> ## Documentation Index > Fetch the complete documentation index at: https://newscatcherinc-docs.mintlify.site/docs/llms.txt > Use this file to discover all available pages before exploring further. # Search articles with GeoNames filtering > Searches for local news using structured GeoNames filtering with administrative hierarchy, coordinates, localization and confidence scores. ## OpenAPI ````yaml local-news-api post /api/search/advanced openapi: 3.0.3 info: title: Local News API description: > The Local News API provides access to local news articles with location-specific filtering capabilities. ## Standard endpoints - `/search`: Search articles by keywords with simple location filtering ("City, State" format). - `/latest_headlines`: Retrieve recent articles for specified locations and time periods. - `/search_by`: Retrieve articles by URL, ID, or RSS GUID. - `/sources`: List available news sources. ## Advanced endpoints - `/search/advanced`: Search with structured GeoNames filtering. - `/latest_headlines/advanced`: Latest headlines with structured GeoNames filtering. ## Features - Multiple location detection methods including dedicated sources, proximity analysis, and AI extraction - Natural language processing for sentiment analysis and entity recognition on original content and English translations - Article clustering for topic analysis - English translations for non-English content termsOfService: https://newscatcherapi.com/terms-of-service contact: name: Maksym Sugonyaka email: maksym@newscatcherapi.com url: https://www.newscatcherapi.com/book-a-demo version: 1.2.0 servers: - url: https://local-news.newscatcherapi.com description: Local News API production server security: - ApiKeyAuth: [] tags: - name: Search description: >- Operations to search for local news articles. Includes both standard location filtering and advanced GeoNames filtering. - name: LatestHeadlines description: >- Operations to retrieve local news latest headlines. Includes both standard location filtering and advanced GeoNames filtering. - name: SearchBy description: Operations to search local news by link, ID or RSS GUID. - name: Sources description: Operations to retrieve local news sources. externalDocs: description: Find out more about Local News API url: https://www.newscatcherapi.com/docs/local-news-api/get-started/introduction paths: /api/search/advanced: post: tags: - Search summary: Search articles with GeoNames filtering description: > Searches for local news using structured GeoNames filtering with administrative hierarchy, coordinates, localization and confidence scores. operationId: SearchAdvanced_post requestBody: $ref: '#/components/requestBodies/SearchAdvancedRequestBody' responses: '200': $ref: '#/components/responses/SearchAdvancedResponse' '400': $ref: '#/components/responses/BadRequestError' '401': $ref: '#/components/responses/UnauthorizedError' '403': $ref: '#/components/responses/ForbiddenError' '408': $ref: '#/components/responses/RequestTimeoutError' '422': $ref: '#/components/responses/ValidationError' '429': $ref: '#/components/responses/RateLimitError' '500': $ref: '#/components/responses/InternalServerError' components: requestBodies: SearchAdvancedRequestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SearchAdvancedRequestDto' responses: SearchAdvancedResponse: description: > A successful response containing articles that match the specified search criteria with GeoNames location data. The response may include clustering information if enabled. content: application/json: schema: oneOf: - $ref: '#/components/schemas/ArticleSearchAdvancedResponseDto' - $ref: '#/components/schemas/ClusteringSearchAdvancedResponseDto' BadRequestError: description: Bad request content: application/json: schema: $ref: '#/components/schemas/Error' example: message: Invalid JSON in request body status_code: 400 status: Bad request UnauthorizedError: description: Unauthorized - Authentication failed content: application/json: schema: $ref: '#/components/schemas/Error' example: message: 'Invalid api key: INVALID_API_KEY' status_code: 401 status: Unauthorized ForbiddenError: description: Forbidden - Server refuses action content: application/json: schema: $ref: '#/components/schemas/Error' example: message: Your plan request date range cannot be greater than 400 days status_code: 403 status: Forbidden RequestTimeoutError: description: Request timeout content: application/json: schema: $ref: '#/components/schemas/Error' example: message: Request timed out after 30 seconds status_code: 408 status: Request timeout ValidationError: description: Validation error content: application/json: schema: $ref: '#/components/schemas/Error' example: message: Invalid date format status_code: 422 status: Validation error RateLimitError: description: Too many requests - Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/Error' example: message: Max API requests concurrency reached status_code: 429 status: Too many requests InternalServerError: description: Internal server error content: text/plain: schema: type: string example: Internal Server Error schemas: SearchAdvancedRequestDto: allOf: - type: object properties: q: $ref: '#/components/schemas/Q' from_: $ref: '#/components/schemas/From' to_: $ref: '#/components/schemas/To' search_in: $ref: '#/components/schemas/SearchIn' sort_by: $ref: '#/components/schemas/SortBy' - $ref: '#/components/schemas/BaseAdvancedRequestDto' ArticleSearchAdvancedResponseDto: title: Advanced Search Response description: > The response model for the `Search advanced`, `Latest headlines advanced`, and `Search by` requests. Response field behavior: - Required fields are guaranteed to be present and non-null. - Optional fields may be `null`/`undefined` if the data couldn't be extracted during processing. - To access article properties in the `articles` response array, use array index notation. For example, `articles[n].title`, where `n` is the zero-based index of the article object (0, 1, 2, etc.). allOf: - $ref: '#/components/schemas/SearchResponseDto' - type: object properties: articles: type: array items: $ref: '#/components/schemas/ArticleAdvancedResultEntity' default: [] user_input: type: object ClusteringSearchAdvancedResponseDto: title: Clustered Search Response (Advanced) description: > The response model when clustering is enabled, grouping similar articles into clusters. Applies to the `Search advanced` and `Latest headlines advanced` requests. Response field behavior: - Required fields are guaranteed to be present and non-null. - Optional fields may be `null`/`undefined` if the data couldn't be extracted during processing. - To access article properties in the `articles` response array, use array index notation. For example, `articles[n].title`, where `n` is the zero-based index of the article object (0, 1, 2, etc.). allOf: - $ref: '#/components/schemas/SearchResponseDto' - type: object required: - clusters_count - agg_clusters - clusters - user_input properties: clusters_count: type: integer agg_clusters: type: array items: type: string clusters: type: object additionalProperties: $ref: '#/components/schemas/ClusterAdvancedEntity' user_input: type: object Error: type: object properties: message: type: string description: A detailed description of the error. status_code: type: integer description: The HTTP status code of the error. status: type: string description: A short description of the status code. required: - message - status_code - status Q: type: string description: > The keyword(s) to search for in articles. Query syntax supports logical operators (`AND`, `OR`, `NOT`) and wildcards: - For exact phrases, use escaped quotes: `\"technology news\"` - Use `*` for wildcards: `technolog*` (cannot start with `*`) - Use `+` to include and `-` to exclude: `+Apple`, `-Google` - Boolean operators: `technology AND (Apple OR Microsoft) NOT Google` - Forbidden characters: `[` `]` `/` `\\` `:` `^` and URL-encoded equivalents **Note:** The API automatically inserts `AND` operators between standalone terms, so strings like `"machine learning"` become `"machine AND learning"`. To avoid syntax errors (especially in queries with `OR` operators), use literal escape `"\"machine learning\""`. For detailed syntax rules, see [Advanced querying](https://www.newscatcherapi.com/docs/news-api/guides-and-concepts/advanced-querying). example: '"supply chain" AND Amazon NOT China' From: oneOf: - type: string format: date-time example: '2024-09-24T00:00:00.000Z' - type: string example: 1 day ago default: 7 days ago description: > The starting point in time to search from. Accepts date-time strings in ISO 8601 format and plain text strings. The default time zone is UTC. Formats with examples: - YYYY-mm-ddTHH:MM:SS: `2024-09-24T00:00:00` - YYYY-MM-dd: `2024-09-24` - YYYY/mm/dd HH:MM:SS: `2024/09/24 00:00:00` - YYYY/mm/dd: `2024/09/24` - English phrases: `1 day ago`, `today` **Note**: By default, applied to the publication date of the article. To use the article's parse date instead, set the `by_parse_date` parameter to `true`. example: 2024/09/24 To: oneOf: - type: string format: date-time example: '2024-09-25T00:00:00.000Z' - type: string example: 1 day ago default: now description: > The ending point in time to search up to. Accepts date-time strings in ISO 8601 format and plain text strings. The default time zone is UTC. Formats with examples: - YYYY-mm-ddTHH:MM:SS: `2024-09-25T00:00:00` - YYYY-MM-dd: `2024-09-25` - YYYY/mm/dd HH:MM:SS: `2024/09/25 00:00:00` - YYYY/mm/dd: `2024/09/25` - English phrases: `1 day ago`, `today`, `now` **Note**: By default, applied to the publication date of the article. To use the article's