{
  "openapi": "3.0.1",
  "info": {
    "title": "Website Contact Scraper — Email Phone Social Extractor",
    "description": "Website contact scraper for emails, phones & named contacts. Soft CTA → Maps email / email-finder / Skip Trace.",
    "version": "1.0",
    "x-build-id": "udz04cvgTyjea3Cza"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/intelscrape~contact-info-scraper/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-intelscrape-contact-info-scraper",
        "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": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/intelscrape~contact-info-scraper/runs": {
      "post": {
        "operationId": "runs-sync-intelscrape-contact-info-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/intelscrape~contact-info-scraper/run-sync": {
      "post": {
        "operationId": "run-sync-intelscrape-contact-info-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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",
        "properties": {
          "urls": {
            "title": "🌐 Website URLs",
            "type": "array",
            "description": "Paste website URLs to scrape. We'll visit each one and extract every email, phone number, and social media link. You can paste full URLs (https://example.com) or just domains (example.com) — we'll handle both.",
            "items": {
              "type": "string"
            }
          },
          "websites": {
            "title": "🌐 Websites (alias)",
            "type": "array",
            "description": "Compatibility alias for urls — paste bare domains (acme.com) or full URLs. Deduplicated with urls / domains / startUrls.",
            "default": [],
            "items": {
              "type": "string"
            }
          },
          "domains": {
            "title": "🏷️ Domains (alias)",
            "type": "array",
            "description": "Compatibility alias for urls — bare domains or full URLs. Merged and deduped with urls / websites / startUrls.",
            "default": [],
            "items": {
              "type": "string"
            }
          },
          "searchQueries": {
            "title": "🔍 Google Maps Search Queries",
            "type": "array",
            "description": "Search Google Maps to discover businesses and their websites. Try: 'plumbers in Miami FL', 'dentists in Brooklyn NY', 'restaurants in Austin TX'. We'll find every matching business, grab their website URL, and scrape it for emails.",
            "items": {
              "type": "string"
            }
          },
          "maxResults": {
            "title": "🔢 Max Websites to Scrape",
            "minimum": 1,
            "maximum": 5000,
            "type": "integer",
            "description": "Maximum number of websites to process. Start with 10-20 to test, then scale up. Each website costs ~$0.005 base + $0.04 per email found.",
            "default": 50
          },
          "scrapeContactPages": {
            "title": "🔎 Deep Scan Contact Pages",
            "type": "boolean",
            "description": "Follow links to /contact, /about, /team, and /get-in-touch pages to find hidden email addresses. This finds 30-50% more emails but takes slightly longer. Recommended ON.",
            "default": true
          },
          "stopWhenEmailFound": {
            "title": "⏹️ Stop early once a company email is found",
            "type": "boolean",
            "description": "Speed switch for large lists: stop crawling a site the moment a same-domain company email turns up (webdata_labs parity). Off by default so full crawl still returns phones, socials, and contact pages.",
            "default": false
          },
          "includePhones": {
            "title": "📞 Extract Phone Numbers",
            "type": "boolean",
            "description": "Extract US and international phone numbers from each website. Finds tel: links and phone patterns in the page text.",
            "default": true
          },
          "includeSocial": {
            "title": "📱 Extract Social Media Links",
            "type": "boolean",
            "description": "Find links to Facebook, Instagram, LinkedIn, Twitter/X, YouTube, TikTok, Pinterest, Yelp, WhatsApp, Telegram, GitHub, Threads, and Discord.",
            "default": true
          },
          "includeTechStack": {
            "title": "💻 Detect Tech Stack",
            "type": "boolean",
            "description": "Identify the website's CMS and framework: WordPress, Shopify, Wix, Squarespace, Webflow, Next.js, React, WooCommerce, BigCommerce, HubSpot, and more. Perfect for web design agencies prospecting outdated sites.",
            "default": true
          },
          "includePixels": {
            "title": "📊 Detect Ad Tracking Pixels",
            "type": "boolean",
            "description": "Find Facebook Pixel (with ID), Google Analytics (with GA/GTM ID), TikTok Pixel, LinkedIn Insight Tag, and Hotjar. Great for ad agencies to identify businesses already running paid ads.",
            "default": true
          },
          "maxContactPages": {
            "title": "Max Sub-Pages Per Website",
            "minimum": 1,
            "maximum": 15,
            "type": "integer",
            "description": "How many internal pages to crawl per website (e.g. /contact, /about, /team), including sitemap hits. Higher = more emails found, but slower. 5 is optimal for most sites.",
            "default": 5
          },
          "concurrency": {
            "title": "Parallel Scraping",
            "minimum": 1,
            "maximum": 50,
            "type": "integer",
            "description": "How many websites to scrape at the same time. Higher = faster but uses more memory. 10 is a good default.",
            "default": 10
          },
          "webhookUrl": {
            "title": "🔗 Webhook URL",
            "type": "string",
            "description": "Automatically POST all results as JSON to this URL when the run finishes. Works with Zapier, Make.com, n8n, or your own API endpoint."
