added a readCSV function and updated docs

Author: Lanny-MacMillan

README.md

@@ -4,39 +4,211 @@ description: API parameters, returns, examples.
 sidebar_position: 4
 ---
 
-### `functionName(param1, param2)`
+## WebScraper Class
 
-Description of function.
+### `new WebScraper(options?: ScraperOptions)`
+
+Creates a new instance of the `WebScraper` class.
+
+**Parameters:**
+
+- `options` (optional) - `ScraperOptions` - An object containing configuration
+  options for the scraper.
+
+  - `usePuppeteer` - `boolean` (optional) - Whether to use Puppeteer for
+    JavaScript-rendered pages. Default: `true`.
+  - `throttle` - `number` (optional) - Delay in milliseconds between requests.
+    Default: `1000`.
+  - `rules` - `Record<string, string>` - CSS selectors defining data extraction
+    rules.
+
+**Returns:**
+
+- A new instance of `WebScraper`.
+
+**Example:**
+
+```typescript
+import { WebScraper } from 'simple-web-scraper';
+
+const scraper = new WebScraper({
+  usePuppeteer: true,
+  rules: { title: 'h1', content: 'p' },
+});
+```
+
+---
+
+## Methods
+
+### `scrape(url: string): Promise<Record<string, any>>`
+
+Scrapes the given URL based on the configured options.
+
+**Parameters:**
+
+- `url` - `string` - The webpage URL to scrape.
+
+**Returns:**
+
+- `Promise<Record<string, any>>` - The extracted data as an object.
+
+**Example:**
+
+```typescript
+const data = await scraper.scrape('https://example.com');
+console.log(data);
+```
+
+---
+
+### `exportToJSON(data: any, filePath: string): void`
+
+Exports the given data to a JSON file.
+
+**Parameters:**
+
+- `data` - `any` - The data to be exported.
+- `filePath` - `string` - The path where the JSON file should be saved.
+
+**Returns:**
+
+- `void`
+
+**Example:**
+
+```typescript
+import { exportToJSON } from 'simple-web-scraper';
+
+const data = { name: 'Example', value: 42 };
+exportToJSON(data, 'output.json');
+```
+
+---
+
+### `exportToCSV(data: any | any[], filePath: string): void`
+
+Exports the given data to a CSV file.
 
 **Parameters:**
 
-- `param1` - Type - Description
-- `param2` - Type - Description
+- `data` - `any | any[]` - The data to be exported.
+- `filePath` - `string` - The path where the CSV file should be saved.
 
 **Returns:**
 
-- Return Type - Description
+- `void`
 
-**Examples:**
+**Example:**
 
-```js
-functionName(arg1, arg2);
+```typescript
+import { exportToCSV } from 'simple-web-scraper';
+
+const data = [
+  { name: 'Example 1', value: 42 },
+  { name: 'Example 2', value: 99 },
+];
+exportToCSV(data, 'output.csv');
 ```
 
-```js
-const { greet } = require('./packageName');
+---
+
+### `readCSV(filePath: string): Promise<any[]>`
+
+Reads a CSV file and converts it to JSON.
+
+**Parameters:**
 
-console.log(greet('Charlie')); // Output: Hello, Charlie!
+- `filePath` - `string` - The path to the CSV file.
+
+**Returns:**
+
+- `Promise<any[]>` - The parsed CSV data as an array of objects.
+
+**Example:**
+
+```typescript
+import { readCSV } from 'simple-web-scraper';
+
+(async () => {
+  try {
+    const data = await readCSV('output.csv');
+    console.log(data);
+  } catch (error) {
+    console.error('Error reading CSV:', error);
+  }
+})();
 ```
 
-```js
-import React from 'react';
-import { greet } from './packageName';
+---
+
+## Backend Example
 
-const Greeting: React.FC<{ name: string }> = ({ name }) => {
-  return <h1>{greet(name)}</h1>;
-};
+This example demonstrates how to use `simple-web-scraper` in a Node.js backend:
 
-export default Greeting;
+```typescript
+import express from 'express';
+import { WebScraper, exportToJSON, exportToCSV, readCSV } from 'simple-web-scraper';
 
