Amazon proxies for production scraping.

import requests, time, random

PROXY = "http://login:country-us@ip.simplynode.io:9003"
PROXIES = {"http": PROXY, "https": PROXY}

HEADERS = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 14_2) "
                  "AppleWebKit/605.1.15 (KHTML, like Gecko) "
                  "Version/17.2 Safari/605.1.15",
    "Accept-Language": "en-US,en;q=0.9",
}

def fetch_asin(asin, retries=3):
    url = f"https://www.amazon.com/dp/{asin}"
    for attempt in range(retries):
        r = requests.get(url, proxies=PROXIES, headers=HEADERS, timeout=10)
        # 503 = captcha challenge, 429 = rate limit - back off & retry on a new IP
        if r.status_code in (503, 429):
            time.sleep((2 ** attempt) + random.random())
            continue
        if r.status_code == 200:
            return r.text
    return None

# Sticky for paginated reviews - same IP across the entire review walk
def fetch_reviews(asin, pages=10):
    sticky = f"http://login:country-us-session-{asin}-ttl-1800@ip.simplynode.io:9003"
    p = {"http": sticky, "https": sticky}
    for page in range(1, pages + 1):
        url = f"https://www.amazon.com/product-reviews/{asin}?pageNumber={page}"
        yield requests.get(url, proxies=p, headers=HEADERS, timeout=10).text