sampleFAQScript.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

"""
This script extracts all FAQ questions and their corresponding answers from
the REDCap.html file and saves them to a text file. It uses the
BeautifulSoup library to parse the HTML.
"""

from bs4 import BeautifulSoup

def extract_qa_pairs_from_html(file_path="REDCap.html"):
    """
    Parses an HTML file and extracts pairs of questions and answers.

    Args:
        file_path (str): The path to the HTML file.

    Returns:
        list: A list of dictionaries, where each dictionary contains
              a 'question' and an 'answer' key.
    """
    qa_pairs = []
    try:
        with open(file_path, 'r', encoding='utf-8') as f:
            html_content = f.read()

        soup = BeautifulSoup(html_content, 'html.parser')

        # Find all the main container divs for each Q&A pair.
        # The class 'panel panel-default card' consistently wraps one question and one answer.
        qa_containers = soup.find_all('div', class_='panel panel-default card')

        if not qa_containers:
            print("Warning: Could not find any Q&A containers. The HTML structure might have changed.")
            return []

        # Loop through each container to find the question and answer within it.
        for container in qa_containers:
            question_tag = container.find('a', class_='accordion-toggle')
            answer_tag = container.find('div', class_='panel-body')

            # Ensure both a question and an answer were found before proceeding.
            if question_tag and answer_tag:
                question_text = question_tag.get_text(strip=True)
                answer_text = answer_tag.get_text(strip=True)
                
                qa_pairs.append({
                    'question': question_text,
                    'answer': answer_text
                })

        return qa_pairs

    except FileNotFoundError:
        print(f"Error: The file '{file_path}' was not found.")
        return []
    except Exception as e:
        print(f"An unexpected error occurred: {e}")
        return []

def save_qa_to_file(qa_pairs, output_file="sample_data.txt"):
    """
    Saves a list of question-answer pairs to a text file.

    Args:
        qa_pairs (list): A list of dictionaries containing questions and answers.
        output_file (str): The name of the file to save the data to.
    """
    try:
        with open(output_file, 'w', encoding='utf-8') as f:
            for i, pair in enumerate(qa_pairs, 1):
                f.write(f"Q{i}: {pair['question']}\n")
                f.write(f"A{i}: {pair['answer']}\n")
                f.write("-" * 20 + "\n\n") # Separator for readability
        print(f"\n✅ Success! {len(qa_pairs)} Q&A pairs have been saved to '{output_file}'.")
    except IOError as e:
        print(f"\n❌ Error: Could not write to the file '{output_file}'. Reason: {e}")


if __name__ == "__main__":
    # 1. Extract the Q&A pairs from the HTML file.
    faq_data = extract_qa_pairs_from_html()

    # 2. If data was found, save it to a text file.
    if faq_data:
        save_qa_to_file(faq_data)
    else:
        print("No Q&A pairs were extracted, so no file was created.")