          },
          "useSitemapCrawl": {
            "title": "🗺️ Use sitemap.xml discovery",
            "type": "boolean",
            "description": "Discover /contact, /about, /team pages from sitemap.xml in addition to homepage link scraping. Finds more emails on large sites. Recommended ON.",
            "default": true
          },
          "verifyEmails": {
            "title": "✅ Verify emails (MX deliverability)",
            "type": "boolean",
            "description": "Check each email domain has MX records (can receive mail). Adds emailMx[{email,mxStatus}] — valid / no-mx / invalid. No extra PPE charge.",
            "default": true
          },
          "excludeRolePrefixes": {
            "title": "🚫 Exclude role-based email prefixes",
            "type": "array",
            "description": "Drop emails whose local-part equals or starts with these prefixes (e.g. info, sales, support, hello, contact, admin). Leave empty to keep all non-spam emails.",
            "default": [],
            "items": {
              "type": "string"
            }
          },
          "onlyWithContact": {
            "title": "✅ Only sites with email or phone",
            "type": "boolean",
            "description": "Skip websites that have neither an email nor a phone after scraping. Saves dataset noise and PPE on empty rows.",
            "default": false
          },
          "mergeContacts": {
            "title": "🔗 Merge contacts (one row per site)",
            "type": "boolean",
            "description": "ON (default): one dataset row per website with emails[] and phones[] arrays. OFF: one row per email (site fields duplicated) — useful for CRM import.",
            "default": true
          },
          "defaultPhoneCountry": {
            "title": "📞 Default phone country (E.164)",
            "type": "string",
            "description": "ISO country used to parse local numbers into E.164 (e.g. US, GB, CA, AU). Invalid / too-short numbers are dropped. Uses libphonenumber-js.",
            "default": "US"
          },
          "includeNamedContacts": {
            "title": "👥 Extract named contacts (people)",
            "type": "boolean",
            "description": "Parse /team, /about, /leadership pages, JSON-LD Person, and linkedin.com/in/ anchors into people[{name,title,linkedin,email?}]. Charged as named-contact PPE when people are delivered.",
            "default": true
          },
          "maxDepth": {
            "title": "Crawl depth",
            "minimum": 0,
            "maximum": 5,
            "type": "integer",
            "description": "How many link hops from each start URL (delicious_zebu Depth parity). 0 = homepage only. 1 = homepage + contact/about/team (default). Higher follows matching links further.",
            "default": 1
          },
          "sameDomainOnly": {
            "title": "Same domain only (lock domain)",
            "type": "boolean",
            "description": "If ON, only crawl URLs on the starting domain (delicious_zebu Lock_domain). Recommended ON.",
            "default": true
          },
          "urlIncludePatterns": {
            "title": "URL include patterns",
            "type": "array",
            "description": "Only enqueue URLs whose path/URL contains at least one of these keywords (e.g. /contact, /about, /team). Empty = default contact-ish heuristics at depth 0.",
            "default": [],
            "items": {
              "type": "string"
            }
          },
          "urlExcludePatterns": {
            "title": "URL exclude patterns",
            "type": "array",
            "description": "Skip URLs containing any of these keywords (e.g. /blog, /news, /cart, /login, /wp-admin).",
            "default": [],
            "items": {
              "type": "string"
            }
          },
          "maxUrlsPerDepth": {
            "title": "Max URLs per depth",
            "minimum": 1,
            "maximum": 500,
            "type": "integer",
            "description": "Cap enqueue count at each depth level (delicious_zebu Max_urls_per_depth). Also capped by Max Sub-Pages Per Website.",
            "default": 50
          }
        }
      },
      "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
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}