Website Contact Crawler
Pricing
Pay per usage
Pricing
Pay per usage
Rating
5.0
(1)
Developer
Man Mohit verma
Maintained by CommunityActor stats
0
Bookmarked
12
Total users
4
Monthly active users
16 days ago
Last modified
Categories
Share
You can access the Website Contact Crawler programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "gkU6b8z1hsgFcgvbi" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/competent_clarinet~website-contact-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-competent_clarinet-website-contact-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/competent_clarinet~website-contact-crawler/runs": { "post": { "operationId": "runs-sync-competent_clarinet-website-contact-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/competent_clarinet~website-contact-crawler/run-sync": { "post": { "operationId": "run-sync-competent_clarinet-website-contact-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Start URLs", "type": "array", "description": "List of website URLs to start crawling from (supports hundreds or thousands of seeds as a JSON array).", "items": { "type": "string" } }, "depthOfPages": { "title": "Depth of pages", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many link hops to follow from each starting URL.", "default": 1 }, "maxPagesPerStartUrl": { "title": "Max pages per start URL", "minimum": 0, "type": "integer", "description": "Maximum number of pages to scrape per starting URL (including the start page itself). Crawling stops for a site when this limit or the depth limit is reached, whichever comes first. Set to 0 for no limit.", "default": 0 }, "defaultPhoneRegion": { "title": "Default phone region", "type": "string", "description": "Default region used by phonenumbers for national numbers.", "default": "US" }, "maxConcurrencyPerIp": { "title": "Max concurrency per worker band", "minimum": 1, "maximum": 200, "type": "integer", "description": "Concurrent page fetches per worker band. With proxyPoolSize=10 and this set to 50, up to 500 pages can be fetched in parallel. Each fetch uses a new residential proxy session (per-request IP rotation), not a fixed IP pool.", "default": 50 }, "proxyPoolSize": { "title": "Worker bands", "minimum": 1, "maximum": 100, "type": "integer", "description": "Number of parallel worker bands. Total workers = maxConcurrencyPerIp × proxyPoolSize. Does not reserve fixed IPs; each request still rotates to a new residential proxy session.", "default": 10 }, "maxConcurrencyPerHost": { "title": "Max concurrency per host", "minimum": 0, "maximum": 100, "type": "integer", "description": "Maximum simultaneous in-flight requests to the same website host. Helps avoid overwhelming a single domain when many seeds share infrastructure. Set to 0 to disable the limit.", "default": 5 }, "dedupeScope": { "title": "Contact dedupe scope", "enum": [ "global", "perStartingUrl" ], "type": "string", "description": "global: keep one row per contact value across all seeds. perStartingUrl: allow the same value under different starting URLs.", "default": "global" }, "additionalPaths": { "title": "Additional paths", "type": "array", "description": "Paths that are added for depth 1 from each start URL.", "items": { "type": "string" } }, "excludeKeywords": { "title": "Exclude keywords", "type": "array", "description": "Skip any URL containing one of these keywords at any depth.", "items": { "type": "string" } }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Use Apify Proxy (RESIDENTIAL recommended) or your own proxy URLs. Each HTTP request opens a new proxy session for IP rotation." } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Website Contact Crawler from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: