{"uid":"cap_4tOboVmLKYS2zdVJnzdPi","slug":"pdf-text-and-tables-extractor-2dfc4299","name":"PDF Text and Tables Extractor","description":"Download a PDF by URL and return per-page text (layout preserved), detected tables as rows of cells, and metadata (title, author, page count). Up to 50 pages per call via first_page/last_page; flags scanned image-only PDFs.","url":"https://164.160.90.241.sslip.io/api/doc-pdf-extract?utm_source=zero.xyz","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","description":"URL of a PDF"},"last_page":{"type":"integer","description":"Last page (max 50 pages per call)"},"first_page":{"type":"integer","description":"First page, default 1"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/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_GJRXzQxHqEwzUuRDz-BZV","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Downloads a PDF from a URL and returns per-page layout-preserved text, detected tables as structured rows/cells, and document metadata (title, author, page count) — with scanned-image detection.","exampleAgentPrompt":"Can you download the PDF at https://example.com/annual-report-2023.pdf and extract all the text and tables from pages 1 through 20, along with the document title and author?","exampleUseCases":[{"title":"Extract financial tables from annual report","prompt":"Pull all the tables and text from this SEC filing PDF at https://sec.gov/filings/acme-10k-2023.pdf, pages 1 to 50, so I can see the balance sheet and income statement rows."},{"title":"Parse research paper content","prompt":"Grab the full text and any data tables from this academic paper PDF at https://arxiv.org/pdf/2301.00001.pdf — I need the content from pages 1 through 15."},{"title":"Check if scanned PDF has extractable text","prompt":"Try to extract text from this scanned document at https://storage.example.com/old-contract.pdf and let me know if it's a scanned image-only file or if you can pull actual text from it."}],"resultDescription":"Returns per-page layout-preserved text content, detected tables represented as rows of cells, and document metadata including title, author, and total page count. Also flags whether the PDF is a scanned image-only document (where text extraction is not possible).","failureModes":["PDF URL is unreachable or returns a non-PDF response","PDF is password-protected or encrypted","PDF is scanned image-only — text extraction returns empty or a scanned flag","Requested page range exceeds 50-page limit per call","Network timeout fetching a large PDF","Malformed or corrupted PDF file"],"whenToPreferThis":"Choose this endpoint when you need to extract readable text, structured table data, or metadata from a PDF document accessible via a public URL. It is ideal for processing reports, research papers, contracts, or any structured document in PDF format. It handles multi-page documents up to 50 pages per call and explicitly flags scanned-only PDFs where text is not extractable.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T00:41:19.971Z","isFirstParty":false,"canonicalSlug":"pdf-text-and-tables-extractor-2dfc4299"}