refactor: exports

nerdstep · nerdstep · commit 32c38faca10e · 2025-06-18T07:15:29.000-07:00
diff --git a/README.md b/README.md
@@ -37,16 +37,52 @@ bun add recipe-scrapers-js
 import { getScraper } from 'recipe-scrapers-js'
 
 const html = `<html>The html to scrape...</html>`
+const url = 'https://allrecipes.com/recipe/example'
 
 // Get a scraper for a specific URL
 // This function will throw if a scraper does not exist.
-const scraper = getScraper(html, 'https://allrecipes.com/recipe/example')
-
+const MyScraper = getScraper(url)
+const scraper = new MyScraper(html, url, /* { ...options } */)
 const recipe = await scraper.toObject()
-  
+
 console.log(recipe)
 ```
 
+### Options
+
+```typescript
+interface ScraperOptions {
+  /**
+   * Additional extractors to be used by the scraper.
+   * These extractors will be added to the default set of extractors.
+   * Extractors are applied according to their priority.
+   * Higher priority extractors will run first.
+   * @default []
+   */
+  extraExtractors?: ExtractorPlugin[]
+  /**
+   * Additional post-processors to be used by the scraper.
+   * These post-processors will be added to the default set of post-processors.
+   * Post-processors are applied after all extractors have run.
+   * Post-processors are also applied according to their priority.
+   * Higher priority post-processors will run first.
+   * @default []
+   */
+  extraPostProcessors?: PostProcessorPlugin[]
+  /**
+   * Whether link scraping is enabled.
+   * @default false
+   */
+  linksEnabled?: boolean
+  /**
+   * Logging level for the scraper.
+   * This controls the verbosity of logs produced by the scraper.
+   * @default LogLevel.Warn
+   */
+  logLevel?: LogLevel
+}
+```
+
 ## Supported Sites
 
 This library supports recipe extraction from various popular cooking websites. The scraper automatically detects the appropriate parser based on the URL.
diff --git a/package.json b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "recipe-scrapers-js",
-  "version": "0.1.0-alpha.2",
+  "version": "0.1.0-alpha.3",
   "license": "MIT",
   "description": "A recipe scrapers library",
   "author": {
diff --git a/src/index.ts b/src/index.ts
@@ -1,29 +1,21 @@
 import { scrapers } from './scrapers/_index'
+import { getHostName } from './utils'
 
 export * from '@/types/recipe.interface'
 export * from '@/types/scraper.interface'
+export * from './abstract-extractor-plugin'
+export * from './abstract-postprocessor-plugin'
+export * from './logger'
+export { scrapers }
 
 /**
- * Extracts the host name from a URL string.
+ * Returns a scraper class for the given URL, if implemented.
  */
-function getHostName(urlString: string) {
-  try {
-    const url = new URL(urlString)
-    return url.host
-  } catch {
-    throw new Error(`Invalid URL: ${urlString}`)
-  }
-}
-
-/**
- * Returns a scraper instance for the given URL, if implemented.
- */
-export function getScraper(html: string, url: string) {
+export function getScraper(url: string) {
   const hostName = getHostName(url)
 
   if (scrapers[hostName]) {
-    const ScraperClass = scrapers[hostName]
-    return new ScraperClass(html, url)
+    return scrapers[hostName]
   }
 
   throw new Error(
diff --git a/src/utils/index.ts b/src/utils/index.ts
@@ -24,3 +24,15 @@ export function isPlainObject(
 export function isString(value: unknown): value is string {
   return typeof value === 'string'
 }
+
+/**
+ * Extracts the host name from a URL string.
+ */
+export function getHostName(value: string) {
+  try {
+    const url = new URL(value)
+    return url.host
+  } catch {
+    throw new Error(`Invalid URL: ${value}`)
+  }
+}

Original file line number	Diff line number	Diff line change
`@@ -1,6 +1,6 @@`
`1`	`1`	`{`
`2`	`2`	`"name": "recipe-scrapers-js",`
`3`		`- "version": "0.1.0-alpha.2",`
	`3`	`+ "version": "0.1.0-alpha.3",`
`4`	`4`	`"license": "MIT",`
`5`	`5`	`"description": "A recipe scrapers library",`
`6`	`6`	`"author": {`