{"uid":"cap_WL5lEHT0z7Xv5WvDz_sqw","slug":"clawfetch-document-parser-acaa9f80","name":"ClawFetch Document Parser","description":"Document parsing: convert office documents (docx, pptx, xlsx, pdf, odt, ods, odp, rtf, epub, csv, doc, ppt) to clean GitHub-Flavored Markdown. Pass a document URL or base64-encoded bytes. Deterministic local Rust converter (Firecrawl anydoc) — fast, typed structure preserved (headings, tables, lists), no OCR for scanned/image-only PDFs.","url":"https://api.clawfetch.ai/parse","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","description":"URL of the document to download and parse. Provide either url or base64."},"base64":{"type":"string","description":"Base64-encoded document bytes (max ~15MB). Provide either url or base64."},"format":{"type":"string","description":"Optional explicit format override. One of: doc, docx, odt, pdf, ppt, pptx, rtf, epub, xlsx, ods, odp, csv"},"filename":{"type":"string","description":"Optional filename hint (e.g. \"report.docx\") used for format detection when bytes carry no signature (csv)."}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","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":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_RM_ri-uJkbTCnIeNabK4p","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Converts office documents (docx, pptx, xlsx, pdf, odt, epub, csv, rtf, and more) to clean GitHub-Flavored Markdown, preserving headings, tables, and lists.","exampleAgentPrompt":"Can you convert this Word document to clean markdown? Here's the URL: https://example.com/reports/q3-report.docx","exampleUseCases":[{"title":"Research report ingestion pipeline","prompt":"I have a PDF research report at https://example.com/papers/annual-review-2024.pdf — can you convert it to markdown so I can feed it into my summarization pipeline?"},{"title":"Spreadsheet to markdown table","prompt":"Here's a base64-encoded Excel spreadsheet with our sales data. Convert it to a markdown table so I can include it in our wiki."},{"title":"Slide deck content extraction","prompt":"Pull the text and structure out of this PowerPoint presentation at https://storage.example.com/decks/product-launch.pptx and give it back to me as markdown."}],"resultDescription":"Returns GitHub-Flavored Markdown text of the parsed document, with structural elements like headings (# H1, ## H2), tables (pipe syntax), and lists (- item) faithfully preserved. Does not perform OCR, so scanned or image-only PDFs will not yield meaningful text.","failureModes":["Scanned/image-only PDFs return empty or minimal markdown because no OCR is performed","Unsupported file format returns an error; use the format override parameter if auto-detection fails","Base64 payload exceeding ~15MB will be rejected","Inaccessible or redirected document URL returns a fetch error","CSV files without a filename hint may fail format detection since they lack a file signature"],"whenToPreferThis":"Choose this endpoint when you need fast, deterministic, structure-preserving conversion of standard office document formats (docx, xlsx, pptx, pdf with selectable text, odt, epub, csv, rtf) to clean markdown — especially when table and heading structure must be retained. It is not suitable for scanned PDFs needing OCR, image extraction, or formats outside the supported list. Prefer this over general-purpose web scrapers when the input is a document file rather than an HTML page.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":1,"lastUsedAt":"2026-09-15T23:45:23.044Z","lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T23:44:35.547Z","isFirstParty":false}