{"uid":"cap_IaD7LXLbdimneDZSCOPO_","slug":"pdf-text-metadata-extractor-70581609","name":"PDF Text & Metadata Extractor","description":"Extract plain text and metadata (title, author, producer, page count) from a PDF supplied by URL or base64 — heavy pdf.js parsing an agent can't self-run.","url":"https://pdf.openverbs.com/v1/extract?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"pdf":{"type":"string","maxLength":7000000,"description":"Base64-encoded PDF bytes (≤5 MB decoded). Provide this or `url`."},"url":{"type":"string","format":"uri","maxLength":2048,"description":"Public http(s) URL of the PDF to fetch. Private/loopback/link-local addresses are rejected. Provide this or `pdf`."},"perPage":{"type":"boolean","description":"When true, also return the text split per page as `perPage[]`."},"maxPages":{"type":"integer","maximum":500,"minimum":1,"description":"Cap the number of pages extracted (from the start). Default 500."}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.006","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":"$0.006/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.006","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.006","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_WXRpgxEqxkx5LSZ-dsewn","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.006","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts plain text and metadata (title, author, producer, page count) from a PDF supplied via URL or base64-encoded bytes using server-side pdf.js parsing.","exampleAgentPrompt":"Can you extract all the text and metadata from this PDF — https://example.com/report.pdf — and also give me the text broken out page by page?","exampleUseCases":[{"title":"Research paper content extraction","prompt":"I need you to pull out all the text from this academic PDF at https://arxiv.org/pdf/2301.00001.pdf so I can summarize it — also tell me the title, author, and how many pages it is."},{"title":"Contract review from base64 upload","prompt":"I've got a PDF contract encoded in base64 — can you extract the plain text from it so I can check the terms? I only need the first 10 pages."},{"title":"Invoice metadata and text retrieval","prompt":"Grab the text and metadata from this invoice PDF at https://invoices.mycompany.com/inv-2024-042.pdf and give me the content split page by page so I can find the line items."}],"resultDescription":"Returns extracted plain text from the PDF, along with document metadata including title, author, producer, and page count. If perPage is true, also returns an array of per-page text strings. Covers up to maxPages pages (default 500).","failureModes":["Private, loopback, or link-local URLs are rejected with an error","PDF exceeds 5 MB decoded size limit when using base64 input","URL is unreachable or returns a non-PDF file","Malformed or corrupted PDF that pdf.js cannot parse","Neither pdf nor url parameter provided — request rejected","maxPages out of allowed range (1–500)"],"whenToPreferThis":"Choose this endpoint when an agent needs to extract text or metadata from a PDF document but cannot run pdf.js or similar parsing libraries locally. Ideal when the PDF is available at a public URL or as base64 bytes. Prefer over general web scraping tools when the target is specifically a PDF. Best when structured per-page text or metadata fields like author and producer are needed alongside content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-18T06:34:15.314Z","isFirstParty":false,"canonicalSlug":"pdf-text-metadata-extractor-70581609"}