Last active
April 14, 2023 18:59
-
-
Save alexjyong/dd54aab7c7596d2e45a5f9a348ff6df4 to your computer and use it in GitHub Desktop.
Converts an html page with image links to an html page with base64 links in python
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys | |
import base64 | |
import requests | |
from bs4 import BeautifulSoup | |
def convert_images_to_base64(input_file, output_file): | |
with open(input_file, 'r', encoding='utf-8') as f: | |
html_content = f.read() | |
soup = BeautifulSoup(html_content, 'html.parser') | |
for img in soup.find_all('img'): | |
src = img['src'] | |
if src.startswith('http'): | |
response = requests.get(src) | |
img_data = response.content | |
else: | |
# Handle local image paths | |
with open(src, 'rb') as f: | |
img_data = f.read() | |
img_b64 = base64.b64encode(img_data).decode() | |
img['src'] = 'data:image/png;base64,' + img_b64 | |
# Prettify the HTML output | |
pretty_html = soup.prettify() | |
with open(output_file, 'w', encoding='utf-8') as f: | |
f.write(pretty_html) | |
if __name__ == '__main__': | |
if len(sys.argv) <= 2: | |
print("Usage: python3 doStuff.py input_file output_file") | |
sys.exit(1) | |
output_file = None | |
input_file = sys.argv[1] | |
if len(sys.argv) >= 3: | |
output_file = sys.argv[2] | |
if output_file is None: | |
output_file = "pretty_index.html" | |
# Example usage: | |
convert_images_to_base64(input_file, output_file) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment