = 0
token_ids = []
while offset < supply:
url = "url_1" + str(offset)
response = requests.request("GET", url)
a = response.json()
assets = a["assets"]
def get_token_ids(an):
if str(an['sell_orders']) == 'None' and str(an['last_sale']) == 'None' and str(an['num_sales']) == '0':
token_ids.append(str(an['token_id']))
with concurrent.futures.ThreadPoolExecutor() as executor:
results = [executor.submit(get_token_ids, asset) for asset in assets]
offset += 50
print(token_ids)
The problem is that the codes run through and wait for all actions to be finished before making another request. I am thinking of an improvement that when the request is sent, the offset value gets added, and the loop processes to another request, thus I don't have to wait. I don't know how to do it, I studied 'asyncio', but it is still a challenge for me. Can anyone help me with this?

The problem is that Requests is not asynchronous code, so each of its network calls blocks the loop until its completion.
https://docs.python-requests.org/en/latest/user/advanced/#blocking-or-non-blocking
Therefore, it is better to try asynchronous libraries, for example, aiohttp:
https://github.com/aio-libs/aiohttp
Example
Create session for all connections:
async with aiohttp.ClientSession() as session:
and run all desired requests:
results = await asyncio.gather(
*[get_data(session, offset) for offset in range(0, supply, step)]
)
here, requests are executed asynchronously, with session.get(url) gets only the response headers, and the content gets await response.json():
async with session.get(url) as response:
a = await response.json()
And in the main block main loop starts:
loop = asyncio.get_event_loop()
token_ids = loop.run_until_complete(main())
loop.close()
The full code
import aiohttp
import asyncio
async def get_data(session, offset):
token_ids = []
url = "url_1" + str(offset)
async with session.get(url) as response:
# For tests:
# print("Status:", response.status)
# print("Content-type:", response.headers['content-type'])
a = await response.json()
assets = a["assets"]
for asset in assets:
if str(asset['sell_orders']) == 'None' and str(asset['last_sale']) == 'None' and str(asset['num_sales']) == '0':
token_ids.append(str(asset['token_id']))
return token_ids
async def main():
supply = 3000
step = 50
token_ids = []
# Create session for all connections and pass it to "get" function
async with aiohttp.ClientSession() as session:
results = await asyncio.gather(
*[get_data(session, offset) for offset in range(0, supply, step)]
)
for ids in results:
token_ids.extend(ids)
return token_ids
if __name__ == "__main__":
# asynchronous code start here
loop = asyncio.get_event_loop()
token_ids = loop.run_until_complete(main())
loop.close()
# asynchronous code end here
print(token_ids)

