Reuters News Scraper
Pricing
from $3.00 / 1,000 article founds
Scrape Reuters headlines, publish times, sections, images and tags from the public news sitemap and Bing News site:reuters.com search. Honest metadata — no DataDome bypass. MCP-ready.
You can access the Reuters News Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "zbb2Zt2hQaF8rVbpL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/khadinakbar~reuters-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-khadinakbar-reuters-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/khadinakbar~reuters-news-scraper/runs": { "post": { "operationId": "runs-sync-khadinakbar-reuters-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/khadinakbar~reuters-news-scraper/run-sync": { "post": { "operationId": "run-sync-khadinakbar-reuters-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", "properties": { "sections": { "title": "Reuters sections", "type": "array", "description": "Reuters sections to pull from the public Google News sitemap (headline, publish time, image, tags, URL). Select one or more. Use \"latest\" for all English paths. reuters.com HTML is DataDome-blocked — this Actor returns sitemap/search metadata only (bodyText is always null).", "items": { "type": "string", "enum": [ "latest", "world", "business", "markets", "legal", "sports", "technology", "science", "sustainability", "lifestyle", "commentary", "podcasts" ], "enumTitles": [ "Latest (all English)", "World", "Business", "Markets", "Legal", "Sports", "Technology", "Science", "Sustainability", "Lifestyle", "Commentary", "Podcasts" ] }, "default": [ "world", "business" ] }, "searchKeywords": { "title": "Keyword filter", "type": "array", "description": "Optional case-insensitive keywords. Keep only articles whose headline, summary, or keywords contain at least one term (e.g. ['Fed','oil']). Leave empty to keep all items from selected sections.", "default": [], "items": { "type": "string" } }, "searchQuery": { "title": "Keyword search (Bing News site:reuters.com)", "type": "string", "description": "Optional topic search via Bing News RSS filtered to reuters.com. Use when section sitemap browsing is too broad. Returns headline + snippet + URL. Leave empty to skip.", "default": "" }, "articleUrls": { "title": "Article URLs", "type": "array", "description": "Optional list of reuters.com article URLs. Matched against the public news sitemap when possible; otherwise a URL-derived title/date row is returned. Does not scrape article HTML (DataDome) and does not return full body text.", "default": [], "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "Language/locale filter from the URL path. Default is English only (en). Add de/es/fr/pt for localized Reuters editions, or \"all\" to keep every locale present in the sitemap pages fetched.", "items": { "type": "string", "enum": [ "en", "de", "es", "fr", "pt", "all" ], "enumTitles": [ "English", "German", "Spanish", "French", "Portuguese", "All locales" ] }, "default": [ "en" ] }, "sinceHours": { "title": "Only articles newer than (hours)", "minimum": 0, "type": "integer", "description": "Optional recency window. If set to e.g. 24, only articles with publishedAt within the last 24 hours are kept. Use 0 (default) for all currently returned sitemap/search items.", "default": 0 }, "maxItems": { "title": "Max articles", "minimum": 1, "maximum": 500, "type": "integer", "description": "Hard cap on articles scraped and billed across all sources. Each accepted article is one billable article-found event. Defaults to 50. Prefill 10 for cheap quality tests.", "default": 50 }, "maxSitemapPages": { "title": "Max sitemap pages", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many Reuters news-sitemap pages to fetch (~50 URLs each, offset by 100). Default 4 (~200 candidate URLs before section/language filters). Raise only when maxItems is large.", "default": 4 }, "proxyConfiguration": { "title": "Proxy (optional)", "type": "object", "description": "Optional Apify proxy. The public news sitemap and Bing News RSS usually work without a proxy. Enable only if your environment blocks outbound XML/RSS.", "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "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 Reuters News Scraper from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: