知乎批量导出工具

Greasy Fork is available in English.
知乎批量导出工具

批量抓取知乎回答/文章/收藏夹，支持导出包含“评论区”的单页 HTML 文件。
当前为 2025-12-23 提交的版本，查看最新版本。
换行
// ==UserScript==
// @name         知乎批量导出工具
// @namespace    http://qtqz.zhihu/
// @version      3.0
// @description  批量抓取知乎回答/文章/收藏夹，支持导出包含“评论区”的单页 HTML 文件。
// @author       AI & qtqz logic
// @match        https://www.zhihu.com/people/*
// @match        https://www.zhihu.com/collection/*
// @icon         https://static.zhihu.com/heifetz/favicon.ico
// @require      https://cdn.jsdelivr.net/npm/[email protected]/dist/FileSaver.min.js
// @grant        GM_xmlhttpRequest
// @grant        GM_registerMenuCommand
// @license      MIT
// ==/UserScript==

(function () {
    'use strict';

    // --- 核心配置 ---
    const CONFIG = {
        commentLimit: 20, // 每个回答只抓取前20条评论（防止请求过多被封）
        requestDelay: 800 // 每次请求的间隔毫秒数
    };

    const STATE = {
        isRunning: false,
        items: [],
        currentType: '',
        id: '',
        cancel: false
    };

    const UI = {
        panel: null,
        logArea: null,
        progressBar: null
    };

    // --- UI 构建 ---
    function initUI() {
        const style = document.createElement('style');
        style.textContent = `
            #zbc-panel {
                position: fixed; top: 100px; right: 20px; width: 340px;
                background: #fff; box-shadow: 0 4px 12px rgba(0,0,0,0.15);
                border-radius: 8px; z-index: 9999; font-family: sans-serif;
                border: 1px solid #ebebeb; display: none;
            }
            #zbc-header {
                padding: 12px 16px; border-bottom: 1px solid #f0f0f0;
                background: #f6f6f6; border-radius: 8px 8px 0 0;
                font-weight: bold; color: #1772f6; display: flex; justify-content: space-between;
            }
            #zbc-body { padding: 16px; }
            .zbc-btn {
                display: block; width: 100%; padding: 8px; margin-bottom: 8px;
                border: 1px solid #1772f6; color: #1772f6; background: #fff;
                border-radius: 4px; cursor: pointer; text-align: center;
                transition: 0.2s;
            }
            .zbc-btn:hover { background: #eef6ff; }
            .zbc-btn:disabled { border-color: #ccc; color: #ccc; cursor: not-allowed; background: #f9f9f9;}
            .zbc-btn.primary { background: #1772f6; color: #fff; }
            .zbc-btn.primary:hover { background: #1062d6; }
            #zbc-log {
                height: 180px; overflow-y: auto; background: #f9f9f9;
                border: 1px solid #eee; padding: 8px; font-size: 12px;
                margin-bottom: 10px; color: #666; line-height: 1.4;
            }
            .zbc-progress { height: 4px; background: #eee; width: 100%; margin-bottom: 10px; }
            .zbc-progress-bar { height: 100%; background: #1772f6; width: 0%; transition: width 0.3s; }
            .zbc-close { cursor: pointer; color: #999; }
            .zbc-tip { font-size: 12px; color: #999; margin-bottom: 10px; }
        `;
        document.head.appendChild(style);

        const panel = document.createElement('div');
        panel.id = 'zbc-panel';
        panel.innerHTML = `
            <div id="zbc-header">
                <span>知乎导出助手 (含评论版)</span>
                <span class="zbc-close" onclick="document.getElementById('zbc-panel').style.display='none'">✕</span>
            </div>
            <div id="zbc-body">
                <div id="zbc-status">请进入用户主页或收藏夹页面</div>
                <div class="zbc-tip">提示：开启评论抓取会显著降低速度，每个回答仅抓取前 ${CONFIG.commentLimit} 条热评。</div>
                <div class="zbc-progress"><div class="zbc-progress-bar" id="zbc-bar"></div></div>
                <div id="zbc-log"></div>
                <button id="zbc-start" class="zbc-btn primary">开始抓取 (含评论)</button>
                <button id="zbc-stop" class="zbc-btn" disabled>停止抓取</button>
                <hr style="border:0; border-top:1px solid #eee; margin: 10px 0;">
                <button id="zbc-export-html" class="zbc-btn" disabled>💾 导出单页 HTML (含评论)</button>
                <button id="zbc-export-json" class="zbc-btn" disabled>💾 导出 JSON</button>
            </div>
        `;
        document.body.appendChild(panel);

        UI.panel = panel;
        UI.logArea = document.getElementById('zbc-log');
        UI.progressBar = document.getElementById('zbc-bar');

        document.getElementById('zbc-start').onclick = startScraping;
        document.getElementById('zbc-stop').onclick = () => { STATE.cancel = true; log('正在停止...'); };
        document.getElementById('zbc-export-html').onclick = () => exportSingleHTML();
        document.getElementById('zbc-export-json').onclick = () => exportJSON();

        const toggleBtn = document.createElement('div');
        toggleBtn.innerText = '📥';
        toggleBtn.style.cssText = 'position:fixed; bottom:20px; right:20px; width:40px; height:40px; background:#1772f6; color:#fff; border-radius:50%; text-align:center; line-height:40px; cursor:pointer; z-index:9998; box-shadow:0 2px 10px rgba(0,0,0,0.2); font-size:20px;';
        toggleBtn.onclick = () => {
            panel.style.display = panel.style.display === 'none' ? 'block' : 'none';
            detectPage();
        };
        document.body.appendChild(toggleBtn);
    }

    // --- 逻辑控制 ---

    function log(msg) {
        const p = document.createElement('div');
        p.innerText = `[${new Date().toLocaleTimeString()}] ${msg}`;
        UI.logArea.prepend(p);
    }

    function detectPage() {
        const url = window.location.href;
        const statusDiv = document.getElementById('zbc-status');

        if (url.includes('/collection/')) {
            STATE.currentType = 'collection';
            STATE.id = url.match(/collection\/(\d+)/)[1];
            statusDiv.innerText = `当前：收藏夹 (ID: ${STATE.id})`;
            return true;
        } else if (url.includes('/people/')) {
            const match = url.match(/people\/([^/]+)/);
            if(match) {
                STATE.id = match[1];
                if(url.includes('/posts') || url.includes('/articles')) {
                    STATE.currentType = 'people_articles';
                    statusDiv.innerText = `当前：用户文章 (${STATE.id})`;
                } else {
                    STATE.currentType = 'people_answers';
                    statusDiv.innerText = `当前：用户回答 (${STATE.id})`;
                }
                return true;
            }
        }
        statusDiv.innerText = '未知页面';
        return false;
    }

    async function startScraping() {
        if (!detectPage()) { alert('无法识别当前页面'); return; }

        STATE.isRunning = true;
        STATE.cancel = false;
        STATE.items = [];

        document.getElementById('zbc-start').disabled = true;
        document.getElementById('zbc-stop').disabled = false;
        toggleExportBtns(false);

        let offset = 0;
        let isEnd = false;
        const limit = 20;

        try {
            while (!isEnd && !STATE.cancel) {
                let apiUrl = '';
                if (STATE.currentType === 'collection') {
                    apiUrl = `https://www.zhihu.com/api/v4/collections/${STATE.id}/items?offset=${offset}&limit=${limit}`;
                } else if (STATE.currentType === 'people_answers') {
                    apiUrl = `https://www.zhihu.com/api/v4/members/${STATE.id}/answers?include=data%5B*%5D.is_normal%2Ccontent%2Cvoteup_count%2Ccomment_count%2Ccreated_time%2Cupdated_time&offset=${offset}&limit=${limit}&sort_by=created`;
                } else if (STATE.currentType === 'people_articles') {
                    apiUrl = `https://www.zhihu.com/api/v4/members/${STATE.id}/articles?include=data%5B*%5D.content%2Cvoteup_count%2Ccomment_count&offset=${offset}&limit=${limit}&sort_by=created`;
                }

                log(`正在请求列表 offset: ${offset}...`);
                const data = await fetchAPI(apiUrl);

                if (data.data && data.data.length > 0) {
                    // --- 核心循环：处理每个条目并抓取评论 ---
                    for (const item of data.data) {
                        if (STATE.cancel) break;

                        const realItem = item.content ? item.content : item;
                        if (!realItem) continue;

                        const processedItem = processItem(realItem);

                        // 抓取评论
                        log(`  └ 抓取评论: ${processedItem.title.slice(0, 10)}...`);
                        try {
                            const comments = await fetchComments(processedItem.id, processedItem.type);
                            processedItem.comments = comments;
                        } catch (err) {
                            log(`  (评论抓取失败，跳过)`);
                            processedItem.comments = [];
                        }

                        STATE.items.push(processedItem);

                        // 为了防止封号，每抓取一个完整的（含评论）条目，稍微休息一下
                        await sleep(CONFIG.requestDelay);
                    }

                    offset += limit;
                    isEnd = data.paging.is_end;
                    UI.progressBar.style.width = '50%';
                } else {
                    isEnd = true;
                }
            }
        } catch (e) {
            log('错误: ' + e.message);
            console.error(e);
        }

        STATE.isRunning = false;
        document.getElementById('zbc-start').disabled = false;
        document.getElementById('zbc-stop').disabled = true;
        UI.progressBar.style.width = '100%';

        if (STATE.items.length > 0) {
            log(`抓取完成！共 ${STATE.items.length} 条。`);
            toggleExportBtns(true);
        } else {
            log('未抓取到数据。');
        }
    }

