{"uid":"cap_94PCzYD1Bttn2Cj5mjlkR","slug":"pdf-metadata-intelligence-api-hustler-extract-pdfmeta-e88b0344","name":"PDF Metadata Intelligence API (hustler-extract /pdfmeta)","description":"URL-to-clean-markdown extraction API, on-demand broken-link scan API, pre-deploy link audit API, DNS health audit API, llms.txt / AI-crawler audit API, spec-linted llms.txt audit API, email-deliverability (SPF/DKIM/DMARC) audit API, PDF-to-markdown conversion API, technology-stack fingerprinting API, security-headers audit API, and PDF metadata-intel API for coding agents. Paid per call in USDC via x402 on Base.","url":"https://x402-extract-service.onrender.com/pdfmeta","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","format":"uri","description":"Public http(s) URL of the PDF to analyze."},"pdfBase64":{"type":"string","description":"Base64-encoded PDF (alternative to url for small files). Or POST multipart/form-data with a \"pdf\" file field."}}},"responseSchema":{"type":"json","example":{"ok":true,"xmp":{"fields":{"title":"Quarterly Report"},"present":true},"info":{"title":"Quarterly Report","author":"Ada Lovelace","creator":"AcmePDF 2.5.1","modDate":"D:20260401103000+00'00'","subject":"numbers","keywords":"revenue, q3","producer":"AcmePDF Engine 2.5.1","linearized":false,"modDateIso":"2026-04-01T10:30:00.000Z","creationDate":"D:20260315120000+00'00'","creationDateIso":"2026-03-15T12:00:00.000Z"},"fonts":{"count":1,"names":["Helvetica"],"embeddedLikely":true,"embeddedStreams":1},"pages":12,"source":"https://example.com/report.pdf","anomalies":[{"code":"future_creation_date","detail":"CreationDate D:20301225120000+00'00' is in the future."}],"checkedAt":"2026-09-15T00:00:00.000Z","encrypted":false,"imageCount":3,"pdfVersion":"1.7","pricePaidAtomic":"20000"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.02","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":"$0.02/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_EVVlTmtfm5XvGbzcVgVJZ","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts and audits PDF metadata including XMP fields, document info, fonts, page count, encryption status, image count, PDF version, and anomaly detection from a URL or base64-encoded file.","exampleAgentPrompt":"Pull the full metadata from this PDF — https://example.com/report.pdf — and tell me the author, creation date, what fonts are used, whether it's encrypted, and flag any anomalies like future-dated timestamps.","exampleUseCases":[{"title":"Verify PDF provenance before publishing","prompt":"Before we post this white paper to the site, grab its metadata from https://example.com/whitepaper.pdf and tell me who created it, what software generated it, when it was made, and whether anything looks suspicious like a future creation date."},{"title":"Font compliance check for legal documents","prompt":"I need to know which fonts are embedded in this contract PDF at https://legal.example.com/contract.pdf — list all font names and whether they're embedded, so I can confirm it meets our print compliance standards."},{"title":"Audit uploaded PDFs for hidden metadata","prompt":"We just received a PDF from a vendor — here it is in base64. Can you extract all the metadata including XMP fields, author, producer software, and page count, and flag anything anomalous?"}],"resultDescription":"Returns a JSON object with: XMP fields and presence flag, document info dictionary (title, author, creator, producer, subject, keywords, creation and modification dates in both raw and ISO formats), font details (count, names, embedded streams), total page count, encryption status, image count, PDF version string, source URL, list of detected anomalies (e.g. future-dated timestamps), and the timestamp of the check.","failureModes":["Invalid or inaccessible URL returns error with ok:false","PDF is password-protected and cannot be parsed","Base64 payload is malformed or not a valid PDF","File too large for inline base64 submission","Payment not completed via x402/USDC results in 402 response","Network timeout fetching remote PDF URL"],"whenToPreferThis":"Choose this endpoint when you need deep PDF metadata extraction including XMP, document info dictionary, font inventory, anomaly detection, and encryption status — especially in automated pipelines that need to audit, fingerprint, or validate PDF documents at $0.02 per call. Prefer over manual tools when integrating metadata extraction into an agent workflow that already uses the hustler-extract suite of auditing APIs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-19T06:41:11.176Z","isFirstParty":false}