レジデンシャルプロキシ用 Scrapy ミドルウェアの概要

import uuid
from urllib.parse import quote


class CrawlRelayProxyMiddleware:
    """Sets request.meta["proxy"]; Scrapy's HttpProxyMiddleware then sends the credentials."""

    def __init__(self, user, password, country):
        self.user, self.password, self.country = user, password, country

    @classmethod
    def from_crawler(cls, crawler):
        s = crawler.settings
        if not s.get("CRAWLRELAY_USER"):
            # Fail loudly: NotConfigured would only disable the middleware and crawl from your own IP
            raise ValueError("CRAWLRELAY_USER is not set: refusing to crawl without the proxy")
        return cls(s.get("CRAWLRELAY_USER"), s.get("CRAWLRELAY_PASSWORD", ""), s.get("CRAWLRELAY_COUNTRY", "us"))

    def process_request(self, request, spider=None):
        if "proxy" in request.meta and not request.meta.get("_crawlrelay"):
            return None  # a proxy set by other code: leave it alone
        parts = [self.user, "country", request.meta.get("proxy_country", self.country)]
        session = request.meta.get("proxy_session")
        if session == "new":  # a fresh session for this request (and for each of its retries)
            session = uuid.uuid4().hex[:12]
        if session:
            parts += ["session", session, "ttl", str(request.meta.get("proxy_ttl", 10))]
        username = "-".join(parts)
        request.meta["proxy"] = "http://%s:%[email protected]:7777" % (
            quote(username, safe=""), quote(self.password, safe=""))
        request.meta["_crawlrelay"] = True
        return None

import os

BOT_NAME = "myproject"
ROBOTSTXT_OBEY = True
USER_AGENT = "ExampleCrawler/1.0 (+https://example.com/crawler-info)"

CRAWLRELAY_USER = os.environ.get("CRAWLRELAY_USER")  # e.g. the username from your dashboard
CRAWLRELAY_PASSWORD = os.environ.get("CRAWLRELAY_PASSWORD")
CRAWLRELAY_COUNTRY = "us"

DOWNLOADER_MIDDLEWARES = {
    "myproject.middlewares.CrawlRelayProxyMiddleware": 350,  # runs before HttpProxyMiddleware (750)
}

CONCURRENT_REQUESTS = 32
CONCURRENT_REQUESTS_PER_DOMAIN = 4
AUTOTHROTTLE_ENABLED = True
AUTOTHROTTLE_START_DELAY = 1.0
AUTOTHROTTLE_MAX_DELAY = 30.0
AUTOTHROTTLE_TARGET_CONCURRENCY = 2.0

RETRY_ENABLED = True
RETRY_TIMES = 3
RETRY_HTTP_CODES = [429, 500, 502, 503, 504, 522, 524, 408]
DOWNLOAD_TIMEOUT = 45

import scrapy


class CatalogSpider(scrapy.Spider):
    name = "catalog"
    start_urls = ["https://books.toscrape.com/"]

    def parse(self, response):
        for href in response.css("article.product_pod h3 a::attr(href)").getall():
            # Product pages are independent: rotating exits
            yield response.follow(href, callback=self.parse_item)
        next_page = response.css("li.next a::attr(href)").get()
        if next_page:
            # The listing flow keeps one sticky exit for 30 minutes
            yield response.follow(next_page, callback=self.parse,
                                  meta={"proxy_session": "listing1", "proxy_ttl": 30})

    def parse_item(self, response):
        yield {
            "title": response.css("div.product_main h1::text").get(),
            "price": response.css("p.price_color::text").get(),
            "url": response.url,
        }

import os

DOWNLOAD_HANDLERS = {
    "http": "scrapy_playwright.handler.ScrapyPlaywrightDownloadHandler",
    "https": "scrapy_playwright.handler.ScrapyPlaywrightDownloadHandler",
}
TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"

PLAYWRIGHT_LAUNCH_OPTIONS = {
    "proxy": {
        "server": "http://gw.crawlrelay.com:7777",
        "username": os.environ.get("CRAWLRELAY_USER", "USERNAME") + "-country-us",
        "password": os.environ.get("CRAWLRELAY_PASSWORD", "PASSWORD"),
    },
}