recipe-scrapers-js 0.1.0-alpha.3 → 0.1.0-alpha.4

package/dist/index.js

@@ -18,11 +18,13 @@ function isString(value) {
 	return typeof value === "string";
 }
 /**
-* Extracts the host name from a URL string.
+* Extracts the host name from a URL string
+* and removes 'www.' prefix if present.
+* Throws an error if the input is not a valid URL.
 */
 function getHostName(value) {
 	try {
-		const url = new URL(value);
+		const url = new URL(value.replace("www.", ""));
 		return url.host;
 	} catch {
 		throw new Error(`Invalid URL: ${value}`);
@@ -280,7 +282,7 @@ var HtmlStripperPlugin = class extends PostProcessorPlugin {
 		return ingredients;
 	}
 	stripHtml(html) {
-		return html.replace(/<[^>]*>/g, "").replace(/&amp;/g, "&").replace(/&lt;/g, "<").replace(/&gt;/g, ">").replace(/&quot;/g, "\"").replace(/&#34;/g, "\"").replace(/&#39;/g, "'").trim();
+		return html.replace(/<[^>]*>/g, "").replace(/&amp;/g, "&").replace(/&nbsp;/g, " ").replace(/&lt;/g, "<").replace(/&gt;/g, ">").replace(/&quot;/g, "\"").replace(/&#34;/g, "\"").replace(/&#39;/g, "'").trim();
 	}
 };
 
@@ -1017,31 +1019,31 @@ var AbstractScraper = class {
 		const instance = this.constructor;
 		if (this.recipeData) return this.recipeData;
 		this.recipeData = {
-			host: instance.host(),
-			siteName: await this.extract("siteName"),
 			author: await this.extract("author"),
-			title: await this.extract("title"),
-			image: await this.extract("image"),
 			canonicalUrl: this.canonicalUrl(),
-			language: this.language(),
-			links: this.links(),
+			category: await this.extract("category"),
+			cookTime: await this.extract("cookTime"),
+			cookingMethod: await this.extract("cookingMethod"),
+			cuisine: await this.extract("cuisine"),
 			description: await this.extract("description"),
+			dietaryRestrictions: await this.extract("dietaryRestrictions"),
+			equipment: await this.extract("equipment"),
+			host: instance.host(),
+			image: await this.extract("image"),
 			ingredients: await this.extract("ingredients"),
 			instructions: await this.extract("instructions"),
-			category: await this.extract("category"),
-			yields: await this.extract("yields"),
-			totalTime: await this.extract("totalTime"),
-			cookTime: await this.extract("cookTime"),
+			keywords: await this.extract("keywords"),
+			language: this.language(),
+			links: this.links(),
+			nutrients: await this.extract("nutrients"),
 			prepTime: await this.extract("prepTime"),
-			cuisine: await this.extract("cuisine"),
-			cookingMethod: await this.extract("cookingMethod"),
 			ratings: await this.extract("ratings"),
 			ratingsCount: await this.extract("ratingsCount"),
-			equipment: await this.extract("equipment"),
 			reviews: await this.extract("reviews"),
-			nutrients: await this.extract("nutrients"),
-			dietaryRestrictions: await this.extract("dietaryRestrictions"),
-			keywords: await this.extract("keywords")
+			siteName: await this.extract("siteName"),
+			title: await this.extract("title"),
+			totalTime: await this.extract("totalTime"),
+			yields: await this.extract("yields")
 		};
 		return this.recipeData;
 	}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "recipe-scrapers-js",
-  "version": "0.1.0-alpha.3",
+  "version": "0.1.0-alpha.4",
   "license": "MIT",
   "description": "A recipe scrapers library",
   "author": {

