Extract and Convert HTML Links to Absolute URLs

This function extracts all links from the given HTML content and converts them to absolute URLs. It uses the BeautifulSoup library to parse HTML and the requests library to handle relative URLs.

Technology Stack : BeautifulSoup, requests

Code Type : Python Function

Code Difficulty : Intermediate

                
                    
def extract_links_from_html(html_content, base_url):
    from bs4 import BeautifulSoup
    import requests

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

    # Extract all the anchor tags from the soup
    links = soup.find_all('a')

    # Create a list to store the absolute URLs
    absolute_urls = []

    # Iterate through each link and append the absolute URL to the list
    for link in links:
        href = link.get('href')
        if href and not href.startswith('#'):
            # Use requests to get the absolute URL if it's a relative link
            if href.startswith('/'):
                absolute_url = requests.get(base_url + href).url
            else:
                absolute_url = href
            absolute_urls.append(absolute_url)

    return absolute_urls