{"uid":"cap_RwfrnPPhWn2J8-C3d75v7","slug":"agishub-web-scraper-4b1883c0","name":"AGISHub Web Scraper","description":"Fetch any public web page and return its main content as clean, token-efficient Markdown (title, description, headings, links, lists). Set render:true to execute JavaScript first for single-page apps or JS-heavy pages that would otherwise come back empty. Built for RAG and for agents that need to read the contents of a URL.","url":"https://api.agishub.com/v1/web-scraper","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input","output"],"properties":{"input":{"type":"object","required":["type","method","queryParams"],"properties":{"type":{"enum":["http"],"type":"string"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","format":"uri","description":"Full http/https URL of the page to extract."},"render":{"type":"boolean","description":"Render JavaScript with a headless browser before extracting (default false). Enable for SPAs / JS-heavy pages that return empty content otherwise. Slower."},"max_chars":{"type":"integer","minimum":0,"description":"Truncate the markdown to at most this many characters (sets truncated:true).","exclusiveMinimum":true},"include_links":{"type":"boolean","description":"Keep hyperlinks in the markdown output (default true)."},"include_images":{"type":"boolean","description":"Keep images as markdown (default false)."}},"additionalProperties":false}},"additionalProperties":false},"output":{"type":"object","required":["type","example"],"properties":{"type":{"enum":["json"],"type":"string"},"example":{"type":"object"}},"additionalProperties":false}}},"responseSchema":{"type":"json","example":{"result":"Fetch any public web page and return its main content as clean, token-efficient Markdown (title, description, headings, "}},"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_vrQY1ru2NtoqyNUtzi9gO","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 any public web page and returns its main content as clean, token-efficient Markdown, with optional JavaScript rendering for SPAs.","exampleAgentPrompt":"Can you fetch the content of https://en.wikipedia.org/wiki/Artificial_intelligence and give me the main text as clean markdown, keeping the links but skipping images?","exampleUseCases":[{"title":"Reading a competitor's pricing page","prompt":"Go grab the content of https://www.competitor.com/pricing and return it as readable markdown so I can see what they're offering."},{"title":"Extracting article text for RAG pipeline","prompt":"Fetch the article at https://techcrunch.com/2024/05/01/openai-news and return its main body text as clean markdown — keep the links but no images, and cap it at 5000 characters."},{"title":"Scraping a JavaScript-rendered SPA","prompt":"Can you scrape https://app.someservice.com/blog/latest-post for me? It's a React app so you'll need to render the JavaScript first before extracting the content."}],"resultDescription":"A JSON object containing the page's main content rendered as clean, token-efficient Markdown, including the title, description, headings, links, and lists. Optionally truncated to a specified character limit, with a flag indicating if truncation occurred.","failureModes":["URL is not publicly accessible or returns 4xx/5xx — empty or error response","JavaScript-heavy SPA returns empty content when render:false (solution: set render:true)","Page behind authentication or paywall — content not accessible","Very large pages may be truncated if max_chars is set low","Malformed or invalid URL format causes request failure","Rate limiting or blocking by target site may result in partial or empty content"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read and understand the text content of a specific public web page, especially for RAG pipelines, research tasks, or when the agent needs to act on information at a known URL. Prefer it over full-site crawlers when you only need a single page. Use the render:true option specifically for JavaScript-heavy SPAs that return empty HTML without execution. It is more token-efficient than raw HTML fetching due to its Markdown cleaning.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T18:45:08.155Z","isFirstParty":false}