Python BeautifulSoup: Extract Paragraphs by Title from Local HTML File

This code demonstrates how to use Python's BeautifulSoup library to extract paragraphs associated with specific headings (h1-h6) from a local HTML file.

from bs4 import BeautifulSoup

def retrieve_paragraphs_by_title(html):
    soup = BeautifulSoup(html, 'html.parser')

    paragraphs = []
    for title in soup.find_all(['h1', 'h2', 'h3', 'h4', 'h5', 'h6']):
        paragraph_text = ''
        for sibling in title.find_next_siblings():
            if sibling.name.startswith('h'):
                break
            elif sibling.name == 'p':
                paragraph_text += sibling.get_text()
        paragraphs.append((title.get_text(), paragraph_text.strip()))

    return paragraphs

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

# Process the HTML file
result = retrieve_paragraphs_by_title(html)

# Print the paragraphs
for title, paragraph in result:
    print('Title:', title)
    print('Paragraph:', paragraph)
    print()

To modify the code to process the local HTML file 'index.html', you can use the open() function to read the file and pass its contents to the retrieve_paragraphs_by_title() function. Make sure to replace 'index.html' with the actual file path if it's in a different location.