{"uid":"cap_0kfAa0YzrnEMpPaCNs7Qw","slug":"doc-json-page-extractor-42cc464c","name":"Doc-JSON Page Extractor","description":"Web pages, PDFs and feeds turned into clean structured JSON for AI agents: metadata, schema.org data, tables, headings, readable text, per-page PDF text, feed items. Pay per call over x402, no API key.","url":"https://doc-json.agent-utils.workers.dev/v1/page","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","format":"uri","description":"Absolute http(s) URL of the page"},"maxChars":{"type":"integer","default":20000,"maximum":200000,"minimum":500,"description":"Cap on returned text length"},"includeText":{"type":"boolean","default":true}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"url":{"type":"string"},"meta":{"type":"object","additionalProperties":{"type":"string"}},"text":{"type":"string","description":"Readable text without nav, scripts, footers"},"chars":{"type":"integer"},"links":{"type":"object","properties":{"sample":{"type":"array","items":{"type":"object","properties":{"href":{"type":"string"},"text":{"type":"string"}}}},"external":{"type":"integer"},"internal":{"type":"integer"}}},"title":{"type":["string","null"]},"author":{"type":["string","null"]},"images":{"type":"integer"},"jsonLd":{"type":"array","items":{},"description":"Parsed schema.org JSON-LD blocks (products, articles, organizations, events...)"},"status":{"type":"integer"},"tables":{"type":"array","items":{"type":"object","properties":{"rows":{"type":"array","items":{"type":"array","items":{"type":"string"}}},"caption":{"type":["string","null"]},"headers":{"type":"array","items":{"type":"string"}}}},"description":"Up to 20 HTML tables as headers + rows"},"twitter":{"type":"object","additionalProperties":{"type":"string"}},"finalUrl":{"type":"string"},"headings":{"type":"array","items":{"type":"object","properties":{"text":{"type":"string"},"level":{"type":"integer"}}}},"language":{"type":["string","null"]},"canonical":{"type":["string","null"]},"fetchedAt":{"type":"string"},"openGraph":{"type":"object","additionalProperties":{"type":"string"}},"truncated":{"type":"boolean"},"wordCount":{"type":"integer"},"responseMs":{"type":"integer"},"contentType":{"type":"string"},"description":{"type":["string","null"]},"publishedAt":{"type":["string","null"]}}}}}}},"responseSchema":{"type":"json","example":{"url":"https://example.com/product/42","meta":{"viewport":"width=device-width"},"text":"Acme Widget 42\nThe 42nd widget...\nSpecifications\nWeight 1.2 kg\nColor Blue","chars":2600,"links":{"sample":[{"href":"https://example.com/product/42#specs","text":"Specifications"}],"external":3,"internal":34},"title":"Acme Widget 42","author":null,"images":6,"jsonLd":[{"name":"Acme Widget 42","@type":"Product","offers":{"@type":"Offer","price":"19.99","priceCurrency":"USD"}}],"status":200,"tables":[{"rows":[["Weight","1.2 kg"],["Color","Blue"]],"caption":null,"headers":["Spec","Value"]}],"twitter":{},"finalUrl":"https://example.com/product/42","headings":[{"text":"Acme Widget 42","level":1},{"text":"Specifications","level":2}],"language":"en","canonical":"https://example.com/product/42","fetchedAt":"2026-09-06T21:30:00.000Z","openGraph":{"type":"product","image":"https://example.com/w42.jpg","title":"Acme Widget 42"},"truncated":false,"wordCount":412,"responseMs":210,"contentType":"text/html; charset=utf-8","description":"The 42nd widget.","publishedAt":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_sRB4ieTOuWnTWN78OFkkn","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":"Fetches any web page, PDF, or feed URL and returns clean structured JSON with metadata, readable text, tables, headings, schema.org JSON-LD, and link data for AI agents","exampleAgentPrompt":"Can you fetch https://www.bbc.com/news/technology-12345678 and give me the clean article text, headings, author, and any schema.org data from the page — cap the text at 10000 characters?","exampleUseCases":[{"title":"Product page data extraction","prompt":"Pull all the structured data from https://www.amazon.com/dp/B09XYZ123 — I need the title, price, description, any JSON-LD product schema, and the main readable text, capped at 50000 characters."},{"title":"Article content for AI summarization","prompt":"Fetch the article at https://techcrunch.com/2024/05/01/some-article and give me the clean readable text without nav or footers, plus the author and publish date — limit the text to 20000 chars."},{"title":"PDF document text extraction","prompt":"Extract the readable text and metadata from this PDF: https://example.gov/reports/annual-report-2023.pdf — I need the per-page text and any document metadata you can find, up to 100000 characters."}],"resultDescription":"A JSON object containing: page URL, final redirected URL, HTTP status, content type, title, author, language, canonical URL, meta tags, Open Graph data, Twitter card data, schema.org JSON-LD blocks (products, articles, events etc.), readable body text (stripped of nav/scripts/footers), word count, character count, headings with levels, up to 20 HTML tables with headers and rows, a sample of internal and external links, image count, fetch timestamp, and response time in milliseconds.","failureModes":["URL is unreachable or returns non-200 status — status field reflects actual HTTP code","Page behind login/paywall returns only gated content","PDF is image-only (scanned) and contains no extractable text","Text truncated if page exceeds maxChars limit (truncated field set to true)","Feed URL returns malformed XML, resulting in partial or empty feed items","JavaScript-heavy SPAs may return minimal content if JS is not executed server-side"],"whenToPreferThis":"Choose this endpoint when you need to turn any arbitrary public URL — web page, PDF, or feed — into structured, AI-ready JSON in a single call with no API key setup. It is ideal for agents that need readable article text, product schema, tables, or Open Graph metadata without building a scraping pipeline. Prefer it over raw HTTP fetching when you need clean text (nav/footer stripped), structured headings, JSON-LD, and link analysis all in one response. It is pay-per-call via x402 micropayments, making it cost-effective for sporadic or high-volume use without subscription overhead.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:34:05.713Z","isFirstParty":false}