{"uid":"cap_FBw4IDQ7w1T7L1oDmGXK8","slug":"brainiac-structured-page-extract-dbd408f5","name":"BRAINIAC Structured Page Extract","description":"Pay-per-call APIs for AI agents: OFAC sanctions screening, compliance checks, token security, and Base chain data via x402. No account. Fixed USDC price. MCP-ready.","url":"https://www.brainiac.software/api/v1/web-intelligence/structured-page-extract?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","pattern":"^https?:\\/\\/\\S+$","maxLength":2000,"minLength":8},"schema":{"type":"array","items":{"type":"object","required":["name","type"],"properties":{"name":{"type":"string","pattern":"^[A-Za-z][A-Za-z0-9_]{0,40}$"},"type":{"enum":["string","number","boolean","url"],"type":"string"},"selector":{"type":"string","maxLength":160,"minLength":1},"attribute":{"type":"string","pattern":"^[A-Za-z_:][A-Za-z0-9_:-]{0,40}$"}},"additionalProperties":false},"maxItems":12,"minItems":1}}},"responseSchema":{"type":"json","example":{"fields":[{"name":"heading","type":"string","value":"Example Domain","warnings":["2 elements matched; the first was used."]}],"sources":[{"url":"https://example.com/","source":"Public HTTP response","retrievedAt":"2026-11-02T18:00:00.000Z"}],"finalUrl":"https://example.com/","warnings":["A JSON-LD script could not be parsed."],"httpStatus":200,"contentType":"text/html","limitations":["Without a selector, a field is filled only from a JSON-LD property, a meta name or property, or the document title when the field name is title."],"retrievedAt":"2026-11-02T18:00:00.000Z","requestedUrl":"https://example.com/"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.05","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":"$0.05/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_rJfjHOQOd15oIHvmryaAz","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.05","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 and extracts user-defined structured fields from its HTML using CSS selectors, attributes, or JSON-LD/meta properties","exampleAgentPrompt":"Fetch https://example.com/product/42 and extract the product title as a string field called 'title', the price as a number field called 'price' using the CSS selector '.product-price', and the main image URL as a url field called 'imageUrl' using selector 'img.hero'.","exampleUseCases":[{"title":"Real-time competitor price monitoring","prompt":"Go to https://www.competitorsite.com/pricing and extract the plan names and monthly prices — grab the plan name as a string using '.plan-title' and the price as a number using '.plan-price'."},{"title":"News article headline extraction","prompt":"Pull the article headline and author name from https://www.techcrunch.com/2024/01/15/some-article/ — I want the headline as a string field called 'headline' using selector 'h1.article__title', and the author as a string called 'author' using selector '.article__byline'."},{"title":"Job listing data extraction","prompt":"Scrape https://jobs.example.com/listing/987 and extract the job title as a string field called 'jobTitle', the salary range as a string called 'salary' using selector '.compensation', and whether remote work is allowed as a boolean called 'isRemote' using selector '.remote-badge'."}],"resultDescription":"Returns a JSON object containing an array of extracted fields (each with name, type, and value), the final resolved URL after any redirects, HTTP status code, content type, retrieval timestamp, and any warnings encountered during extraction (e.g. multiple element matches, JSON-LD parse errors). Also includes a sources array noting where the data came from.","failureModes":["URL is unreachable or returns a non-200 status — httpStatus field will reflect the actual status code","CSS selector matches no elements — field value will be null or missing with a warning","Multiple elements match a selector — first match is used and a warning is emitted","JSON-LD on the page cannot be parsed — a top-level warning is added","Page requires JavaScript rendering — static HTTP fetch may return incomplete HTML","URL redirects to a different final page — finalUrl will differ from requestedUrl","Schema array is empty or exceeds 12 items — request rejected with validation error","Field name doesn't match the required pattern — request rejected"],"whenToPreferThis":"Choose this endpoint when you need to extract specific, named data fields from a known URL in a single call without setting up an account or managing API keys. It is ideal for one-off or low-volume structured data extraction tasks where you can identify the target elements by CSS selector, attribute, or JSON-LD/meta property. Prefer this over headless browser services when the target page renders its key content server-side. The pay-per-call x402 model makes it especially suitable for agent workflows that need to scrape unpredictably or infrequently without subscription overhead.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-17T00:37:04.359Z","isFirstParty":false,"canonicalSlug":"brainiac-structured-page-extract-dbd408f5"}