@hydrafetch/node-sdk 0.6.0 → 0.7.1

package/README.md

@@ -127,7 +127,7 @@ tells the model which one you meant. The same works in a plain JSON Schema with
 
 ```ts
 const { links } = await hf.map('https://example.com', { limit: 1000 });
-const docs = links.filter((url) => url.includes('/docs/'));
+const docs = links.map((l) => l.url).filter((url) => url.includes('/docs/'));
 ```
 
 `batchAndWait` and `crawlAndWait` submit a job and poll until it finishes.
@@ -166,6 +166,18 @@ const { results } = await hf.search('post-quantum TLS adoption', {
 results.forEach((r) => console.log(r.title, r.url, r.data?.markdown));
 ```
 
+## News
+
+Find recent news articles about anything, newest first, each with its outlet and publish time:
+
+```ts
+const { results } = await hf.news('acme raises funding', { timeRange: 'week', limit: 10 });
+
+results.forEach((a) => console.log(a.publishedAt, a.source, a.title, a.url));
+```
+
+A news search costs 1 credit, and one that finds nothing is free. Set `scrapeResults: true` to also read each article as clean data, at 1 extra credit per article.
+
 ## Jobs
 
 Search open jobs collected from company career sites and hiring platforms, by the words in the job title:
@@ -276,6 +288,7 @@ const hf = new Hydrafetch({
 | `markdown(url, options?)` | `string` | 1 |
 | `map(url, options?)` | `MapResult` | 1 |
 | `search(query, options?)` | `SearchResult` | 1 + 1 per scraped result |
+| `news(query, options?)` | `NewsResult` | 1 + 1 per article read; free when empty |
 | `searchJobs(query, options?)` | `OpenJob[]` | 1 per 10 jobs |
 | `hiringChanges(domains, since, options?)` | `CompanyHiringChanges[]` | 1 per company with jobs |
 | `extract(urls, options?)` | `ExtractResult<T>` | 5 per URL |

package/dist/index.cjs

@@ -235,6 +235,9 @@ var Hydrafetch = class {
   search(query, options = {}) {
     return this.request("POST", "/v1/web/search", { query, ...options });
   }
+  news(query, options = {}) {
+    return this.request("POST", "/v1/web/news", { query, ...options });
+  }
   searchJobs(query, options = {}) {
     return this.request("POST", "/v1/web/index/jobs/search", { query, ...options });
   }

package/dist/index.d.cts

@@ -67,9 +67,14 @@ interface MapOptions {
     includeSubdomains?: boolean;
     ignoreQueryParameters?: boolean;
 }
+interface MapLink {
+    url: string;
+    /** When the site's sitemap says the page last changed, or null when it does not say. */
+    lastmod: string | null;
+}
 interface MapResult {
     url: string;
-    links: string[];
+    links: MapLink[];
     count: number;
     total?: number;
     truncated?: boolean;
@@ -323,6 +328,41 @@ interface CompanyHiringChanges {
     closed: HiringChangePosting[];
     truncated: boolean;
 }
+type NewsTimeRange = 'hour' | 'day' | 'week' | 'month';
+interface NewsOptions {
+    /** Max articles to return, 1 to 50 (default 10). */
+    limit?: number;
+    /** Only articles published within this window before now (default "week"). */
+    timeRange?: NewsTimeRange;
+    /** ISO 3166 alpha-2 country code to lean results toward, like "us". */
+    country?: string;
+    /** Only articles from these sites, up to 15. */
+    includeDomains?: string[];
+    /** Drop articles from these sites, up to 15. */
+    excludeDomains?: string[];
+    /** Also read each article as clean data, 1 extra credit per article read. */
+    scrapeResults?: boolean;
+    scrapeOptions?: ScrapeOptions;
+}
+interface NewsArticle {
+    title: string;
+    /** The article's address on the publisher's own site. */
+    url: string;
+    /** The outlet that published it. */
+    source: string | null;
+    /** When it was published, ISO 8601. */
+    publishedAt: string;
+    snippet: string | null;
+    imageUrl: string | null;
+    /** The article read as clean data when scrapeResults is on, otherwise null. */
+    data: ScrapeResult | null;
+}
+interface NewsResult {
+    query: string;
+    status: 'ok' | 'no_results';
+    /** Newest first. */
+    results: NewsArticle[];
+}
 
 interface HydrafetchOptions {
