{"uid":"cap_TLRKk3hUM2UFePYTUOuzR","slug":"agent-souk-pdf-text-extractor-7a2ed72f","name":"Agent Souk PDF Text Extractor","description":"Fetch a PDF and extract its text per page, with the document info","url":"https://api.agentsouk.dev/v1/x402/lst_01M2N6GWB06867BFMSKJATK2QC?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","format":"uri","description":"Public http(s) URL of a PDF"},"pages":{"type":"string","pattern":"^\\d{1,6}(-\\d{1,6})?(,\\d{1,6}(-\\d{1,6})?)*$","description":"Pages to extract, e.g. \"1-5\" or \"1,3,8-10\" (at most 100); the first 100 by default"},"max_chars":{"type":"integer","default":50000,"maximum":200000,"minimum":100}}},"responseSchema":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_xHshOnvmpqDJ08MKQhEau","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 a PDF from a public URL and extracts its text content page-by-page, along with document metadata","exampleAgentPrompt":"Can you fetch the PDF at https://example.com/report.pdf and extract the text from pages 1-10?","exampleUseCases":[{"title":"Extract contract clauses from PDF","prompt":"Pull the text from this legal contract PDF at https://contracts.example.com/agreement.pdf — I only need pages 1 through 5, and cap the output at 20000 characters."},{"title":"Research paper content ingestion","prompt":"Fetch the research paper PDF at https://arxiv.org/pdf/2301.00001.pdf and extract all the text page by page so I can analyze its contents."},{"title":"Invoice data extraction pipeline","prompt":"Grab the PDF invoice from https://billing.example.com/invoice-2024-03.pdf and extract its full text — just the first page should be enough."}],"resultDescription":"Returns the extracted text content organized per page along with document metadata such as page count, title, author, and other PDF info fields. Text is limited by the max_chars parameter (default 50,000, up to 200,000 characters).","failureModes":["URL is not publicly accessible or returns a non-200 HTTP status","URL does not point to a valid PDF file","PDF is encrypted or password-protected and cannot be parsed","Requested page range exceeds the document's actual page count","max_chars limit reached before all requested pages are extracted","PDF contains only scanned images with no embedded text (returns empty text per page)","Network timeout fetching a large PDF"],"whenToPreferThis":"Choose this endpoint when you need to programmatically read the text content of a remotely hosted PDF, especially when you need per-page granularity and document metadata. It is preferable over general web scraping endpoints when the source is definitely a PDF file. Use it as a preprocessing step before LLM-based summarization, classification, or structured extraction.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-11T00:39:42.317Z","isFirstParty":false,"canonicalSlug":"agent-souk-pdf-text-extractor-7a2ed72f"}