modify_html_for_pos.py

import os
import shutil
from pathlib import Path
import re
from bs4 import BeautifulSoup


def process_html_file(file_path, output_path):
    with open(file_path, 'r', encoding='utf-8') as file:
        content = file.read()

    # Remove lines containing 'Prediction'
    content = re.sub(r'<h3>Prediction:.*?</h3>\n?', '', content, flags=re.DOTALL)

    # Parse the HTML content
    soup = BeautifulSoup(content, 'html.parser')

    # Remove tables with 'verification_result' column
    for table in soup.find_all('table'):
        if table.find('td', string='verification_result'):
            table.decompose()

    # Write the modified content
    with open(output_path, 'w', encoding='utf-8') as file:
        file.write(str(soup))


def process_directory(input_dir, output_dir):
    for root, dirs, files in os.walk(input_dir):
        for file in files:
            if file.endswith('.html'):
                input_path = Path(root) / file
                relative_path = input_path.relative_to(input_dir)
                output_path = Path(output_dir) / relative_path

                output_path.parent.mkdir(parents=True, exist_ok=True)
                process_html_file(input_path, output_path)


# Define input and output directories
input_directory = "htmls_POS"
output_directory = "htmls_POS_mod2"

# Process the files
process_directory(input_directory, output_directory)

print("Processing complete for POS. Modified files are in the output directory.")