{"uid":"cap_e6_XC3C9O3JiQTP2S8J9h","slug":"pdf-text-extractor-by-url-a8f9a818","name":"PDF Text Extractor by URL","description":"Extract the text of a PDF by URL (up to 15 MB), page by page, with title, author and page count. Use to read reports, papers, whitepapers and filings.","url":"https://api.agent-data.workers.dev/api/v1/pdf?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":"http(s) URL of a PDF"},"max_chars":{"type":"integer","maximum":200000,"minimum":500},"max_pages":{"type":"integer","maximum":300,"minimum":1}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"url":"https://bitcoin.org/bitcoin.pdf","text":"--- page 1 ---\nBitcoin: A Peer-to-Peer Electronic Cash System...","title":"Bitcoin: A Peer-to-Peer Electronic Cash System","truncated":false,"pages_read":9,"pages_total":9}},"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_gHTFjBitqQhJQUgQHMMDE","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":"Fetches a PDF from a given URL (up to 15 MB) and returns its full text content page by page, along with metadata such as title, author, and page count.","exampleAgentPrompt":"Can you read the PDF at https://bitcoin.org/bitcoin.pdf and give me its full text, up to 9 pages?","exampleUseCases":[{"title":"Summarize a research whitepaper","prompt":"Grab the text from this arXiv paper PDF at https://arxiv.org/pdf/2303.08774.pdf and summarize the key findings for me."},{"title":"Extract SEC filing content","prompt":"Read the PDF filing at https://www.sec.gov/Archives/edgar/data/1018724/000101872423000006/amzn-20221231.pdf and pull out all the text so I can analyze the financials."},{"title":"Read a technical whitepaper for a DeFi project","prompt":"Can you extract the full text from the whitepaper PDF at https://uniswap.org/whitepaper-v3.pdf, including title and author info?"}],"resultDescription":"A JSON object containing the full extracted text of the PDF organized page by page (with '--- page N ---' separators), the document title and author (if available in the PDF metadata), total page count, number of pages actually read, and a boolean indicating whether the text was truncated due to the max_chars or max_pages limits.","failureModes":["URL is not a valid or accessible PDF — returns an error indicating the resource could not be fetched","PDF exceeds 15 MB size limit — request may fail or be rejected","PDF is password-protected or encrypted — text extraction may fail or return empty","max_chars or max_pages parameters out of allowed range — validation error","PDF URL is unreachable or returns a non-200 response — fetch error"],"whenToPreferThis":"Use this endpoint when you need to read or extract text from a PDF available at a public URL, especially for research papers, whitepapers, regulatory filings, or reports. It is preferable over general web scraping endpoints when the source is specifically a PDF file rather than an HTML page. It supports up to 300 pages and 200,000 characters, making it suitable for long documents.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-11T13:21:55.073Z","isFirstParty":false,"canonicalSlug":"pdf-text-extractor-by-url-a8f9a818"}