parse date instead, set the `by_parse_date` parameter to `true`. example: 2024/09/25 SearchIn: type: string default: title_content description: > The article fields to search in. Use a comma-separated string for multiple options, with a maximum of 2 in a single request. Available options: - Standard fields: `title`, `content`, `summary`, `title_content` - Translation fields: `title_translated`, `content_translated`, `summary_translated`, `title_content_translated` **Note**: Search in summaries and translations is only available for NLP subscription plans. example: title_content, title_content_translated SortBy: type: string enum: - relevancy - date - rank default: date description: > The sorting order of the results. Possible values are: - `relevancy`: The most relevant results first. - `date`: The most recently published results first. - `rank`: Highest-ranked sources first; when clustering enabled, sorts by `cluster_rank` within clusters. example: date BaseAdvancedRequestDto: type: object properties: geonames: $ref: '#/components/schemas/GeoNamesFilter' geonames_operator: $ref: '#/components/schemas/GeoNamesOperator' lang: $ref: '#/components/schemas/Lang' countries: $ref: '#/components/schemas/Countries' sources: $ref: '#/components/schemas/Sources' not_sources: $ref: '#/components/schemas/NotSources' parent_url: $ref: '#/components/schemas/ParentUrl' is_paid_content: $ref: '#/components/schemas/IsPaidContent' page: $ref: '#/components/schemas/Page' page_size: $ref: '#/components/schemas/PageSize' word_count_min: $ref: '#/components/schemas/WordCountMin' word_count_max: $ref: '#/components/schemas/WordCountMax' clustering: $ref: '#/components/schemas/ClusteringEnabled' theme: $ref: '#/components/schemas/Theme' PER_entity_name: $ref: '#/components/schemas/PerEntityName' LOC_entity_name: $ref: '#/components/schemas/LocEntityName' MISC_entity_name: $ref: '#/components/schemas/MiscEntityName' ORG_entity_name: $ref: '#/components/schemas/OrgEntityName' title_sentiment_min: $ref: '#/components/schemas/TitleSentimentMin' title_sentiment_max: $ref: '#/components/schemas/TitleSentimentMax' content_sentiment_min: $ref: '#/components/schemas/ContentSentimentMin' content_sentiment_max: $ref: '#/components/schemas/ContentSentimentMax' include_translation_fields: $ref: '#/components/schemas/IncludeTranslationFields' SearchResponseDto: title: Base Search Response required: - status - total_hits - page - total_pages - page_size type: object properties: status: title: Status description: The status of the response. type: string default: ok total_hits: title: Total Hits description: The total number of articles matching the search criteria. type: integer page: title: Page description: The current page number of the results. type: integer total_pages: title: Total Pages description: The total number of pages available for the given search criteria. type: integer page_size: title: Page Size description: The number of articles per page. type: integer ArticleAdvancedResultEntity: title: Article Result (Advanced) allOf: - $ref: '#/components/schemas/BaseArticleEntity' - type: object properties: geonames: type: array items: $ref: '#/components/schemas/GeoNamesResponseEntity' description: > A list of locations identified in the article, including detection methods, confidence, and localization scores. The location data adheres to the GeoNames format. ClusterAdvancedEntity: title: Cluster Entity (Advanced) type: object required: - articles - agg_cluster - original_cluster_size - cluster_size properties: articles: type: array items: $ref: '#/components/schemas/ClusterArticleAdvancedResultEntity' agg_cluster: type: boolean original_cluster_size: type: integer cluster_size: type: integer GeoNamesFilter: type: array items: $ref: '#/components/schemas/GeoNamesEntity' description: > Filters articles by geographic locations using structured GeoNames data. All location criteria within an object must be met (internal `AND`). Multiple objects are combined using the `geonames_operator` parameter. For detailed information, see [GeoNames filtering](/local-news-api/guides-and-concepts/geonames-filtering). example: - name: New York City country: US feature_class: A - name: San Francisco admin1: name: California localization_score: min: 7 GeoNamesOperator: type: string enum: - AND - OR default: AND description: > The operator to combine multiple `geonames` objects. If `AND`, all geonames objects must match. If `OR`, at least one geonames object must match. example: AND Lang: oneOf: - type: string - type: array items: type: string description: > The language(s) of the search. The only accepted format is the two-letter [ISO 639-1](https://en.wikipedia.org/wiki/ISO_639-1) code. To select multiple languages, use a comma-separated string or an array of strings. To learn more, see [Enumerated parameters > Language](https://www.newscatcherapi.com/docs/news-api/api-reference/enumerated-parameters#language-lang-and-not-lang). example: - en - es Countries: oneOf: - type: string - type: array items: type: string description: > The countries where the news publisher is located. The accepted format is the two-letter [ISO 3166-1 alpha-2](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) code. To select multiple countries, use a comma-separated string or an array of strings. To learn more, see [Enumerated parameters > Country](https://www.newscatcherapi.com/docs/news-api/api-reference/enumerated-parameters#country-country-and-not-country). example: - US - CA Sources: oneOf: - type: string - type: array items: type: string description: > One or more news sources to narrow down the search. The format must be a domain URL. Subdomains, such as `finance.yahoo.com`, are also acceptable. To specify multiple sources, use a comma-separated string or an array of strings. example: - nytimes.com - theguardian.com NotSources: oneOf: - type: string - type: array items: type: string description: > The news sources to exclude from the search. To exclude multiple sources, use a comma-separated string or an array of strings. example: - cnn.com - wsj.com ParentUrl: oneOf: - type: string - type: array items: type: string description: > The categorical URL(s) to filter your search. To filter your search by multiple categorical URLs, use a comma-separated string or an array of strings. example: - wsj.com/politics - wsj.com/tech IsPaidContent: type: boolean description: > Filters articles by content completeness. If false, returns only articles for which full-text content is publicly available. If true, returns all indexed articles, including those where only partial content is publicly available (e.g., headlines, summaries, or preview paragraphs from paywalled sources). **Note**: NewsCatcher indexes content that is publicly accessible and available for crawling in accordance with publisher access controls (e.g., robots.txt and similar mechanisms). For paywalled sources, only content that publishers make publicly available (such as headlines, summaries, or preview text) is indexed. NewsCatcher does not bypass paywalls, authentication systems, or other technical access restrictions. example: false Page: type: integer minimum: 1 default: 1 description: > The page number to scroll through the results. This parameter is used to paginate: scroll through results because one API response cannot return more than 1000 articles. example: 2 PageSize: type: integer minimum: 1 maximum: 1000 default: 100 description: | The number of articles to return per page. Range: `1` to `1000`. example: 100 WordCountMin: type: integer minimum: 0 description: > The minimum number of words an article must contain. To be used for avoiding articles with small content. example: 300 WordCountMax: type: integer minimum: 0 description: > The maximum number of words an article can contain. To be used for avoiding articles with large content. example: 1000 ClusteringEnabled: type: boolean default: false description: > If true, groups similar articles into clusters and returns clustered results. If false, returns individual articles without clustering. To learn more, see [Clustering news articles](https://www.newscatcherapi.com/docs/news-api/guides-and-concepts/clustering-news-articles). example: true Theme: oneOf: - type: string - type: array items: type: string description: > Filters articles based on their general topic, as determined by NLP analysis. To select multiple themes, use a comma-separated string or an array of strings. To learn more, see [NLP features](https://www.newscatcherapi.com/docs/news-api/guides-and-concepts/nlp-features). Available options: `Business`, `Economics`, `Entertainment`, `Finance`, `Health`, `Politics`, `Science`, `Sports`, `Tech`, `Crime`, `Financial Crime`, `Lifestyle`, `Automotive`, `Travel`, `Weather`, `General`. example: - Business - Finance PerEntityName: type: string description: > Filters articles that mention specific person names, as identified by NLP analysis. - To specify multiple names, use `AND`, `OR`, `NOT` operators, and `\"` escape literals for exact matches. - To search in translations, combine with the translation options of the `search_in` parameter (e.g., `title_content_translated`). To learn more, see [Search by entity](https://www.newscatcherapi.com/docs/news-api/how-to/search-by-entity). example: '"Elon Musk" OR "Jeff Bezos"' LocEntityName: type: string description: > Filters articles that mention specific location names, as identified by NLP analysis. - To specify multiple locations, use `AND`, `OR`, `NOT` operators, and `\"` escape literals for exact matches. - To search in translations, combine with the translation options of the `search_in` parameter (e.g., `title_content_translated`). To learn more, see [Search by entity](https://www.newscatcherapi.com/docs/news-api/how-to/search-by-entity). example: '"San Francisco" OR "New York City"' MiscEntityName: type: string description: > Filters articles that mention other named entities not falling under person, organization, or location categories. Includes events, nationalities, products, works of art, and more. - To specify multiple entities, use `AND`, `OR`, `NOT` operators, and `\"` escape literals for exact matches. - To search in translations, combine with the translation options of the `search_in` parameter (e.g., `title_content_translated`). To learn more, see [Search by entity](https://www.newscatcherapi.com/docs/news-api/how-to/search-by-entity). example: AWS OR "Microsoft Azure" OrgEntityName: type: string description: > Filters articles that mention specific organization names, as identified by NLP analysis. - To specify multiple organizations, use `AND`, `OR`, `NOT` operators, and `\"` escape literals for exact matches. - To search in translations, combine with the translation options of the `search_in` parameter (e.g., `title_content_translated`). To learn more, see [Search by entity](https://www.newscatcherapi.com/docs/news-api/how-to/search-by-entity). example: '"Apple Inc" OR Microsoft' TitleSentimentMin: type: number format: float minimum: -1 maximum: 1 description: > Filters articles based on the minimum sentiment score of their titles. Range is `-1.0` to `1.0`, where: - Negative values indicate negative sentiment. - Positive values indicate positive sentiment. - Values close to 0 indicate neutral sentiment. To learn more, see [NLP features](https://www.newscatcherapi.com/docs/news-api/guides-and-concepts/nlp-features). example: -0.5 TitleSentimentMax: type: number format: float minimum: -1 maximum: 1 description: > Filters articles based on the maximum sentiment score of their titles. Range is `-1.0` to `1.0`, where: - Negative values indicate negative sentiment. - Positive values indicate positive sentiment. - Values close to 0 indicate neutral sentiment. To learn more, see [NLP features](https://www.newscatcherapi.com/docs/news-api/guides-and-concepts/nlp-features). example: 0.5 ContentSentimentMin: type: number format: float minimum: -1 maximum: 1 description: > Filters articles based on the minimum sentiment score of their content. Range is `-1.0` to `1.0`, where: - Negative values indicate negative sentiment. - Positive values indicate positive sentiment. - Values close to 0 indicate neutral sentiment. To learn more, see [NLP features](https://www.newscatcherapi.com/docs/news-api/guides-and-concepts/nlp-features). example: -0.5 ContentSentimentMax: type: number format: float minimum: -1 maximum: 1 description: > Filters articles based on the maximum sentiment score of their content. Range is `-1.0` to `1.0`, where: - Negative values indicate negative sentiment. - Positive values indicate positive sentiment. - Values close to 0 indicate neutral sentiment. To learn more, see [NLP features](https://www.newscatcherapi.com/docs/news-api/guides-and-concepts/nlp-features). example: 0.5 IncludeTranslationFields: type: boolean default: false description: > If true, includes English translation fields in the response (`title_translated_en`, `content_translated_en`, and NLP translation fields). If false, excludes translation fields. example: true BaseArticleEntity: title: Article Result description: >- The data model representing the commont properties of the article object in the search results. Required fields are always non-null. Optional fields may be `null`/`undefined` if data extraction is unsuccessful. type: object required: - id - title - link - content - domain_url - published_date_precision - published_date - is_opinion - rank properties: id: type: string description: The unique identifier for the article. score: type: number format: float description: The relevance score of the article. title: type: string description: The title of the article. author: type: string description: The primary author of the article. link: type: string description: The URL link to the article. description: type: string description: A brief description of the article. media: type: string description: >- The URL of the media associated with the article, typically an image. content: type: string description: The full content of the article. authors: type: array items: type: string description: A list of authors of the article. published_date: type: string format: date-time description: The date and time the article was published. published_date_precision: type: string description: The precision of the published date. updated_date: type: string format: date-time description: The date and time the article was last updated. updated_date_precision: type: string