{ "openapi": "3.0.1", "info": { "title": "Contact Info Scraper", "description": "Crawl any website and get one deduplicated row per company: emails with deliverability checks (MX, role mailbox), validated phone numbers, 15 social networks, address and opening hours. Optional social profile enrichment. HTTP-first, browser only when a page needs it.", "version": "2.0", "x-build-id": "CvxSwESAZmAqz3P2B" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/delicious_zebu~contact-info-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-delicious_zebu-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/delicious_zebu~contact-info-scraper/runs": { "post": { "operationId": "runs-sync-delicious_zebu-contact-info-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/delicious_zebu~contact-info-scraper/run-sync": { "post": { "operationId": "run-sync-delicious_zebu-contact-info-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "Urls" ], "properties": { "Urls": { "title": "Target URLs", "uniqueItems": false, "type": "array", "description": "List of URLs to start scraping for contact information. Any website URL can be provided here.", "items": { "type": "string" } }, "Depth": { "title": "Depth", "minimum": 0, "maximum": 100, "type": "integer", "description": "How many link levels to follow from each starting URL. 0 = only the starting page. 2 (default) reaches most contact/about pages. Higher values crawl more pages (slower and more costly).", "default": 2 }, "Total_num": { "title": "Total Results", "minimum": 1, "maximum": 10000, "type": "integer", "description": "The maximum number of page results to collect during the entire Actor run. The last record in the dataset is always a deduplicated summary of all collected data.", "default": 50 }, "Lock_domain": { "title": "Lock Domain", "type": "boolean", "description": "If set to true, only collects contact information from URLs within the same domain as the starting URL.", "default": true }, "render_mode": { "title": "Rendering mode", "enum": [ "auto", "browser", "http" ], "type": "string", "description": "How pages are fetched. Auto (recommended) fetches with a fast HTTP request and only opens a browser for pages that need JavaScript — best balance of completeness and cost. Browser always renders every page (most complete, slowest, most expensive). HTTP never uses a browser (fastest and cheapest, may miss contacts that load via JavaScript).", "default": "auto" }, "output_mode": { "title": "Output mode", "enum": [ "both", "summary_only", "pages" ], "type": "string", "description": "What to return. Both (default) gives one record per page plus a deduplicated per-site summary. Summary only gives one clean row per website (best for lead lists / CRM import). Pages gives only the per-page records.", "default": "both" }, "only_with_contacts": { "title": "Only return pages that have contacts", "type": "boolean", "description": "Output filter: if enabled, per-page records with no email, phone, or social link are omitted, so your dataset only contains useful rows. The per-site summary is unaffected. (Billing is per page scraped, so this is for cleaner output, not cost.)", "default": false }, "verify_emails": { "title": "Verify emails (free deliverability check)", "type": "boolean", "description": "Add deliverability signals to each email in the summary: whether the domain has a mail server (MX), and whether the address is a role mailbox (info@, sales@…), a free/personal provider (gmail…), or a disposable address. No paid API, no emails sent.", "default": true }, "enrich_social_profiles": { "title": "Enrich social profiles (optional add-on)", "type": "array", "description": "For the platforms you select, fetch profile data (followers, verification, bio, post counts) for the social links found. This runs a dedicated per-platform scraper, whose cost is billed directly to YOUR Apify account as a separate line item (pass-through, no markup). Facebook is the most expensive (~$0.01/page, requires a browser). Leave empty to skip.", "items": { "type": "string", "enum": [ "instagram", "tiktok", "youtube", "twitter", "facebook", "linkedin" ], "enumTitles": [ "Instagram (~$0.0026/profile)", "TikTok (~$0.004/profile)", "YouTube (~$0.0013/channel)", "Twitter/X (~$0.0005/profile)", "Facebook (~$0.01/page, browser)", "LinkedIn company (~$0.004 — followers, employees, industry)" ] }, "default": [] }, "Concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum number of pages processed in parallel. The scraper auto-scales up to this limit based on available resources.", "default": 5 }, "Max_urls_per_depth": { "title": "Max links to follow per page", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of new links to enqueue from each crawled page. Limits how wide the crawl fans out. The overall run is still capped by Total Results.", "default": 200 }, "url_include_patterns": { "title": "URL Include Patterns", "type": "array", "description": "Only crawl URLs whose path contains at least one of these keywords. Leave empty to crawl all URLs. Example: [\"/contact\", \"/about\", \"/team\"]", "default": [], "items": { "type": "string" } }, "url_exclude_patterns": { "title": "URL Exclude Patterns", "type": "array", "description": "Skip URLs whose path contains any of these keywords. Example: [\"/blog\", \"/news\", \"/cart\", \"/login\"]", "default": [], "items": { "type": "string" } } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }