{"uid":"cap_SBbrKrvAdyLjM4DijBw5k","slug":"reader-api-html-article-extractor-0fcda0e7","name":"Reader API – HTML Article Extractor","description":"Extract a readable article from supplied HTML, including title, author, language, metadata, clean Markdown, links and tables. Uses Mozilla Readability with a fallback for short pages. No remote fetches or script execution; URLs resolve relative links.","url":"https://reader-api-production-bde1.up.railway.app/v1/articles/extract?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","format":"uri","default":"https://example.com/article"},"html":{"type":"string","maxLength":250000,"minLength":1},"include_tables":{"type":"boolean","default":true}}},"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_AX2UuKnWyYYoNBSBCXW7N","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":"Extracts readable article content from supplied HTML, returning clean Markdown, title, author, language, metadata, links, and tables using Mozilla Readability.","exampleAgentPrompt":"I have the raw HTML of this news article — can you extract the readable content from it, including the title, author, and main body as clean Markdown, and also pull out any tables?","exampleUseCases":[{"title":"Summarize a paywalled article snippet","prompt":"I've got the HTML source of this article I saved locally — pull out the main readable text as Markdown so I can summarize it without all the nav bars and ads getting in the way."},{"title":"Extract structured data from a blog post","prompt":"Here's the raw HTML of a blog post — extract the title, author, language, and body as clean Markdown, and make sure to include any tables it contains."},{"title":"Feed article content into a RAG pipeline","prompt":"I need to index this article into my knowledge base — take this HTML and give me the clean article text in Markdown format along with any metadata like title and author so I can store it properly."}],"resultDescription":"Returns a structured object containing the article title, author name, detected language, clean Markdown body, extracted hyperlinks, any tables present in the article, and additional metadata — all parsed from the supplied HTML using Mozilla Readability, with a fallback for short pages.","failureModes":["HTML too short or lacking article-like content — fallback heuristic may return minimal content","HTML exceeds 250,000 character limit — request rejected","Malformed or unparseable HTML — parser may return empty or incomplete fields","Relative links in HTML cannot be resolved without a base URL supplied in the url field","Non-article pages (e.g. homepages, search results) may yield poor extraction quality"],"whenToPreferThis":"Choose this endpoint when you already have the raw HTML of a page and need to extract its readable article content without making any outbound HTTP requests. It is ideal for pipelines where fetching is handled upstream, for privacy-sensitive workflows where no remote calls should be made, or when you need reliable Markdown output plus structured metadata (title, author, language, tables, links) from article-style HTML. Prefer alternatives if you need the service to fetch the URL itself.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-19T00:35:53.797Z","isFirstParty":false,"canonicalSlug":"reader-api-html-article-extractor-0fcda0e7"}