{ "openapi": "3.0.1", "info": { "title": "B2B Lead Scraper — Company Emails, Phones & Tech Stack", "description": "Generate public B2B lead records from company websites with emails, phones, social links, tech stack, team signals, job posts, and quality scoring.", "version": "1.0", "x-build-id": "j7ZuWAOxsysaVkuD0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~b2b-lead-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-b2b-lead-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/junipr~b2b-lead-scraper/runs": { "post": { "operationId": "runs-sync-junipr-b2b-lead-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/junipr~b2b-lead-scraper/run-sync": { "post": { "operationId": "run-sync-junipr-b2b-lead-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "scrapeMode": { "title": "Scrape Mode", "enum": [ "companyWebsite", "linkedinCompany", "directory", "search" ], "type": "string", "description": "What to scrape. 'companyWebsite' scrapes provided company URLs. 'linkedinCompany' scrapes LinkedIn company pages. 'directory' scrapes business directories. 'search' discovers companies via search queries.", "default": "companyWebsite" }, "urls": { "title": "Company URLs", "type": "array", "description": "Company website URLs or LinkedIn company page URLs. Required for companyWebsite and linkedinCompany modes.", "items": { "type": "string" }, "default": [ "https://crawlee.dev" ] }, "searchQuery": { "title": "Search Query", "type": "string", "description": "Search query for finding companies. Required for search mode. E.g., 'SaaS companies in Austin Texas'.", "default": "" }, "directorySource": { "title": "Directory Source", "enum": [ "yellowPages", "yelp", "bbb", "crunchbase", "googleMaps" ], "type": "string", "description": "Business directory to scrape. Required for directory mode.", "default": "yellowPages" }, "industry": { "title": "Industry Filter", "type": "array", "description": "Industry filters for search mode. E.g., SaaS, fintech, healthcare.", "items": { "type": "string" }, "default": [] }, "location": { "title": "Location Filter", "type": "string", "description": "Geographic filter for search mode. E.g., 'Austin, TX', 'United Kingdom', 'California'.", "default": "" }, "companySize": { "title": "Company Size Filter", "enum": [ "", "1-10", "11-50", "51-200", "201-500", "501-1000", "1001-5000", "5001+" ], "type": "string", "description": "Filter by employee count range.", "default": "" }, "fundingStage": { "title": "Funding Stage Filter", "enum": [ "", "seed", "seriesA", "seriesB", "seriesC+", "public", "bootstrapped" ], "type": "string", "description": "Filter by funding stage.", "default": "" }, "maxCompanies": { "title": "Max Companies", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of companies to find in search or directory mode.", "default": 1 }, "directoryCategory": { "title": "Directory Category", "type": "string", "description": "Category within the directory. E.g., restaurants, plumbers, software.", "default": "" }, "directoryLocation": { "title": "Directory Location", "type": "string", "description": "Location filter for directory search.", "default": "" }, "directoryMaxResults": { "title": "Directory Max Results", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum results from directory scrape.", "default": 1 }, "extractEmails": { "title": "Extract Emails", "type": "boolean", "description": "Find email addresses on company websites.", "default": true }, "extractPhones": { "title": "Extract Phone Numbers", "type": "boolean", "description": "Find phone numbers on company websites.", "default": true }, "extractSocials": { "title": "Extract Social Media Links", "type": "boolean", "description": "Find social media profile links.", "default": true }, "extractTeamMembers": { "title": "Extract Team Members", "type": "boolean", "description": "Find team member names and titles from public about/team pages.", "default": false }, "maxTeamMembers": { "title": "Max Team Members", "minimum": 1, "maximum": 25, "type": "integer", "description": "Maximum team members to extract per company.", "default": 5 }, "detectEmailPattern": { "title": "Detect Email Pattern", "type": "boolean", "description": "Analyze found emails to detect the company's email naming pattern (e.g., firstname@, first.last@).", "default": true }, "verifyEmails": { "title": "Verify Emails (SMTP)", "type": "boolean", "description": "Verify email addresses via SMTP check. Slower and may trigger spam filters on the target mail server.", "default": false }, "detectTechStack": { "title": "Detect Tech Stack", "type": "boolean", "description": "Detect technologies used by company websites (analytics, CMS, frameworks, hosting, CDN, etc.).", "default": false }, "techCategories": { "title": "Tech Categories", "type": "array", "description": "Technology categories to detect. Options: all, analytics, cms, ecommerce, framework, hosting, marketing, payment, security, cdn.", "items": { "type": "string" }, "default": [ "all" ] }, "estimateCompanySize": { "title": "Estimate Company Size", "type": "boolean", "description": "Estimate employee count from various signals on the website.", "default": false }, "extractJobPostings": { "title": "Extract Job Postings", "type": "boolean", "description": "Check for open job postings as a company growth signal.", "default": false }, "maxJobPostings": { "title": "Max Job Postings", "minimum": 1, "maximum": 25, "type": "integer", "description": "Maximum job postings to extract per company.", "default": 5 }, "extractPressReleases": { "title": "Extract Press Releases", "type": "boolean", "description": "Look for recent news and press releases on the company site.", "default": false }, "extractPricing": { "title": "Extract Pricing", "type": "boolean", "description": "Attempt to find pricing page information.", "default": false }, "outputFormat": { "title": "Output Format", "enum": [ "json", "csv" ], "type": "string", "description": "Output format for results.", "default": "json" }, "deduplicateByDomain": { "title": "Deduplicate by Domain", "type": "boolean", "description": "Prevent duplicate entries for the same domain.", "default": true }, "enrichWithLinkedIn": { "title": "Enrich with LinkedIn", "type": "boolean", "description": "After scraping company website, also check LinkedIn company page for additional data. Adds ~3s per company.", "default": false }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Residential proxy recommended for LinkedIn scraping. Defaults to Apify residential proxy (requires paid Apify plan). Free-plan users can provide their own residential proxy URL.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "requestDelay": { "title": "Request Delay (ms)", "minimum": 0, "maximum": 30000, "type": "integer", "description": "Minimum delay between requests to the same domain in milliseconds.", "default": 2000 }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum concurrent requests.", "default": 1 }, "maxRetries": { "title": "Max Retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retry failed requests up to this many times.", "default": 2 } } }, "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 } } } } } } } } } }