{"uid":"cap_NpaCbgsdZVPXZs2KwuV8p","slug":"website-audit-web-extract-5a00ff4f","name":"Website Audit & Web Extract","description":"Read a web page as clean Markdown for an LLM: fetches the URL, drops navigation, header, footer, forms and scripts, and returns the main text as Markdown with title, description, language, author, publish date, image and word count. Optional links=true adds the page's links. Text and JSON URLs come back as-is.","url":"https://onchaincheck.dev/web/extract?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","pattern":"^\\S+$","maxLength":2000,"description":"Page URL"},"links":{"enum":["true","false"],"type":"string","description":"true adds the page's links (up to 300)"}},"additionalProperties":false}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","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":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_cUK8fj4QUP0LOXTxOOkfW","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a web page URL and returns the main content as clean Markdown, stripping navigation, headers, footers, and scripts, with metadata like title, description, language, author, publish date, image, and word count.","exampleAgentPrompt":"Can you grab the main article text from https://www.example.com/article/ai-trends-2025 and give it to me as clean markdown, including any links on the page?","exampleUseCases":[{"title":"Summarize a news article","prompt":"Fetch the article at https://www.bbc.com/news/technology-67890123 and extract just the main readable content as markdown so I can summarize it."},{"title":"Research a competitor's pricing page","prompt":"Pull the main content from https://competitor.com/pricing as clean markdown — I want to see their pricing tiers without all the nav and footer noise."},{"title":"Audit a blog post's metadata","prompt":"Read the page at https://myblog.com/posts/seo-guide and tell me the title, author, publish date, language, and word count — plus give me the main text as markdown."}],"resultDescription":"Returns the main body of the webpage as clean Markdown text, along with structured metadata fields: page title, meta description, detected language, author name, publish date, featured image URL, and word count. If the `links=true` option is passed, up to 300 links found on the page are also returned. Plain text and JSON URLs are returned as-is without transformation.","failureModes":["URL is unreachable or returns a non-200 status — error returned with HTTP status","Page has no extractable main content (e.g. fully JavaScript-rendered SPA) — may return empty or minimal markdown","Malformed or non-HTTP URL passed — validation error","Page blocks crawlers via robots.txt or Cloudflare — may return error or incomplete content","Very large pages may be truncated or slow to process"],"whenToPreferThis":"Choose this endpoint when you need to extract clean, readable main content from a public web URL for LLM consumption — especially when you want metadata like author, publish date, and language alongside the text. It is ideal for article summarization, research pipelines, and content auditing. Prefer it over raw HTTP fetching when you need boilerplate stripped and markdown-formatted output without writing your own HTML parser.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-19T06:36:23.606Z","isFirstParty":false,"canonicalSlug":"website-audit-web-extract-47e792f8"}