{
  "openapi": "3.0.1",
  "info": {
    "title": "Website Contact & Email Crawler",
    "description": "📞🔍 Extract phone numbers, emails, contact details & social media links from any website in seconds. ⚡️ Scrapes tel, mailto, WhatsApp, LinkedIn, X/Twitter, Instagram & more; dedupes & validates. 📊 Export CSV/JSON, API-ready. 🚀 Ideal for lead gen, sales & CRM enrichment.",
    "version": "0.1",
    "x-build-id": "qumZ4pdcCO4taGgem"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/scrapio~extract-phone-numbers-contacts-socials-from-any-website/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-scrapio-extract-phone-numbers-contacts-socials-from-any-website",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/scrapio~extract-phone-numbers-contacts-socials-from-any-website/runs": {
      "post": {
        "operationId": "runs-sync-scrapio-extract-phone-numbers-contacts-socials-from-any-website",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/scrapio~extract-phone-numbers-contacts-socials-from-any-website/run-sync": {
      "post": {
        "operationId": "run-sync-scrapio-extract-phone-numbers-contacts-socials-from-any-website",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "inputSchema": {
        "type": "object",
        "required": [
          "startUrls"
        ],
        "properties": {
          "startUrls": {
            "title": "🌐 Website URLs or Domains",
            "type": "array",
            "description": "Websites to crawl for contact data. Accepts full URLs or bare domains.\n\nExamples:\n• https://www.apify.com/contact\n• stripe.com\n\nEach domain is crawled once and returned as one aggregated contact profile.",
            "items": {
              "type": "string"
            }
          },
          "maxDepth": {
            "title": "🔗 Max Crawl Depth",
            "minimum": 0,
            "maximum": 4,
            "type": "integer",
            "description": "How many link-hops from the start page to follow. 0 = only the given page; 1 = the page + its direct links; 2 = two hops. Contact/about/team pages are visited first. Default is 2.",
            "default": 2
          },
          "maxPagesPerDomain": {
            "title": "📄 Max Pages per Domain",
            "minimum": 1,
            "maximum": 200,
            "type": "integer",
            "description": "Hard cap on how many pages are fetched per domain. Higher = more coverage but slower/costlier. Example: 20 pages usually covers a small-business site fully. Default is 20.",
            "default": 20
          },
          "prioritizeContactPages": {
            "title": "🎯 Prioritize Contact / About / Team Pages",
            "type": "boolean",
            "description": "Visit contact, about, team, impressum and support pages first (biggest contact yield). Default is true.",
            "default": true
          },
          "respectRobotsTxt": {
            "title": "🤖 Respect robots.txt",
            "type": "boolean",
            "description": "Skip URLs disallowed by the site's robots.txt. Default is true.",
            "default": true
          },
          "useBrowser": {
            "title": "🧭 Use Browser Fallback (SPAs)",
            "type": "boolean",
            "description": "When a page returns an empty/JS-only shell (React/Vue/Angular SPA), re-render it with a headless Chromium browser before extracting. Slower; leave OFF for normal HTML sites. Default is false.",
            "default": false
          },
          "checkMx": {
            "title": "📬 Email MX/Syntax Heuristic",
            "type": "boolean",
            "description": "Add a HEURISTIC per email: syntax-valid flag + whether the domain has an MX (mail) DNS record. This is a heuristic ONLY — no SMTP handshake, no deliverability guarantee. Default is false.",
            "default": false
          },
          "discoveryMode": {
            "title": "🔎 Discovery Mode (optional)",
            "enum": [
              "off",
              "google_serp"
            ],
            "type": "string",
            "description": "How to obtain the sites to crawl. 'Provided URLs only' uses your startUrls (recommended). 'Google search discovery' additionally finds candidate sites via a Google search of your keywords, then crawls those real sites. Any emails visible in the Google snippet are stored separately as low-confidence inferred emails, never mixed into scraped emails.",
            "default": "off"
          },
          "keywords": {
            "title": "🔍 Discovery Keywords",
            "type": "array",
            "description": "Only used when Discovery Mode = Google search discovery. Keywords to search for candidate sites (e.g. ['marketing agency', 'dentist']).",
            "items": {
              "type": "string"
            }
          },
          "platform": {
            "title": "🌐 Discovery Platform Filter",
            "type": "string",
            "description": "Optional site: filter for discovery (e.g. limit the Google search to one platform). 'any' searches the open web.",
            "default": "any"
          },
          "location": {
            "title": "📍 Discovery Location",
            "type": "string",
            "description": "Optional location term appended to the discovery search (e.g. 'London').",
            "default": ""
          },
          "discoveryMaxSites": {
            "title": "🔢 Discovery Max Sites",
            "minimum": 1,
            "maximum": 200,
            "type": "integer",
            "description": "Cap on how many candidate sites the discovery layer returns to crawl. Default is 20.",
            "default": 20
          },
          "aiEnhancement": {
            "title": "🤖 AI Company Classification (optional)",
            "type": "boolean",
            "description": "OFF by default. When on, classify each domain's company type / industry from its public contact data using your own LLM key. AI is NEVER used to invent or guess contacts.",
            "default": false
          },
          "aiModel": {
            "title": "🤖 AI Model / Provider",
            "enum": [
              "claude-haiku-4-5",
              "claude-sonnet-5",
              "gpt-4o-mini",
              "gpt-4.1-mini",
              "gemini-2.0-flash-lite",
              "gemini-2.0-flash",
              "grok-3-mini",
              "deepseek-chat",
              "sonar",
              "mistral-small-latest"
            ],
            "type": "string",
            "description": "Provider auto-detected from the name: claude-*=Anthropic, gpt-*/o1/o3=OpenAI, gemini-*=Google, grok-*=xAI, deepseek-*=DeepSeek, sonar*=Perplexity, mistral-*=Mistral.",
            "default": "claude-haiku-4-5"
          },
          "aiApiKey": {
            "title": "🔑 AI API Key",
            "type": "string",
            "description": "API key for the selected provider (used only when AI Company Classification is on). Falls back to the provider env var (ANTHROPIC_API_KEY / OPENAI_API_KEY / GEMINI_API_KEY / XAI_API_KEY / DEEPSEEK_API_KEY / PERPLEXITY_API_KEY / MISTRAL_API_KEY)."
          },
          "proxyConfiguration": {
            "title": "🌐 Proxy Configuration",
            "type": "object",
            "description": "Proxy used for crawling websites (honored — the crawler routes fetches through it). By default no proxy is used."
          }
        }
      },
      "runsResponseSchema": {
        "type": "object",
        "properties": {
          "data": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string"
              },
              "actId": {
                "type": "string"
              },
              "userId": {
                "type": "string"
              },
              "startedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "finishedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "status": {
                "type": "string",
                "example": "READY"
              },
              "meta": {
                "type": "object",
                "properties": {
                  "origin": {
                    "type": "string",
                    "example": "API"
                  },
                  "userAgent": {
                    "type": "string"
                  }
                }
              },
              "stats": {
                "type": "object",
                "properties": {
                  "inputBodyLen": {
                    "type": "integer",
                    "example": 2000
                  },
                  "rebootCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "restartCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "resurrectCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "computeUnits": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "options": {
                "type": "object",
                "properties": {
                  "build": {
                    "type": "string",
                    "example": "latest"
                  },
                  "timeoutSecs": {
                    "type": "integer",
                    "example": 300
                  },
                  "memoryMbytes": {
                    "type": "integer",
                    "example": 1024
                  },
                  "diskMbytes": {
                    "type": "integer",
                    "example": 2048
                  }
                }
              },
              "buildId": {
                "type": "string"
              },
              "defaultKeyValueStoreId": {
                "type": "string"
              },
              "defaultDatasetId": {
                "type": "string"
              },
              "defaultRequestQueueId": {
                "type": "string"
              },
              "buildNumber": {
                "type": "string",
                "example": "1.0.0"
              },
              "containerUrl": {
                "type": "string"
              },
              "usage": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "integer",
                    "example": 1
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "usageTotalUsd": {
                "type": "number",
                "example": 0.00005
              },
              "usageUsd": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "number",
                    "example": 0.00005
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}