{ "openapi": "3.0.1", "info": { "title": "Website Classifier & Text Classifier - Industry & Sentiment", "description": "Classify URLs, domains or texts with AI: industry with B2B/B2C, page type, topic, IAB category, sentiment, content moderation or your own labels, with confidence and reason. $4/1,000.", "version": "0.1", "x-build-id": "tkilX8krL7pg8z6RO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tidytools~ai-page-classifier/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tidytools-ai-page-classifier", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/tidytools~ai-page-classifier/runs": { "post": { "operationId": "runs-sync-tidytools-ai-page-classifier", "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/tidytools~ai-page-classifier/run-sync": { "post": { "operationId": "run-sync-tidytools-ai-page-classifier", "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": { "domains": { "title": "URLs or domains", "type": "array", "description": "Main input (fill this, or `startUrls` / `texts` / `datasetId`). Websites or pages to classify, one per line: bare domains (stripe.com) or full URLs. Duplicates of the same site (stripe.com, https://www.Stripe.com/) are classified and charged once, with every original line listed in \"inputs\". A line that is not a URL becomes one free error row; the rest of the run continues.", "items": { "type": "string" } }, "startUrls": { "title": "URLs (request list, optional)", "type": "array", "description": "Same as \"URLs or domains\", in Apify's request list format (also accepts a link to a text file with URLs). Kept for existing integrations; new integrations should use \"domains\".", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "taxonomy": { "title": "Classify by", "enum": [ "pageType", "topic", "industry", "iab", "sentiment", "contentModeration", "custom" ], "type": "string", "description": "pageType: 20 page types (homepage, product, category, article, news, documentation, pricing, careers, legal, other...). topic: 23 topics such as technology, finance, health (several can apply). industry: the company's industry (30) plus business model and a one-line summary; best with domains. iab: the 30 tier-1 IAB categories. sentiment: positive, neutral, negative or mixed. contentModeration: safe, adult, violence, hate, spam, self-harm (several can apply). custom: your labels below.", "default": "pageType" }, "customLabels": { "title": "Custom labels", "type": "array", "description": "Used when \"Classify by\" is \"Custom labels\". One label per line, optionally with a description after a colon, e.g. \"Competitor: sells project management software\". 2 to 100 labels, any language.", "items": { "type": "string" } }, "multiLabel": { "title": "Allow several labels per page", "type": "boolean", "description": "Return all labels that clearly apply (in \"labels\") besides the main one. On by default for topics and IAB, off for page types, industries and custom labels." }, "instructions": { "title": "Extra instructions", "maxLength": 1000, "type": "string", "description": "Optional hints for the AI, up to 1,000 characters, e.g. \"Pages about our own product are not competitors.\"" }, "texts": { "title": "Texts to classify (optional)", "type": "array", "description": "Your own texts instead of (or besides) URLs: reviews, posts, company descriptions, support tickets. Each text is one item.", "items": { "type": "string" } }, "datasetId": { "title": "Dataset ID (optional)", "type": "string", "description": "Classify the output of another Actor run, e.g. a Google Maps or lead scraper. Values that look like URLs or domains are read as web pages; other values are classified as text." }, "datasetField": { "title": "Dataset field", "type": "string", "description": "Field of the dataset items to use, e.g. \"website\" or \"text\" (dot paths such as \"company.url\" work). Empty = the first URL field found (url, website, link...), else the first long text field." }, "analysisDepth": { "title": "Analysis depth", "enum": [ "quick", "standard", "deep" ], "type": "string", "description": "How much of each page the AI reads. Quick: the first 4,000 characters (cheapest, fine for home pages). Standard: 12,000. Deep: 32,000 (long or complex pages). Each depth has its own price.", "default": "standard" }, "readAboutPage": { "title": "Read the About page when the home page is almost empty", "type": "boolean", "description": "For home pages or bare domains with less than 300 characters of text (JavaScript shells, splash pages), also read the site's About page (an About / Company link, or /about) and classify both together. No extra charge. Not used with the Page type taxonomy.", "default": true }, "mode": { "title": "Page fetching (HTTP or browser)", "enum": [ "auto", "fast", "browser" ], "type": "string", "description": "\"Auto\" reads pages over plain HTTP and uses a real browser only when a site blocks that or needs JavaScript. Values: auto = Auto (recommended); fast = Plain HTTP only; browser = Browser only.", "default": "auto" }, "maxConcurrency": { "title": "Parallel pages", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many pages are classified at the same time.", "default": 10 }, "httpVia": { "title": "Plain HTTP requests from", "enum": [ "auto", "backend", "direct", "vm" ], "type": "string", "description": "Some sites block requests from data centers. Auto retries from a second network before falling back to a real browser. If both are refused, Auto also tries our second server (Oracle, different IP) before a real browser.", "default": "auto" }, "itemTimeoutSecs": { "title": "Time limit per item (seconds)", "minimum": 0, "maximum": 900, "type": "integer", "description": "A page or text that takes longer (reading + AI) is stopped and returned as a free error row with errorType \"timeout\". 0 = no limit.", "default": 180 }, "dedupeStoreName": { "title": "Skip items classified in earlier runs (store name, optional)", "maxLength": 45, "type": "string", "description": "For lists you run again and again. Give a name (e.g. \"my-leads\"): each charged result is also kept in a key-value store named classifier-cache- in your Apify account, and a later run with the same name and the same settings (taxonomy, labels, instructions, depth; for URLs also the reading mode, route and proxy) returns the earlier result for that URL or text instead of classifying it again, marked fromCache and not charged. Empty = off." }, "dedupeMaxAgeDays": { "title": "Reuse earlier results for (days)", "minimum": 1, "maximum": 365, "type": "integer", "description": "Only with the store name above: results older than this are classified again (and charged as usual).", "default": 30 }, "proxyConfiguration": { "title": "Proxy (optional)", "type": "object", "description": "Only used for requests sent from Apify's network. Apify proxy usage is billed to your Apify account." } } }, "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 } } } } } } } } } }