Python asyncio link body and response from it in aiohttp asyncio - python

I have async requests, i send 100 requests and get response from them
I send body to get resonse, the problem is i caanot join request body with response,
sometime there is no response
i collect requests into a list
def __gaterTasks(self, session, total_schets):
_tasks = []
_updates = []
for schet in total_schets:
_payload_objct = PayloadParams.objects.using('analytic_db').get(payload=schet['payload'])
_payload_objct.status = True
_updates.append(_payload_objct)
_tasks.append(
session.get(url=self.url, body=schet['payload'])
)
PayloadParams.objects.using('analytic_db').bulk_update(_updates, ['status'])
return _tasks
i need to link body=schet['payload'] with the response with i get from it
the function with runs
async def get_data(self, total_schets):
async with aiohttp.ClientSession(trust_env=True, auth=aiohttp.BasicAuth()) as session:
tasks = self.__gaterTasks(session=session, total_schets=total_schets)
responses = await asyncio.gather(*tasks)
for each in responses:
_each = await each.json()

Related

Using Python asyncio and aiohttp - one request is fast, two or more very slow

I'm trying to speed up multiple requests to the US Census API by using asyncio and aiohttp.
If I make a request with only one lat/lon pair, it is fast, less than 1 second. With two or more, it is very slow, always 20 seconds or more.
Can't figure out why.
import pprint
import aiohttp
import time
async def getCensusInfo(lat, lon, session):
url = f'https://geocoding.geo.census.gov/geocoder/geographies/coordinates?x={lon}&y={lat}&format=json&benchmark=Public_AR_Current&vintage=Census2020_Current&layers=all'
async with session.get(url) as response:
result = await response.json()
return result
async def main():
async with aiohttp.ClientSession() as session:
tasks = []
locations = [(27.652250703997332, -80.42654388841413)]
locations = [(27.652250703997332, -80.42654388841413), (27.459669616175788, -80.30859777448217)]
for location in locations:
tasks.append(getCensusInfo(location[0], location[1], session))
results = await asyncio.gather(*tasks, return_exceptions=True)
for result in results:
pprint.pprint(result["result"]["geographies"]["Incorporated Places"][0], sort_dicts=False, indent = 4)
start_time = time.perf_counter()
asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
asyncio.run(main())
duration = time.perf_counter() - start_time
print(f'Time to download geoCode data: {duration} seconds')

Python: How to use asyncio with huge list of urls to send asynchronous requests?

I have a huge list of urls that I need to send request and retrieve a json data.But the problem is Since the list with the urls is too big to load it at once, I would like to read the urls one by one, and each time the url is loaded, it should start a request. My code work for small list(~20k) with no problem but I got stuck with a huge list.
It would be great if you could tell me how to change my code, to get it to send asynchronous requests for each url of the urls list. Thank you in advance.
Here is my code:
import json
import urllib
from urllib.parse import quote
import time
import asyncio
import aiohttp
import json
from json.decoder import JSONDecodeError
urls = ["url_1", "url_2". "url_3"........"url_3,000,000"]
START = time.monotonic()
class RateLimiter:
RATE = 20
MAX_TOKENS = 10
def __init__(self, client):
self.client = client
self.tokens = self.MAX_TOKENS
self.updated_at = time.monotonic()
async def get(self, *args, **kwargs):
await self.wait_for_token()
now = time.monotonic() - START
print(f'{now:.0f}s: ask {args[0]}')
return self.client.get(*args, **kwargs)
async def wait_for_token(self):
while self.tokens < 1:
self.add_new_tokens()
await asyncio.sleep(0.1)
self.tokens -= 1
def add_new_tokens(self):
now = time.monotonic()
time_since_update = now - self.updated_at
new_tokens = time_since_update * self.RATE
if self.tokens + new_tokens >= 1:
self.tokens = min(self.tokens + new_tokens, self.MAX_TOKENS)
self.updated_at = now
async def fetch_one(client, url):
# Watch out for the extra 'await' here!
async with await client.get(url) as resp:
for response in resp:
try:
results = await response.json()
try:
answer = results['results'][0]['locations']
output = {
"Provided location" : results['results'][0]['providedLocation'].get('location'),
"City": answer[0].get('adminArea5'),
"State" : answer[0].get('adminArea3'),
"Country": answer[0].get('adminArea1')
}
json_results.append(output)
except (IndexError,JSONDecodeError):
output = {
"Provided location": 'null',
"City": 'null',
"State" : 'null',
"Country":'null'
}
json_results.append(output)
except:
output = {
"Provided location": None,
"City": 'null',
"State" : 'null',
"Country":'null'
}
json_results.append(output)
now = time.monotonic() - START
async def main():
async with aiohttp.ClientSession() as client:
client = RateLimiter(client)
tasks = [asyncio.ensure_future(fetch_one(client, url)) for url in urls]
await asyncio.gather(*tasks)
if __name__ == '__main__':
asyncio.run(main())

Asyncio - how to limit requests per 1 second?

