Python Script to Extract Heading and Body Text from HTML

Here's the Python code that fulfills the given requirement:

from bs4 import BeautifulSoup

# Read the HTML file
with open("index.html", "r") as file:
    html_data = file.read()

# Parse the HTML data using BeautifulSoup
soup = BeautifulSoup(html_data, "html.parser")

# Find the desired title
desired_title = "Specific Title"  # Replace with the desired title
title_element = soup.find(lambda tag: tag.name in ["h1", "h2", "h3", "h4", "h5", "h6"] and tag.get_text(strip=True) == desired_title)

if title_element:
    # Find all the body text within <p> tags under the desired title
    body_text = []
    next_element = title_element.find_next_sibling()
    while next_element and next_element.name != "h1" and next_element.name != "h2" and next_element.name != "h3" and next_element.name != "h4" and next_element.name != "h5" and next_element.name != "h6":
        if next_element.name == "p":
            body_text.append(next_element.get_text(strip=True))
        next_element = next_element.find_next_sibling()

    # Print the found heading and body text
    print("Heading:", title_element.get_text(strip=True))
    print("Body Text:")
    for text in body_text:
        print(text)
else:
    print("Title not found.")

Note: Replace the value of desired_title with the specific title you want to find. Make sure the HTML file "index.html" is in the same directory as the Python script.