{"uid":"cap_yNMmlNTKHOMwKLxJl8UYH","slug":"x402-money-farm-clean-text-extractor-b315aa8d","name":"x402 Money Farm: Clean Text Extractor","description":"URL → Clean Text — Fetches a web page and returns boilerplate-free main content as plain text or Markdown, with title, language and word count.","url":"https://x402-money-farm.fly.dev/v1/clean-text?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","format":"uri","description":"Absolute http(s) URL of the page to process."},"fresh":{"type":"boolean","default":false},"format":{"enum":["text","markdown"],"type":"string","default":"text"},"max_chars":{"type":"integer","default":200000,"maximum":500000,"minimum":200},"include_links":{"type":"boolean","default":true}},"additionalProperties":false}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"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_sGVv89JYBenVnjrARtmpG","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 web page and returns boilerplate-free main content as plain text or Markdown, along with title, language, and word count.","exampleAgentPrompt":"Grab the main article text from https://www.theverge.com/2024/5/1/some-article and return it as clean Markdown, including any links.","exampleUseCases":[{"title":"LLM context from a news article","prompt":"Pull the main readable content from https://www.bbc.com/news/world-us-canada-12345678 and give it to me as plain text so I can summarize it."},{"title":"Research page extraction for RAG pipeline","prompt":"Fetch https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and return the clean Markdown version of the page content, up to 100000 characters, with links included."},{"title":"Competitive intelligence content grab","prompt":"Get the clean text from https://www.competitor.com/pricing and strip all the nav and footer junk — I just want the core pricing page content as plain text."}],"resultDescription":"Returns the main body content of the fetched page as plain text or Markdown, stripped of navigation, ads, and other boilerplate. Also includes the page title, detected language, and word count of the extracted content.","failureModes":["URL is unreachable or returns non-200 status — likely returns an error with HTTP status details","Page requires JavaScript rendering — may return empty or incomplete content","max_chars too small for page content — content will be truncated at the specified limit","Invalid or non-HTTP URL provided — schema validation error","Paywalled or bot-blocked pages — may return login prompts or empty content instead of article body"],"whenToPreferThis":"Choose this endpoint when you need clean, human-readable text from a web page for downstream LLM processing, summarization, or analysis, and want boilerplate automatically stripped. Prefer it over raw HTML fetchers when you need plain text or Markdown output with metadata like title, language, and word count included. It is especially useful for article and documentation pages where main content is clearly delimited from navigation and ads.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-03T06:32:49.641Z","isFirstParty":false,"canonicalSlug":"x402-money-farm-clean-text-extractor-b315aa8d"}