{"uid":"cap_IizRYdHY76IwtRYIjNUW1","slug":"openverbs-web-article-extractor-0bfa2aaa","name":"OpenVerbs Web Article Extractor","description":"Fetch a URL and return its main article as clean HTML, Markdown and plain text.","url":"https://web.openverbs.com/v1/extract","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","required":["url"],"properties":{"url":{"type":"string","format":"uri","maxLength":2048,"description":"Public http(s) URL to fetch. Private/loopback/link-local addresses are rejected."}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.006","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":"$0.006/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.006","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.006","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_KYWc4VvrYuZjQ86zhSToy","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.006","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a public URL and returns its main article content as clean HTML, Markdown, and plain text","exampleAgentPrompt":"Can you fetch the article at https://www.bbc.com/news/technology-12345678 and give me the main content as clean markdown, without all the ads and navigation clutter?","exampleUseCases":[{"title":"Summarize news article for briefing","prompt":"Pull the full article text from this Reuters URL — https://www.reuters.com/article/example — and give me a clean version I can summarize."},{"title":"Archive blog post as markdown","prompt":"Grab the main content of this blog post at https://blog.example.com/my-post and convert it to markdown so I can save it to my notes."},{"title":"Feed article text to LLM pipeline","prompt":"Extract the readable article body from https://techcrunch.com/2024/01/01/some-article/ as plain text so I can run it through my analysis workflow."}],"resultDescription":"Returns the main article content of the fetched URL in three formats: clean HTML (boilerplate and navigation stripped), Markdown, and plain text. The response isolates the primary editorial content, removing ads, headers, footers, and sidebars.","failureModes":["Private, loopback, or link-local URLs are rejected with an error","Non-article pages (e.g. homepages, login walls) may return minimal or empty content","URLs returning non-200 HTTP status codes will fail","Paywalled content behind authentication cannot be extracted","Very large pages or slow-loading targets may time out","Malformed or non-URI-format URLs are rejected at schema validation"],"whenToPreferThis":"Choose this endpoint when you need clean, readable article content from a public URL in multiple formats (HTML, Markdown, and plain text) simultaneously. It is ideal for agent pipelines that need to feed article text into LLMs, summarizers, or note-taking systems. Prefer it over raw HTTP fetch tools when you want boilerplate removed and structured text output without building a readability parser yourself.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T18:30:28.054Z","isFirstParty":false}