{"uid":"cap_KE7zCoJmwahK6uGpcbM0J","slug":"aiworker-data-web-page-to-markdown-scraper-725fe9b4","name":"aiworker-data Web Page to Markdown Scraper","description":"Deterministic-first data for agents, paid per call in USDC over x402 v2: DeFi yields, Base token and wallet cards, Polymarket odds and backtests, news, fact checks, cited briefs. 20 routes, $0.005-$1","url":"https://aiworker.duckdns.org/v1/scrape/markdown","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","description":"absolute https url of a public page"},"max_chars":{"type":"integer","default":60000,"maximum":60000,"minimum":500}}},"responseSchema":{"type":"json","example":{"title":"Example","source":"web","truncated":false,"content_md":"# Example\n…","source_url":"https://example.com/article","word_count":812,"attribution":"Fetched from https://example.com"}},"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_QTd6eOo24PDyMVWLkEjSu","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":"Fetches a public web page and returns its content as clean, agent-readable Markdown","exampleAgentPrompt":"Fetch the content of https://example.com/blog/2024-annual-report and give it back to me as clean markdown, keeping it under 60000 characters.","exampleUseCases":[{"title":"Research article ingestion for agent","prompt":"Pull down the full text of this news article at https://techcrunch.com/2024/05/01/openai-gpt5-launch/ as markdown so I can summarize it — limit it to 40000 characters."},{"title":"Documentation page extraction","prompt":"Grab the content from https://docs.uniswap.org/contracts/v3/reference/core/UniswapV3Pool as clean markdown so I can answer questions about the contract interface."},{"title":"Competitor landing page snapshot","prompt":"Fetch https://www.anthropic.com/product as markdown, capped at 20000 characters, so I can compare their positioning to ours."}],"resultDescription":"A JSON object containing the page title, a boolean indicating whether content was truncated, the full page content rendered as clean Markdown (up to 60,000 characters), and a word count integer.","failureModes":["Non-HTTPS or relative URLs rejected — URL must be absolute and start with https://","Pages behind authentication or paywalls will return incomplete or empty content","max_chars below 500 or above 60000 will be rejected by schema validation","Slow or unresponsive target servers may cause timeout errors","JavaScript-heavy SPAs may return minimal content if server-side rendering is unavailable","Truncated flag will be true if page content exceeds max_chars — downstream agent should handle partial content"],"whenToPreferThis":"Use this endpoint when you need a fast, cheap ($0.02/call), clean Markdown rendering of any public HTTPS webpage for LLM consumption. Prefer it over raw HTML fetching when you want noise-free, structured text. Choose the sibling /v1/scrape/summarize endpoint if you also need a structured summary and key entities in the same call. This endpoint is best for agents that need the full raw page content in a readable format without additional AI-generated analysis.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T18:36:45.039Z","isFirstParty":false}