{"uid":"cap_986iBSw2AJzHYfhmraYBe","slug":"agent-data-tools-revmesh2074-workers-dev-web-scraping-api-fetch-any-16edd8f5","name":"Web Scraping API – Fetch Any URL as Clean Text or Markdown","description":"Web scraping API: fetch any public web page URL and get its main content as clean text or Markdown (headings, code blocks, tables and links kept), ready for an LLM, RAG or an agent's context; static HTML, Markdown or text pages, up to 100,000 characters. JavaScript-rendered pages: /extract/rendered. Empty pages, bot walls and errors are never charged. Use to read articles, docs and product pages at scale.","url":"https://agent-data-tools.revmesh2074.workers.dev/scrape?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"Absolute http(s) URL of the page to scrape"},"format":{"enum":["text","markdown","both"],"type":"string","description":"Returned representation: text (default), markdown, or both"},"section":{"type":"string","description":"Optional visible HTML ID within the main content, 1-500 characters; a leading # (a docs link's fragment) or a URL ending in #id is accepted, and so is a heading's visible text when exactly one heading matches; leave it out to read the whole page"},"maxChars":{"type":"integer","description":"Maximum characters of body text to return (500-100000, default 20000)"}}},"responseSchema":{"type":"object","properties":{"url":{"type":"string"},"lang":{"type":"string"},"text":{"type":"string"},"links":{"type":"array","items":{}},"title":{"type":"string"},"format":{"type":"string"},"status":{"type":"number"},"tables":{"type":"array","items":{}},"section":{},"finalUrl":{"type":"string"},"headings":{"type":"array","items":{"type":"object","properties":{"id":{},"text":{"type":"string"},"level":{"type":"number"}}}},"warnings":{"type":"array","items":{}},"canonical":{},"fetchedAt":{"type":"string"},"truncated":{"type":"boolean"},"codeBlocks":{"type":"array","items":{}},"hashFormat":{"type":"string"},"textLength":{"type":"number"},"contentHash":{"type":"string"},"contentType":{"type":"string"},"description":{},"linkBaseUrl":{"type":"string"},"sourceFormat":{"type":"string"},"sourceMetadata":{"type":"object","properties":{"dates":{"type":"array","items":{}},"authors":{"type":"array","items":{}},"truncated":{"type":"boolean"},"verification":{"type":"string"}}},"contentSelection":{"type":"string"}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","displayCostAsset":"USD","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":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_6VNc5vUipF_38z0wty7DK","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"agent-data-tools.revmesh2074.workers.dev","brandSlug":"agent-data-tools-revmesh2074-workers-dev-x402","brandBaseUrl":"https://agent-data-tools.revmesh2074.workers.dev","brandDocsUrl":null,"whatItDoes":"Fetches any public static web page and returns its main content as clean text or structured Markdown, stripped of boilerplate, ready for LLM/RAG consumption.","exampleAgentPrompt":"Can you fetch the content of https://docs.python.org/3/library/asyncio.html and give it to me as clean markdown so I can drop it into my context window?","exampleUseCases":[{"title":"Reading documentation for RAG ingestion","prompt":"Fetch the content of https://react.dev/reference/react/useState as clean markdown — I want to index it into my RAG system."},{"title":"Extracting a news article","prompt":"Grab the main article text from https://www.bbc.com/news/technology-12345678 and return it as plain text, up to 10000 characters."},{"title":"Pulling a product page for competitive research","prompt":"Scrape https://www.notion.so/product and return the main content as markdown so I can compare features with our own product."}],"resultDescription":"Returns a JSON object containing the page title, cleaned body text and/or markdown, extracted headings, code blocks, tables, links, page language, content hash, fetch timestamp, truncation flag, source metadata (authors, dates), and any warnings. The `finalUrl` reflects any redirects followed.","failureModes":["Bot wall or CAPTCHA detected — page returns empty content (not charged)","URL is invalid or unreachable — HTTP error returned","JavaScript-rendered page returns empty body — use /extract/rendered instead","Content exceeds maxChars — response is truncated with truncated:true flag","Page returns non-HTML content type — may produce unexpected output"],"whenToPreferThis":"Use this endpoint when you need to read a known public static URL (HTML, Markdown, plain text) and get its main content quickly and cheaply. Ideal for reading articles, documentation, and product pages in LLM/RAG pipelines. Prefer this over browser-based renderers when the page does not require JavaScript execution. Use /extract/rendered for JS-heavy SPAs. At $0.002/call with no charge for failed fetches, it is cost-effective for high-volume agent workflows.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-22T06:32:43.927Z","isFirstParty":false,"canonicalSlug":"agent-data-tools-revmesh2074-workers-dev-web-scraping-api-fetch-any-16edd8f5"}