{ "openapi": "3.0.1", "info": { "title": "Website Contact Scraper - Emails, Phones & Socials", "description": "Extract public contact details from any list of websites. Finds emails, international phone numbers and LinkedIn, X, Facebook, Instagram, YouTube, TikTok and GitHub profiles by reading the pages that actually carry them - contact, about, team and imprint. No login or API key.", "version": "0.1", "x-build-id": "u6AqPQiipOgcOjdSb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jmlp~web-contact-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jmlp-web-contact-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jmlp~web-contact-scraper/runs": { "post": { "operationId": "runs-sync-jmlp-web-contact-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jmlp~web-contact-scraper/run-sync": { "post": { "operationId": "run-sync-jmlp-web-contact-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Websites", "type": "array", "description": "The websites to scan. One per line, with or without https://. Each site is visited independently, so a list of 500 domains is a normal input. Accepts plain strings or {\"url\": \"...\"} objects.", "items": { "type": "string" } }, "url": { "title": "Website (single)", "type": "string", "description": "A single website, for convenience when you only have one." }, "maxPagesPerSite": { "title": "Max pages per site", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many pages to read on each site. The crawler does not spider blindly: it scores every internal link and visits only the page types that carry contact details - contact, imprint, about, team, support - shallowest first. 8 finds almost everything; raise it for large corporate sites.", "default": 8 }, "maxResults": { "title": "Max results", "minimum": 1, "type": "integer", "description": "Stop after this many sites have been delivered. Caps both runtime and cost. Empty = every site in the list." }, "skipSitesWithoutContacts": { "title": "Skip sites with no contacts", "type": "boolean", "description": "Leave a site out of the dataset entirely when nothing was found, instead of writing an empty row. Under pay-per-result pricing this means you are not charged for the misses.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many sites to scan at once. Different sites are unrelated hosts, so this parallelises cleanly - 5 is polite, 20 is fast.", "default": 5 }, "delayMs": { "title": "Delay between pages (ms)", "minimum": 0, "type": "integer", "description": "Politeness pause between requests to the SAME site. Does not slow down different sites running in parallel.", "default": 300 }, "requestTimeoutSecs": { "title": "Request timeout (s)", "minimum": 5, "maximum": 120, "type": "integer", "description": "How long to wait for a single page before giving up on it.", "default": 20 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Most sites are happy to serve their own contact page to anyone, so a proxy is not needed for typical lists. Use one if you are scanning thousands of sites or hitting a WAF.", "default": { "useApifyProxy": false } }, "resume": { "title": "Checkpoint progress", "type": "boolean", "description": "Save progress every ~30s so a run that gets migrated or restarted by the platform picks up where it stopped, without repeating sites.", "default": true }, "continueFromLastRun": { "title": "Continue from last run", "type": "boolean", "description": "If your previous run with the same input was interrupted, scan only the sites it missed. Those already done stay in THAT run's dataset.", "default": false }, "impersonate": { "title": "TLS fingerprint", "type": "string", "description": "Which browser TLS fingerprint to present. Only matters for sites behind a WAF that refuses plain HTTP clients.", "default": "chrome131" } } }, "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 } } } } } } } } } }