{ "openapi": "3.0.1", "info": { "title": "Smart Article Scraper - Text, Data & Insights", "description": "𝗔𝗿𝘁𝗶𝗰𝗹𝗲 𝗦𝗰𝗿𝗮𝗽𝗲𝗿 & 𝗖𝗼𝗻𝘁𝗲𝗻𝘁 𝗘𝘅𝘁𝗿𝗮𝗰𝘁𝗼𝗿 - Extract clean text, metadata, keywords & summaries from any web article or blog post. Perfect for 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵, 𝗰𝗼𝗺𝗽𝗲𝘁𝗶𝘁𝗶𝘃𝗲 𝗮𝗻𝗮𝗹𝘆𝘀𝗶𝘀 & 𝗰𝗼𝗻𝘁𝗲𝗻𝘁 𝗺𝗮𝗿𝗸𝗲𝘁𝗶𝗻𝗴.", "version": "0.2", "x-build-id": "AaERCg2gtHodDgq9R" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/xtech~article-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-xtech-article-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/xtech~article-extractor/runs": { "post": { "operationId": "runs-sync-xtech-article-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/xtech~article-extractor/run-sync": { "post": { "operationId": "run-sync-xtech-article-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "minItems": 1, "type": "array", "description": "Article or blog post URLs to extract. Add one or more direct article pages.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "language": { "title": "Article language", "maxLength": 2, "type": "string", "description": "Optional two-letter language code such as en, es, de, or fr. Leave empty to let extraction libraries infer the language when possible." }, "requestTimeout": { "title": "Request timeout", "minimum": 5, "maximum": 120, "type": "integer", "description": "Maximum time in seconds to wait for each article page to respond.", "default": 30 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Number of article URLs to process in parallel. Keep the default for most publishers and lower it if a website rate-limits requests.", "default": 3 }, "maxRetries": { "title": "Max retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Number of retries for transient request failures such as timeouts, rate limits, and temporary server errors.", "default": 2 }, "fetchImages": { "title": "Extract images", "type": "boolean", "description": "Include article image URLs when the newspaper3k fallback is used. The Actor stores image URLs, not image files.", "default": true }, "browserUserAgent": { "title": "User agent", "maxLength": 256, "type": "string", "description": "Custom browser User-Agent header for article requests." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional proxy settings. Enable Apify Proxy or provide a custom proxy URL for sites that block direct requests.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }