{"uid":"cap_Cyg1-8uFttnqIsKfI_yjw","slug":"taskfleet-web-scraper-8df3c131","name":"TaskFleet Web Scraper","description":"Scrape any website to clean Markdown, text, or structured JSON. Renders JavaScript/SPA pages with headless Chromium (captures content raw-fetch scrapers miss), handles PDFs, optional schema-driven extraction. Input: { url, format? (markdown|text|html), links? (bool), fields? OR schema? }.","url":"https://taskfleet.net/scrape","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"required":["url"],"properties":{"url":{"type":"string","description":"Public http(s) URL (HTML or PDF)"},"links":{"type":"boolean","description":"Include extracted links"},"fields":{"type":"string","description":"Comma-separated fields to extract as JSON"},"format":{"type":"string","description":"markdown (default) | text | html"},"schema":{"type":"object","description":"JSON Schema for structured extraction"}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.02","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","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_8GeRvOknB7V08FcHGTy-v","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Scrapes any URL to clean Markdown, plain text, HTML, or structured JSON — rendering JavaScript/SPA pages with headless Chromium, with optional schema-driven field extraction.","exampleAgentPrompt":"Scrape https://example.com/product-page and give me the content as clean markdown — make sure to render JavaScript since it's a React app, and also pull out all the links on the page.","exampleUseCases":[{"title":"Extract article content from news site","prompt":"Scrape this article at https://techcrunch.com/2024/05/01/some-story and return the full body text as markdown — it's a JS-heavy page so make sure you fully render it."},{"title":"Structured product data extraction","prompt":"Go to https://shop.example.com/product/12345 and extract these specific fields for me: product name, price, availability, and description — give me the result as structured JSON."},{"title":"PDF document text extraction","prompt":"There's a PDF at https://reports.example.org/annual-report-2023.pdf — can you scrape it and return the full text as plain text so I can read through it?"}],"resultDescription":"Returns page content in the requested format: clean Markdown preserving headings/links/structure, plain text stripped of markup, raw HTML, or a structured JSON object with fields extracted per the provided schema or field list. May also include a list of discovered page links if requested.","failureModes":["URL is unreachable or returns non-200 — scrape fails with error","Page requires login/authentication — content may be partial or blocked","Anti-bot measures (Cloudflare, CAPTCHAs) block headless browser — returns error or empty content","Schema/field mismatch — extracted JSON may have null values if fields aren't found","PDF is scanned image-only — text extraction may return empty or garbled output","Timeout on very large or slow-loading pages"],"whenToPreferThis":"Choose this endpoint when you need to extract content from JavaScript-rendered or SPA pages that raw HTTP fetchers miss, or when you want schema-driven structured extraction from arbitrary web pages or PDFs. Prefer over basic fetch-based scrapers when the target site uses React, Vue, Angular, or other client-side rendering frameworks.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T00:38:21.681Z","isFirstParty":false}