{"uid":"cap_4CX0eteCNycn96zJSgvew","slug":"fetchharbor-pdf-parser-ca94a57c","name":"FetchHarbor PDF Parser","description":"Extract embedded text from a public PDF URL or multipart upload for research and retrieval pipelines. Returns text, page count, and character count; scanned-image OCR is not included. Remote and uploaded PDFs are limited to the operator-configured maximum size.","url":"https://fetchharbor.benlab.download/pdf-parse","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","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","format":"uri"}},"additionalProperties":false}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","required":["status","text","page_count","character_count"],"properties":{"text":{"type":"string"},"status":{"type":"string","const":"success"},"page_count":{"type":"integer","minimum":0},"character_count":{"type":"integer","minimum":0}},"additionalProperties":false}}}}},"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_emkGJJA-kkRQjnHFNEjKU","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":"Extracts embedded text, page count, and character count from a public PDF URL (no OCR for scanned images).","exampleAgentPrompt":"Can you extract all the text from this PDF so I can process it further — here's the URL: https://example.com/report.pdf","exampleUseCases":[{"title":"RAG pipeline document ingestion","prompt":"Pull the full text out of this publicly hosted research paper PDF so I can chunk it and add it to my vector database: https://arxiv.org/pdf/2401.00001.pdf"},{"title":"Legal document text extraction","prompt":"I need you to extract all the text from this contract PDF at https://docs.example.com/contract.pdf — also tell me how many pages it has."},{"title":"Automated report summarization","prompt":"Fetch the text content from this quarterly earnings report PDF at https://investor.example.com/Q3-2024.pdf and then summarize the key financial highlights for me."}],"resultDescription":"Returns a JSON object with a 'status' field ('success'), the full extracted plain text of the PDF, the total page count as an integer, and the character count as an integer. OCR is not performed on scanned or image-only PDFs; only embedded selectable text is returned.","failureModes":["PDF URL is not publicly accessible or returns a non-200 response","PDF exceeds the operator-configured maximum file size limit","PDF contains only scanned images — no embedded text is returned (OCR not supported)","Invalid or malformed URL provided in the query parameter","Network timeout fetching the remote PDF","Corrupted or password-protected PDF files may fail to parse"],"whenToPreferThis":"Choose this endpoint when you need to extract embedded text from a remote PDF URL quickly and cheaply ($0.01/call) without needing OCR. It is ideal for research, RAG ingestion pipelines, and document processing workflows where the PDF contains selectable text. Prefer this over general-purpose web scrapers when the target is specifically a PDF document and you need structured metadata (page count, character count) alongside the text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T12:33:19.736Z","isFirstParty":false}