I'm new to asyncio, trying to make async calls to API, but when I'm sending more than 1 request/second the API responding with 429 status code - too many requests... According to API documentation, I should be doing only 1 req/sec.
Can not figure out how to do only 1 request per second for this code:
#Call to API
async def ps_request_marshal(converted_urls, device_input):
global device_settings, data, tasks
data = []
device_settings = device_input
tasks = []
url = 'https://www.googleapis.com/pagespeedonline/v5/runPagespeed?url={}' '&key=+key &strategy=' +device_input
async with aiohttp.ClientSession() as session:
for page in converted_urls:
tasks.append(asyncio.create_task(session.get(url.format(page), ssl=False)))
responses = await asyncio.gather(*tasks)
for response in responses:
data.append(await response.json())
print(responses)
Will much appreciate your help!
Solved, just added 'await asyncio.sleep(delay_per request)' to loop of task creation.
async def ps_request_marshal(converted_urls, device_input):
global device_settings, data, tasks
data = []
device_settings = device_input
tasks = []
url = 'https://www.googleapis.com/pagespeedonline/v5/runPagespeed?url={}' '&key=key=' +device_input
delay_per_request = 1
async with aiohttp.ClientSession() as session:
for page in converted_urls:
tasks.append(asyncio.create_task(session.get(url.format(page), ssl=False)))
await asyncio.sleep(delay_per_request)
responses = await asyncio.gather(*tasks)
print(responses)
for response in responses:
data.append(await response.json())
print(responses)

python asyncio asynchronously fetch data by key from a dict when the key becomes available

Like title told, my use case is like this:
I have one aiohttp server, which accept request from client, when i have the request i generate one unique request id for it, and then i send the {req_id: req_pyaload} dict to some workers (the worker is not in python thus running in another process), when the workers complete the work, i get back the response and put them in a result dict like this: {req_id_1: res_1, req_id_2: res_2}.
Then I want my aiohttp server handler to await on above result dict, so when the specific response become available (by req_id) it can send it back.
I build below example code to try to simulate the process, but got stuck in implementing the coroutine async def fetch_correct_res(req_id) which should asynchronously/unblockly fetch the correct response by req_id.
import random
import asyncio
import shortuuid
n_tests = 1000
idxs = list(range(n_tests))
req_ids = []
for _ in range(n_tests):
req_ids.append(shortuuid.uuid())
res_dict = {}
async def fetch_correct_res(req_id):
pass
async def handler(req):
res = await fetch_correct_res(req)
assert req == res, "the correct res for the req should exactly be the req itself."
print("got correct res for req: {}".format(req))
async def randomly_put_res_to_res_dict():
for _ in range(n_tests):
random_idx = random.choice(idxs)
await asyncio.sleep(random_idx / 1000)
res_dict[req_ids[random_idx]] = req_ids[random_idx]
print("req: {} is back".format(req_ids[random_idx]))
So:
Is it possible to make this solution work? how?
If above solution is not possible, what should be the correct solution for this use case with asyncio?
Many thanks.
The only approach i can think of for now to make this work is: pre-created some asyncio.Queue with pre-assigned id, then for each incoming request assign one queue to it, so the handler just await on this queue, when the response come back i put it into this pre-assigned queue only, after the request fulfilled, i collect back the queue to use it for next incoming request. Not very elegant, but will solve the problem.
See if the below sample implementation fulfils your need
basically you want to respond back to the request(id) with your response(unable to predict the order) in an asynchronous way
So at the time of request handling, populate the dict with {request_id: {'event':<async.Event>, 'result': <result>}} and await on asyncio.Event.wait(), once the response is received, signal the event with asyncio.Event.set() which will release the await and then fetch the response from the dict based on the request id
I modified your code slightly to pre-populate the dict with request id and put the await on asyncio.Event.wait() until the signal comes from the response
import random
import asyncio
import shortuuid
n_tests = 10
idxs = list(range(n_tests))
req_ids = []
for _ in range(n_tests):
req_ids.append(shortuuid.uuid())
res_dict = {}
async def fetch_correct_res(req_id, event):
await event.wait()
res = res_dict[req_id]['result']
return res
async def handler(req, loop):
print("incoming request id: {}".format(req))
event = asyncio.Event()
data = {req :{}}
res_dict.update(data)
res_dict[req]['event']=event
res_dict[req]['result']='pending'
res = await fetch_correct_res(req, event)
assert req == res, "the correct res for the req should exactly be the req itself."
print("got correct res for req: {}".format(req))
async def randomly_put_res_to_res_dict():
random.shuffle(req_ids)
for i in req_ids:
await asyncio.sleep(random.randrange(2,4))
print("req: {} is back".format(i))
if res_dict.get(i) is not None:
event = res_dict[i]['event']
res_dict[i]['result'] = i
event.set()
loop = asyncio.get_event_loop()
tasks = asyncio.gather(handler(req_ids[0], loop),
handler(req_ids[1], loop),
handler(req_ids[2], loop),
handler(req_ids[3], loop),
randomly_put_res_to_res_dict())
loop.run_until_complete(tasks)
loop.close()
sample response from the above code
incoming request id: NDhvBPqMiRbteFD5WqiLFE
incoming request id: fpmk8yC3iQcgHAJBKqe2zh
incoming request id: M7eX7qeVQfWCCBnP4FbRtK
incoming request id: v2hAfcCEhRPUDUjCabk45N
req: VeyvAEX7YGgRZDHqa2UGYc is back
req: M7eX7qeVQfWCCBnP4FbRtK is back
got correct res for req: M7eX7qeVQfWCCBnP4FbRtK
req: pVvYoyAzvK8VYaHfrFA9SB is back
req: soP8NDxeQKYjgeT7pa3wtG is back
req: j3rcg5Lp59pQXuvdjCAyZe is back
req: NDhvBPqMiRbteFD5WqiLFE is back
got correct res for req: NDhvBPqMiRbteFD5WqiLFE
req: v2hAfcCEhRPUDUjCabk45N is back
got correct res for req: v2hAfcCEhRPUDUjCabk45N
req: porzHqMqV8SAuttteHRwNL is back
req: trVVqZrUpsW3tfjQajJfb7 is back
req: fpmk8yC3iQcgHAJBKqe2zh is back
got correct res for req: fpmk8yC3iQcgHAJBKqe2zh
This may work (note: I removed UUID in order to know req id in advance)
import random
import asyncio
n_tests = 1000
idxs = list(range(n_tests))
req_ids = []
for i in range(n_tests):
req_ids.append(i)
res_dict = {}
async def fetch_correct_res(req_id):
while not res_dict.get(req_id):
await asyncio.sleep(0.1)
return req_ids[req_id]
async def handler(req):
print("fetching req: ", req)
res = await fetch_correct_res(req)
assert req == res, "the correct res for the req should exactly be the req itself."
print("got correct res for req: {}".format(req))
async def randomly_put_res_to_res_dict(future):
for i in range(n_tests):
res_dict[req_ids[i]] = req_ids[i]
await asyncio.sleep(0.5)
print("req: {} is back".format(req_ids[i]))
future.set_result("done")
loop = asyncio.get_event_loop()
future = asyncio.Future()
asyncio.ensure_future(randomly_put_res_to_res_dict(future))
loop.run_until_complete(handler(10))
loop.close()
Is it the best solution? according to me No, basically its kind of requesting long running job status, and you should have (REST) api for doing the job submission and knowing job status like:
http POST server:port/job
{some job json paylod}
Response: 200 OK {"req_id": 1}
http GET server:port/job/1
Response: 200 OK {"req_id": 1, "status": "in process"}
http GET server:port/job/1
Response: 200 OK {"req_id": 1, "status": "done", "result":{}}

