content_script.js

// This script is injected into the page to extract its main content.

// We check if Readability is available. If not, this script was likely injected
// without its dependency, which is an error condition we can't recover from.
if (typeof Readability === 'undefined') {
    // eslint-disable-next-line no-alert
    alert('Error: Readability library not found. The extension cannot proceed.');
    // In a real-world scenario, you'd want more robust error handling,
    // but for this example, an alert is sufficient to indicate a problem.
} else {
    /*
     * We are cloning the document element because Readability.js can modify
     * the DOM, and we don't want to break the original page.
     */
    const documentClone = document.cloneNode(true);
    const reader = new Readability(documentClone);
    const article = reader.parse();

    /*
     * The 'article' object contains the extracted content.
     * - title: The article title
     * - content: An HTML string of the main content
     * - textContent: A string of the main content, stripped of HTML
     * - length: The length of the text content
     *
     * We'll send the most useful parts back to our background script.
     */
    if (article) {
        chrome.runtime.sendMessage({
            type: 'CONTENT_PARSED',
            payload: {
                title: article.title,
                textContent: article.textContent,
            },
        });
    } else {
        chrome.runtime.sendMessage({
            type: 'PARSING_FAILED'
        });
    }
}