{"uid":"cap_JaBycbvKKw11dRWiAVeWN","slug":"scrapingant-markdown-scraper-via-vaaya-9177c289","name":"ScrapingAnt Markdown Scraper via Vaaya","description":"ScrapingAnt — Scrape a URL and return LLM-ready markdown (rendered in headless Chrome, then converted). Pass `url`; optional browser/wait_for_selector/proxy_country/timeout knobs. Returns `{ url, markdown }`. Alternative to crw/scrape or firecrawl/scrape when you want ScrapingAnt's proxy pool behind the fetch.","url":"https://vaaya.ai/api/run/scrapingant/markdown","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["url"],"properties":{"url":{"type":"string","format":"uri"},"browser":{"type":"boolean"},"cookies":{"type":"string","minLength":1},"timeout":{"type":"integer","maximum":60,"minimum":5},"js_snippet":{"type":"string","minLength":1},"proxy_country":{"type":"string","maxLength":2,"minLength":2},"block_resource":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}]},"wait_for_selector":{"type":"string","minLength":1},"return_page_source":{"type":"boolean"}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"pathParams":{"type":"object"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"1.00","reviews":0,"stars":null,"state":"rated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_r7bMtFHUMhikKkn8E4ldL","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a URL using ScrapingAnt's residential proxy pool with headless Chrome rendering, then converts the page to LLM-ready markdown","exampleAgentPrompt":"Scrape https://techcrunch.com/2024/01/15/openai-news/ using ScrapingAnt's proxy pool and give me the content as clean markdown — wait for the main article selector '.article-content' to load before converting.","exampleUseCases":[{"title":"Scrape paywalled or bot-protected news","prompt":"Fetch https://www.wsj.com/tech/ai/latest-ai-regulation-article and return the full article as markdown using a US proxy — the site blocks regular scrapers so use ScrapingAnt's residential proxies."},{"title":"Extract product details from e-commerce page","prompt":"Scrape https://www.amazon.com/dp/B0EXAMPLE123 with a headless browser and give me the product description, specs, and reviews as markdown so I can summarize it."},{"title":"Pull documentation for LLM context","prompt":"Fetch https://docs.stripe.com/api/charges and convert it to clean markdown using ScrapingAnt — I need the rendered content, not raw HTML, to feed into my coding assistant."}],"resultDescription":"Returns a JSON object with two fields: `url` (the original URL that was scraped) and `markdown` (the full page content converted to LLM-ready markdown after headless Chrome rendering). The markdown is cleaned of scripts and styling, preserving readable structure like headings, lists, and links.","failureModes":["URL is unreachable or returns a non-200 status — empty or error markdown returned","Target site blocks all proxies including ScrapingAnt's pool — partial or empty content","wait_for_selector never appears in the DOM — timeout error","Invalid or malformed URL input — validation error","Timeout exceeded due to slow page load — partial render returned","Geo-restricted content not available in the requested proxy_country — empty or blocked response"],"whenToPreferThis":"Choose this endpoint over generic fetch tools or firecrawl/scrape when you specifically want ScrapingAnt's residential proxy pool to bypass bot-detection, need headless Chrome to render JavaScript-heavy pages, or need output pre-formatted as clean LLM-ready markdown. Prefer it when the target site is known to block datacenter IPs or requires a specific geographic proxy origin. If you need multi-page crawling instead of a single URL, use the sibling CRW crawl endpoint.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":1,"lastUsedAt":"2026-08-10T15:19:43.732Z","lastSuccessfullyRanAt":"2026-08-10T15:19:43.732Z","lastHealthCheckAt":"2026-09-14T12:41:36.491Z","isFirstParty":false}