Asyncio and aiohttp returning task instead of results

I have a script to run parallel requests against an API within a class. However, the results I'm getting is basically a task instead of the actual results. Any reason why?
I mimicked the modified Client code on https://pawelmhm.github.io/asyncio/python/aiohttp/2016/04/22/asyncio-aiohttp.html.
import asyncio
from aiohttp import ClientSession
class Requestor:
async def _async_request(self, url, session, sema_sz=10):
sema = asyncio.Semaphore(sema_sz)
async with sema:
async with session.get(url) as response:
req = await response.json()
return req
async def _async_chunk_request(self, url, chunks, headers=None, sema_sz=10):
async with ClientSession(headers=headers) as session:
futures = [asyncio.ensure_future(self._async_request(url.format(chunk), session, sema_sz)) for chunk in chunks]
responses = asyncio.gather(*futures)
await responses
def get_request(self, url, chunks):
loop = asyncio.get_event_loop()
bulk_req = asyncio.ensure_future(self._async_chunk_request(url, chunks))
loop.run_until_complete(bulk_req)
return bulk_req
bulk_req is actually a Task variable and not the results and shows this in PyCharm, Task finished coro=<Requestor._async_chunk_request() done, defined at ...
When I debug, I see that req has a full and proper response value, so there's no issue with that. I feel like it's something to do with the actual gathering of the futures?
Your _chunk_request does not return anything.
async def _chunk_request(...):
...
...
await responses
I made a toy example trying to mimic your process. If I ended _chunk_request like you did, i got the same result - a finished Task with No results. Changing _chunk_request to return something fixed it:
async def _chunk_request(...):
...
...
return await responses
If you only need the return values from the tasks, get_request should return the result of the loop.run_until_complete() call.
My toy example
import asyncio
import random
from pprint import pprint
async def response(n):
asyncio.sleep(random.choice([1,3,5]))
return f'i am {n}'
async def _request(n):
req = await response(n)
#print(req)
return req
async def _chunk_request(chunks):
futures = [asyncio.ensure_future(_request(chunk)) for chunk in chunks]
#pprint(futures)
responses = asyncio.gather(*futures, return_exceptions=True)
#pprint(responses)
return await responses
def get_request(chunks):
loop = asyncio.get_event_loop()
bulk_req = asyncio.ensure_future(_chunk_request(chunks))
return loop.run_until_complete(bulk_req)
In [7]: result = get_request(range(1,6))
In [8]: print(result)
['i am 1', 'i am 2', 'i am 3', 'i am 4', 'i am 5']

Categories