How do I add a backup to Scrapfly instead of paying for residential?

// npm i scrapfly-sdk   (Node 18+)   env: SCRAPFLY_API_KEY, UPROCK_API_KEYimport { ScrapflyClient, ScrapeConfig, ScrapeResult, errors } from "scrapfly-sdk";​const scrapfly = new ScrapflyClient({ key: process.env.SCRAPFLY_API_KEY ?? "" });​// Scrapfly error codes (scrapfly.io/docs/scrape-api/errors, checked 25 Oct 2026) worth a// second network: the domain needs the residential pool, the page is over budget, a// timeout, trouble on Scrapfly's side, your concurrency or quota, a country it lacks.const TRY_UPROCK = new Set([  "ERR::PROXY::POOL_NOT_AVAILABLE_FOR_TARGET",  "ERR::SCRAPE::COST_BUDGET_LIMIT",  "ERR::SCRAPE::OPERATION_TIMEOUT",  "ERR::SCRAPE::UPSTREAM_TIMEOUT",  "ERR::SCRAPE::DRIVER_TIMEOUT",  "ERR::PROXY::TIMEOUT",  "ERR::SCRAPE::NETWORK_ERROR",  "ERR::SCRAPE::NO_BROWSER_AVAILABLE",  "ERR::SCRAPE::DRIVER_CRASHED",  "ERR::PROXY::RESOURCES_SATURATION",  "ERR::SCRAPE::TOO_MANY_CONCURRENT_REQUEST",  "ERR::SCRAPE::QUOTA_LIMIT_REACHED",  "ERR::SCRAPE::COUNTRY_NOT_AVAILABLE_FOR_TARGET",  "ERR::PROXY::POOL_UNAVAILABLE_COUNTRY",]);// Also every ERR::ASP:: (the Unblocker didn't get the page) and ERR::THROTTLE:: code.// The rest are answers: DOMAIN_NOT_ALLOWED and PROXY::UNAVAILABLE (a restricted domain),// a broken site (DNS_NAME_NOT_RESOLVED, SSL_ERROR), bad parameters.​// A site's own status, from BAD_UPSTREAM_RESPONSE: 404 and 410 are the site's answer.const siteWorthRetrying = (status: number) =>  status === 403 || status === 408 || status === 429 || status >= 500;​function worthUpRock(err: unknown) {  if (!(err instanceof errors.ScrapflyError)) return true; // network error or our timeout  const code = String(err.args.code ?? "");  // Errors from the API itself carry no code: send on a bad key (401) or a rate limit (429).  if (!code) return /"http_code":\s*(401|429)\b/.test(err.message);  if (code === "ERR::SCRAPE::BAD_UPSTREAM_RESPONSE")    return siteWorthRetrying(Number(err.args.http_status_code));  if (code === "ERR::ASP::SHIELD_NOT_ELIGIBLE") return false;  return TRY_UPROCK.has(code) || /^ERR::(ASP|THROTTLE)::/.test(code);}​async function viaUpRock(url: string, country: string) {  // One call: UpRock loads the page on a real device in that country, tries a fresh device  // every 7 s (up to 3 tries) and returns markdown. Failed calls aren't billed.  const res = await fetch("https://edge.uprock.com/v1/crawl", {    method: "POST",    headers: {      Authorization: `Bearer ${process.env.UPROCK_API_KEY}`,      "Content-Type": "application/json",    },    body: JSON.stringify({ url, country }),    signal: AbortSignal.timeout(90_000),  });  const page = await res.json();  if (!res.ok) throw new Error(`UpRock ${res.status} ${page.code}: ${page.error}`);  return page.markdown ?? "";}​// The SDK's scrape() has no timeout of its own.async function scrapeWithin(config: ScrapeConfig, ms: number) {  let timer: ReturnType<typeof setTimeout> | undefined;  const timeout = new Promise<never>((_, reject) => {    timer = setTimeout(() => reject(new Error(`no answer in ${ms / 1000} s`)), ms);  });  try {    return (await Promise.race([scrapfly.scrape(config), timeout])) as ScrapeResult;  } finally {    clearTimeout(timer);  }}​export async function read(url: string, country = "US") {  const config = new ScrapeConfig({    url,    format: "markdown",    render_js: true, // +5 credits    proxy_pool: "public_datacenter_pool", // 1 credit; the residential pool is 25    cost_budget: 6, // never more than a datacenter page with a browser    country: country.toLowerCase(),    retry: false, // fail over instead of waiting out Scrapfly's own retries,    timeout: 90_000, // after 90 s of trying  });  try {    const res = await scrapeWithin(config, 95_000); // Scrapfly's timeout + 5 s    return { via: "scrapfly", markdown: res.result.content };  } catch (err) {    if (!worthUpRock(err)) throw err;    console.warn(`Scrapfly: ${(err as Error).message.slice(0, 160)}; trying UpRock`);  }  return { via: "uprock", markdown: await viaUpRock(url, country) };}​// node read.ts https://developer.mozilla.org/en-US/docs/Web/HTTP DEconst [url = "https://developer.mozilla.org/en-US/docs/Web/HTTP", country = "US"] =  process.argv.slice(2);const page = await read(url, country);console.log(page.via, page.markdown.slice(0, 200));

# pip install scrapfly-sdk requests   env: SCRAPFLY_API_KEY, UPROCK_API_KEYimport osimport sys​import requestsfrom scrapfly import ScrapeConfig, ScrapflyClientfrom scrapfly.errors import ScrapflyError​# Read timeout: Scrapfly's own 90 s timeout (set below) plus 5 s.scrapfly = ScrapflyClient(    key=os.environ.get("SCRAPFLY_API_KEY", ""), web_scraping_api_read_timeout=95)​# Scrapfly error codes (scrapfly.io/docs/scrape-api/errors, checked 25 Oct 2026) worth a# second network: the domain needs the residential pool, the page is over budget, a# timeout, trouble on Scrapfly's side, your concurrency or quota, a country it lacks.TRY_UPROCK = {    "ERR::PROXY::POOL_NOT_AVAILABLE_FOR_TARGET",    "ERR::SCRAPE::COST_BUDGET_LIMIT",    "ERR::SCRAPE::OPERATION_TIMEOUT",    "ERR::SCRAPE::UPSTREAM_TIMEOUT",    "ERR::SCRAPE::DRIVER_TIMEOUT",    "ERR::PROXY::TIMEOUT",    "ERR::SCRAPE::NETWORK_ERROR",    "ERR::SCRAPE::NO_BROWSER_AVAILABLE",    "ERR::SCRAPE::DRIVER_CRASHED",    "ERR::PROXY::RESOURCES_SATURATION",    "ERR::SCRAPE::TOO_MANY_CONCURRENT_REQUEST",    "ERR::SCRAPE::QUOTA_LIMIT_REACHED",    "ERR::SCRAPE::COUNTRY_NOT_AVAILABLE_FOR_TARGET",    "ERR::PROXY::POOL_UNAVAILABLE_COUNTRY",}# Also every ERR::ASP:: (the Unblocker didn't get the page) and ERR::THROTTLE:: code.# The rest are answers: DOMAIN_NOT_ALLOWED and PROXY::UNAVAILABLE (a restricted domain),# a broken site (DNS_NAME_NOT_RESOLVED, SSL_ERROR), bad parameters.​​def worth_uprock(err: ScrapflyError) -> bool:    code = err.code or ""    status = err.http_status_code or 0    if not code:  # errors from the API itself: send on a bad key or a rate limit        return status in (401, 429)    if code == "ERR::SCRAPE::BAD_UPSTREAM_RESPONSE":  # status is the site's own        return status in (403, 408, 429) or status >= 500  # not 404 or 410    if code == "ERR::ASP::SHIELD_NOT_ELIGIBLE":        return False    return code in TRY_UPROCK or code.startswith(("ERR::ASP::", "ERR::THROTTLE::"))​​def via_uprock(url: str, country: str) -> str:    # One call: UpRock loads the page on a real device in that country, tries a fresh device    # every 7 s (up to 3 tries) and returns markdown. Failed calls aren't billed.    res = requests.post(        "https://edge.uprock.com/v1/crawl",        headers={"Authorization": f"Bearer {os.environ['UPROCK_API_KEY']}"},        json={"url": url, "country": country},        timeout=90,    )    page = res.json()    if not res.ok:        raise RuntimeError(f"UpRock {res.status_code} {page.get('code')}: {page.get('error')}")    return page.get("markdown", "")​​def read(url: str, country: str = "US") -> dict:    config = ScrapeConfig(        url=url,        format="markdown",        render_js=True,  # +5 credits        proxy_pool="public_datacenter_pool",  # 1 credit; the residential pool is 25        cost_budget=6,  # never more than a datacenter page with a browser        country=country.lower(),        retry=False,  # fail over instead of waiting out Scrapfly's own retries,        timeout=90_000,  # after 90 s of trying    )    try:        return {"via": "scrapfly", "markdown": scrapfly.scrape(config).content}    except ScrapflyError as err:        if not worth_uprock(err):            raise        label = err.code or err.http_status_code        print(f"Scrapfly {label}; trying UpRock", file=sys.stderr)    except Exception as err:  # network error or timeout        print(f"Scrapfly unreachable ({err}); trying UpRock", file=sys.stderr)    return {"via": "uprock", "markdown": via_uprock(url, country)}​​if __name__ == "__main__":    # python read.py https://developer.mozilla.org/en-US/docs/Web/HTTP DE    url = sys.argv[1] if len(sys.argv) > 1 else "https://developer.mozilla.org/en-US/docs/Web/HTTP"    country = sys.argv[2] if len(sys.argv) > 2 else "US"    page = read(url, country)    print(page["via"], page["markdown"][:200])

// npm i scrapfly-sdk @modelcontextprotocol/sdk   (Node 18+)   env: SCRAPFLY_API_KEY, UPROCK_API_KEYimport { ScrapflyClient, ScrapeConfig, ScrapeResult, errors } from "scrapfly-sdk";import { Client } from "@modelcontextprotocol/sdk/client/index.js";import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";​const scrapfly = new ScrapflyClient({ key: process.env.SCRAPFLY_API_KEY ?? "" });const uprock = new Client({ name: "scrapfly-fallback", version: "1.0.0" });await uprock.connect(  new StreamableHTTPClientTransport(    new URL("https://mcp.uprock.ai/mcp"),    { requestInit: { headers: { Authorization: `Bearer ${process.env.UPROCK_API_KEY}` } } },  ),);​// Scrapfly error codes (scrapfly.io/docs/scrape-api/errors, checked 25 Oct 2026) worth a// second network: the domain needs the residential pool, the page is over budget, a// timeout, trouble on Scrapfly's side, your concurrency or quota, a country it lacks.const TRY_UPROCK = new Set([  "ERR::PROXY::POOL_NOT_AVAILABLE_FOR_TARGET",  "ERR::SCRAPE::COST_BUDGET_LIMIT",  "ERR::SCRAPE::OPERATION_TIMEOUT",  "ERR::SCRAPE::UPSTREAM_TIMEOUT",  "ERR::SCRAPE::DRIVER_TIMEOUT",  "ERR::PROXY::TIMEOUT",  "ERR::SCRAPE::NETWORK_ERROR",  "ERR::SCRAPE::NO_BROWSER_AVAILABLE",  "ERR::SCRAPE::DRIVER_CRASHED",  "ERR::PROXY::RESOURCES_SATURATION",  "ERR::SCRAPE::TOO_MANY_CONCURRENT_REQUEST",  "ERR::SCRAPE::QUOTA_LIMIT_REACHED",  "ERR::SCRAPE::COUNTRY_NOT_AVAILABLE_FOR_TARGET",  "ERR::PROXY::POOL_UNAVAILABLE_COUNTRY",]);// Also every ERR::ASP:: (the Unblocker didn't get the page) and ERR::THROTTLE:: code.// The rest are answers: DOMAIN_NOT_ALLOWED and PROXY::UNAVAILABLE (a restricted domain),// a broken site (DNS_NAME_NOT_RESOLVED, SSL_ERROR), bad parameters.