package/src/abstract-scraper.ts

@@ -159,31 +159,31 @@ export abstract class AbstractScraper {
     }
 
     this.recipeData = {
-      host: instance.host(),
-      siteName: await this.extract('siteName'),
       author: await this.extract('author'),
-      title: await this.extract('title'),
-      image: await this.extract('image'),
       canonicalUrl: this.canonicalUrl(),
-      language: this.language(),
-      links: this.links(),
+      category: await this.extract('category'),
+      cookTime: await this.extract('cookTime'),
+      cookingMethod: await this.extract('cookingMethod'),
+      cuisine: await this.extract('cuisine'),
       description: await this.extract('description'),
+      dietaryRestrictions: await this.extract('dietaryRestrictions'),
+      equipment: await this.extract('equipment'),
+      host: instance.host(),
+      image: await this.extract('image'),
       ingredients: await this.extract('ingredients'),
       instructions: await this.extract('instructions'),
-      category: await this.extract('category'),
-      yields: await this.extract('yields'),
-      totalTime: await this.extract('totalTime'),
-      cookTime: await this.extract('cookTime'),
+      keywords: await this.extract('keywords'),
+      language: this.language(),
+      links: this.links(),
+      nutrients: await this.extract('nutrients'),
       prepTime: await this.extract('prepTime'),
-      cuisine: await this.extract('cuisine'),
-      cookingMethod: await this.extract('cookingMethod'),
       ratings: await this.extract('ratings'),
       ratingsCount: await this.extract('ratingsCount'),
-      equipment: await this.extract('equipment'),
       reviews: await this.extract('reviews'),
-      nutrients: await this.extract('nutrients'),
-      dietaryRestrictions: await this.extract('dietaryRestrictions'),
-      keywords: await this.extract('keywords'),
+      siteName: await this.extract('siteName'),
+      title: await this.extract('title'),
+      totalTime: await this.extract('totalTime'),
+      yields: await this.extract('yields'),
     }
 
     return this.recipeData

package/src/plugins/__tests__/html-stripper.processor.test.ts

@@ -20,6 +20,9 @@ describe('HtmlStripperPlugin', () => {
     expect(plugin.process('title', '<span>Test &lt;tag&gt;</span>')).toBe(
       'Test <tag>',
     )
+    expect(plugin.process('description', '<span>Hello&nbsp;World</span>')).toBe(
+      'Hello World',
+    )
   })
 
   it('strips HTML from instructions Set<string>', () => {

package/src/plugins/html-stripper.processor.ts

@@ -69,6 +69,7 @@ export class HtmlStripperPlugin extends PostProcessorPlugin {
     return html
       .replace(/<[^>]*>/g, '') // Remove HTML tags
       .replace(/&amp;/g, '&') // Decode common entities
+      .replace(/&nbsp;/g, ' ')
       .replace(/&lt;/g, '<')
       .replace(/&gt;/g, '>')
       .replace(/&quot;/g, '"')

package/src/utils/__tests__/index.test.ts

@@ -1,5 +1,6 @@
 import { describe, expect, it } from 'bun:test'
 import {
+  getHostName,
   isDefined,
   isFunction,
   isNumber,
@@ -92,3 +93,36 @@ describe('isString', () => {
     expect(isString({})).toBe(false)
   })
 })
+describe('getHostName', () => {
+  it('should return the host for a standard URL', () => {
+    expect(getHostName('https://www.example.com/path')).toBe('example.com')
+  })
+
+  it('should return the host for a URL with a subdomain', () => {
+    expect(getHostName('http://sub.domain.co.uk/page?q=1')).toBe(
+      'sub.domain.co.uk',
+    )
+  })
+
+  it('should return the host for a URL without a path', () => {
+    expect(getHostName('https://anothersite.org')).toBe('anothersite.org')
+  })
+
+  it('should throw an error for an invalid URL string', () => {
+    const invalidUrl = 'not a url'
+    expect(() => getHostName(invalidUrl)).toThrow(
+      new Error(`Invalid URL: ${invalidUrl}`),
+    )
+  })
+
+  it('should throw an error for an empty string', () => {
+    expect(() => getHostName('')).toThrow(new Error('Invalid URL: '))
+  })
+
+  it('should throw an error for a string that looks like a host but lacks a protocol', () => {
+    const urlWithoutProtocol = 'example.com'
+    expect(() => getHostName(urlWithoutProtocol)).toThrow(
+      new Error(`Invalid URL: ${urlWithoutProtocol}`),
+    )
+  })
+})

package/src/utils/index.ts

@@ -26,11 +26,13 @@ export function isString(value: unknown): value is string {
 }
 
 /**
- * Extracts the host name from a URL string.
+ * Extracts the host name from a URL string
+ * and removes 'www.' prefix if present.
+ * Throws an error if the input is not a valid URL.
  */
 export function getHostName(value: string) {
   try {
-    const url = new URL(value)
+    const url = new URL(value.replace('www.', ''))
     return url.host
   } catch {
     throw new Error(`Invalid URL: ${value}`)