Related

Python aiohttp how to handle client session token timeout

I am making several 100's of http request using aiohttp. I am relatively new to the async world but have managed to get the basic code working.
First I am generating a token. Then, making aiohttp calls using this token.
Token has a validity of 30 mins. So I am assuming if my calls run for more than 30 mins then they will start failing.
How do I update my code to plug-in a new token after 30 mins then resume the remaining calls. This my first time implementing async calls, so relatively clueless on how to handle this.
async def a_get_all_user_details(urls):
results = []
connector = aiohttp.TCPConnector(limit=70)
timeout = aiohttp.ClientTimeout(total=None, connect=300, sock_connect=300, sock_read=None)
auth_token = get_token() # token expires in 30 mins
headers = {
'accept': 'application/json',
'Authorization': 'Bearer ' + auth_token
}
async with aiohttp.ClientSession(trust_env=True, headers=headers, connector=connector, timeout=timeout) as session:
for url in urls:
result = asyncio.ensure_future(a_get_user_details(url, session))
results.append(result)
responses = await asyncio.gather(*results)
return responses
def main():
loop = asyncio.get_event_loop()
future = asyncio.ensure_future(a_get_all_user_details(search_urls))
user_details = loop.run_until_complete(future)
Maybe there's simpler way to do it but here's my take:
The problem is that there are many connections in the fly when you want to refresh session. When you close the session and create new one, active connections which are waiting for data throw an exception.
In my example I have a list of all sessions and when time arrives I simply create new session (with new token) and append it to the list. The new connections will use the last (freshest) session.
At the end of script I close all sessions.
import aiohttp
import asyncio
sessions = []
async def get_token():
return "XYZ"
async def refresh_session():
# this function periodically refreshes the token every X sec
connector = aiohttp.TCPConnector(limit=3)
timeout = aiohttp.ClientTimeout(
total=None, connect=300, sock_connect=300, sock_read=None
)
while True:
headers = {
"accept": "application/json",
"Authorization": "Bearer " + await get_token(),
}
sessions.append(
aiohttp.ClientSession(
trust_env=True,
headers=headers,
connector=connector,
timeout=timeout,
)
)
print("New session created")
await asyncio.sleep(5) # every 5 seconds refresh session
async def get_user_detail(url):
# wait for session to show up:
while not sessions:
await asyncio.sleep(1)
# use last (freshest) session:
async with sessions[-1].get(url) as resp:
assert resp.status == 200
html = await resp.text()
return f"some result for {url} length of data {len(html)}"
async def get_user_details(urls):
results = []
for url in urls:
results.append(asyncio.ensure_future(get_user_detail(url)))
responses = await asyncio.gather(*results)
return responses
async def main():
# some urls to gather:
urls = [
"https://www.google.com",
"https://www.microsoft.com",
"https://www.yahoo.com",
] * 30
t1 = asyncio.create_task(refresh_session())
t2 = asyncio.create_task(get_user_details(urls))
# finish when first task ends (in this case get_user_details())
done, _ = await asyncio.wait([t1, t2], return_when=asyncio.FIRST_COMPLETED)
# close all opened sessions:
for s in sessions:
await s.close()
# print the result
print("Domains gathered ", len(done.pop().result()))
if __name__ == "__main__":
asyncio.run(main())
This prints:
New session created
New session created
Domains gathered 90

Async check of several hundred proxies

I need to check several hundred proxy servers and get the number of not working. Script for this
import urllib.request
import socket
net = ['http://192.168.1.1:8080',
'http://192.168.1.2:8080',
'http://192.168.1.3:8080',
'http://192.168.1.4:8080',
'http://192.168.1.5:8080',
'http://192.168.1.6:8080',
'http://192.168.1.7:8080',
'http://192.168.1.8:8080',
'http://192.168.1.9:8080',
'http://192.168.1.10:8080']
fail = 0
socket.setdefaulttimeout(3)
for x in net:
try:
print(x)
proxy = urllib.request.ProxyHandler({'http': (x)})
opener = urllib.request.build_opener(proxy)
urllib.request.install_opener(opener)
urllib.request.urlretrieve('http://google.com')
except IOError:
print ("Connection error")
fail+=1
print(fail)
Proxies in the list, I have given a simple version.
It takes 55 seconds to check 250 working proxies. I can't wait that long, need to increase the execution speed.
How can this be done using async?
This should give you an idea of how to approach it. You have to wrap the various connection blocks in try, except yourself.
NOTE: This code is not tested as I do not have any way of doing so.
import asyncio, aiohttp
def returnPartionedList(inputlist, x=100):
return([inputlist[i:i + x] for i in range(0, len(inputlist), x)])
# Returns: Original list split into segments of x.
async def TestProxy(url, proxy, session):
async with session.get(url, proxy=proxy, timeout=3) as response:
if response.status == 200:
_ = await response.text()
return(proxy)
async def TestProxies(listofproxies):
returnResults = []
url = "https://google.com" # Test proxy with this url
ProxyPartitions = returnPartionedList(listofproxies, 20) # Rate limit 20 per second
for partition in ProxyPartitions:
ProxyTasks = []
async with aiohttp.ClientSession() as session:
for proxy in partition:
ProxyTasks.append(asyncio.create_task(TestProxy(url, proxy, session)))
results = await asyncio.gather(*ProxyTasks, return_exceptions=False)
if results:
for result in results:
if result:
returnResults.append(result)
await asyncio.sleep(1)
return(returnResults)
async def main():
listofproxies = [
'http://10.10.1.1:8080',
'http://10.10.1.2:8080',
'http://10.10.1.3:8080',
'http://10.10.1.4:8080',
'http://10.10.1.5:8080',
'http://10.10.1.6:8080',
'http://10.10.1.7:8080',
'http://10.10.1.8:8080',
'http://10.10.1.9:8080',
'http://10.10.1.10:8080'
]
test_proxies = await TestProxies(listofproxies)
print(test_proxies)
if __name__ == "__main__":
asyncio.run(main())