     apiKey?: string;
@@ -346,6 +386,7 @@ declare class Hydrafetch {
     rateResult(input: RateResultInput): Promise<RateResultResponse>;
     map(url: string, options?: MapOptions): Promise<MapResult>;
     search(query: string, options?: SearchOptions): Promise<SearchResult>;
+    news(query: string, options?: NewsOptions): Promise<NewsResult>;
     searchJobs(query: string, options?: SearchJobsOptions): Promise<OpenJob[]>;
     hiringChanges(domains: string | string[], since: string | Date, options?: HiringChangesOptions): Promise<CompanyHiringChanges[]>;
     extract<T = unknown>(urls: string | string[], options?: ExtractOptions): Promise<ExtractResult<T>>;
@@ -387,4 +428,4 @@ declare class HydrafetchTimeoutError extends HydrafetchError {
     constructor(message: string);
 }
 
-export { type BatchOptions, type BrandOptions, type BrandResult, type CompanyHiringChanges, type CrawlOptions, type ExtractItem, type ExtractOptions, type ExtractResult, type ExtractSchema, type Format, type HiringChangePosting, type HiringChangesOptions, type HiringCounts, Hydrafetch, HydrafetchError, type HydrafetchOptions, HydrafetchTimeoutError, type ImagesResult, type JobPage, type JobPay, type JobResult, type JobStatus, type Location, type LogoResult, type MapOptions, type MapResult, type OpenJob, type PageImage, type PageMetadata, type RateResultInput, type RateResultResponse, type ResultFeedbackReason, type ResultRating, type ScrapeBase, type ScrapeContent, type ScrapeOptions, type ScrapeResult, type ScreenshotOptions, type ScreenshotResult, type SearchJobsOptions, type SearchOptions, type SearchResult, type SearchResultItem, type StyleguideOptions, type StyleguideResult, type Usage, type WaitOptions, type ZodLike };
+export { type BatchOptions, type BrandOptions, type BrandResult, type CompanyHiringChanges, type CrawlOptions, type ExtractItem, type ExtractOptions, type ExtractResult, type ExtractSchema, type Format, type HiringChangePosting, type HiringChangesOptions, type HiringCounts, Hydrafetch, HydrafetchError, type HydrafetchOptions, HydrafetchTimeoutError, type ImagesResult, type JobPage, type JobPay, type JobResult, type JobStatus, type Location, type LogoResult, type MapLink, type MapOptions, type MapResult, type NewsArticle, type NewsOptions, type NewsResult, type NewsTimeRange, type OpenJob, type PageImage, type PageMetadata, type RateResultInput, type RateResultResponse, type ResultFeedbackReason, type ResultRating, type ScrapeBase, type ScrapeContent, type ScrapeOptions, type ScrapeResult, type ScreenshotOptions, type ScreenshotResult, type SearchJobsOptions, type SearchOptions, type SearchResult, type SearchResultItem, type StyleguideOptions, type StyleguideResult, type Usage, type WaitOptions, type ZodLike };

package/dist/index.d.ts

@@ -67,9 +67,14 @@ interface MapOptions {
     includeSubdomains?: boolean;
     ignoreQueryParameters?: boolean;
 }
+interface MapLink {
+    url: string;
+    /** When the site's sitemap says the page last changed, or null when it does not say. */
+    lastmod: string | null;
+}
 interface MapResult {
     url: string;
-    links: string[];
+    links: MapLink[];
     count: number;
     total?: number;
     truncated?: boolean;
@@ -323,6 +328,41 @@ interface CompanyHiringChanges {
     closed: HiringChangePosting[];
     truncated: boolean;
 }
+type NewsTimeRange = 'hour' | 'day' | 'week' | 'month';
+interface NewsOptions {
+    /** Max articles to return, 1 to 50 (default 10). */
+    limit?: number;
+    /** Only articles published within this window before now (default "week"). */
+    timeRange?: NewsTimeRange;
+    /** ISO 3166 alpha-2 country code to lean results toward, like "us". */
+    country?: string;
+    /** Only articles from these sites, up to 15. */
+    includeDomains?: string[];
+    /** Drop articles from these sites, up to 15. */
+    excludeDomains?: string[];
+    /** Also read each article as clean data, 1 extra credit per article read. */
+    scrapeResults?: boolean;
+    scrapeOptions?: ScrapeOptions;
+}
+interface NewsArticle {
