html_to_json_converter.py

import json
import sys
from bs4 import BeautifulSoup

def html_to_json(html_content):
    soup = BeautifulSoup(html_content, 'html.parser')
    
    # 1. Parse tables if they exist
    tables_data = []
    for table_idx, table in enumerate(soup.find_all('table')):
        headers = [th.get_text(strip=True) for th in table.find_all('th')]
        rows = []
        for tr in table.find_all('tr'):
            cells = tr.find_all('td')
            if cells:
                row_data = {}
                for cell_idx, cell in enumerate(cells):
                    header = headers[cell_idx] if cell_idx < len(headers) else f"column_{cell_idx}"
                    row_data[header] = cell.get_text(strip=True)
                rows.append(row_data)
        tables_data.append({
            "table_index": table_idx,
            "headers": headers,
            "rows": rows
        })
        
    # 2. Parse general hierarchical text elements (headings and paragraphs)
    hierarchical_content = []
    current_section = {"section": "Root", "content": []}
    
    for element in soup.find_all(['h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'p', 'li']):
        text = element.get_text(strip=True)
        if not text:
            continue
            
        if element.name.startswith('h'):
            if current_section["content"] or current_section["section"] != "Root":
                hierarchical_content.append(current_section)
            current_section = {
                "section": text,
                "level": int(element.name[1]),
                "content": []
            }
        else:
            current_section["content"].append({
                "type": element.name,
                "text": text
            })
            
    if current_section["content"] or current_section["section"] != "Root":
        hierarchical_content.append(current_section)
        
    # 3. Combine result
    result = {
        "title": soup.title.string if soup.title else "Untitled Document",
        "tables": tables_data,
        "document_structure": hierarchical_content
    }
    return result

if __name__ == "__main__":
    # Example usage:
    # python html_to_json_converter.py input.html output.json
    if len(sys.argv) < 3:
        print("Usage: python html_to_json_converter.py <input_html_path> <output_json_path>")
        sys.exit(1)
        
    input_path = sys.argv[1]
    output_path = sys.argv[2]
    
    try:
        with open(input_path, 'r', encoding='utf-8') as f:
            html = f.read()
            
        json_data = html_to_json(html)
        
        with open(output_path, 'w', encoding='utf-8') as f:
            json.dump(json_data, f, indent=2, ensure_ascii=False)
            
        print(f"Successfully converted '{input_path}' to '{output_path}'!")
    except Exception as e:
        print(f"Error during conversion: {e}")