clean-web-scraper 2.2.1 → 2.3.0

package/README.md

@@ -13,6 +13,7 @@ A powerful Node.js web scraper that extracts clean, readable content from websit
 - 🎯 No duplicate page visits
 - 📊 Generates JSONL output file for ML training
 - 📊 AI-friendly clean text and csv output (perfect for LLM fine-tuning!)
+- 📊 Rich metadata extraction including:
 
 ## 🛠️ Prerequisites
 
@@ -44,6 +45,7 @@ const WebScraper = require('clean-web-scraper');
 
 const scraper = new WebScraper({
   baseURL: 'https://example.com',       // Required: The website to scrape
+  startURL: 'https://example.com/blog', // Optional: Custom starting URL
   excludeList: ['/admin', '/private'],  // Optional: Paths to exclude
   exactExcludeList: ['/specific-page'], // Optional: Exact URLs to exclude
   scrapResultPath: './dataset',         // Required: Where to save the content
@@ -72,26 +74,17 @@ Your AI-ready content is saved in a clean, structured format:
 
 ```bash
 dataset/
-├── decolonizepalestine.com
-│   ├── faq.json
-│   ├── faq.txt
-│   ├── intro
-│   │   ├── bds-101.json
-│   │   ├── bds-101.txt
-│   ├── myth
-│   │   ├── a-land-without-a-people-for-a-people-without-a-land.json
-│   │   ├── a-land-without-a-people-for-a-people-without-a-land.txt
-│   └── rainbow-washing
-│       ├── bluewashing.json
-│       ├── bluewashing.txt
-├── texts
-│   ├── 1.txt
-│   ├── 2.txt
-│   ├── 3.txt
-│   ├── 4.txt
-│   └── 5.txt
-├── train.csv
-└── train.jsonl
+├── example.com/
+│   ├── page1.txt         # Clean text content
+│   ├── page1.json        # Full metadata
+│   ├── blog/
+│   │   ├── post1.txt
+│   │   ├── post1.json
+│   ├── texts/           # Numbered text files
+│   │   ├── 1.txt
+│   │   ├── 2.txt
+│   ├── train.jsonl      # Combined content
+│   └── train.csv        # Clean text in CSV format
 ```
 
 ## 🤖 AI/LLM Training Ready

package/example-usage.js

@@ -1,28 +1,62 @@
 const WebScraper = require( "./src/WebScraper" );
 
-// Configuration
-const baseURL = "https://decolonizepalestine.com";
-const scrapResultPath = "./dataset";
-const excludeList = [
-	"https://decolonizepalestine.com/cdn-cgi",
-	"https://decolonizepalestine.com/introduction-to-palestine",
-	"https://decolonizepalestine.com/myths",
-	"https://decolonizepalestine.com/reading-list",
-	"https://decolonizepalestine.com/support-us"
-];
-const exactExcludeList = [
-	"https://decolonizepalestine.com/rainbow-washing",
-	"https://decolonizepalestine.com/"
-]
-
-// Initialize scraper with all available options
-const scraper = new WebScraper({
-	baseURL,
-	scrapResultPath,
-	excludeList,
-	exactExcludeList,
-	jsonlPath: "./dataset/train.jsonl",
-	textOutputPath: "./dataset/texts",
-	csvPath: "./dataset/train.csv"
-});
-scraper.start();
+
+async function khameneiIrFreePalestineTag ()
+{
+	// 1
+	// https://english.khamenei.ir/Opinions/FreePalestine
+	// https://english.khamenei.ir/page/search.xhtml?topicid=0&period=0&q=FreePalestine&pageSize=100#
+	const scraper = new WebScraper({
+		baseURL: "https://english.khamenei.ir/news",
+		startURL: "https://english.khamenei.ir/page/search.xhtml?topicid=0&period=0&q=FreePalestine&pageSize=100#",
+		excludeList: [
+		],
+		exactExcludeList: [
+		],
+		scrapResultPath: "./dataset/khamenei-ir-free-palestine-tag",
+		jsonlPath: "./dataset/khamenei-ir-free-palestine-tag/train.jsonl",
+		textOutputPath: "./dataset/khamenei-ir-free-palestine-tag/texts",
+		csvPath: "./dataset/khamenei-ir-free-palestine-tag/train.csv"
+	});
+	await scraper.start();
+}
+
+// decolonizepalestine
+async function decolonizepalestine ()
+{
+	// 2
+	// https://decolonizepalestine.com
+	const scraper = new WebScraper({
+		baseURL: "https://decolonizepalestine.com",
+		excludeList: [
+			"https://decolonizepalestine.com/cdn-cgi",
+			"https://decolonizepalestine.com/introduction-to-palestine",
+			"https://decolonizepalestine.com/myths",
+			"https://decolonizepalestine.com/reading-list",
+			"https://decolonizepalestine.com/support-us"
+		],
+		exactExcludeList: [
+			"https://decolonizepalestine.com/rainbow-washing",
+			"https://decolonizepalestine.com/"
+		],
+		scrapResultPath: "./dataset/decolonizepalestine",
+		jsonlPath: "./dataset/decolonizepalestine/train.jsonl",
+		textOutputPath: "./dataset/decolonizepalestine/texts",
+		csvPath: "./dataset/decolonizepalestine/train.csv"
+	});
+	await scraper.start();
+}
+
+void async function main ()
+{
+	await khameneiIrFreePalestineTag();
+	// await decolonizepalestine();
+
+
+	// 3
+	// https://bdsmovement.net
+
+	// 4
+	// https://electronicintifada.net/
+}()
+

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "clean-web-scraper",
-  "version": "2.2.1",
+  "version": "2.3.0",
   "main": "main.js",
   "scripts": {
     "start": "node main.js",

package/src/WebScraper.js

@@ -9,6 +9,7 @@ class WebScraper
 {
 	constructor ({
 		baseURL,
+		startURL,
 		excludeList,
 		exactExcludeList,
 		scrapResultPath = "./dataset",
@@ -18,6 +19,7 @@ class WebScraper
 	})
 	{
 		this.baseURL = baseURL;
+		this.startURL = startURL || baseURL;
 		this.scrapResultPath = path.join( scrapResultPath, baseURL.replace( /^(https?:\/\/)?(www\.)?/, "" ).replace( /\/$/, "" ) );
 		this.jsonlPath = jsonlPath || path.join( this.scrapResultPath, "train.jsonl" );
 		this.textOutputPath = textOutputPath || path.join( this.scrapResultPath, "texts" );
@@ -25,14 +27,13 @@ class WebScraper
 		this.visited = new Set();
 		this.excludeList = new Set( excludeList );
 		this.exactExcludeList = this.normalizeExcludeList( exactExcludeList );
-		this.processedContent = []; // Add this line
+		this.allProcessedContent = []; // Add this line
 		this.createOutputDirectory();
 	}
 
 	async start ()
 	{
-		this.visited.add( this.baseURL );
-		await this.fetchPage( this.baseURL );
+		await this.fetchPage( this.startURL );
 		this.createJSONLFile();
 		this.saveNumberedTextFiles();
 		this.createCSVFile();
@@ -41,20 +42,22 @@ class WebScraper
 
 	async fetchPage ( url )
 	{
+		this.visited.add( url );
 		try
 		{
-			const { data } = await axios.get( url );
+			const { data, headers } = await axios.get( url );
 			const dom = new JSDOM( data, { url });
+			const { document } = dom.window;
 
