{"uid":"cap_FpblnSsYkX6t5S9Altx0g","slug":"autoscrape-sitemap-url-extractor-8bd801fb","name":"AutoScrape Sitemap URL Extractor","description":"No-key evaluation APIs for public data and utilities: business filings, permits, bankruptcy dockets, NPI providers, HTTP status checks, sitemap URL extraction, SEC EDGAR, IRS 990, WHOIS, and validation. Paid x402 access is live.","url":"https://autoscrape-api-seven.vercel.app/x402/v1/sitemap-urls","method":"GET","headers":{},"bodySchema":null,"responseSchema":{"type":"json","example":{"count":1,"results":[{"url":"https://autoscrape-api-seven.vercel.app/","sitemapSource":"https://autoscrape-api-seven.vercel.app/sitemap.xml"}],"setupStatus":"found"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_E2BzG0rrT9RMoJ7GIBC9n","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts all URLs declared in a website's XML sitemap(s), with optional auto-discovery from robots.txt and filtering by last-modified date","exampleAgentPrompt":"Can you pull all the URLs listed in the sitemap for example.com — auto-discover from robots.txt if needed, and only include pages modified since 2024-01-01, up to 100 results?","exampleUseCases":[{"title":"SEO audit page inventory","prompt":"Get me all the URLs that example.com declares in its sitemap so I can audit what pages they have indexed — auto-discover the sitemap from robots.txt and give me up to 100 results."},{"title":"Competitor content monitoring","prompt":"Extract every URL from competitor.com's sitemap that has been modified since 2024-06-01 — I want to see what new content they've been publishing lately."},{"title":"Site migration URL checklist","prompt":"Pull the complete list of URLs from the sitemap at https://myoldsite.com/sitemap.xml so I can use them as a checklist when migrating to the new domain."}],"resultDescription":"Returns a JSON object with a count of URLs found, an array of result objects each containing a page URL and the sitemap source it was found in, and a setupStatus field indicating whether sitemap discovery succeeded.","failureModes":["URL is not publicly accessible — returns empty results or error status","No sitemap found and autoDiscover fails to locate one via robots.txt or common paths — setupStatus indicates not found","Malformed or non-standard sitemap XML may cause partial or empty results","maxResults cap of 100 may truncate large sitemaps","modifiedSince filter relies on publisher-supplied lastmod values which may be absent or inaccurate","Invalid or private domain returns error or zero results"],"whenToPreferThis":"Use this endpoint when you need to enumerate all publicly declared pages on a website without crawling it link-by-link. It is ideal for SEO audits, content inventories, migration checklists, and monitoring recently updated pages. Prefer it over raw HTML crawling when the site publishes a structured sitemap and you need a clean URL list quickly and cheaply at $0.01 per call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:44:35.284Z","isFirstParty":false}