This Python script parses through all HTML files and replaces the external image references with embedded base64 encoded strings.

embedd-images-into-html-base64.py

# This Python script parses through all HTML files and replaces the external image references with embedded base64 encoded strings.

## create a directory
# mkdir ~/path2convert && cd ~/path2convert
# git init # optional to revert changes
# git add -A && git commit -m "Start" # optional to revert changes

## create a virtual environment
# python3 -m venv ./
# source ./bin/activate
# pip3 install beautifulsoup4 pillow
## Example: python3 embedd-images-into-html-base64.py

import os
import base64
from bs4 import BeautifulSoup
from urllib.parse import unquote

# Directory containing your HTML files
html_files_directory = os.path.expanduser('~/Downloads/paname-convert')

# Function to convert image to base64
def img_to_base64(img_path):
    with open(img_path, 'rb') as img_file:
        encoded_string = base64.b64encode(img_file.read()).decode('utf-8')
    return encoded_string

# Function to process a single HTML file
def process_html_file(file_path):
    with open(file_path, 'r', encoding='utf-8') as file:
        soup = BeautifulSoup(file, 'html.parser')

    # Find all image tags
    for img in soup.find_all('img'):
        img_src = img.get('src')
        if img_src and not img_src.startswith('data:'):  # Only process if it's not already base64
            decoded_img_src = unquote(img_src)  # Decode the URL-encoded path
            img_path = os.path.join(os.path.dirname(file_path), decoded_img_src)
            
            # Check if the image file exists
            if os.path.exists(img_path):
                mime_type = f"image/{img_path.split('.')[-1]}"
                base64_string = img_to_base64(img_path)
                img['src'] = f"data:{mime_type};base64,{base64_string}"
                print(f"Replaced image {img_src} with base64 in {file_path}")
            else:
                print(f"Image not found: {img_path}")
        else:
            print(f"Skipping image {img_src} in {file_path} (already base64 or invalid)")

    # Save the modified HTML back to the file
    with open(file_path, 'w', encoding='utf-8') as file:
        file.write(str(soup))

# Function to process all HTML files in a directory
def process_html_files_in_directory(directory):
    for root, dirs, files in os.walk(directory):
        for file in files:
            if file.endswith('.html'):
                process_html_file(os.path.join(root, file))



# Process all HTML files in the specified directory
process_html_files_in_directory(html_files_directory)

print("All HTML files have been processed and images have been embedded as Base64.")