Website Metadata & Content Scraper GPT

Website Metadata & Content Scraper GPT · GPT 작업

Microlink API

API for retrieving detailed website metadata, screenshots, generating PDFs, extracting color palettes, and more, suitable for analyzing web page content and appearance.

  • GET /Retrieve detailed webpage information including metadata, screenshots, PDFs, color palettes, and performance insights.
원본 API 스키마
{
  "openapi": "3.0.0",
  "info": {
    "title": "Microlink API",
    "version": "1.0.0",
    "description": "API for retrieving detailed website metadata, screenshots, generating PDFs, extracting color palettes, and more, suitable for analyzing web page content and appearance."
  },
  "servers": [
    {
      "url": "https://api.microlink.io"
    }
  ],
  "paths": {
    "/": {
      "get": {
        "summary": "Retrieve detailed webpage information including metadata, screenshots, PDFs, color palettes, and performance insights.",
        "operationId": "getWebpageInformation",
        "tags": [
          "metadata",
          "screenshot",
          "pdf",
          "palette",
          "performance"
        ],
        "parameters": [
          {
            "name": "url",
            "in": "query",
            "required": true,
            "description": "The target URL to retrieve data for.",
            "schema": {
              "type": "string"
            }
          },
          {
            "name": "prerender",
            "in": "query",
            "description": "Defines prerendering behavior to capture dynamic content.",
            "schema": {
              "type": "string",
              "enum": [
                "auto",
                true,
                false
              ]
            }
          },
          {
            "name": "pdf",
            "in": "query",
            "description": "When enabled, generates a PDF of the webpage.",
            "required": true,
            "schema": {
              "type": "boolean"
            }
          },
          {
            "name": "screenshot",
            "in": "query",
            "description": "When enabled, captures a screenshot of the webpage.",
            "required": true,
            "schema": {
              "type": "boolean"
            }
          },
          {
            "name": "audio",
            "in": "query",
            "description": "Enables detection of audio sources on the webpage.",
            "schema": {
              "type": "boolean"
            }
          },
          {
            "name": "video",
            "in": "query",
            "description": "Enables detection of video sources on the webpage.",
            "schema": {
              "type": "boolean"
            }
          },
          {
            "name": "palette",
            "in": "query",
            "description": "Extracts the dominant color palette from the webpage's primary image.",
            "required": true,
            "schema": {
              "type": "boolean"
            }
          },
          {
            "name": "data",
            "in": "query",
            "description": "Allows for specifying JSON object for dynamic data extraction using CSS selectors. For example, to extract the HTML content of the body tag, send a JSON object as {'body': {'selector': 'body', 'type': 'html'}}.\n",
            "schema": {
              "type": "string"
            },
            "required": true
          }
        ],
        "responses": {
          "200": {
            "description": "Successful response with webpage data.",
            "content": {
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "status": {
                      "type": "string"
                    },
                    "data": {
                      "type": "object",
                      "properties": {
                        "body": {
                          "type": "string"
                        },
                        "title": {
                          "type": "string"
                        },
                        "description": {
                          "type": "string"
                        },
                        "image": {
                          "type": "object",
                          "properties": {
                            "url": {
                              "type": "string"
                            },
                            "type": {
                              "type": "string"
                            },
                            "size": {
                              "type": "integer"
                            },
                            "height": {
                              "type": "integer"
                            },
                            "width": {
                              "type": "integer"
                            }
                          }
                        },
                        "pdf": {
                          "type": "object",
                          "properties": {
                            "url": {
                              "type": "string"
                            }
                          }
                        },
                        "screenshot": {
                          "type": "object",
                          "properties": {
                            "url": {
                              "type": "string"
                            }
                          }
                        },
                        "palette": {
                          "type": "object",
                          "properties": {
                            "vibrant": {
                              "type": "string"
                            },
                            "muted": {
                              "type": "string"
                            },
                            "darkVibrant": {
                              "type": "string"
                            },
                            "darkMuted": {
                              "type": "string"
                            },
                            "lightVibrant": {
                              "type": "string"
                            },
                            "lightMuted": {
                              "type": "string"
                            }
                          }
                        }
                      }
                    }
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}