{ "openapi": "3.0.1", "info": { "title": "Analyze Website Content: Extract Keywords and Terminology", "description": "The tool analyzes the textual content of a website, scrapes pages, cleans the html, analyze text and extract the terminology (keywords, words, n-grams and seed related keywords). It can be used to identify the main topics covered, analyze competitor content, find new ideas or trends and help for SEO", "version": "1.0", "x-build-id": "4BhhIV9DxNrGftEpV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nlp_data_lni~analyze-website-content-extract-keywords-and-terminology/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nlp_data_lni-analyze-website-content-extract-keywords-and-terminology", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nlp_data_lni~analyze-website-content-extract-keywords-and-terminology/runs": { "post": { "operationId": "runs-sync-nlp_data_lni-analyze-website-content-extract-keywords-and-terminology", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nlp_data_lni~analyze-website-content-extract-keywords-and-terminology/run-sync": { "post": { "operationId": "run-sync-nlp_data_lni-analyze-website-content-extract-keywords-and-terminology", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "start_url" ], "properties": { "start_url": { "title": "Start URL", "type": "string", "description": "Domain url to start with" }, "seed_keywords": { "title": "Seed Keywords", "type": "array", "description": "The seed keywords will be used to detect similar keywords in the content", "items": { "type": "string" } }, "max_depth": { "title": "Maximum depth", "type": "integer", "description": "Depth to which to scrape to", "default": 1 }, "max_pages": { "title": "Max pages per run", "type": "integer", "description": "The maximum number of pages that the scraper will process. The scraper will stop when this limit is reached. Since the analysis is performed on all of the scraped data, it is recommended not to exceed the value of 500. This is sufficient for a general analysis of the website content.", "default": 50 }, "clean_text": { "title": "Clean text", "type": "boolean", "description": "Enable Boilerplate removal. This consists in removing navigation links, headers, and footers from HTML pages. It is designed to extract only the main text.", "default": true }, "proxy_settings": { "title": "Proxy configuration", "type": "object", "description": "Select proxies to be used for crawling." }, "max_display_number": { "title": "Maximum top terms number to display", "type": "integer", "description": "Maximum number of the most frequent terms to display. This applies to the extracted 'words' and 'ngrams'", "default": 50 }, "generate_wordcloud": { "title": "Generate Wordcloud images", "type": "boolean", "description": "Enable Wordcloud images generation. If set, Wordcloud SVG images will be produced for the extracted 'keywords', 'words' and 'ngrams'", "default": false }, "max_wordcloud_number": { "title": "Maximum top keywords number in Wordcloud", "type": "integer", "description": "Maximum number of the most frequent keywords to render in the Wordcloud. This applies to extracted 'keywords', 'words' and 'ngrams'", "default": 50 }, "min_wordcloud_number": { "title": "Minimum keywords number in Wordcloud", "type": "integer", "description": "Minimum number of keywords to render in the Wordcloud (otherwise, no wordlcoud generation). This applies to extracted 'keywords', 'words' and 'ngrams'", "default": 5 } } }, "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 } } } } } } } } } }