{"uid":"cap_QmCyLrcaP5N_yP2VqMyE0","slug":"x402-orth-sh-scrapegraphai-website-crawler-3c23ad6e","name":"x402.orth.sh ScrapeGraphAI Website Crawler","description":"Start a website crawl from a seed URL with configurable depth and page limits.","url":"https://x402.orth.sh/scrapegraphai/api/crawl","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","description":"Seed URL to crawl"},"formats":{"type":"array","description":"Output formats"},"maxDepth":{"type":"number","description":"Max crawl depth (default 2)"},"maxPages":{"type":"number","description":"Max pages (1-1000, default 50)"},"fetchConfig":{"type":"object","description":"Fetch options"},"contentTypes":{"type":"array","description":"Allowed content types"},"allowExternal":{"type":"boolean","description":"Follow external links (default false)"},"excludePatterns":{"type":"array","description":"URL patterns to exclude"},"includePatterns":{"type":"array","description":"URL patterns to include"},"maxLinksPerPage":{"type":"number","description":"Max links per page (default 10)"}}},"responseSchema":null,"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_AJu5ne5Ta_ELjzXLZ28iV","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":"Crawls a website starting from a seed URL, following links up to a configurable depth and page count, returning multi-format scraped content.","exampleAgentPrompt":"Crawl https://docs.example.com starting from the homepage, go up to 3 levels deep, scrape at most 200 pages, only follow internal links, and return the content in markdown format.","exampleUseCases":null,"resultDescription":"Returns scraped content from all discovered and crawled pages within the configured depth and page limits, in the requested output formats (e.g. markdown, HTML, JSON), subject to include/exclude URL pattern filters.","failureModes":["Seed URL is unreachable or returns non-200 status — crawl fails with an error","maxPages exceeds 1000 — validation error returned","maxDepth set too high causing timeout on large sites","External links followed unexpectedly if allowExternal is true, leading to large crawl scope","excludePatterns/includePatterns misconfigured leading to missed or excess pages","Payment of $0.01 USDC not provided or rejected — 402 error returned"],"whenToPreferThis":"Choose this endpoint when you need to crawl multiple pages of a website by following links from a seed URL, rather than scraping a single known URL. Ideal for documentation sites, knowledge bases, or any multi-page content collection task where you don't know all URLs in advance. Use the LLM-driven extraction sibling endpoint instead if you need AI-structured output from a single known URL.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:50:41.252Z","isFirstParty":false}