​// A site's own status, from BAD_UPSTREAM_RESPONSE: 404 and 410 are the site's answer.const siteWorthRetrying = (status: number) =>  status === 403 || status === 408 || status === 429 || status >= 500;​function worthUpRock(err: unknown) {  if (!(err instanceof errors.ScrapflyError)) return true; // network error or our timeout  const code = String(err.args.code ?? "");  // Errors from the API itself carry no code: send on a bad key (401) or a rate limit (429).  if (!code) return /"http_code":\s*(401|429)\b/.test(err.message);  if (code === "ERR::SCRAPE::BAD_UPSTREAM_RESPONSE")    return siteWorthRetrying(Number(err.args.http_status_code));  if (code === "ERR::ASP::SHIELD_NOT_ELIGIBLE") return false;  return TRY_UPROCK.has(code) || /^ERR::(ASP|THROTTLE)::/.test(code);}​const textOf = (content: unknown) =>  (content as { type: string; text?: string }[]).find((c) => c.type === "text")?.text ??  "";​async function viaUpRock(url: string, country: string) {  const res = await uprock.callTool(    { name: "crawl_fetch", arguments: { url, country } },    undefined,    { timeout: 300_000 },  );  if (res.isError) throw new Error(`UpRock: ${textOf(res.content)}`);  const uri = JSON.parse(textOf(res.content)).content?.markdown?.resource;  if (!uri) throw new Error(`UpRock: no markdown for ${url}`);  return textOf(    (await uprock.callTool({ name: "resource_fetch", arguments: { uri } })).content,  );}​// The SDK's scrape() has no timeout of its own.async function scrapeWithin(config: ScrapeConfig, ms: number) {  let timer: ReturnType<typeof setTimeout> | undefined;  const timeout = new Promise<never>((_, reject) => {    timer = setTimeout(() => reject(new Error(`no answer in ${ms / 1000} s`)), ms);  });  try {    return (await Promise.race([scrapfly.scrape(config), timeout])) as ScrapeResult;  } finally {    clearTimeout(timer);  }}​export async function read(url: string, country = "US") {  const config = new ScrapeConfig({    url,    format: "markdown",    render_js: true, // +5 credits    proxy_pool: "public_datacenter_pool", // 1 credit; the residential pool is 25    cost_budget: 6, // never more than a datacenter page with a browser    country: country.toLowerCase(),    retry: false, // fail over instead of waiting out Scrapfly's own retries,    timeout: 90_000, // after 90 s of trying  });  try {    const res = await scrapeWithin(config, 95_000); // Scrapfly's timeout + 5 s    return { via: "scrapfly", markdown: res.result.content };  } catch (err) {    if (!worthUpRock(err)) throw err;    console.warn(`Scrapfly: ${(err as Error).message.slice(0, 160)}; trying UpRock`);  }  return { via: "uprock", markdown: await viaUpRock(url, country) };}​// node read.ts https://developer.mozilla.org/en-US/docs/Web/HTTP DEconst [url = "https://developer.mozilla.org/en-US/docs/Web/HTTP", country = "US"] =  process.argv.slice(2);try {  const page = await read(url, country);  console.log(page.via, page.markdown.slice(0, 200));} finally {  await uprock.close();}