-			// Only save if the URL is not excluded
 			if ( !this.isExcluded( url ) )
 			{
-				const reader = new Readability( dom.window.document, { charThreshold: 500, nbTopCandidates: 20 });
+				const reader = new Readability( document, { charThreshold: 500, nbTopCandidates: 20 });
 				const article = reader.parse();
 
 				if ( article )
 				{
-					this.saveArticle( url, article.textContent );
+					const metadata = this.metadataextractor( url, document, headers );
+					this.saveArticle( url, article.textContent, metadata );
 				}
 				else
 				{
@@ -67,7 +70,6 @@ class WebScraper
 			{
 				if ( !this.visited.has( link ) )
 				{
-					this.visited.add( link );
 					await this.fetchPage( link );
 				}
 			}
@@ -87,6 +89,10 @@ class WebScraper
 		while ( ( match = regex.exec( data ) ) !== null )
 		{
 			let href = match[2];
+			if ( href.startsWith( "/" ) )
+			{
+				href = new URL( href, this.baseURL ).href
+			}
 			if ( href.endsWith( "/" ) )
 			{
 				href = href.slice( 0, -1 );
@@ -95,21 +101,17 @@ class WebScraper
 			{
 				links.add( href );
 			}
-			else if ( href.startsWith( "/" ) )
-			{
-				links.add( new URL( href, this.baseURL ).href );
-			}
 		}
-
 		return links;
 	}
 
-	saveArticle ( url, content )
+	saveArticle ( url, content, metadata )
 	{
 		const processedContent = this.processContent( content );
 
-		this.processedContent.push({
-			text: processedContent.trim()
+		this.allProcessedContent.push({
+			text: processedContent.trim(),
+			metadata
 		});
 
 		let urlPath = new URL( url ).pathname;
@@ -120,14 +122,6 @@ class WebScraper
 		const filePath = path.join( __dirname, this.scrapResultPath, urlPath );
 		const dir = path.dirname( filePath );
 
-		// Create metadata object
-		const metadata = {
-			url,
-			dateScraped: new Date().toISOString(),
-			contentLength: processedContent.length,
-			fileName: `${path.basename( filePath )}.txt`
-		};
-
 		// Create directory if it doesn't exist
 		fs.mkdirSync( dir, { recursive: true });
 
@@ -145,7 +139,7 @@ class WebScraper
 	{
 		const writeStream = fs.createWriteStream( path.join( __dirname, this.jsonlPath ) );
 
-		for ( const content of this.processedContent )
+		for ( const content of this.allProcessedContent )
 		{
 			const jsonLine = `${JSON.stringify( content )}\n`;
 			writeStream.write( jsonLine );
@@ -161,7 +155,7 @@ class WebScraper
 
 		writeStream.write( "text\n" );
 
-		for ( const content of this.processedContent )
+		for ( const content of this.allProcessedContent )
 		{
 			const escapedText = content.text.replace( /"/g, "\"\"" );
 			const csvLine = `"${escapedText}"\n`;
@@ -174,7 +168,7 @@ class WebScraper
 
 	saveNumberedTextFiles ()
 	{
-		this.processedContent.forEach( ( content, index ) =>
+		this.allProcessedContent.forEach( ( content, index ) =>
 		{
 			const fileName = `${index + 1}.txt`;
 			const filePath = path.join( __dirname, this.textOutputPath, fileName );
@@ -205,6 +199,29 @@ class WebScraper
 		return processed;
 	}
 
+	metadataextractor ( url, document, headers )
+	{
+		return {
+			url,
+			title: document.title,
+			description: document.querySelector( "meta[name=\"description\"]" )?.content,
+			keywords: document.querySelector( "meta[name=\"keywords\"]" )?.content,
+			author: document.querySelector( "meta[name=\"author\"]" )?.content,
+			lastModified: headers["last-modified"],
+			contentType: headers["content-type"],
+			contentLength: headers["content-length"],
+			language: document.documentElement.lang || document.querySelector( "html" )?.getAttribute( "lang" ),
+			canonicalUrl: document.querySelector( "link[rel=\"canonical\"]" )?.href,
+			ogTags: {
+				title: document.querySelector( "meta[property=\"og:title\"]" )?.content,
+				description: document.querySelector( "meta[property=\"og:description\"]" )?.content,
+				image: document.querySelector( "meta[property=\"og:image\"]" )?.content,
+				type: document.querySelector( "meta[property=\"og:type\"]" )?.content
+			},
+			dateScraped: new Date().toISOString()
+		};
+	}
+
 	normalizeExcludeList ( list )
 	{
 		const normalizedSet = new Set();