{
  "x402Version": 2,
  "id": 29482,
  "slug": "29482",
  "resource": "https://netintel.dev/web/extract",
  "description": "Extract text from a web page or PDF as clean Markdown — HTML to Markdown for any URL: 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. Web scraper / reader for article and main content. For JS-rendered or bot-walled pages a plain fetch can't read, use /exa/contents.",
  "type": "http",
  "serviceName": "NetIntel",
  "iconUrl": "https://res.cloudinary.com/bdb-prod/image/upload/c_fill,ar_1:1,w_256,h_256,f_auto,q_auto/v1784214098/bazaar-icons/7d2bf437631b2e4e.png",
  "resourceType": "Beauty & Personal Care",
  "accepts": [
    {
      "scheme": "exact",
      "network": "eip155:8453",
      "payTo": "0xdaDc335482AD545296Fd7b28518A251fFCbEb9Df",
      "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
      "amount": "3000",
      "amountUsd": 0.003,
      "maxTimeoutSeconds": 300
    },
    {
      "scheme": "exact",
      "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
      "payTo": "8FVeybWnB4dYrxTuPK7WzFZNAiEcFVaDLFnKpRwVGr5s",
      "asset": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
      "amount": "3000",
      "amountUsd": 0.003,
      "maxTimeoutSeconds": 300
    }
  ],
  "outputSchema": {
    "properties": {
      "example": {
        "properties": {
          "char_count": {
            "type": "number"
          },
          "content_type": {
            "description": "article | pdf | other (non-HTML/PDF falls back to best-effort plain text)",
            "type": "string"
          },
          "final_url": {
            "type": "string"
          },
          "findings": {
            "type": "array"
          },
          "grade": {
            "type": "string"
          },
          "markdown": {
            "type": "string"
          },
          "output_bytes": {
            "type": "number"
          },
          "score": {
            "type": "number"
          },
          "status_code": {
            "type": "number"
          },
          "title": {
            "type": "string"
          },
          "truncated": {
            "type": "boolean"
          },
          "url": {
            "type": "string"
          },
          "word_count": {
            "type": "number"
          }
        },
        "type": "object"
      },
      "type": {
        "type": "string"
      }
    },
    "required": [
      "type"
    ],
    "type": "object"
  },
  "extensions": {
    "bazaar": {
      "info": {
        "input": {
          "method": "GET",
          "queryParams": {
            "url": "https://www.sitemaps.org/protocol.html"
          },
          "type": "http"
        },
        "output": {
          "example": {
            "char_count": 21619,
            "content_type": "article",
            "final_url": "https://www.sitemaps.org/protocol.html",
            "findings": [],
            "grade": "A",
            "markdown": "## Sitemaps XML format\n\nThis document describes the XML schema for the Sitemap protocol...",
            "output_bytes": 21619,
            "score": 100,
            "status_code": 200,
            "title": "sitemaps.org - Protocol",
            "truncated": false,
            "url": "https://www.sitemaps.org/protocol.html",
            "word_count": 2707
          },
          "type": "json"
        }
      },
      "schema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "input": {
            "additionalProperties": false,
            "properties": {
              "method": {
                "enum": [
                  "GET"
                ],
                "type": "string"
              },
              "queryParams": {
                "properties": {
                  "url": {
                    "description": "Public URL of an HTML page or PDF to extract (e.g. https://www.sitemaps.org/protocol.html)",
                    "type": "string"
                  }
                },
                "required": [
                  "url"
                ],
                "type": "object"
              },
              "type": {
                "const": "http",
                "type": "string"
              }
            },
            "required": [
              "type",
              "method"
            ],
            "type": "object"
          },
          "output": {
            "properties": {
              "example": {
                "properties": {
                  "char_count": {
                    "type": "number"
                  },
                  "content_type": {
                    "description": "article | pdf | other (non-HTML/PDF falls back to best-effort plain text)",
                    "type": "string"
                  },
                  "final_url": {
                    "type": "string"
                  },
                  "findings": {
                    "type": "array"
                  },
                  "grade": {
                    "type": "string"
                  },
                  "markdown": {
                    "type": "string"
                  },
                  "output_bytes": {
                    "type": "number"
                  },
                  "score": {
                    "type": "number"
                  },
                  "status_code": {
                    "type": "number"
                  },
                  "title": {
                    "type": "string"
                  },
                  "truncated": {
                    "type": "boolean"
                  },
                  "url": {
                    "type": "string"
                  },
                  "word_count": {
