# NewsCatcher

> Search and monitor news articles with powerful company and entity filtering, NLP enrichment, and breaking news clustering.

Source: https://cotera.co/docs/reference/tools/individual-tools/newscatcher

---

**Authentication Type:** API Key

**Description:** Search and monitor news articles with powerful company and entity filtering, NLP enrichment, and breaking news clustering.

***

## Authentication

To authenticate, you'll need a NewsCatcher API key from the [NewsCatcher v3 API](https://www.newscatcherapi.com/).

**Note:** The v3\_nlp plan allows historical search up to 30 days. Higher tier plans provide extended historical access.

***

## News Search

Search for news articles with company, domain, and entity filters.

### Search Articles

Search for news articles by query with filters for companies, domains, languages, and date ranges. Supports NLP enrichment for sentiment and entity extraction.

**Operation Type:** Query (Read)

**Parameters:**

* **q** `string` (required): Search query string
* **ORG\_entity\_name** `string` (nullable): Filter by organization/company name entity
* **all\_domain\_links** `array of strings` (nullable): Filter articles that link to any of these domains
* **all\_links** `array of strings` (nullable): Filter articles that contain any of these URLs
* **from\_** `string` (nullable): Start date for search (ISO format or relative like 7d)
* **to\_** `string` (nullable): End date for search (ISO format or relative)
* **lang** `string` (nullable): Language code (e.g., en, es, fr)
* **countries** `array of strings` (nullable): Country codes to filter by
* **sources** `array of strings` (nullable): Source domains to include
* **not\_sources** `array of strings` (nullable): Source domains to exclude
* **is\_opinion** `boolean` (nullable): Filter for opinion articles only
* **include\_nlp\_data** `boolean` (nullable): Include NLP enrichment data in response
* **page** `number` (default: 1): Page number (starting from 1)
* **page\_size** `number` (default: 5): Number of results per page (max: 100)

**Returns:**

* **status** `string`: Response status
* **articles** `array of objects`: Matching articles
  * **title** `string`: Article title
  * **author** `string` (nullable): Article author
  * **authors** `array of strings` (nullable): List of article authors
  * **journalists** `array of strings` (nullable): List of journalists
  * **published\_date** `string` (nullable): Publication date
  * **published\_date\_precision** `string` (nullable): Date precision level
  * **updated\_date** `string` (nullable): Last updated date
  * **link** `string`: Article URL
  * **domain\_url** `string` (nullable): Source domain
  * **full\_domain\_url** `string` (nullable): Full source domain URL
  * **name\_source** `string` (nullable): Source name
  * **description** `string` (nullable): Article description
  * **content** `string` (nullable): Full article content
  * **word\_count** `number` (nullable): Word count
  * **is\_opinion** `boolean` (nullable): Whether article is an opinion piece
  * **twitter\_account** `string` (nullable): Twitter account of source
  * **score** `number` (nullable): Relevance score
  * **language** `string` (nullable): Article language
  * **external\_links** `array of strings` (nullable): External links in article
  * **external\_domain\_links** `array of strings` (nullable): External domain links in article
  * **nlp** `object` (nullable): NLP enrichment data
    * **theme** `array of strings` (nullable): Article themes
    * **summary** `string` (nullable): AI-generated summary
    * **sentiment** `object` (nullable): Sentiment analysis
      * **title** `number`: Title sentiment score (-1 to 1)
      * **content** `number`: Content sentiment score (-1 to 1)
    * **ner\_PER** `array of objects` (nullable): Named entities - persons
      * **entity** `string`: Person name
      * **count** `number`: Mention count
    * **ner\_ORG** `array of objects` (nullable): Named entities - organizations
      * **entity** `string`: Organization name
      * **count** `number`: Mention count
    * **ner\_LOC** `array of objects` (nullable): Named entities - locations
      * **entity** `string`: Location name
      * **count** `number`: Mention count
* **page** `number`: Current page number
* **page\_size** `number`: Results per page
* **total\_hits** `number`: Total number of matching articles
* **total\_pages** `number`: Total number of pages

**Example Usage:**

```json
{
  "q": "artificial intelligence startup funding",
  "ORG_entity_name": "OpenAI",
  "lang": "en",
  "countries": ["US", "GB"],
  "from_": "7d",
  "include_nlp_data": true,
  "page": 1,
  "page_size": 25
}
```

### Search by Clusters

Search for news articles grouped into clusters of similar stories. Useful for deduplicating coverage of the same event.

**Operation Type:** Query (Read)

**Parameters:**

* **q** `string` (required): Search query string
* **ORG\_entity\_name** `string` (nullable): Filter by organization/company name entity
* **all\_domain\_links** `array of strings` (nullable): Filter articles that link to any of these domains
* **from\_** `string` (nullable): Start date for search (ISO format or relative like 7d)
* **to\_** `string` (nullable): End date for search (ISO format or relative)
* **lang** `string` (nullable): Language code (e.g., en, es, fr)
* **countries** `array of strings` (nullable): Country codes to filter by
* **include\_nlp\_data** `boolean` (nullable): Include NLP enrichment data in response
* **clustering\_threshold** `number` (nullable): Similarity threshold for clustering (0-1)
* **page** `number` (default: 1): Page number (starting from 1)
* **page\_size** `number` (default: 5): Number of clusters per page

**Returns:**

* **status** `string`: Response status
* **clusters** `array of objects`: Clustered articles
  * **cluster\_id** `string`: Unique cluster identifier
  * **cluster\_size** `number`: Number of articles in cluster
  * **articles** `array of objects`: Articles in this cluster (same schema as Search Articles)
* **clusters\_count** `number`: Total number of clusters
* **page** `number`: Current page number
* **page\_size** `number`: Results per page
* **total\_hits** `number`: Total number of matching articles
* **total\_pages** `number`: Total number of pages

**Example Usage:**

```json
{
  "q": "Tesla earnings report",
  "lang": "en",
  "from_": "24h",
  "clustering_threshold": 0.7,
  "include_nlp_data": true,
  "page": 1,
  "page_size": 10
}
```

***

## Headlines

Get latest headlines and breaking news.

### Latest Headlines

Get the latest news headlines filtered by theme, language, and country. Available themes: Tech, Politics, Sports, Business, Finance, Entertainment, Science, Health, Travel, Lifestyle, Auto, Environment, World, Music, Food, Gaming.

**Operation Type:** Query (Read)

**Parameters:**

* **when** `string` (nullable): Time range (e.g., 24h, 7d, 1m)
* **lang** `string` (nullable): Language code (e.g., en, es, fr)
* **countries** `array of strings` (nullable): Country codes to filter by
* **theme** `string` (nullable): Theme filter (Tech, Politics, Sports, Business, Finance, Entertainment, Science, Health, Travel, Lifestyle, Auto, Environment, World, Music, Food, Gaming)
* **sources** `array of strings` (nullable): Source domains to include
* **not\_sources** `array of strings` (nullable): Source domains to exclude
* **include\_nlp\_data** `boolean` (nullable): Include NLP enrichment data in response
* **page** `number` (default: 1): Page number (starting from 1)
* **page\_size** `number` (default: 5): Number of results per page (max: 100)

**Returns:**

* **status** `string`: Response status
* **articles** `array of objects`: Latest headlines (same schema as Search Articles)
* **page** `number`: Current page number
* **page\_size** `number`: Results per page
* **total\_hits** `number`: Total number of matching articles
* **total\_pages** `number`: Total number of pages

**Example Usage:**

```json
{
  "theme": "Tech",
  "lang": "en",
  "countries": ["US"],
  "when": "24h",
  "include_nlp_data": true,
  "page": 1,
  "page_size": 20
}
```

### Breaking News

Get emerging breaking news stories clustered by event. Shows rapidly developing stories as they unfold.

**Operation Type:** Query (Read)

**Parameters:**

* **when** `string` (nullable): Time range (e.g., 1h, 6h, 24h)
* **lang** `string` (nullable): Language code (e.g., en, es, fr)
* **countries** `array of strings` (nullable): Country codes to filter by
* **include\_nlp\_data** `boolean` (nullable): Include NLP enrichment data in response
* **page** `number` (default: 1): Page number (starting from 1)
* **page\_size** `number` (default: 5): Number of results per page

**Returns:**

* **status** `string`: Response status
* **clusters** `array of objects`: Breaking news clusters
  * **cluster\_id** `string`: Unique cluster identifier
  * **cluster\_size** `number`: Number of articles in cluster
  * **articles** `array of objects`: Articles in this cluster (same schema as Search Articles)
* **clusters\_count** `number`: Total number of breaking stories
* **page** `number`: Current page number
* **page\_size** `number`: Results per page
* **total\_hits** `number`: Total number of matching articles
* **total\_pages** `number`: Total number of pages

**Example Usage:**

```json
{
  "when": "6h",
  "lang": "en",
  "countries": ["US", "GB"],
  "include_nlp_data": true,
  "page": 1,
  "page_size": 10
}
```

***

## Related Tools

For extracting structured data from web sources using natural language queries, see [NewsCatcher CatchAll](https://cotera.co/docs/reference/tools/individual-tools/newscatcher-catchall.md).

***

## Common Use Cases

**News Monitoring:**

* Track breaking news and developments for specific companies or products
* Monitor competitor mentions and market developments with entity filtering
* Set up real-time news alerts by searching with NLP enrichment enabled

**Content Research:**

* Gather recent articles from trusted sources with source filtering
* Find news articles with sentiment analysis for brand perception tracking
* Search for trending topics within defined geographic regions and languages

**Market Intelligence:**

* Monitor industry news and regulatory changes affecting business operations
* Track competitor announcements through organization entity filtering
* Analyze news clusters to understand how stories spread across publications

**Media Analysis:**

* Study news coverage patterns using cluster-based search to deduplicate stories
* Analyze sentiment trends across different news sources and topics
* Extract named entities (people, organizations, locations) for relationship mapping