+const app = express();
+const scraper = new WebScraper({
+  usePuppeteer: true,
+  rules: {
+    fullHTML: 'html', // Entire page HTML
+    title: 'head > title', // Page title
+    description: 'meta[name="description"]', // Meta description
+    keywords: 'meta[name="keywords"]', // Meta keywords
+    favicon: 'link[rel="icon"]', // Favicon URL
+    mainHeading: 'h1', // First H1 heading
+    allHeadings: 'h1, h2, h3, h4, h5, h6', // All headings on the page
+    firstParagraph: 'p', // First paragraph
+    allParagraphs: 'p', // All paragraphs on the page
+    links: 'a', // All links on the page
+    images: 'img', // All image URLs
+    imageAlts: 'img', // Alternative text for images
+    videos: 'video, iframe[src*="youtube.com"], iframe[src*="vimeo.com"]', // Video sources
+    tables: 'table', // Capture table elements
+    tableData: 'td', // Capture table cells
+    lists: 'ul, ol', // Capture all lists
+    listItems: 'li', // Capture all list items
+    scripts: 'script', // JavaScript file sources
+    stylesheets: 'link[rel="stylesheet"]', // External CSS files
+    structuredData: 'script[type="application/ld+json"]', // JSON-LD structured data
+    socialLinks:
+      'a[href*="facebook.com"], a[href*="twitter.com"], a[href*="linkedin.com"], a[href*="instagram.com"]', // Social media links
+    author: 'meta[name="author"]', // Author meta tag
+    publishDate: 'meta[property="article:published_time"], time', // Publish date
+    modifiedDate: 'meta[property="article:modified_time"]', // Last modified date
+    canonicalURL: 'link[rel="canonical"]', // Canonical URL
+    openGraphTitle: 'meta[property="og:title"]', // OpenGraph title
+    openGraphDescription: 'meta[property="og:description"]', // OpenGraph description
+    openGraphImage: 'meta[property="og:image"]', // OpenGraph image
+    twitterCard: 'meta[name="twitter:card"]', // Twitter card type
+    twitterTitle: 'meta[name="twitter:title"]', // Twitter title
+    twitterDescription: 'meta[name="twitter:description"]', // Twitter description
+    twitterImage: 'meta[name="twitter:image"]', // Twitter image
+  },
+});
+
+app.get('/scrape-example', async (req, res) => {
+  try {
+    const url = 'https://github.com/The-Node-Forge';
+    const data = await scraper.scrape(url);
+
+    exportToJSON(data, 'output.json'); // export JSON
+    exportToCSV(data, 'output.csv'); // export CSV
+
+    const readData = await readCSV(data); // Read CSV
+
+    res.status(200).json({ success: true, readData });
+  } catch (error) {
+    res.status(500).json({ success: false, error: error.message });
+  }
+});
 ```
+
+---
+
+## Contributing
+
+Contributions are welcome! Please submit issues or pull requests on GitHub.

docs/docs/API_REFERENCE.md

@@ -4,10 +4,10 @@ description: A detailed changelog.
 sidebar_position: 5
 ---
 
-### v1.0.0 - YYYY-MM-DD
+### v1.0.0 - 2025-02-28
 
 - Initial release
 
-### v1.0.1 - YYYY-MM-DD
+<!-- ### v1.0.1 - YYYY-MM-DD
 
-- Bug fix
+- Bug fix -->

docs/docs/CHANGELOG.md

@@ -1,18 +1,54 @@
 ---
 title: Installation
-description: Installation details.
+description: How to install and set up Simple Web Scraper.
 sidebar_position: 2
 ---
 
-### Prerequisites
+## 📌 Prerequisites
 
-- Node.js version X.X.X
-- npm or yarn
+Before installing, ensure you have the following:
 
-### Installation Steps
+- **Node.js** (Version `16.x` or higher recommended)
+- **npm** (included with Node.js) or **Yarn**
+
+## 📥 Installation
+
+You can install `simple-web-scraper` using npm or Yarn:
+
+### **Using npm**
+
+```sh
+npm install simple-web-scraper
+```
+
+### **Using Yarn**
 
 ```sh
-npm install package-name
+yarn add simple-web-scraper
+```
+
+## 📦 Importing the Package
+
+After installation, you can import it into your project:
+
+### **For ES Modules (Recommended)**
+
+```typescript
+import { WebScraper, exportToJSON, exportToCSV, readCSV } from 'simple-web-scraper';
 ```
 
-For more details, see [USAGE.md](USAGE.md).
+### **For CommonJS (Node.js Default)**
+
+```javascript
+const {
+  WebScraper,
+  exportToJSON,
+  exportToCSV,
+  readCSV,
+} = require('simple-web-scraper');
+```
+
+## 🚀 Next Steps
+
+After installation, check out the [Usage Guide](USAGE.md) for how to integrate
+`simple-web-scraper` into your project.

docs/docs/INSTALLATION.md

@@ -1,22 +1,68 @@
 ---
 title: Usage
-description: Basic example and config.
+description: Basic examples and configuration for Simple Web Scraper.
 sidebar_position: 3
 ---
 
-### Basic Example
+## 📌 Basic Example
 
-```js
-const pkg = require('package-name');
-pkg.doSomething();
+You can use `simple-web-scraper` with either ES Modules or CommonJS.
+
+### **Using ES Modules (Recommended)**
+
+```typescript
+import { WebScraper } from 'simple-web-scraper';
+
+const scraper = new WebScraper({
+  usePuppeteer: true,
+  rules: { title: 'h1', content: 'p' },
+});
+
+(async () => {
+  const data = await scraper.scrape('https://example.com');
+  console.log(data);
+})();
 ```
 
-### Configuration
+### **Using CommonJS (Node.js Default)**
+
+```javascript
+const { WebScraper } = require('simple-web-scraper');
+
+const scraper = new WebScraper({
+  usePuppeteer: true,
+  rules: { title: 'h1', content: 'p' },
+});
+
+(async () => {
+  const data = await scraper.scrape('https://example.com');
+  console.log(data);
+})();
+```
+
+## ⚙️ Configuration Options
+
+You can customize the scraper's behavior using the following options:
 
 ```json
 {
-  "option": "value"
+  "usePuppeteer": true,
+  "throttle": 1000,
+  "rules": {
+    "title": "h1",
+    "content": "p"
+  }
 }
 ```
 
-For API details, see [API_REFERENCE.md](API_REFERENCE.md).
+### **Option Details**
+
+| Option         | Type                     | Description                                                          |
+| -------------- | ------------------------ | -------------------------------------------------------------------- |
+| `usePuppeteer` | `boolean` (optional)     | Whether to use Puppeteer for JavaScript-heavy pages. Default: `true` |
+| `throttle`     | `number` (optional)      | Delay in milliseconds between requests. Default: `1000`              |
+| `rules`        | `Record<string, string>` | CSS selectors defining the data to extract                           |
+
+## 📖 More Details
+
+For full API details, see [API_REFERENCE.md](API_REFERENCE.md).