                    "type": "number"
                  }
                },
                "type": "object"
              },
              "type": {
                "type": "string"
              }
            },
            "required": [
              "type"
            ],
            "type": "object"
          }
        },
        "required": [
          "input"
        ],
        "type": "object"
      }
    }
  },
  "tags": [
    "web content",
    "retrieve url content",
    "read webpage",
    "html to markdown",
    "web reader",
    "bazaar"
  ],
  "sourceHost": "netintel.dev",
  "lastUpdated": "2026-10-11T09:08:27.118Z",
  "quality": {
    "calls30d": 45,
    "uniquePayers30d": 7,
    "lastCalledAt": "2026-10-11T09:08:26.836Z"
  },
  "metadata": {
    "serviceName": "NetIntel",
    "iconUrl": "https://res.cloudinary.com/bdb-prod/image/upload/c_fill,ar_1:1,w_256,h_256,f_auto,q_auto/v1784214098/bazaar-icons/7d2bf437631b2e4e.png",
    "extensions": {
      "bazaar": {
        "info": {
          "input": {
            "method": "GET",
            "queryParams": {
              "url": "https://www.sitemaps.org/protocol.html"
            },
            "type": "http"
          },
          "output": {
            "example": {
              "char_count": 21619,
              "content_type": "article",
              "final_url": "https://www.sitemaps.org/protocol.html",
              "findings": [],
              "grade": "A",
              "markdown": "## Sitemaps XML format\n\nThis document describes the XML schema for the Sitemap protocol...",
              "output_bytes": 21619,
              "score": 100,
              "status_code": 200,
              "title": "sitemaps.org - Protocol",
              "truncated": false,
              "url": "https://www.sitemaps.org/protocol.html",
              "word_count": 2707
            },
            "type": "json"
          }
        },
        "schema": {
          "$schema": "https://json-schema.org/draft/2020-12/schema",
          "properties": {
            "input": {
              "additionalProperties": false,
              "properties": {
                "method": {
                  "enum": [
                    "GET"
                  ],
                  "type": "string"
                },
                "queryParams": {
                  "properties": {
                    "url": {
                      "description": "Public URL of an HTML page or PDF to extract (e.g. https://www.sitemaps.org/protocol.html)",
                      "type": "string"
                    }
                  },
                  "required": [
                    "url"
                  ],
                  "type": "object"
                },
                "type": {
                  "const": "http",
                  "type": "string"
                }
              },
              "required": [
                "type",
                "method"
              ],
              "type": "object"
            },
            "output": {
              "properties": {
                "example": {
                  "properties": {
                    "char_count": {
                      "type": "number"
                    },
                    "content_type": {
                      "description": "article | pdf | other (non-HTML/PDF falls back to best-effort plain text)",
                      "type": "string"
                    },
                    "final_url": {
                      "type": "string"
                    },
                    "findings": {
                      "type": "array"
                    },
                    "grade": {
                      "type": "string"
                    },
                    "markdown": {
                      "type": "string"
                    },
                    "output_bytes": {
                      "type": "number"
                    },
                    "score": {
                      "type": "number"
                    },
                    "status_code": {
                      "type": "number"
                    },
                    "title": {
                      "type": "string"
                    },
                    "truncated": {
                      "type": "boolean"
                    },
                    "url": {
                      "type": "string"
                    },
                    "word_count": {
                      "type": "number"
                    }
                  },
                  "type": "object"
                },
                "type": {
                  "type": "string"
                }
              },
              "required": [
                "type"
              ],
              "type": "object"
            }
          },
          "required": [
            "input"
          ],
          "type": "object"
        }
      }
    }
  },
  "liveness": {
    "reliability": null
  },
  "verified": false,
  "featured": false,
  "provider": {
    "host": "netintel.dev",
    "manifest_name": "netintel.dev",
    "source": "cdp-mirror",
    "source_manifest_url": "https://api.cdp.coinbase.com/platform/v2/x402/discovery/resources",
    "submitted_at": "2026-10-14T01:15:01.050Z"
  },
  "exampleResponse": {
    "example": {
      "char_count": 0,
      "content_type": "string",
      "final_url": "string",
      "findings": [
        "value"
      ],
      "grade": "string",
      "markdown": "string",
      "output_bytes": 0,
      "score": 0,
      "status_code": 0,
      "title": "string",
      "truncated": true,
      "url": "string",
      "word_count": 0
    },
    "type": "string"
  }
}