{ "openapi": "3.0.1", "info": { "title": "Article Extractor & News Scraper", "description": "Extract articles from any news site, blog, or webpage. Get title, full text, author, date, images & metadata using 7 extraction engines (Newspaper4k, Trafilatura, Goose3). Anti-bot bypass, proxy rotation, automatic fallback. Perfect for news monitoring, NLP datasets & content aggregation.", "version": "0.0", "x-build-id": "NYu1FriShVwxDvOLc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/web.harvester~article-extractor-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-web.harvester-article-extractor-news-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/web.harvester~article-extractor-news-scraper/runs": { "post": { "operationId": "runs-sync-web.harvester-article-extractor-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/web.harvester~article-extractor-news-scraper/run-sync": { "post": { "operationId": "run-sync-web.harvester-article-extractor-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Article URLs", "type": "array", "description": "Enter the URLs of articles, news pages, or blog posts you want to extract content from. The extractor will parse each page and extract the title, main text, author information, publication date, images, and other metadata.", "items": { "type": "string" } }, "extractorEngine": { "title": "Extraction Engine", "enum": [ "newspaper4k", "trafilatura", "boilerpy3", "news-please", "goose3", "article-parser", "justext" ], "type": "string", "description": "Select the extraction engine to use. Each engine has unique strengths for different types of content.", "default": "newspaper4k" }, "useFallbackExtractors": { "title": "Use Fallback Extractors", "type": "boolean", "description": "When enabled, automatically tries alternative extraction engines if the primary one fails or returns insufficient content. This significantly improves success rates.", "default": false }, "saveHtml": { "title": "Save Full Page HTML", "type": "boolean", "description": "Enable this option to save the complete HTML source of each webpage alongside the extracted content. Useful for debugging or custom post-processing.", "default": false }, "saveArticleHtml": { "title": "Save Article HTML", "type": "boolean", "description": "When enabled, preserves the cleaned article HTML (just the article content, not the full page) with formatting, links, and embedded media intact. Works with Newspaper4k and Article Parser extractors.", "default": false }, "maxRetries": { "title": "Maximum Retries", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many times to retry if a page fails to load. Higher values improve success rates for difficult sites but may take longer. The default of 15 works well for most sites.", "default": 35 }, "useHeaderGenerator": { "title": "Use Smart Header Generator", "type": "boolean", "description": "Automatically generate realistic browser headers for each request using browserforge. This helps bypass anti-bot measures by mimicking real browser fingerprints. Highly recommended for most sites.", "default": true }, "headerGeneratorOptions": { "title": "Header Generator Options", "type": "object", "description": "Configure which devices and browsers to emulate when generating headers. Only applies when Smart Header Generator is enabled." }, "customHeaders": { "title": "Custom Headers", "type": "object", "description": "Add specific HTTP headers to your requests. These headers will be merged with generated headers (custom headers take priority). Useful for authentication or specialized access." }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Configure proxies to avoid IP blocking, bypass geo-restrictions, and access region-specific content. Residential proxies are recommended for news sites with strict anti-bot measures.", "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 } } } } } } } } } }