{"uid":"cap_xsWVckELKVYsasuMEoxfH","slug":"agent-tools-uk-web-page-to-clean-markdown-extractor-bb36d27d","name":"Agent Tools UK – Web Page to Clean Markdown Extractor","description":"Fetch a public web page and return just the main article as clean Markdown, with title, byline and excerpt. Menus, ads and footers are removed. Use when you need to read, summarise or quote a web page cheaply without parsing HTML yourself. Returns JSON {title, byline, siteName, excerpt, markdown}. Errors: 400 bad or private URL, 422 no readable article, 502 site returned an error.","url":"https://agent-tools-production-e6aa.up.railway.app/v1/extract?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":"Page to read (http/https, public)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","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":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_f8JsL3S_2LxB-L5c_-mNp","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a public web page and returns only the main article content as clean Markdown, stripping menus, ads, and footers","exampleAgentPrompt":"Can you grab the main article text from https://www.bbc.co.uk/news/technology-12345678 and give me a clean, readable version without all the navigation menus and ads?","exampleUseCases":[{"title":"Summarising a news article for a briefing","prompt":"Pull the main article from https://www.theguardian.com/technology/2024/jan/15/ai-regulation-uk and summarise the key points for me — just the article content, none of the sidebar junk."},{"title":"Quoting a blog post in a report","prompt":"I need to quote the article at https://martinfowler.com/articles/microservices.html in a report I'm writing — can you extract just the article text as clean markdown so I can copy from it easily?"},{"title":"Feeding a web page into an AI analysis pipeline","prompt":"Fetch the content from https://www.economist.com/leaders/2024/03/01/the-ai-race and return it as clean markdown with the title and author — I want to run it through sentiment analysis without having to deal with the raw HTML."}],"resultDescription":"A JSON object containing: title (page/article headline), byline (author name if present), siteName (name of the publishing site), excerpt (short summary or first paragraph), and markdown (the full main article body as clean Markdown). Errors: 400 for bad or private URLs, 422 if no readable article is found, 502 if the target site itself returned an error.","failureModes":["400 Bad Request – URL is malformed, non-HTTP/HTTPS, or points to a private/intranet resource","422 Unprocessable Entity – the page exists but contains no identifiable article body (e.g. homepage, login wall, dynamic SPA content)","502 Bad Gateway – the target website returned an error or was unreachable at time of request","Paywalled articles may return only a short excerpt rather than full content","Pages that require JavaScript rendering may not return full content"],"whenToPreferThis":"Choose this endpoint when you need clean, readable article text from a public URL without writing an HTML parser or dealing with boilerplate. It is ideal for summarisation, quoting, or feeding article content into LLM pipelines. Prefer this over a full browser screenshot endpoint when you need text rather than a visual render, and over raw HTTP fetching when you want structured output (title, byline, excerpt, markdown) rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-13T12:42:26.475Z","isFirstParty":false,"canonicalSlug":"agent-tools-uk-web-page-to-clean-markdown-extractor-bb36d27d"}