{ "openapi": "3.0.1", "info": { "title": "Website Tech Stack Detector (Bulk) ยท SiteVerdict", "description": "Find the tech stack of thousands of websites: CMS, ecommerce, analytics, ad pixels, cookie banners, CRM, chat, payments, CDN, hosting, frameworks, JS library versions and email provider (MX/SPF). Evidence for every detection, filters and change monitoring.", "version": "1.1", "x-build-id": "6MLSiRpVEB1qnT97c" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/siteverdict~siteverdict-tech-stack-detector/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-siteverdict-siteverdict-tech-stack-detector", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/siteverdict~siteverdict-tech-stack-detector/runs": { "post": { "operationId": "runs-sync-siteverdict-siteverdict-tech-stack-detector", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/siteverdict~siteverdict-tech-stack-detector/run-sync": { "post": { "operationId": "run-sync-siteverdict-siteverdict-tech-stack-detector", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Websites (domains or URLs)", "type": "array", "description": "One per line. Bare domains (example.com) are fine; we try https first, then http. Duplicates are removed.", "items": { "type": "string" } }, "csvText": { "title": "Paste a CSV", "type": "string", "description": "Optional. Paste a CSV export (e.g. from a CRM). We use the column named url / website / domain / homepage, or the column you name below." }, "csvUrl": { "title": "CSV file URL", "type": "string", "description": "Optional. Public link to a CSV file (e.g. a Google Sheets 'publish to web' CSV link)." }, "csvColumn": { "title": "CSV column with the website", "type": "string", "description": "Optional. Header of the column that holds the domain/URL. Auto-detected when empty." }, "datasetId": { "title": "Read websites from an Apify dataset", "type": "string", "description": "Optional. Dataset ID or name from another run (e.g. a leads scraper). Each item's url / website / domain field is used." }, "datasetField": { "title": "Dataset field with the website", "type": "string", "description": "Optional. Field name (dot path allowed, e.g. company.website). Auto-detected when empty." }, "mode": { "title": "Detection mode", "enum": [ "http", "browser" ], "type": "string", "description": "Fast HTTP (default, cheapest): reads HTML, headers, cookies, DNS, TLS and robots.txt. Browser: renders the page in headless Chrome, so it also sees scripts injected by tag managers, global JS variables and framework internals. More accurate, slower, priced higher.", "default": "http" }, "extraPaths": { "title": "Extra pages to check on every site", "type": "array", "description": "Optional paths such as /pricing, /contact or /cart. Some tools (checkout, booking, chat) only load on inner pages. Max 10, fetched over plain HTTP.", "items": { "type": "string" } }, "autoSamplePages": { "title": "Auto-sample inner pages", "minimum": 0, "maximum": 5, "type": "integer", "description": "Also check up to N internal links picked from the homepage (shop, pricing, contact, blog first). 0 = homepage only.", "default": 0 }, "checkDns": { "title": "Check DNS (email provider, marketing tools, DNS host, CNAME)", "type": "boolean", "description": "Reads public MX, SPF, TXT verification tokens, DMARC reporting vendor, NS and CNAME records.", "default": true }, "checkTls": { "title": "Check TLS certificate issuer", "type": "boolean", "description": "Connects to port 443 and reads the certificate issuer and expiry date.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "If a site's robots.txt disallows our crawler (or all crawlers) for a page, we do not fetch it and only use DNS/TLS. Keep this on.", "default": true }, "minConfidence": { "title": "Minimum confidence (0-100)", "minimum": 0, "maximum": 100, "type": "integer", "description": "Hide detections below this confidence. 50 keeps single weak signals; 100 = only strong evidence.", "default": 50 }, "includeEvidence": { "title": "Include evidence strings", "type": "boolean", "description": "Show why each technology was detected (script URL, header, cookie name, DNS record...).", "default": true }, "onlySitesUsing": { "title": "Only output sites using...", "type": "array", "description": "Technology names, e.g. Shopify, Klaviyo, HubSpot. Case-insensitive. Sites without a match are not output and not charged.", "items": { "type": "string" } }, "onlyCategories": { "title": "Only output sites with a technology in categories...", "type": "array", "description": "Category names, e.g. Ecommerce, Live chat, Consent management (CMP), Email provider.", "items": { "type": "string" } }, "matchAll": { "title": "Require ALL of the above (AND)", "type": "boolean", "description": "Off = any match is enough (OR).", "default": false }, "excludeSitesUsing": { "title": "Exclude sites using...", "type": "array", "description": "Drop sites that use any of these technologies, e.g. Klaviyo (to find Shopify stores that do not use it yet). Excluded sites are not charged.", "items": { "type": "string" } }, "offerPreset": { "title": "What do you sell? (lead scoring)", "enum": [ "general-b2b", "ecommerce-email-sms", "consent-cmp", "cro-experimentation", "live-chat-support", "shopify-apps", "wordpress-agency", "email-security-dmarc", "b2b-intent-data", "analytics-cdp" ], "type": "string", "description": "Every site gets a 0-100 prospect score for this offer, with the reasons (fit, need, budget, buying intent). Free, always on.", "default": "general-b2b" }, "offer": { "title": "Custom offer (optional, overrides the preset)", "type": "object", "description": "Fields: name, description, targetTechs, targetCategories, competitorTechs, complementTechs, gapCategories, excludeTechs, hiringFunctions. Example: {\"name\":\"Klaviyo agency\",\"targetTechs\":[\"Shopify\"],\"competitorTechs\":[\"Mailchimp\"],\"gapCategories\":[\"SMS marketing\"]}" }, "minLeadScore": { "title": "Only output sites scoring at least", "minimum": 0, "maximum": 100, "type": "integer", "description": "Sites below this score are not output and not charged.", "default": 0 }, "hiringSignals": { "title": "Hiring signals (careers page + public job boards)", "type": "boolean", "description": "Finds the careers page and, if linked, reads the public Greenhouse / Lever / Ashby job-board API: open roles by function and the tools job ads mention (e.g. \"HubSpot\", \"Snowflake\"). Charged (hiring-signals) only when roles or tool mentions are found. Job titles only, never recruiter names.", "default": false }, "companyEnrichment": { "title": "Company details from the website", "type": "boolean", "description": "Free: reads the UK company number, VAT number, schema.org organisation data and company social pages the site itself publishes.", "default": true }, "companiesHouseApiKey": { "title": "Companies House API key (optional, UK)", "type": "string", "description": "Your free key from developer.company-information.service.gov.uk. Adds status, incorporation date, SIC codes, accounts type and registered office. Charged (company-enriched) only when a record is attached. No officers or personal data." }, "companyNameSearch": { "title": "Match by company name when no number is on the site", "type": "boolean", "description": "UK sites only. Uses an EXACT normalised name match (one active company), so it never guesses.", "default": false }, "aiProvider": { "title": "AI outreach angle (your own key)", "enum": [ "none", "anthropic", "openai" ], "type": "string", "description": "Writes one factual sentence per good prospect: the reason to contact them now. Uses only the detected company-level facts. Nothing is sent to prospects.", "default": "none" }, "aiApiKey": { "title": "AI API key", "type": "string", "description": "Your Anthropic or OpenAI key. Billed by your provider; never logged or stored." }, "aiModel": { "title": "AI model (optional)", "type": "string", "description": "Default: claude-sonnet-5-5 (Anthropic) or gpt-4o-mini (OpenAI)." }, "aiMinLeadScore": { "title": "Only write angles for sites scoring at least", "minimum": 0, "maximum": 100, "type": "integer", "description": "Saves your LLM spend: only prospects at or above this score get an outreach angle.", "default": 50 }, "aiMaxSites": { "title": "Max outreach angles per run", "minimum": 0, "type": "integer", "description": "Hard cap on generated angles (and on the ai-outreach-angle event) per run.", "default": 100 }, "exportHubspot": { "title": "Write HUBSPOT_COMPANIES.csv", "type": "boolean", "description": "Ready for HubSpot > Import > Companies (Company Domain Name is the de-duplication key).", "default": true }, "monitor": { "title": "Monitor mode (tech added / removed = buying signals)", "type": "boolean", "description": "Stores each site's stack in a named key-value store (siteverdict-tech-monitor) and adds a diff to every result. Schedule the Actor to track competitors or customers.", "default": false }, "monitorKey": { "title": "Monitor list name", "type": "string", "description": "Keeps separate histories for different lists, e.g. competitors or shopify-leads.", "default": "default" }, "onlyChanges": { "title": "Only output sites whose stack changed", "type": "boolean", "description": "With monitor mode: skip sites that are unchanged or seen for the first time (baseline). Skipped sites are not charged.", "default": false }, "slackWebhookUrl": { "title": "Slack alert webhook (monitor mode)", "type": "string", "description": "Incoming-webhook URL (https://hooks.slack.com/...). Posts the sites whose stack changed. Nothing is posted when nothing changed." }, "webhookUrl": { "title": "Webhook alert (monitor mode)", "type": "string", "description": "HTTPS URL that receives a JSON list of changed sites with buying signals." }, "maxSites": { "title": "Max sites", "minimum": 0, "type": "integer", "description": "Stop after this many unique sites. 0 = no limit.", "default": 0 }, "maxConcurrency": { "title": "Parallel sites", "minimum": 1, "maximum": 25, "type": "integer", "description": "Default 8 in HTTP mode, 2 in browser mode." }, "timeoutSecs": { "title": "Per-page timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "How long to wait for a page before giving up.", "default": 25 } } }, "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 } } } } } } } } } }