{"uid":"cap_JdQQmbHklGzQeOnl5ZUNc","slug":"machine-shop-html-document-preparation-a9c133bb","name":"Machine Shop – HTML Document Preparation","description":"Turn Apify product scrape results into safe catalog updates with Catalog Update Gate. Find evidence in supplied documents, compare snapshots, extract typed JSON fields, inspect x402 quotes and assess API migrations. Preview inputs, evidence and cost for free. No live web search, scheduled monitoring or third-party purchasing.","url":"https://api.pay-forge.online/v1/html-prepare-document?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"html":{"type":"string","title":"Html","maxLength":50000},"overlap":{"type":"integer","title":"Overlap","default":150,"maximum":9999,"minimum":0},"base_url":{"type":"string","title":"Base Url","default":"","maxLength":2048},"chunk_size":{"type":"integer","title":"Chunk Size","default":1500,"maximum":10000,"minimum":64}}},"responseSchema":{"type":"json","example":{"text":"Hello\nAgent documents.","links":[],"document":{"text":"Hello\nAgent documents.","chunks":[{"end":22,"text":"Hello\nAgent documents.","index":0,"start":0}],"sha256":"ad5d70c4710c7e4d89fd61cc8a948080c97155017935a37327b3c88d4ed9f88f","entities":{"urls":[],"dates":[],"money":[],"emails":[],"evm_addresses":[]},"removed_duplicate_lines":0},"markdown":"# Hello\n\nAgent documents.","metadata":{"meta":{},"title":"Example","language":"en","canonical":"","description":""},"limitations":["Static HTML only; no JavaScript, CSS visibility, article detection, table reconstruction or microdata parsing."],"structured_data":[]}},"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_uyQ3CmfZwsST7MrvQgTXA","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":"Parses and chunks raw HTML into clean text, extracts entities (URLs, dates, money, emails, EVM addresses), and returns structured document metadata ready for downstream analysis.","exampleAgentPrompt":"Parse this HTML page into clean text chunks of 1500 characters each with 150-character overlap, and pull out any emails, dates, money amounts, and Ethereum addresses you find in it.","exampleUseCases":[{"title":"Prep web page for RAG pipeline","prompt":"I have the raw HTML for a product documentation page — can you break it into 1000-character chunks with 100-character overlap and give me the clean text and any links so I can load it into my vector database?"},{"title":"Extract financial figures from report HTML","prompt":"Here's the HTML of a quarterly earnings report — please pull out all the money amounts, dates, and any Ethereum addresses mentioned in it and return them as structured data."},{"title":"Convert HTML article to markdown","prompt":"Take this HTML blog post and convert it to clean markdown text, and also give me the page title, description, and language from the metadata."}],"resultDescription":"Returns a JSON object containing: clean plain text, an array of overlapping text chunks with start/end character positions and index, a SHA-256 hash of the document, extracted entities (URLs, dates, money amounts, emails, EVM addresses), a markdown rendering, page metadata (title, description, language, canonical URL), any detected structured data, and a list of parser limitations.","failureModes":["HTML exceeding 50,000 characters is rejected","JavaScript-rendered content will not be visible — only static HTML is processed","CSS-hidden elements may appear in output","No table reconstruction or microdata parsing — complex layouts lose structure","Invalid or malformed JSON body returns a 422 validation error","chunk_size below 64 or above 10,000 is rejected with a validation error"],"whenToPreferThis":"Choose this endpoint when you have raw HTML content in hand and need to prepare it for downstream tasks such as embedding, entity extraction, or evidence finding — particularly when you want chunked output with overlap for RAG pipelines. Prefer this over generic text extractors when you need EVM address extraction or SHA-256 document fingerprinting alongside standard NLP entities. Not suitable when you need JavaScript rendering, live web fetching, or scheduled monitoring.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T12:30:13.640Z","isFirstParty":false,"canonicalSlug":"machine-shop-html-document-preparation-a9c133bb"}