{"uid":"cap_eolmYMnJQYrOZkpx7WQgA","slug":"fresh402-web-intelligence-api-web-extraction-687cd9ee","name":"Fresh402 Web Intelligence API – Web Extraction","description":"Fresh402 2.0.0: durable payment results, private recovery, public web extraction, structural comparison and backward-compatible freshness. On-demand requests; no browser rendering or LLM inference.","url":"https://fresh402.kirilllabs.workers.dev/v2/extract?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","format":"uri","pattern":"^[Hh][Tt][Tt][Pp][Ss]://","maxLength":4096,"description":"Public HTTPS URL on port 443; embedded credentials and private targets are rejected."},"selector":{"type":"string","maxLength":256,"minLength":1},"max_chars":{"type":"integer","default":20000,"maximum":50000,"minimum":100},"include_links":{"type":"boolean","default":true},"ignore_selectors":{"type":"array","items":{"type":"string","maxLength":256,"minLength":1},"maxItems":20},"ignore_json_paths":{"type":"array","items":{"type":"string","pattern":"^\\/","maxLength":256,"minLength":1},"maxItems":20},"include_structured_data":{"type":"boolean","default":true}}},"responseSchema":{"type":"json","example":{"url":"https://example.com/","data":null,"hash":"1111111111111111111111111111111111111111111111111111111111111111","text":"Example Domain","links":[],"title":"Example Domain","headings":[{"text":"Example Domain","level":1}],"final_url":"https://example.com/","truncated":false,"description":null,"text_length":14,"content_kind":"html","canonical_url":null,"structured_data":[]}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/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_QHgK8qizCkzysYpUM_20U","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts text, links, headings, structured data, and metadata from any public HTTPS URL via a paid on-demand HTTP request, without browser rendering or LLM inference.","exampleAgentPrompt":"Fetch the full text, all links, and any structured data from https://en.wikipedia.org/wiki/Octopus — limit the result to 10000 characters and skip the navigation and footer sections.","exampleUseCases":[{"title":"Article text extraction for summarization","prompt":"Pull the main article text and title from https://www.bbc.com/news/technology-68123456 — give me up to 15000 characters and include any structured data embedded on the page so I can summarize it."},{"title":"Product page data harvesting","prompt":"Extract the text and JSON-LD structured data from https://www.amazon.com/dp/B09XYZ1234 — focus on the main product section using the CSS selector '#productTitle', skip ads and recommendations, and include all links."},{"title":"Competitive intelligence snapshot","prompt":"Grab the visible text, headings, and all links from https://www.competitor.com/pricing — limit to 20000 characters and include structured data so I can analyze their pricing tiers."}],"resultDescription":"Returns a JSON object containing the page title, extracted text content (up to the specified character limit), a list of headings with their levels, an array of links, embedded structured data (e.g. JSON-LD), the final resolved URL after redirects, canonical URL, meta description, a SHA-256 hash of the content, content kind (e.g. 'html'), and a truncation flag indicating whether the content was cut off.","failureModes":["URL uses non-443 port or embedded credentials — request rejected","Target is a private or non-public host — rejected by policy","URL returns non-200 status — extraction fails with error","Page requires JavaScript rendering — content may be incomplete or empty","Content exceeds max_chars limit — result is truncated and truncated flag is set true","Invalid CSS selector syntax — selector ignored or error returned","Network timeout on target URL — request fails"],"whenToPreferThis":"Choose this endpoint when you need structured, parseable web content (text, links, headings, structured data) from a known public URL without spinning up a headless browser. It is ideal for lightweight, on-demand scraping of static or server-rendered HTML pages where you want a content hash for change detection and don't need JavaScript execution or AI inference. Prefer it over browser-based scrapers when speed and cost matter and the page renders server-side.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-11T12:30:09.802Z","isFirstParty":false,"canonicalSlug":"fresh402-web-intelligence-api-web-extraction-687cd9ee"}