Script for converting <img> references in an Anki CSV to inline webp images.

to_webp.py

#!/usr/bin/env python3
import typer
import pandas as pd
import requests
import base64
from bs4 import BeautifulSoup
from PIL import Image
from io import BytesIO
from typing import Optional

def img_to_base64(url: str) -> str:
    response = requests.get(url)
    img = Image.open(BytesIO(response.content))
    buffered = BytesIO()
    img.save(buffered, format="WEBP")
    image_data = base64.b64encode(buffered.getvalue()).decode('utf-8')
    return f'data:image/webp;base64,{image_data}'

def convert_images_to_base64(html: Optional[str]) -> str:
    if html is None or pd.isna(html):
        return html
    soup = BeautifulSoup(html, 'html.parser')
    images = soup.find_all('img')
    
    for img in images:
        src = img['src']
        if not src.startswith('data:'):
            base64_img = img_to_base64(src)
            img['src'] = base64_img

    return str(soup)

def main(input_file: str, output_file: str):
    """
    Convert image URLs in a CSV file to base64 encoded WebP images.

    Arguments:
    input_file: Path to the input CSV file.
    output_file: Path to the output CSV file.
    """
    # Read the CSV file into a DataFrame
    df = pd.read_csv(input_file)
    
    # Remove rows where all elements are NaN
    df.dropna(how='all', inplace=True)

    # Iterate through each row and each HTML field to convert images to base64
    for index, row in df.iterrows():
        for column in ['Question', 'Answer']:
            html_content = row[column]
            html_content_with_base64 = convert_images_to_base64(html_content)
            df.at[index, column] = html_content_with_base64

    # Save the DataFrame back to a new CSV file
    df.to_csv(output_file, index=False)

    typer.echo(f"Converted images in {input_file} and saved to {output_file}")

if __name__ == "__main__":
    typer.run(main)