Problem in using async and await in python

I am trying to using async and await, I am still new to it I cannot figure out what I am doing wrong
import requests
import bs4
import colorama
from colorama import Fore
import time
import datetime
import asyncio
async def get_html(episode_number: int) -> str:
print(Fore.YELLOW + f"Getting HTML for episode {episode_number}", flush=True)
url = f'https://talkpython.fm/{episode_number}'
async with aiohttp.ClientSession() as session:
async with session.get(url) as resp:
resp.raise_for_status()
return await resp.text
await resp.raise_for_status()
# return await resp.text
def get_title(html: str, episode_number: int) -> str:
print(colorama.Fore.CYAN + f"Getting TITLE for episode {episode_number}", flush=True)
soup = bs4.BeautifulSoup(html, 'html.parser')
header = soup.select_one('h1')
if not header:
return "MISSING"
return header.text.strip()
def main():
t0 = datetime.datetime.now()
print(colorama.Fore.WHITE + ' App started.', flush=True )
loop = asyncio.get_event_loop()
final_task = asyncio.gather(loop)
#get_title_range()
dt = datetime.datetime.now() - t0
loop.run_until_complete(final_task)
print(colorama.Fore.CYAN + "Done. " + ' App exiting total time: {:,.2f} sec.'.format(dt.total_seconds()), flush=True)
def get_title_range():
for n in range(150, 170):
html = get_html(n)
title = get_title(html, n)
print(Fore.CYAN + f"Title found: {title}", flush=True)
if __name__ == '__main__':
main()
It looks like you're not initializing tasks for your event loop to run on. I typically follow this pattern:
async def main():
headers = {'Connection': 'keep-alive', 'Content-Type': 'application/json', 'Authorization': auth}
url = 'some-api.com/post-request-something'
# We use a session to take advantage of tcp keep-alive
timeout = aiohttp.ClientTimeout(total=10000)
async with aiohttp.ClientSession(timeout=timeout) as session:
tasks = [async_wrap(session, q, url, headers) for q in queue]
# gather literally 'gathers' all the tasks and schedules them in the event loop
await asyncio.gather(*tasks, return_exceptions=True)
if __name__ == '__main__':
ts = time()
# Create the asyncio event loop - from the main function
loop = asyncio.get_event_loop()
try:
loop.run_until_complete(main())
finally:
# Lets avoid an unclosed loop running a DDoS attack on ourselves
loop.close()
logger.info('Took %s seconds to complete', time() - ts)
note the line containing, takes those tasks gathered to schedule as coroutines in the main event loop:
loop.run_until_complete(main())
and then this, which calls my function, async_wrap() for each record I wanted to send in the http client (which I had stored in a list), but in your case it would call your asynchronous function get_html() using each record from get_title_range():
tasks = [async_wrap(session, q, url, headers) for q in queue] # -> mine
await asyncio.gather(*tasks, return_exceptions=True) # -> gather those tasks!
tasks = [get_html(episode_number=episode) for episode in list_of_episode_nums] # -> yours
await asyncio.gather(*tasks, return_exceptions=True) # -> gather those tasks!
Hope this helps you shore some details up, but unfortunately, asynchronous code can be quite a headache, requiring lots of trial-and-error.

