爬虫遇到 HTTP 429 Too Many Requests 怎么修

# No install needed. Dump headers, throw the body away.
curl -sS -o /dev/null -D - "https://example.com/api/items?page=2"

# Look for these, in this order of usefulness:
#   Retry-After: 30           seconds, or an HTTP date
#   RateLimit-Reset: 1724500000
#   X-RateLimit-Remaining: 0
#   RateLimit-Limit: 100

# pip install requests
from email.utils import parsedate_to_datetime
from datetime import datetime, timezone

def retry_delay(response, fallback):
    """Seconds to wait, from Retry-After if the server sent one."""
    raw = response.headers.get("Retry-After")
    if not raw:
        return fallback
    try:
        return max(0.0, float(raw))          # the delay-seconds form
    except ValueError:
        pass
    try:
        when = parsedate_to_datetime(raw)    # the HTTP-date form
        return max(0.0, (when - datetime.now(timezone.utc)).total_seconds())
    except (TypeError, ValueError):
        return fallback

# pip install requests
import random, time, requests

def get_with_backoff(url, attempts=5, base=1.0, ceiling=60.0):
    for attempt in range(attempts):
        response = requests.get(url, timeout=30)
        if response.status_code != 429:
            return response
        # Full jitter: sleep somewhere in [0, base * 2 ** attempt].
        window = min(ceiling, base * (2 ** attempt))
        delay = retry_delay(response, random.uniform(0, window))
        time.sleep(min(delay, ceiling))
    raise RuntimeError(f"still rate limited after {attempts} attempts")

# Waits land near 0-1s, 0-2s, 0-4s, 0-8s, 0-16s unless the
# server named a delay, in which case that wins.

# pip install requests
import requests
from requests.adapters import HTTPAdapter
from urllib3.util import Retry

retry = Retry(
    total=5,
    # status_forcelist defaults to none, so 429 is NOT retried
    # unless you list it here yourself. This is the usual bug.
    status_forcelist=[429, 500, 502, 503, 504],
    backoff_factor=1,        # 1 * 2 ** previous_retries seconds
    backoff_jitter=1.0,      # urllib3 2.x only
    allowed_methods=["GET", "HEAD"],
)

session = requests.Session()
session.mount("https://", HTTPAdapter(max_retries=retry))

# Standard library only.
import asyncio

# Six in flight is a sane starting point for an unknown API.
gate = asyncio.Semaphore(6)
MIN_GAP = 0.2          # seconds between starts, per worker

async def fetch(client, url):
    async with gate:
        response = await client.get(url)
        await asyncio.sleep(MIN_GAP)
        return response

# Tune down on the first 429, and stay there for a while.
# Tuning back up too eagerly just rediscovers the limit.

# pip install capskip
from capskip import CapSkip, NetworkException, TimeoutException

# Local mode. In Server mode, host is the solver box's address.
solver = CapSkip(host="127.0.0.1", port=8080, pollingInterval=2)

try:
    result = solver.recaptcha(
        sitekey="YOUR_SITEKEY",
        url="https://example.com/page-with-recaptcha",
    )
    print(result["code"][:24])   # token, submit it with the form
except TimeoutException:
    # Polling ran past recaptchaTimeout, 300 seconds by default.
    print("gave up waiting, try again or lower the timeout")
except NetworkException:
    # The solver is not reachable on that host and port.
    print("check CapSkip is running and the mode you set")