+    title: string;
+    /** The article's address on the publisher's own site. */
+    url: string;
+    /** The outlet that published it. */
+    source: string | null;
+    /** When it was published, ISO 8601. */
+    publishedAt: string;
+    snippet: string | null;
+    imageUrl: string | null;
+    /** The article read as clean data when scrapeResults is on, otherwise null. */
+    data: ScrapeResult | null;
+}
+interface NewsResult {
+    query: string;
+    status: 'ok' | 'no_results';
+    /** Newest first. */
+    results: NewsArticle[];
+}
 
 interface HydrafetchOptions {
     apiKey?: string;
@@ -346,6 +386,7 @@ declare class Hydrafetch {
     rateResult(input: RateResultInput): Promise<RateResultResponse>;
     map(url: string, options?: MapOptions): Promise<MapResult>;
     search(query: string, options?: SearchOptions): Promise<SearchResult>;
+    news(query: string, options?: NewsOptions): Promise<NewsResult>;
     searchJobs(query: string, options?: SearchJobsOptions): Promise<OpenJob[]>;
     hiringChanges(domains: string | string[], since: string | Date, options?: HiringChangesOptions): Promise<CompanyHiringChanges[]>;
     extract<T = unknown>(urls: string | string[], options?: ExtractOptions): Promise<ExtractResult<T>>;
@@ -387,4 +428,4 @@ declare class HydrafetchTimeoutError extends HydrafetchError {
     constructor(message: string);
 }
 
-export { type BatchOptions, type BrandOptions, type BrandResult, type CompanyHiringChanges, type CrawlOptions, type ExtractItem, type ExtractOptions, type ExtractResult, type ExtractSchema, type Format, type HiringChangePosting, type HiringChangesOptions, type HiringCounts, Hydrafetch, HydrafetchError, type HydrafetchOptions, HydrafetchTimeoutError, type ImagesResult, type JobPage, type JobPay, type JobResult, type JobStatus, type Location, type LogoResult, type MapOptions, type MapResult, type OpenJob, type PageImage, type PageMetadata, type RateResultInput, type RateResultResponse, type ResultFeedbackReason, type ResultRating, type ScrapeBase, type ScrapeContent, type ScrapeOptions, type ScrapeResult, type ScreenshotOptions, type ScreenshotResult, type SearchJobsOptions, type SearchOptions, type SearchResult, type SearchResultItem, type StyleguideOptions, type StyleguideResult, type Usage, type WaitOptions, type ZodLike };
+export { type BatchOptions, type BrandOptions, type BrandResult, type CompanyHiringChanges, type CrawlOptions, type ExtractItem, type ExtractOptions, type ExtractResult, type ExtractSchema, type Format, type HiringChangePosting, type HiringChangesOptions, type HiringCounts, Hydrafetch, HydrafetchError, type HydrafetchOptions, HydrafetchTimeoutError, type ImagesResult, type JobPage, type JobPay, type JobResult, type JobStatus, type Location, type LogoResult, type MapLink, type MapOptions, type MapResult, type NewsArticle, type NewsOptions, type NewsResult, type NewsTimeRange, type OpenJob, type PageImage, type PageMetadata, type RateResultInput, type RateResultResponse, type ResultFeedbackReason, type ResultRating, type ScrapeBase, type ScrapeContent, type ScrapeOptions, type ScrapeResult, type ScreenshotOptions, type ScreenshotResult, type SearchJobsOptions, type SearchOptions, type SearchResult, type SearchResultItem, type StyleguideOptions, type StyleguideResult, type Usage, type WaitOptions, type ZodLike };

package/dist/index.js

@@ -207,6 +207,9 @@ var Hydrafetch = class {
   search(query, options = {}) {
     return this.request("POST", "/v1/web/search", { query, ...options });
   }
+  news(query, options = {}) {
+    return this.request("POST", "/v1/web/news", { query, ...options });
+  }
   searchJobs(query, options = {}) {
     return this.request("POST", "/v1/web/index/jobs/search", { query, ...options });
   }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@hydrafetch/node-sdk",
-  "version": "0.6.0",
+  "version": "0.7.1",
   "description": "Official Node/TypeScript client for the Hydrafetch web data API. Turn any URL into clean Markdown and structured data.",
   "keywords": [
     "hydrafetch",