## Cleaning Content Instructions

### Overview
This document outlines the procedure for cleaning web page content by removing non-semantic elements to reveal the main content within a webpage.

### Steps to Clean Content
1. **Identify Non-Semantic Elements:**  
   - **Navigation menus and links**  
   - **Cookie banners and consent notices**  
   - **Advertisements**  
   - **Sidebar content**  
   - **Footer links and content**  
   - **Social media buttons/links**  
   - **Breadcrumb navigation**  
   - **Header links**  
   - **Newsletter signups**  
   - **Comment sections**  
   - **Related article suggestions**

2. **Preserve Semantic Content:**  
   - **Main article or page content**  
   - **Headings and subheadings**  
   - **Lists, tables, structured data**  
   - **Code blocks and technical content**  
   - **Image references**  
   - **Inline links**

### Example of Cleaned Content

#### Sample Title  
This is an example of the main content that would be preserved.

- Bullet point one  
- Bullet point two

```python  
print("Hello, World!")  
```

### Final Checks
- Ensure all non-semantic elements are removed.
- Confirm that the main content is coherent and retains its original meaning.
