{"uid":"cap_hnnnWo5Y5HuFSMOoV8-hf","slug":"402utils-readability-article-extractor-66d7509c","name":"402utils Readability Article Extractor","description":"Extract the main article from a web page with Mozilla Readability — drops nav, ads, sidebars and footer boilerplate. Send inline {html} or a public {url} to fetch (SSRF-checked). Returns the article title, byline, cleaned HTML content, plain textContent, excerpt, character length, language and site name. THE pre-processing step before sending a page to an LLM. Distinct from html-to-md (which renders Markdown). Max 5 MB.","url":"https://402utils.com/v1/readability?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","format":"uri","description":"Public http(s) page URL to fetch instead of inline html."},"html":{"type":"string","description":"HTML document to extract from (non-empty, max 5 MB UTF-8)."}}},"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_PdFvFMRptJtCdzuSxyIAQ","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":"Extracts the main article content from a web page or HTML string using Mozilla Readability, stripping nav, ads, sidebars, and footers","exampleAgentPrompt":"Strip out all the ads, nav, and sidebar junk from this page and give me just the article title, author, and clean readable text — here's the URL: https://www.theguardian.com/technology/2024/jan/15/some-article","exampleUseCases":[{"title":"News aggregation for content curation","prompt":"I need to pull articles from these five news links and extract just the main content, titles, and authors so I can summarize them for my team. Can you clean them up and give me the plain text for each?"},{"title":"Research synthesis from multiple sources","prompt":"Go through these blog posts and documentation pages I've gathered, strip out all the navigation and ads, and give me the core text and title from each one — I need to compile them into a knowledge base."},{"title":"Content moderation and safety filtering","prompt":"Check these URLs for problematic content — pull out the clean article text, author, and title from each page so I can review what's actually being published."}],"resultDescription":"Returns a JSON object with the article title, byline (author), cleaned HTML content, plain textContent (boilerplate-free), a short excerpt, total character length, detected language code, and site name — everything needed to pass clean article text to an LLM.","failureModes":["URL is not publicly accessible or returns non-200 status","HTML exceeds 5 MB limit — returns error","SSRF check blocks private/internal IP ranges","Page has no extractable main article (e.g. login wall, empty body) — returns null content fields","Neither url nor html provided — returns validation error","Malformed URL format — returns schema validation error"],"whenToPreferThis":"Use this endpoint when you need to preprocess a web page or raw HTML for LLM consumption — especially when you want clean plain text and structured metadata (title, byline, language) rather than Markdown. Prefer this over html-to-md when you need the plain textContent field or structured article metadata rather than a rendered Markdown document. Best for news articles, blog posts, and any long-form content page.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-10T06:47:53.247Z","isFirstParty":false,"canonicalSlug":"402utils-readability-article-extractor-66d7509c"}