# pip install scrapfly-sdk; npm i -g uprock   env: SCRAPFLY_API_KEY, UPROCK_API_KEYimport jsonimport osimport subprocessimport sys​from scrapfly import ScrapeConfig, ScrapflyClientfrom scrapfly.errors import ScrapflyError​# Read timeout: Scrapfly's own 90 s timeout (set below) plus 5 s.scrapfly = ScrapflyClient(    key=os.environ.get("SCRAPFLY_API_KEY", ""), web_scraping_api_read_timeout=95)​# Scrapfly error codes (scrapfly.io/docs/scrape-api/errors, checked 25 Oct 2026) worth a# second network: the domain needs the residential pool, the page is over budget, a# timeout, trouble on Scrapfly's side, your concurrency or quota, a country it lacks.TRY_UPROCK = {    "ERR::PROXY::POOL_NOT_AVAILABLE_FOR_TARGET",    "ERR::SCRAPE::COST_BUDGET_LIMIT",    "ERR::SCRAPE::OPERATION_TIMEOUT",    "ERR::SCRAPE::UPSTREAM_TIMEOUT",    "ERR::SCRAPE::DRIVER_TIMEOUT",    "ERR::PROXY::TIMEOUT",    "ERR::SCRAPE::NETWORK_ERROR",    "ERR::SCRAPE::NO_BROWSER_AVAILABLE",    "ERR::SCRAPE::DRIVER_CRASHED",    "ERR::PROXY::RESOURCES_SATURATION",    "ERR::SCRAPE::TOO_MANY_CONCURRENT_REQUEST",    "ERR::SCRAPE::QUOTA_LIMIT_REACHED",    "ERR::SCRAPE::COUNTRY_NOT_AVAILABLE_FOR_TARGET",    "ERR::PROXY::POOL_UNAVAILABLE_COUNTRY",}# Also every ERR::ASP:: (the Unblocker didn't get the page) and ERR::THROTTLE:: code.# The rest are answers: DOMAIN_NOT_ALLOWED and PROXY::UNAVAILABLE (a restricted domain),# a broken site (DNS_NAME_NOT_RESOLVED, SSL_ERROR), bad parameters.​​def worth_uprock(err: ScrapflyError) -> bool:    code = err.code or ""    status = err.http_status_code or 0    if not code:  # errors from the API itself: send on a bad key or a rate limit        return status in (401, 429)    if code == "ERR::SCRAPE::BAD_UPSTREAM_RESPONSE":  # status is the site's own        return status in (403, 408, 429) or status >= 500  # not 404 or 410    if code == "ERR::ASP::SHIELD_NOT_ELIGIBLE":        return False    return code in TRY_UPROCK or code.startswith(("ERR::ASP::", "ERR::THROTTLE::"))​​def via_uprock(url: str, country: str) -> str:    run = subprocess.run(        ["uprock", "ai", "crawl", url, "--country", country, "--content"],        capture_output=True,        text=True,        timeout=330,    )    if run.returncode != 0:        raise RuntimeError(f"UpRock: {run.stderr.strip()}")    return json.loads(run.stdout).get("inlined_markdown", "")​​def read(url: str, country: str = "US") -> dict:    config = ScrapeConfig(        url=url,        format="markdown",        render_js=True,  # +5 credits        proxy_pool="public_datacenter_pool",  # 1 credit; the residential pool is 25        cost_budget=6,  # never more than a datacenter page with a browser        country=country.lower(),        retry=False,  # fail over instead of waiting out Scrapfly's own retries,        timeout=90_000,  # after 90 s of trying    )    try:        return {"via": "scrapfly", "markdown": scrapfly.scrape(config).content}    except ScrapflyError as err:        if not worth_uprock(err):            raise        label = err.code or err.http_status_code        print(f"Scrapfly {label}; trying UpRock", file=sys.stderr)    except Exception as err:  # network error or timeout        print(f"Scrapfly unreachable ({err}); trying UpRock", file=sys.stderr)    return {"via": "uprock", "markdown": via_uprock(url, country)}​​if __name__ == "__main__":    # python read.py https://developer.mozilla.org/en-US/docs/Web/HTTP DE    url = sys.argv[1] if len(sys.argv) > 1 else "https://developer.mozilla.org/en-US/docs/Web/HTTP"    country = sys.argv[2] if len(sys.argv) > 2 else "US"    page = read(url, country)    print(page["via"], page["markdown"][:200])