html2csv

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# Filename: html2csv.py
# Version: 1.0.0
# Author: Jeoi Reqi

"""
Description:
This script converts an HTML file (.html) to a CSV file (.csv).
It uses BeautifulSoup to parse the HTML content and extracts table rows, writing them to a CSV file.

Requirements:
- Python 3.x
- BeautifulSoup library (install using: pip install beautifulsoup4)

Usage:
1. Save this script as 'html2csv.py'.
2. Ensure your HTML file ('example.html') is in the same directory as the script.
3. Install the BeautifulSoup library using the command: 'pip install beautifulsoup4'
4. Run the script.
5. The converted CSV file ('html2csv.csv') will be generated in the same directory.

Note: Adjust the 'html_filename' and 'csv_filename' variables in the script as needed.
"""
import csv
from bs4 import BeautifulSoup

def html_to_csv(html_filename, csv_filename):
    with open(html_filename, 'r') as htmlfile, open(csv_filename, 'w', newline='') as csvfile:
        csvwriter = csv.writer(csvfile)
        soup = BeautifulSoup(htmlfile, 'html.parser')
        for row in soup.find_all('tr'):
            csvwriter.writerow([col.get_text(strip=True) for col in row.find_all(['td', 'th'])])

if __name__ == "__main__":
    html_filename = 'example.html'
    csv_filename = 'html2csv.csv'
    html_to_csv(html_filename, csv_filename)
    print(f"Converted '{html_filename}' to '{csv_filename}'.")