{"uid":"cap_M5gOm77PNIX1xYYoLm5ZW","slug":"netintel-web-extractor-cbbd3b92","name":"NetIntel Web Extractor","description":"Extract article / main content from any URL or PDF to clean, LLM-ready Markdown (web scraper / reader / html-to-markdown) — strips scripts, nav, ads, and boilerplate while preserving headings, links, lists, tables, code blocks, and blockquotes; extracts the text layer from PDFs. Returns Markdown body, title, word count, and a quality grade so agents can read articles and documents without a browser or paid scraping service.","url":"https://netintel-production-440c.up.railway.app/web/extract","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 URL of an HTML page or PDF to extract (e.g. https://www.sitemaps.org/protocol.html)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"url":{"type":"string"},"grade":{"type":"string"},"score":{"type":"number"},"title":{"type":"string"},"findings":{"type":"array"},"markdown":{"type":"string"},"final_url":{"type":"string"},"truncated":{"type":"boolean"},"char_count":{"type":"number"},"word_count":{"type":"number"},"status_code":{"type":"number"},"content_type":{"type":"string","description":"article | pdf | other (non-HTML/PDF falls back to best-effort plain text)"},"output_bytes":{"type":"number"}}}}}}},"responseSchema":{"type":"json","example":{"url":"https://www.sitemaps.org/protocol.html","grade":"A","score":100,"title":"sitemaps.org - Protocol","findings":[],"markdown":"## Sitemaps XML format\n\nThis document describes the XML schema for the Sitemap protocol...","final_url":"https://www.sitemaps.org/protocol.html","truncated":false,"char_count":21619,"word_count":2707,"status_code":200,"content_type":"article","output_bytes":21619}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","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":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_wGy4H02pmOg2hr7nm0Eoi","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a public HTML page or PDF URL and returns its content as clean Markdown with metadata like title, word count, and content quality score","exampleAgentPrompt":"Can you fetch the article at https://techcrunch.com/2024/01/15/openai-funding and give me the full text as markdown along with the title and word count?","exampleUseCases":null,"resultDescription":"Returns a JSON object containing the page's Markdown-rendered content, title, final resolved URL, HTTP status code, content type, character and word counts, output byte size, a quality grade (letter, e.g. 'A') and numeric score (0-100), a findings array, and a boolean indicating whether the content was truncated.","failureModes":["URL is unreachable or returns non-200 status — status_code reflects the HTTP error","Page is JavaScript-heavy SPA with no static HTML content — markdown may be empty or minimal","PDF parsing fails for encrypted or malformed PDFs — may return error or empty content","Content is too large and gets truncated — truncated flag set to true","Invalid or missing url query parameter — request rejected with validation error","Payment failure via x402 micropayment — 402 response before content is returned"],"whenToPreferThis":"Use this endpoint when you need to retrieve and read the textual content of a public webpage or PDF as clean Markdown, especially when you also want quality metadata (grade, score, word count). Prefer it over generic HTTP fetch tools when you need structured extraction with readability scoring rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T00:51:45.709Z","isFirstParty":false}