How to avoid error 429 (Too Many Requests) python with Asyncio

I am using the following code to make requests with aiohttp client. The server that I am trying to send request has a 30k request limit per hour per IP. So I am getting 429 too many request error. I want to put the job on sleep whenever it hits the limit.
I can extract the x_rateLimit_reset from the header so I thought I could use it to put the job on sleep but I observed very strange behavior. Sometimes the job the sleep time becomes negative and sometimes it gets stuck in sleeping mode.
For example, the last time that I ran the job, it first slept for 2000 seconds and then after the time passed, it again tried to sleep for another 2500 seconds and got stuck in sleeping mode. I think maybe the other parallel processes caused the issue so was wondering how to deal with too many request error msg when using Asyncio.
#backoff.on_exception(backoff.expo, (asyncio.TimeoutError, aiohttp.client_exceptions.ServerDisconnectedError,TooManyRequests),
max_time=300)
async def fetch(self, url, session, params):
try:
async with session.get(url, params=params) as response:
now = int(time.time())
print(response)
output = await response.read()
output = json.loads(output)
if 'X-RateLimit-Remaining' in response.headers:
rate = response.headers['X-RateLimit-Remaining']
if 'status' in output and output['status'] == 429:
x_rateLimit_reset = int(response.headers['X-RateLimit-Reset'])
print("sleep mode")
seconds = x_rateLimit_reset - now
LOGGER.info("The job will sleep for {} seconds".format(seconds))
time.sleep(max(seconds,0))
raise TooManyRequests()
return output
except (asyncio.TimeoutError, TypeError, json.decoder.JSONDecodeError,
aiohttp.client_exceptions.ServerDisconnectedError) as e:
print(str(e))
async def bound_fetch(self, sem, url, session, params):
# Getter function with semaphore.
async with sem:
output = await self.fetch(url, session, params)
return {"url": url, "output": output}
Edited:
This is how I initiate bound_fetch and define the URLs:
def get_responses(self, urls, office_token, params=None):
loop = asyncio.get_event_loop()
future = asyncio.ensure_future(self.run(office_token, urls, params))
responses = loop.run_until_complete(future)
return responses
async def run(self, office_token, urls, params):
tasks = []
# create instance of Semaphore
sem = asyncio.BoundedSemaphore(200)
timeout = ClientTimeout(total=1000)
async with ClientSession(auth=BasicAuth(office_token, password=' '), timeout=timeout,
connector=TCPConnector(ssl=False)) as session:
for url in urls:
# pass Semaphore and session to every GET request
task = asyncio.ensure_future(self.bound_fetch(sem, url, session, params))
tasks.append(task)
responses = await asyncio.gather(*tasks)
return responses
urls = [
"{}/{}".format(self.base_url, "{}?page={}&api_key={}".format(object_name, page_number, self.api_keys))
for page_number in range(batch * chunk_size + 1, chunk_size * (1 + batch) + 1)]
Main reason you are using time.sleep() instead await asyncio.sleep().
UPDATE
Here is minimal working solution and some comment how it works.
Please use it to adopt your solution.
Take a look on asyncio-throttle
import aiohttp
import asyncio
from datetime import datetime
async def fetch(session, task): # fetching urls and mark result of execution
async with session.get(task['url']) as response:
if response.status != 200:
# response.raise_for_status()
# Here you need to somehow handle 429 code if it acquired
# In my example I just skip it.
task['result'] = response.status
task['status'] = 'done'
await response.text() # just to be sure we acquire data
print(f"{str(datetime.now())}: Got result of {task['url']}") # logging
task['result'] = response.status
task['status'] = 'done'
async def fetch_all(session, urls, persecond):
# convert to list of dicts
url_tasks = [{'url': i, 'result': None, 'status': 'new'} for i in urls]
n = 0 # counter
while True:
# calc how many tasks are fetching right now
running_tasks = len([i for i in url_tasks if i['status'] in ['fetch']])
# calc how many tasks are still need to be executed
is_tasks_to_wait = len([i for i in url_tasks if i['status'] != 'done'])
# check we are not in the end of list n < len()
# check we have room for one more task
if n < len(url_tasks) and running_tasks < persecond:
url_tasks[n]['status'] = 'fetch'
#
# Here is main trick
# If you schedule task inside running loop
# it will start to execute sync code until find some await
#
asyncio.create_task(fetch(session, url_tasks[n]))
n += 1
print(f'Schedule tasks {n}. '
f'Running {running_tasks} '
f'Remain {is_tasks_to_wait}')
# Check persecond constrain and wait a sec (or period)
if running_tasks >= persecond:
print('Throttling')
await asyncio.sleep(1)
#
# Here is another main trick
# To keep asyncio.run (or loop.run_until_complete) executing
# we need to wait a little than check that all tasks are done and
# wait and so on
if is_tasks_to_wait != 0:
await asyncio.sleep(0.1) # wait all tasks done
else:
# All tasks done
break
return url_tasks
async def main():
urls = ['http://google.com/?1',
'http://google.com/?2',
'http://google.com/?3']*3
async with aiohttp.ClientSession() as session:
res = await fetch_all(session, urls, 3)
print(res)
if __name__ == '__main__':
asyncio.run(main())
# (asyncio.run) do cancel all pending tasks (we do not have them,
# because we check all task done)
# (asyncio.run) do await canceling all tasks
# (asyncio.run) do stop loop
# exit program

