{"uid":"cap_lZJEgx0tfyTNcb8McdoYg","slug":"web-content-extractor-ai-policy-kit-ac3d5ec9","name":"Web Content Extractor (ai-policy-kit)","description":"Generate an AI_POLICY.md and a pull request template with an AI-disclosure section for your open-source repo. Free, runs in your browser.","url":"https://ai-policy-kit.moneymaker-ai.workers.dev/api/web-extract?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"public http(s) URL"},"max_chars":{"type":"string","description":"optional text limit, 500-50000 (default 20000)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"url":"https://example.com/","lang":"en","meta":{},"text":"This domain is for use in documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes.","links":{"sample":[],"external":0,"internal":0},"title":"Example Domain","robots":{"rule":"robots.txt HTTP 404 (treated as allow)","allowed":true,"checked":true},"favicon":"data:,","headings":[],"canonical":null,"final_url":"https://example.com/","open_graph":{},"word_count":25,"description":null,"http_status":200,"text_source":"body","content_type":"text/html; charset=utf-8","jsonld_types":[],"x_robots_tag":null,"last_modified":"Tue, 13 Oct 2026 22:05:48 GMT","text_truncated":false,"body_truncated_at_2mb":false}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","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":"$0.002/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_6YeBUqAfSSxzYc2FxYXLf","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches and extracts text content, metadata, links, and structured information from a public URL","exampleAgentPrompt":"Can you fetch the content of https://github.com/torvalds/linux/blob/master/README and extract the text and any metadata from the page, with a max of 10000 characters?","exampleUseCases":[{"title":"Extract article text for summarization","prompt":"Go grab the text from this news article at https://www.bbc.com/news/technology-12345678 and pull out the title, description, and main body text so I can summarize it."},{"title":"Check open-source repo README","prompt":"Fetch the content of https://github.com/openai/openai-python and give me the page title, headings, and the first 5000 characters of text."},{"title":"Audit competitor landing page","prompt":"Scrape https://stripe.com/pricing for me — I want the page title, meta description, any open graph data, and all the text content up to 20000 characters."}],"resultDescription":"Returns a JSON object containing the extracted page text, title, meta description, detected language, HTTP status code, word count, internal and external link counts, headings, canonical URL, open graph data, JSON-LD types, favicon, robots rules, content type, last modified date, and whether the text was truncated.","failureModes":["URL is not publicly accessible (private or firewalled) — returns non-200 HTTP status","Invalid or malformed URL provided — request fails with validation error","Page blocks bots via robots.txt — still fetched but flagged as disallowed","Text truncated if page body exceeds 2MB — body_truncated_at_2mb set to true","max_chars out of range (must be 500–50000) — validation error","Timeout on slow-loading pages — request may fail or return partial content"],"whenToPreferThis":"Use this endpoint when you need to fetch and extract readable text and metadata from any public URL in a structured JSON format. It is particularly useful when you need page title, description, open graph tags, headings, link counts, and clean body text without writing your own scraper. Choose this over a full browser automation tool when you need fast, lightweight extraction from publicly accessible pages.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-19T12:35:59.968Z","isFirstParty":false,"canonicalSlug":"web-content-extractor-ai-policy-kit-ac3d5ec9"}