{"slug":"agents-samedaydesk-com-extract-df054c","title":"Extract a public HTTP(S) web page into structured JSON with a clean text excerpt","host":"agents.samedaydesk.com","method":"GET","resource":"https://agents.samedaydesk.com/extract","category":"code","description":"Extract a public HTTP(S) web page into structured JSON with a clean text excerpt for LLM workflows: title, description, JSON-LD, Open Graph/Twitter metadata, headings, links, and AI-readiness signals. Fetches without JavaScript rendering, follows redirects, and applies a 12-second timeout and 3 MB r","price_listed":0.005,"price_asked":0.005,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":1921,"reported_calls_30d":14,"reported_payers_30d":11,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"method":"GET","queryParams":{"url":"https://example.com"},"type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"method":{"enum":["GET"],"type":"string"},"queryParams":{"properties":{"url":{"description":"Public http(s) URL to extract.","type":"string"}},"required":["url"],"type":"object"},"type":{"const":"http","type":"string"}},"required":["type","method"],"type":"object"},"output":{"properties":{"example":{"properties":{"aiReadiness":{"type":"object"},"capture":{"type":"object"},"description":{"type":["string","null"]},"error":{"type":["object","null"]},"finalUrl":{"type":"string"},"headings":{"type":"object"},"jsonLd":{"type":"array"},"links":{"type":"array"},"ok":{"type":"boolean"},"openGraph":{"type":"object"},"requestedUrl":{"type":"string"},"sourceOk":{"type":"boolean"},"status":{"type":"integer"},"text":{"type":"string"},"title":{"type":"string"},"url":{"type":"string"}},"required":["ok","url","title","status","sourceOk","requestedUrl","finalUrl"],"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-09-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.005,"price_match":true,"latency_ms":1921,"error":null}],"description_full":"Extract a public HTTP(S) web page into structured JSON with a clean text excerpt for LLM workflows: title, description, JSON-LD, Open Graph/Twitter metadata, headings, links, and AI-readiness signals. Fetches without JavaScript rendering, follows redirects, and applies a 12-second timeout and 3 MB read cap. The paid JSON keeps requestedUrl, finalUrl, source HTTP status, sourceOk, a nullable error, and capture limits; the excerpt is not the full page. Use /read for longer cleaned Markdown.","last_updated":"2026-09-22T15:50:47.528Z","schemes":["exact"]}