스티키 세션과 IP 회전: 세션 ID, TTL 및 연결 재사용

import random
import uuid

import requests

GATEWAY = "gw.crawlrelay.com:7777"
BASE_USER, PASSWORD = "USERNAME-country-us", "PASSWORD"


class SlowDown(Exception):
    """The target asked us to slow down (403 or 429): back off, do not rotate."""


class StickySession:
    def __init__(self, ttl=15, max_requests=50):
        self.id = uuid.uuid4().hex[:10]
        self.max_requests, self.used = max_requests, 0
        user = "%s-session-%s-ttl-%d" % (BASE_USER, self.id, ttl)
        proxy = "http://%s:%s@%s" % (user, PASSWORD, GATEWAY)
        self.http = requests.Session()
        self.http.proxies = {"http": proxy, "https": proxy}


class SessionPool:
    EXIT_PROBLEMS = {502, 503, 504}

    def __init__(self, size=5, **options):
        self.options = options
        self.sessions = [StickySession(**options) for _ in range(size)]

    def _replace(self, i):
        self.sessions[i].http.close()
        self.sessions[i] = StickySession(**self.options)

    def get(self, url, **kwargs):
        i = random.randrange(len(self.sessions))
        s = self.sessions[i]
        s.used += 1
        try:
            r = s.http.get(url, timeout=(10, 30), **kwargs)
        except requests.exceptions.RequestException:
            self._replace(i)  # dropped exit or timeout: start a fresh session
            raise
        if r.status_code in (403, 429):
            raise SlowDown("%s returned %d" % (url, r.status_code))
        if r.status_code in self.EXIT_PROBLEMS or s.used >= s.max_requests:
            self._replace(i)
        return r


pool = SessionPool(size=5, ttl=15, max_requests=50)
print(pool.get("https://api.ipify.org").text)