{ "openapi": "3.0.1", "info": { "title": "article-scrapper", "description": "A flexible and powerful Apify Actor for scraping articles from tech news websites. This scraper can work with any tech news site - either from predefined presets or custom URLs", "version": "0.0", "x-build-id": "1qEqCybmJwdLJ045S" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/credible_sandal~article-scrapper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-credible_sandal-article-scrapper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/credible_sandal~article-scrapper/runs": { "post": { "operationId": "runs-sync-credible_sandal-article-scrapper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/credible_sandal~article-scrapper/run-sync": { "post": { "operationId": "run-sync-credible_sandal-article-scrapper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "usePresets": { "title": "Use Preset Sites", "type": "boolean", "description": "Use predefined news sites or provide custom URLs", "default": true }, "presetSources": { "title": "Preset News Sources", "uniqueItems": true, "type": "array", "description": "Select from predefined tech news sources (only used if 'Use Preset Sites' is checked)", "items": { "type": "string", "enum": [ "verge", "cnet", "wired", "techcrunch", "arstechnica", "engadget", "theguardian-tech", "thenextweb", "hackernews", "bbc-tech", "mit-tech-review", "venturebeat", "devto", "producthunt" ] }, "default": [ "verge", "techcrunch", "wired" ] }, "customUrls": { "title": "Custom URLs", "uniqueItems": true, "type": "array", "description": "Enter custom URLs to scrape (one per line). Can be homepages or article listing pages. Used when 'Use Preset Sites' is unchecked.", "items": { "type": "string", "pattern": "^https?://.*" } }, "maxArticlesPerSource": { "title": "Max Articles Per Source", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum number of articles to scrape from each source", "default": 10 }, "maxPages": { "title": "Max Listing Pages", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of listing pages to check per source", "default": 1 }, "includeContent": { "title": "Include Full Article Content", "type": "boolean", "description": "Extract full article text (may increase scraping time)", "default": true }, "searchKeywords": { "title": "Search Keywords (Optional)", "type": "array", "description": "Filter articles by keywords. Only articles containing ANY of these keywords in title or description will be included. Leave empty to scrape all articles.", "items": { "type": "string" } }, "filterMode": { "title": "Filter Mode", "enum": [ "any", "all" ], "type": "string", "description": "'any' — article passes if it matches at least one filter (OR logic, recommended). 'all' — article must pass every filter simultaneously (AND logic, very strict).", "default": "any" }, "titleContains": { "title": "Title Must Contain (Optional)", "type": "string", "description": "Only scrape articles where the title contains this text (case-insensitive). Leave empty to scrape all articles." }, "descriptionContains": { "title": "Description Must Contain (Optional)", "type": "string", "description": "Only scrape articles where the summary/description contains this text (case-insensitive). Leave empty to scrape all articles." }, "dateFrom": { "title": "Published After (Optional)", "type": "string", "description": "Only include articles published on or after this date. Format: YYYY-MM-DD or ISO datetime (e.g. 2025-01-15). Leave empty for no restriction." }, "dateTo": { "title": "Published Before (Optional)", "type": "string", "description": "Only include articles published on or before this date. Format: YYYY-MM-DD or ISO datetime (e.g. 2025-03-31). Leave empty for no restriction." }, "publishedWithin": { "title": "Published Within (Optional)", "type": "string", "description": "Only include articles published within this time window. Examples: '24h', '7d', '30d', '2w'. Takes precedence over 'Published After' when both are set." }, "useRssFeeds": { "title": "Use RSS Feeds When Available", "type": "boolean", "description": "For preset sources, use their RSS/Atom feed instead of HTML scraping. Feeds are faster, more reliable, and return cleaner data.", "default": true }, "includeSentiment": { "title": "Include Sentiment Analysis", "type": "boolean", "description": "Analyze each article's sentiment (positive / neutral / negative) based on its title and summary. Adds a 'sentiment' field to the output.", "default": true }, "sentimentFilter": { "title": "Sentiment Filter (Optional)", "enum": [ "all", "positive", "neutral", "negative" ], "type": "string", "description": "Only return articles matching this sentiment. Requires 'Include Sentiment Analysis' to be enabled. Use 'all' to return everything.", "default": "all" } } }, "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 } } } } } } } } } }