SnipHunter API

Web

网页抓取、正文与 Markdown 提取。

Base URL https://api.sniphunter.com

OpenAPI JSON · 完整 Markdown

请求与响应中的 $ref 在 OpenAPI 的 components 中定义。

2 个接口

Web

POST/api/v1/web/scrapeWeb Scrape

抓取网页并提取降噪正文（Markdown）。

{
  "requestBody": {
    "content": {
      "application/json": {
        "schema": {
          "$ref": "#/components/schemas/WebScrapeRequest"
        }
      }
    },
    "required": true
  },
  "responses": {
    "200": {
      "description": "Successful Response",
      "content": {
        "application/json": {
          "schema": {}
        }
      }
    },
    "422": {
      "description": "Validation Error",
      "content": {
        "application/json": {
          "schema": {
            "$ref": "#/components/schemas/HTTPValidationError"
          }
        }
      }
    }
  }
}
GET/api/v1/web/statusWeb Status

{
  "responses": {
    "200": {
      "description": "Successful Response",
      "content": {
        "application/json": {
          "schema": {}
        }
      }
    }
  }
}

数据模型

展开 components
{
  "schemas": {
    "HTTPValidationError": {
      "properties": {
        "detail": {
          "items": {
            "$ref": "#/components/schemas/ValidationError"
          },
          "type": "array",
          "title": "Detail"
        }
      },
      "type": "object",
      "title": "HTTPValidationError"
    },
    "ValidationError": {
      "properties": {
        "loc": {
          "items": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "integer"
              }
            ]
          },
          "type": "array",
          "title": "Location"
        },
        "msg": {
          "type": "string",
          "title": "Message"
        },
        "type": {
          "type": "string",
          "title": "Error Type"
        }
      },
      "type": "object",
      "required": [
        "loc",
        "msg",
        "type"
      ],
      "title": "ValidationError"
    },
    "WebScrapeRequest": {
      "properties": {
        "url": {
          "type": "string",
          "minLength": 1,
          "title": "Url"
        },
        "fetch": {
          "type": "string",
          "enum": [
            "auto",
            "http",
            "browser"
          ],
          "title": "Fetch",
          "default": "auto"
        },
        "pruning_threshold": {
          "type": "number",
          "maximum": 1.0,
          "minimum": 0.0,
          "title": "Pruning Threshold",
          "default": 0.45
        }
      },
      "type": "object",
      "required": [
        "url"
      ],
      "title": "WebScrapeRequest"
    }
  },
  "securitySchemes": {
    "HTTPBearer": {
      "type": "http",
      "scheme": "bearer"
    }
  }
}