description: The precision of the updated date. is_opinion: type: boolean description: Indicates if the article is an opinion piece. twitter_account: type: string nullable: true description: The Twitter account associated with the article. Can be `null`. domain_url: type: string description: The domain URL of the article's source. parent_url: type: string description: >- The parent URL of the article, typically representing the homepage of the source. word_count: type: integer description: The word count of the article. rank: type: integer description: The rank of the article's source. country: type: string description: The country code where the article was published. rights: type: string description: The rights information for the article, typically the domain name. language: type: string description: The language code in which the article is written. nlp: $ref: '#/components/schemas/NlpDataEntity' paid_content: type: boolean description: >- Indicates whether the source labels the article as paywalled or requiring a subscription for full access. title_translated_en: type: string description: > English translation of the article title. Available when using the `search_in` parameter with the `title_translated` option or by setting the `include_translation_fields` parameter to `true`. nullable: true content_translated_en: type: string description: > English translation of the article content. Available when using the `search_in` parameter with the `content_translated` option or by setting the `include_translation_fields` parameter to `true`. nullable: true GeoNamesResponseEntity: type: object description: > Represents a geographic location identified in an article using GeoNames structured data, including detection confidence and localization scores. required: - name - detection_methods properties: geonames_id: type: string description: | The unique GeoNames identifier for the location. example: '5128581' name: type: string description: | The canonical name of the location from GeoNames database. example: New York City country: type: string description: | Two-letter ISO 3166-1 alpha-2 country code. example: US admin1: allOf: - $ref: '#/components/schemas/GeoNamesLocationAdminEntity' description: | First-order administrative division (e.g., state, province, region). admin2: allOf: - $ref: '#/components/schemas/GeoNamesLocationAdminEntity' description: | Second-order administrative division (e.g., county, department). admin3: allOf: - $ref: '#/components/schemas/GeoNamesLocationAdminEntity' description: | Third-order administrative division (e.g., township, borough). admin4: allOf: - $ref: '#/components/schemas/GeoNamesLocationAdminEntity' description: > Fourth-order administrative division (smallest administrative units). coordinates: allOf: - $ref: '#/components/schemas/Coordinates' feature_class: type: string description: > GeoNames feature class (A: Administrative, H: Hydrographic, L: Area, P: Populated places, etc.). example: P feature_code: type: string description: | Specific GeoNames feature code (e.g., PPL for populated place). example: PPL detection_methods: $ref: '#/components/schemas/DetectionMethods' reason: type: string description: > Explanation of why this location was identified in the article context. example: >- New York City is mentioned as the location of the Icahn School of Medicine. localization_score: type: number format: float minimum: 0 maximum: 10 description: > Geographic focus score (0-10) indicating how locally relevant the article is to this location. - 10: Hyper-local with clear local impact - 7-9: Regional relevance - 4-6: Subnational relevance - 1-3: National relevance only - 0: No local relevance example: 10 confidence_score: type: number format: float minimum: 0 maximum: 10 description: | Model confidence score (0-10) in location identification accuracy. - 10: Certain match - 7-9: High confidence - 4-6: Medium confidence - 1-3: Low confidence - 0: Uncertain/not relevant example: 10 ClusterArticleAdvancedResultEntity: title: Cluster Article Result (Advanced) allOf: - $ref: '#/components/schemas/ArticleAdvancedResultEntity' - type: object required: - cluster_id - cluster_rank properties: cluster_id: type: string cluster_rank: type: integer GeoNamesEntity: type: object description: > A single geographic location filter using GeoNames structured data. All provided fields within this object are combined with `AND` logic. properties: geonames_id: type: string nullable: true description: | The unique GeoNames identifier for exact location matching. example: '5128581' name: type: string nullable: true description: > The location name to search in articles. Use leading minus `-` to exclude names (e.g., `-Boston`). Supports wildcard `*` for partial matching when `enable_wildcard` is `true`. When the `search_with_alt_names` parameter is `true`, search in both canonical and alternative names from GeoNames database. example: New York City country: type: string nullable: true description: > Two-letter [ISO 3166-1 alpha-2](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) country code. To learn more, see [Enumerated parameters > Country](https://www.newscatcherapi.com/docs/news-api/api-reference/enumerated-parameters#country-country-and-not-country). example: US admin1: allOf: - $ref: '#/components/schemas/GeoNamesLocationAdminEntity' description: > First-order administrative division filter (e.g., states in US, provinces in Canada, regions in Italy). example: name: California code: CA geonames_id: '5332921' admin2: allOf: - $ref: '#/components/schemas/GeoNamesLocationAdminEntity' description: > Second-order administrative division filter (e.g., counties in the US, departments in France). example: name: Los Angeles County geonames_id: '5368361' admin3: allOf: - $ref: '#/components/schemas/GeoNamesLocationAdminEntity' description: > Third-order administrative division filter (e.g., townships, boroughs, smaller regional divisions). example: name: Manhattan geonames_id: '5125771' admin4: allOf: - $ref: '#/components/schemas/GeoNamesLocationAdminEntity' description: > Fourth-order administrative division filter (smallest administrative units). example: name: Downtown lat: type: object nullable: true description: The latitude range to filter by. Can be `null`. properties: min: type: number format: float minimum: -90 maximum: 90 description: Minimum latitude (inclusive). max: type: number format: float minimum: -90 maximum: 90 description: Maximum latitude (inclusive). example: min: 37 max: 38.5 lon: type: object nullable: true description: The longitude range to filter by. Can be `null`. properties: min: type: number format: float minimum: -180 maximum: 180 description: Minimum longitude (inclusive). max: type: number format: float minimum: -180 maximum: 180 description: Maximum longitude (inclusive). example: min: -123 max: -121.5 feature_class: type: string nullable: true description: | GeoNames feature class. Main classes: - `A`: Administrative - `H`: Hydrographic - `L`: Area - `P`: Populated places - `R`: Roads/rail - `S`: Spots/buildings - `T`: Topography - `U`: Undersea - `V`: Vegetation example: A feature_code: type: string nullable: true description: > Specific GeoNames feature code (e.g., `PPL` for populated place, `PPLA` for administrative seat). Supports wildcards. example: PPL detection_methods: $ref: '#/components/schemas/DetectionMethods' localization_score: allOf: - $ref: '#/components/schemas/RangeModel' description: > Filter by geographic focus score (0-10): - 10: Hyper-local — specific town or neighborhood named with clear local impact - 7–9: Regional — nearby city, metro, or administrative region mentioned with some local detail - 4–6: Subnational — province/state-level reference; town may be named but with limited context - 1–3: National or broader — only national relevance; town appears only in passing - 0: None — no mention or not relevant to the location confidence_score: allOf: - $ref: '#/components/schemas/RangeModel' description: > Filter by model's confidence in location relevance (0-10): - 10: Certain — Clear, unambiguous match; location is definitely relevant - 7–9: High — Strong indications of relevance, but not absolute certainty - 4–6: Medium — Some evidence or indirect relevance, but inconclusive - 1–3: Low — Weak signal or unlikely relevance - 0: Certain Not — Confident the location is not mentioned or relevant search_with_alt_names: type: boolean default: false description: > If true, expands location search to alternative names, such as abbreviations, local language names, historical names, and other variants stored in the GeoNames database. For example, `"NYC"` finds articles about `"New York City"`. If false, searches only in canonical location names. **Note**: This setting affects all location names within the `geonames` object, including the `name` field and all administrative-level names (`admin1.name`, `admin2.name`, etc.). example: true enable_wildcard: type: boolean default: false description: > If true, enables wildcard matching using `*` for partial matching location names. If false, requires exact matching. **Note**: This setting affects all location names within the `geonames` object, including the `name` field and all administrative-level names (`admin1.name`, `admin2.name`, etc.). example: false NlpDataEntity: type: object description: Natural Language Processing data for the article. properties: theme: type: array items: type: string description: The themes or categories identified in the article. summary: type: string description: A brief AI-generated summary of the article content. sentiment: $ref: '#/components/schemas/SentimentScores' new_embedding: type: array items: type: number format: float description: > A dense 1024-dimensional vector representation of the article content, generated using the [multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) model. **Note**: The `new_embedding` field is only available in the `v3_local_news_nlp_embeddings` subscription plan. ner_PER: allOf: - $ref: '#/components/schemas/NamedEntityList' description: Named Entity Recognition for person entities (individuals' names). ner_ORG: allOf: - $ref: '#/components/schemas/NamedEntityList' description: >- Named Entity Recognition for organization entities (company names, institutions). ner_MISC: allOf: - $ref: '#/components/schemas/NamedEntityList' description: >- Named Entity Recognition for miscellaneous entities (events, nationalities, products). ner_LOC: allOf: - $ref: '#/components/schemas/NamedEntityList' description: >- Named Entity Recognition for location entities (cities, countries, geographic features). translation_ner_PER: allOf: - $ref: '#/components/schemas/NamedEntityList' description: > Named Entity Recognition for person entities (individuals' names) extracted from the English translation of the article. translation_ner_ORG: allOf: - $ref: '#/components/schemas/NamedEntityList' description: > Named Entity Recognition for organization entities (company names, institutions) extracted from the English translation of the article. translation_ner_MISC: allOf: - $ref: '#/components/schemas/NamedEntityList' description: > Named Entity Recognition for miscellaneous entities (events, nationalities, products) extracted from the English translation of the article. translation_ner_LOC: allOf: - $ref: '#/components/schemas/NamedEntityList' description: > Named Entity Recognition for location entities (cities, countries, geographic features) extracted from the English translation of the article. GeoNamesLocationAdminEntity: type: object properties: geonames_id: type: string description: GeoNames ID for the administrative division. name: type: string description: > Administrative division name. Use leading minus `-` to exclude the name. code: type: string description: Administrative division code. Coordinates: type: object description: Geographic coordinates for a location. properties: lat: type: number format: float nullable: true minimum: -90 maximum: 90 description: The latitude coordinate. lon: type: number format: float nullable: true minimum: -180 maximum: 180 description: The longitude coordinate. example: lat: 40.71427 lon: -74.00597 DetectionMethods: type: array items: type: string enum: - dedicated_source - local_section - regional_source - standard_format - proximity_mention - ai_extracted description: > The location detection methods to filter results by: - `dedicated_source`: Identifies locations based on sources exclusively covering a specific location. - `local_section`: Identifies locations through location-specific sections within larger publications. - `regional_source`: Identifies locations using regional context from state-level publications. - `standard_format`: Identifies locations written in standard formats like "City, State" or "City, County". - `proximity_mention`: Identifies cities and states mentioned within 15 words of each other. - `ai_extracted`: Identifies locations through AI-based content analysis. Requires AI Extraction plan. For detailed information, see [Location detection methods](/local-news-api/guides-and-concepts/location-detection-methods). example: - dedicated_source - proximity_mention - ai_extracted RangeModel: type: object description: Numeric range filter with minimum and/or maximum values (inclusive). properties: min: type: number minimum: 0 maximum: 10 description: Minimum value (inclusive). max: type: number minimum: 0 maximum: 10 description: Maximum value (inclusive). example: min: 7 max: 10 SentimentScores: type: object description: Sentiment scores for the article's title and content. properties: title: type: number format: float minimum: -1 maximum: 1 description: The sentiment score for the article title (-1.0 to 1.0). content: type: number format: float minimum: -1 maximum: 1 description: The sentiment score for the article content (-1.0 to 1.0). NamedEntityList: type: array description: A list of named entities identified in the article. items: type: object properties: entity_name: type: string description: The name of the entity identified in the article. count: type: integer description: The number of times this entity appears in the article. securitySchemes: ApiKeyAuth: type: apiKey in: header name: x-api-token description: > API Key to authenticate requests. To access the API, include your API key in the `x-api-token` header. To obtain your API key, complete the [form](https://www.newscatcherapi.com/book-a-demo) or contact us directly. ````