NetIntel

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.

Resource: netintel.dev/web/extract

Network: eip155:8453, solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp · Asset: 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913 · Pay to: 0xdaDc335482AD545296Fd7b28518A251fFCbEb9Df

Payment methods: — · Last validation: 2026-10-15 11:29:15.584+00

{
  "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"
          }
        }
      }
    }
  },
  "paymentRequirements": [
    {
      "raw": {
        "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
        "extra": {
          "name": "USD Coin",
          "version": "2"
        },
        "payTo": "0xdaDc335482AD545296Fd7b28518A251fFCbEb9Df",
        "amount": "3000",
        "scheme": "exact",
        "network": "eip155:8453",
        "maxTimeoutSeconds": 300
      },
      "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
      "payTo": "0xdaDc335482AD545296Fd7b28518A251fFCbEb9Df",
      "scheme": "exact",
      "network": "eip155:8453",
      "amountAtomic": "3000"
    },
    {
      "raw": {
        "asset": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
        "extra": {
          "feePayer": "BFK9TLC3edb13K6v4YyH3DwPb5DSUpkWvb7XnqCL9b4F"
        },
        "payTo": "8FVeybWnB4dYrxTuPK7WzFZNAiEcFVaDLFnKpRwVGr5s",
        "amount": "3000",
        "scheme": "exact",
        "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
        "maxTimeoutSeconds": 300
      },
      "asset": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
      "payTo": "8FVeybWnB4dYrxTuPK7WzFZNAiEcFVaDLFnKpRwVGr5s",
      "scheme": "exact",
      "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
      "amountAtomic": "3000"
    }
  ]
}

Source catalog records are retained separately from live endpoint observations. Sonar score, uptime, and latency are advisory metrics. CDP indexing is not inferred from validation.