XPath Text Extractor

Extract text from webpage using XPath with GUI
当前为 2025-03-30 提交的版本，查看最新版本。
换行
// ==UserScript==
// @name         XPath Text Extractor
// @namespace    http://tampermonkey.net/
// @version      0.1
// @description  Extract text from webpage using XPath with GUI
// @author       oovz
// @match        https://www.qidian.com/chapter/*
// @grant        none
// @license MIT
// ==/UserScript==

(function() {
    'use strict';

    // Configure your XPath here
    const TITLE_XPATH = '//div[contains(@class, "chapter-wrapper")]//div[contains(@class, "print")]//h1'; // Fill this with your XPath
    const CONTENT_XPATH = '//div[contains(@class, "chapter-wrapper")]//div[contains(@class, "print")]//main/p/span'; // Fill this with your XPath

    // Create GUI elements
    const gui = document.createElement('div');
    gui.style.cssText = `
        position: fixed;
        bottom: 20px;
        right: 20px;
        background: white;
        padding: 15px;
        border: 1px solid #ccc;
        border-radius: 5px;
        box-shadow: 0 0 10px rgba(0,0,0,0.1);
        z-index: 9999;
    `;

    const output = document.createElement('textarea');
    output.style.width = '300px';
    output.style.height = '150px';
    output.style.marginBottom = '10px';
    output.readOnly = true;

    const copyButton = document.createElement('button');
    copyButton.textContent = 'Copy Text';
    copyButton.style.display = 'block';

    // Add elements to GUI
    gui.appendChild(output);
    gui.appendChild(copyButton);
    document.body.appendChild(gui);

    // Extract text function
    function getElementsByXpath(xpath) {
        const results = [];
        const query = document.evaluate(
            xpath, 
            document, 
            null, 
            XPathResult.ORDERED_NODE_SNAPSHOT_TYPE, 
            null
        );
        
        for (let i = 0; i < query.snapshotLength; i++) {
            const node = query.snapshotItem(i);
            if (node) {
                // Get only direct text content and exclude child elements
                let directTextContent = '';
                for (let j = 0; j < node.childNodes.length; j++) {
                    const childNode = node.childNodes[j];
                    if (childNode.nodeType === Node.TEXT_NODE) {
                        directTextContent += childNode.textContent;
                    }
                }
                
                // Only trim if it's the title (preserve indentation for content)
                if (xpath === TITLE_XPATH) {
                    directTextContent = directTextContent.trim();
                    if (directTextContent) {
                        results.push(directTextContent);
                    }
                } else {
                    // For content, preserve indentation
                    if (directTextContent) {
                        results.push(directTextContent);
                    }
                }
            }
        }
        return results;
    }

    // Initial extraction
    function updateTitleOutput() {
        const elements = getElementsByXpath(TITLE_XPATH);
        return elements.join('\n');
    }

    function updateContentOutput() {
        const elements = getElementsByXpath(CONTENT_XPATH);
        return elements.join('\n');
    }

    function updateOutput() {
        const title = updateTitleOutput();
        const content = updateContentOutput();
        output.value = title ? title + '\n\n' + content : content;
    }

    // Run initial extraction
    updateOutput();

    // Add event listener for copy button
    copyButton.addEventListener('click', () => {
        output.select();
        document.execCommand('copy');
        copyButton.textContent = 'Copied!';
        setTimeout(() => {
            copyButton.textContent = 'Copy Text';
        }, 1000);
    });

    // Update when DOM changes
    const observer = new MutationObserver(updateOutput);
    observer.observe(document.body, {
        childList: true,
        subtree: true
    });
})();
欢迎访问Greasy Fork镜像
