import sys from bs4 import BeautifulSoup def remove_html_tags(input_file, output_file): # Read the HTML content from the input file with open(input_file, 'r', encoding='utf-8') as f: html_content = f.read() # Use BeautifulSoup to parse and extract text soup = BeautifulSoup(html_content, 'html.parser') text = soup.get_text() # Write the plain text to the output file with open(output_file, 'w', encoding='utf-8') as f: f.write(text) if __name__ == "__main__": if len(sys.argv) != 3: print("Usage: python remove_html_tags.py ") else: input_file = sys.argv[1] output_file = sys.argv[2] remove_html_tags(input_file, output_file) print(f"HTML tags removed. Output written to {output_file}")