Making 1 milion requests with aiohttp/asyncio - literally

I followed up this tutorial: https://pawelmhm.github.io/asyncio/python/aiohttp/2016/04/22/asyncio-aiohttp.html and everything works fine when I am doing like 50 000 requests. But I need to do 1 milion API calls and then I have problem with this code:
url = "http://some_url.com/?id={}"
tasks = set()
sem = asyncio.Semaphore(MAX_SIM_CONNS)
for i in range(1, LAST_ID + 1):
task = asyncio.ensure_future(bound_fetch(sem, url.format(i)))
tasks.add(task)
responses = asyncio.gather(*tasks)
return await responses
Because Python needs to create 1 milion tasks, it basically just lags and then prints Killed message in terminal. Is there any way to use a generator insted of pre-made set (or list) of urls? Thanks.
Schedule all 1 million tasks at once
This is the code you are talking about. It takes up to 3 GB RAM so it is easily possible that it will be terminated by the operating system if you have low free memory.
import asyncio
from aiohttp import ClientSession
MAX_SIM_CONNS = 50
LAST_ID = 10**6
async def fetch(url, session):
async with session.get(url) as response:
return await response.read()
async def bound_fetch(sem, url, session):
async with sem:
await fetch(url, session)
async def fetch_all():
url = "http://localhost:8080/?id={}"
tasks = set()
async with ClientSession() as session:
sem = asyncio.Semaphore(MAX_SIM_CONNS)
for i in range(1, LAST_ID + 1):
task = asyncio.create_task(bound_fetch(sem, url.format(i), session))
tasks.add(task)
return await asyncio.gather(*tasks)
if __name__ == '__main__':
asyncio.run(fetch_all())
Use queue to streamline the work
This is my suggestion how to use asyncio.Queue to pass URLs to worker tasks. The queue is filled as-needed, there is no pre-made list of URLs.
It takes only 30 MB RAM :)
import asyncio
from aiohttp import ClientSession
MAX_SIM_CONNS = 50
LAST_ID = 10**6
async def fetch(url, session):
async with session.get(url) as response:
return await response.read()
async def fetch_worker(url_queue):
async with ClientSession() as session:
while True:
url = await url_queue.get()
try:
if url is None:
# all work is done
return
response = await fetch(url, session)
# ...do something with the response
finally:
url_queue.task_done()
# calling task_done() is necessary for the url_queue.join() to work correctly
async def fetch_all():
url = "http://localhost:8080/?id={}"
url_queue = asyncio.Queue(maxsize=100)
worker_tasks = []
for i in range(MAX_SIM_CONNS):
wt = asyncio.create_task(fetch_worker(url_queue))
worker_tasks.append(wt)
for i in range(1, LAST_ID + 1):
await url_queue.put(url.format(i))
for i in range(MAX_SIM_CONNS):
# tell the workers that the work is done
await url_queue.put(None)
await url_queue.join()
await asyncio.gather(*worker_tasks)
if __name__ == '__main__':
asyncio.run(fetch_all())
asyncio is memory bound (like any other program). You can not spawn more task that memory can hold. My guess is that you hit a memory limit. Check dmesg for more information.
1 millions RPS doesn't mean there is 1M tasks. A task can do several request in the same second.

Categories

Resources