{
"openapi": "3.0.1",
"info": {
"title": "Article Extractor - Clean Text, Author, Date & Image",
"description": "Extract clean article content from any list of URLs: title, author, publish date, excerpt, lead image, tags, reading time and the full article text - stripped of nav, ads and clutter with Mozilla Readability. No browser.",
"version": "0.1",
"x-build-id": "6uhqBUzX3NgReg1p7"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/scrapesage~article-extractor/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-scrapesage-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/scrapesage~article-extractor/runs": {
"post": {
"operationId": "runs-sync-scrapesage-article-extractor",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/scrapesage~article-extractor/run-sync": {
"post": {
"operationId": "run-sync-scrapesage-article-extractor",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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",
"properties": {
"urls": {
"title": "URLs",
"type": "array",
"description": "Article / blog / news URLs to extract, one per line. A bare domain gets https://. Duplicates are collapsed. Leave empty and the run returns a small free sample.",
"items": {
"type": "string"
}
},
"urlsFromFile": {
"title": "Import URLs from a file (one per line)",
"type": "string",
"description": "Bulk-load URLs. Either paste the whole list (one per line), or give a single link to a public .txt/.csv, a Google Sheet/Drive share link, or an Apify key-value-store record. A file that cannot be read says so and charges nothing."
},
"includeHtml": {
"title": "Include cleaned content HTML",
"type": "boolean",
"description": "Also return the article body as cleaned HTML (contentHtml) on top of the plain textContent. Off by default keeps records lean.",
"default": false
},
"concurrency": {
"title": "Concurrency",
"minimum": 1,
"maximum": 25,
"type": "integer",
"description": "How many URLs to fetch and parse in parallel.",
"default": 8
},
"outputFields": {
"title": "Output fields (leave empty for all)",
"type": "array",
"description": "Pick the fields you want and every record is trimmed to exactly those - handy for lean CSV/Sheets exports. Open the dropdown and tick, or type to filter (title, text, author).",
"items": {
"type": "string",
"enum": [
"type",
"url",
"finalUrl",
"httpStatus",
"status",
"error",
"title",
"byline",
"siteName",
"lang",
"publishedTime",
"modifiedTime",
"excerpt",
"section",
"tags",
"canonical",
"leadImageUrl",
"textContent",
"contentHtml",
"wordCount",
"readingTimeMinutes",
"charCount",
"isArticle",
"fetchedAt"
],
"enumTitles": [
"Record type (type)",
"URL (url)",
"Final URL (finalUrl)",
"HTTP status (httpStatus)",
"Status (status)",
"Error (error)",
"Title (title)",
"Author / byline (byline)",
"Site name (siteName)",
"Language (lang)",
"Published time (publishedTime)",
"Modified time (modifiedTime)",
"Excerpt (excerpt)",
"Section (section)",
"Tags (tags)",
"Canonical (canonical)",
"Lead image URL (leadImageUrl)",
"Article text (textContent)",
"Content HTML (contentHtml)",
"Word count (wordCount)",
"Reading time min (readingTimeMinutes)",
"Character count (charCount)",
"Is an article (isArticle)",
"Fetched at (fetchedAt)"
]
}
},
"maxItems": {
"title": "Max URLs",
"minimum": 1,
"type": "integer",
"description": "Maximum number of URLs to process in one run (after de-duplication).",
"default": 100
},
"proxyConfiguration": {
"title": "Proxy configuration",
"type": "object",
"description": "Optional. Most article pages serve their HTML to a plain request, so no proxy is needed by default. Enable a proxy only if a site blocks the fetch."
}
}
},
"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
}
}
}
}
}
}
}
}
}
}