{"uid":"cap_Tuk_ZV1d9qo6ezm08qEWp","slug":"web-scrape-to-markdown-21294517","name":"Web Scrape to Markdown","description":"Scrapes the given URL, converts the HTML content to Markdown, and returns the result.","url":"https://x402.orthogonal.com/context-dev/web/scrape/markdown","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","properties":{"url":{"type":"string","description":"Full URL to scrape and convert to markdown (must include http:// or https:// protocol)"},"includeLinks":{"type":"boolean","description":"Preserve hyperlinks in Markdown output"},"includeImages":{"type":"boolean","description":"Include image references in Markdown output"},"useMainContentOnly":{"type":"boolean","description":"Extract only the main content of the page, excluding headers, footers, sidebars, and navigation"},"shortenBase64Images":{"type":"boolean","description":"Shorten base64-encoded image data in the Markdown output"}}}},"additionalProperties":false}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.03","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":"$0.03/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_0PwctVUU4A7TKjxSOuk51","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.03","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a webpage by URL and converts its HTML content into clean Markdown format","exampleAgentPrompt":"Can you scrape https://www.example.com/article/ai-trends-2025 and give me the content as markdown, keeping the links but only pulling the main article body without navigation or sidebars?","exampleUseCases":[{"title":"Research article content extraction","prompt":"Scrape https://techcrunch.com/2025/01/15/openai-latest-update and convert it to markdown for me — just the main article content, no headers or footers, and preserve the hyperlinks."},{"title":"Documentation page archiving","prompt":"Can you fetch https://docs.stripe.com/api/charges and turn the whole page into markdown including images and links so I can save it for offline reference?"},{"title":"Competitor blog monitoring","prompt":"Pull down https://www.hubspot.com/marketing-statistics and convert it to clean markdown, main content only, so I can analyze what data points they're citing."}],"resultDescription":"Returns the page content as a Markdown-formatted string. Optionally includes hyperlinks (as Markdown link syntax), image references, or strips peripheral page elements (navigation, headers, footers, sidebars) to return only the main content body. Base64-encoded images can be shortened to reduce output size.","failureModes":["URL is unreachable or returns a non-200 HTTP status — scrape fails with an error","Page requires JavaScript rendering and content is not present in raw HTML","URL missing protocol prefix (http:// or https://) — request rejected by schema validation","Target site blocks scraping via robots.txt or anti-bot measures — returns empty or error content","Very large pages may time out or return truncated content"],"whenToPreferThis":"Choose this endpoint when you need a webpage's content in readable Markdown format rather than raw HTML. It is ideal for LLM pipelines that need clean, structured text from arbitrary URLs — e.g. summarization, Q&A, research, or archiving workflows. Prefer it over the raw HTML sibling endpoint when downstream processing expects Markdown. Use the useMainContentOnly flag to filter noise for article or documentation pages.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T18:45:08.325Z","isFirstParty":false}