Pricing
$20.00/month + usage
Scrape all articles from any news website. Extract full text, metadata, keywords, and summaries. Ideal for content analysis, research, and news aggregation.
0.0 (0)
Pricing
$20.00/month + usage
5
153
26
Last modified
3 months ago
You can access the News Website Crawler & Article Extractor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, youβll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "WMyDN5qn9AaVIBu8j" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/xtech~news-source-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-xtech-news-source-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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~news-source-crawler/runs": { "post": { "operationId": "runs-sync-xtech-news-source-crawler", "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~news-source-crawler/run-sync": { "post": { "operationId": "run-sync-xtech-news-source-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "url" ], "properties": { "url": { "title": "News Source URL", "pattern": "^https?://.+$", "type": "string", "description": "The URL of the news website you want to crawl (e.g., https://www.cnn.com)." }, "maxArticles": { "title": "Maximum Articles", "minimum": 0, "maximum": 10000, "type": "integer", "description": "The maximum number of articles to scrape. Set to 0 for no limit.", "default": 100 }, "language": { "title": "Language", "enum": [ "en", "es", "fr", "de", "it", "pt", "ru", "zh", "ja", "ko", "ar", "nl", "sv", "da", "no", "fi", "pl", "he", "tr", "hu", "el", "uk", "vi", "id", "sw", "fa", "hi", "hr", "bg", "et", "mk", "be", "sl", "sr", "ro" ], "type": "string", "description": "The language of the articles. Choose from supported languages.", "default": "en" }, "keywordSearch": { "title": "Keyword Search [Optional]", "maxLength": 500, "type": "string", "description": "Filter articles containing specific keywords. Leave blank to get all articles. Supports boolean operators: AND, OR, NOT with parentheses (e.g., 'climate AND (change OR crisis) NOT politics')." }, "searchInTitle": { "title": "Search in Article Titles", "type": "boolean", "description": "Apply keyword search to article titles.", "default": true }, "searchInContent": { "title": "Search in Article Content", "type": "boolean", "description": "Apply keyword search to article text content.", "default": true }, "caseSensitive": { "title": "Case Sensitive Search", "type": "boolean", "description": "Make keyword search case sensitive.", "default": false }, "minWordCount": { "title": "Minimum Word Count", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Skip articles that have fewer words than this number. Use 0 for no minimum.", "default": 0 }, "extractSummary": { "title": "Extract Summary & Keywords", "type": "boolean", "description": "Generate article summaries and keywords using Natural Language Processing (NLP). Note: This increases processing time.", "default": true }, "includeImages": { "title": "Include Images", "type": "boolean", "description": "Extract and include image URLs from articles.", "default": true }, "requestTimeout": { "title": "Request Timeout (seconds)", "minimum": 5, "maximum": 60, "type": "integer", "description": "Timeout for each article request in seconds.", "default": 7 }, "concurrency": { "title": "Concurrent Requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "Number of articles to process simultaneously. Higher values = faster crawling but may trigger rate limits.", "default": 5 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Configure proxy settings for reliable scraping. Apify Proxy is recommended for best results.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for News Website Crawler & Article Extractor from the options below:
If youβd like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: