{"uid":"cap_UISrF4J5ZXfvAv7-hQcng","slug":"scrapingant-schemaless-ai-data-extraction-18a69c36","name":"ScrapingAnt Schemaless AI Data Extraction","description":"ScrapingAnt — AI data extraction WITHOUT a schema: describe the fields in plain English and get structured JSON back. Pass `url` and `extract_properties` — a comma-separated list like 'product title, price(number), full description, reviews(list: review title, review content)'. Optional browser/wait_for_selector/proxy_country/timeout knobs. Vendor cost scales with page length (1 credit per 30 chars of markdown) — prefer crw/extract (schema-driven, 5¢) for big pages; this rung is for quick no-sc…","url":"https://vaaya.ai/api/run/scrapingant/extract","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["url","extract_properties"],"properties":{"url":{"type":"string","format":"uri"},"browser":{"type":"boolean"},"cookies":{"type":"string","minLength":1},"timeout":{"type":"integer","maximum":60,"minimum":5},"js_snippet":{"type":"string","minLength":1},"proxy_country":{"type":"string","maxLength":2,"minLength":2},"block_resource":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}]},"wait_for_selector":{"type":"string","minLength":1},"extract_properties":{"type":"string","maxLength":2000,"minLength":3},"return_page_source":{"type":"boolean"}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"pathParams":{"type":"object"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.2","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","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":"$0.2/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.2","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.2","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_f-jEROhk0-rgIf6fsyUxN","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.2","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts structured JSON from any webpage using plain-English field descriptions — no schema definition required.","exampleAgentPrompt":"Scrape this product page — https://www.example.com/product/123 — and extract the product title, price as a number, full description, and reviews as a list with review title and review content for each one, then give me the results as structured JSON.","exampleUseCases":[{"title":"E-commerce product data extraction","prompt":"Pull the product title, price, star rating, and top 5 customer reviews (with title and body) from this Amazon listing: https://www.amazon.com/dp/B09XYZ1234 — give me everything as structured JSON."},{"title":"Job listing details scraper","prompt":"Scrape this job posting at https://jobs.example.com/posting/456 and extract the job title, company name, location, salary range, and a list of required skills — return it all as structured JSON without me having to define a schema."},{"title":"News article content parser","prompt":"Go to https://techcrunch.com/2024/05/01/some-article and extract the article title, author name, publish date, and full article body text as structured JSON fields."}],"resultDescription":"A structured JSON object whose keys correspond to the plain-English field names provided in extract_properties, with values automatically parsed from the webpage — numbers returned as numbers, lists as arrays of objects, and text fields as strings.","failureModes":["Page requires JavaScript rendering but browser flag not set — returns empty or incomplete fields","Selector specified in wait_for_selector never appears — timeout error returned","Page is behind a login or paywall — extracted fields return null or empty","High credit cost for very long pages (1 credit per 30 chars of markdown) — may exceed budget unexpectedly","Invalid or unreachable URL — HTTP error or connection timeout","Ambiguous field descriptions may cause incorrect extraction or mismatched data types"],"whenToPreferThis":"Choose this endpoint when you need to extract data from a webpage quickly without defining a formal JSON schema — ideal for ad-hoc extractions, prototyping, or one-off scraping tasks where field descriptions in plain English are sufficient. Prefer the schema-driven crw/extract endpoint instead for large pages (to control credit cost) or when you need strict type validation. Use this endpoint when flexibility and speed of setup matter more than cost optimization.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T12:57:12.248Z","isFirstParty":false}