Concurrence et débit grâce aux proxy résidentiels

import asyncio
import random
from urllib.parse import urlsplit

import httpx

PROXY = "http://USERNAME-country-us:[email protected]:7777"


class AdaptiveLimit:
    """One per host: +1 slot after 20 clean responses, halve on 429/503, pause for Retry-After."""

    def __init__(self, start=2, low=1, high=16):
        self.limit, self.low, self.high = start, low, high
        self.in_flight, self.clean = 0, 0
        self.pause_until = 0.0
        self.cond = asyncio.Condition()

    async def __aenter__(self):
        loop = asyncio.get_running_loop()
        while True:
            async with self.cond:
                await self.cond.wait_for(lambda: self.in_flight < self.limit)
                delay = self.pause_until - loop.time()
                if delay <= 0:
                    self.in_flight += 1
                    return self
            await asyncio.sleep(delay)  # the host asked for a pause: wait outside the lock

    async def __aexit__(self, *exc):
        async with self.cond:
            self.in_flight -= 1
            self.cond.notify_all()

    def record(self, status, retry_after=None):
        if status in (429, 503):
            self.limit, self.clean = max(self.low, self.limit // 2), 0
            wait = int(retry_after) if retry_after and retry_after.isdigit() else 5 + random.random()
            now = asyncio.get_running_loop().time()
            self.pause_until = max(self.pause_until, now + wait)
        elif status < 400:
            self.clean += 1
            if self.clean >= 20 and self.limit < self.high:
                self.limit, self.clean = self.limit + 1, 0


gates = {}


def gate_for(url):
    host = urlsplit(url).hostname
    if host not in gates:
        gates[host] = AdaptiveLimit()
    return gates[host]


async def fetch(client, url, attempts=2):
    gate = gate_for(url)
    status = None
    for _ in range(attempts):
        try:
            async with gate:
                r = await client.get(url)
        except httpx.HTTPError as exc:
            return "error: %s" % type(exc).__name__
        status = r.status_code
        gate.record(status, r.headers.get("Retry-After"))
        if status not in (429, 503):
            break  # the retry, if any, waits for the host's pause in __aenter__
    return status


async def main(urls):
    timeout = httpx.Timeout(30.0, connect=10.0)
    async with httpx.AsyncClient(proxy=PROXY, timeout=timeout) as client:
        print(await asyncio.gather(*(fetch(client, u) for u in urls)))
    print({host: gate.limit for host, gate in gates.items()})


asyncio.run(main(["https://example.com/"] * 10))