{"uid":"cap_Av0YjqL6YzBPodIYEoy-H","slug":"scanpay-web-scraper-url-to-llm-markdown-cfcd0a20","name":"ScanPay Web Scraper — URL to LLM Markdown","description":"Deterministic AST code security scanner with x402 Solana micropayments, remote MCP, and ERC-8183 Evaluator oracle.","url":"https://scanpay-ob3w.onrender.com/v2/oracle/scrape?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"Target HTTPS URL to scrape into clean LLM Markdown"},"extract_mode":{"type":"string","description":"'markdown' or 'text'"}}},"responseSchema":{"type":"json","example":{"content":{"markdown":"# Clean Extracted Content","estimated_tokens":120},"bot_protection":{"waf_detected":false}}},"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_aPak3lpEOkM_oRcpBPgvY","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":"Scrapes a target HTTPS URL and returns clean LLM-ready Markdown or plain text content with bot-protection detection","exampleAgentPrompt":"Can you scrape https://example.com/article and give me the content as clean markdown so I can feed it into my LLM pipeline?","exampleUseCases":[{"title":"Research article extraction for AI","prompt":"Grab the content from https://techcrunch.com/2024/05/01/openai-news/ and convert it to clean markdown so I can summarize it."},{"title":"Competitor pricing page scrape","prompt":"Scrape https://competitor.com/pricing and extract the text so I can compare their plans to ours."},{"title":"Documentation ingestion for chatbot","prompt":"Fetch https://docs.myproduct.com/getting-started and return it as markdown — I need to load it into my support chatbot's knowledge base."}],"resultDescription":"Returns a JSON object containing the extracted page content as markdown or plain text, an estimated token count for LLM budgeting, and a bot-protection field indicating whether a WAF was detected on the target site.","failureModes":["Target URL is unreachable or returns a non-200 status — endpoint may return an error or empty content","WAF or bot protection blocks the scrape — waf_detected flag will be true but content may be incomplete","Invalid or non-HTTPS URL provided — likely returns a validation error","Target page is JavaScript-rendered (SPA) — content may be incomplete if JS is not executed","Payment via x402 fails or is insufficient — request may be rejected before scraping begins"],"whenToPreferThis":"Choose this endpoint when you need to convert a live web page into clean, LLM-ready markdown or plain text with token estimation, especially within an x402 micropayment workflow. It is well-suited for one-off page extractions where bot-protection detection is a useful signal. Prefer alternatives if you need full-site crawls, structured data extraction with schema mapping, or JavaScript-heavy SPA rendering guarantees.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-31T18:37:54.631Z","isFirstParty":false,"canonicalSlug":"scanpay-web-scraper-url-to-llm-markdown-cfcd0a20"}