    // 获取评论的 API
    function fetchComments(id, type) {
        return new Promise((resolve) => {
            // 知乎 v4 评论接口
            // type: 'answers' 或 'articles'
            const resourceType = type === 'answer' ? 'answers' : 'articles';
            const url = `https://www.zhihu.com/api/v4/${resourceType}/${id}/root_comments?order=normal&limit=${CONFIG.commentLimit}&offset=0&status=open`;

            GM_xmlhttpRequest({
                method: "GET",
                url: url,
                onload: function(response) {
                    if (response.status === 200) {
                        try {
                            const res = JSON.parse(response.responseText);
                            const comments = res.data.map(c => ({
                                author: c.author.member.name,
                                content: c.content,
                                vote_count: c.vote_count,
                                created_time: new Date(c.created_time * 1000).toLocaleString()
                            }));
                            resolve(comments);
                        } catch (e) {
                            resolve([]); // 解析失败返回空
                        }
                    } else {
                        resolve([]); // 请求失败返回空，不阻断主流程
                    }
                },
                onerror: () => resolve([])
            });
        });
    }

    function fetchAPI(url) {
        return new Promise((resolve, reject) => {
            GM_xmlhttpRequest({
                method: "GET",
                url: url,
                onload: function(response) {
                    if (response.status === 200) {
                        try {
                            resolve(JSON.parse(response.responseText));
                        } catch (e) {
                            reject(e);
                        }
                    } else {
                        reject(new Error("API Error: " + response.status));
                    }
                },
                onerror: (err) => reject(err)
            });
        });
    }

    function processItem(item) {
        let content = item.content || '';
        // 修复图片懒加载
        content = content.replace(/<img [^>]*src="[^"]+"[^>]*data-actualsrc="([^"]+)"[^>]*>/g, '<img src="$1">');
        content = content.replace(/<img [^>]*src="[^"]+"[^>]*data-original="([^"]+)"[^>]*>/g, '<img src="$1">');

        return {
            id: item.id,
            type: item.type, // 'answer' or 'article'
            title: item.question ? item.question.title : item.title,
            author: item.author.name,
            content: content,
            voteup_count: item.voteup_count,
            created_time: new Date(item.created_time * 1000).toLocaleString(),
            url: item.url.replace("api.zhihu.com", "www.zhihu.com"),
            comments: [] // 初始化为空
        };
    }

    function sleep(ms) {
        return new Promise(resolve => setTimeout(resolve, ms));
    }

    function toggleExportBtns(enable) {
        document.getElementById('zbc-export-html').disabled = !enable;
        document.getElementById('zbc-export-json').disabled = !enable;
    }

    // --- 导出功能 (单页 HTML 含评论) ---

    function exportSingleHTML() {
        log('正在生成 HTML...');
        const title = `知乎导出_${STATE.currentType}_${new Date().toISOString().slice(0,10)}`;

        let tocHtml = STATE.items.map((item, index) => {
            return `<li><a href="#item-${index}">${index + 1}. ${item.title}</a> <span style="font-size:12px;color:#999">(${item.author})</span></li>`;
        }).join('');

        let contentHtml = STATE.items.map((item, index) => {
            // 生成评论区 HTML
            let commentsHtml = '';
            if (item.comments && item.comments.length > 0) {
                const commentList = item.comments.map(c => `
                    <div class="comment-item">
                        <div class="comment-meta"><span class="comment-author">${c.author}</span> <span class="comment-time">${c.created_time}</span> <span class="comment-vote">👍 ${c.vote_count}</span></div>
                        <div class="comment-content">${c.content}</div>
                    </div>
                `).join('');
                commentsHtml = `
                    <div class="comments-section">
                        <div class="comments-title">精选评论 (${item.comments.length}条)</div>
                        ${commentList}
                    </div>
                `;
            } else {
                commentsHtml = `<div class="comments-section" style="color:#ccc;text-align:center;font-size:12px;">暂无评论或未抓取</div>`;
            }

            return `
                <div class="article-item" id="item-${index}">
                    <div class="article-header">
                        <h2><a href="${item.url}" target="_blank">${item.title}</a></h2>
                        <div class="meta">
                            作者: ${item.author} | 赞同: ${item.voteup_count} | 时间: ${item.created_time}
                        </div>
                    </div>
                    <div class="article-content">
                        ${item.content}
                    </div>
                    ${commentsHtml}
                    <div class="back-to-top"><a href="#toc">↑ 回到目录</a></div>
                    <hr class="separator">
                </div>
            `;
        }).join('');

        const finalHtml = `
<!DOCTYPE html>
<html>
<head>
    <meta charset="UTF-8">
    <title>${title}</title>
    <style>
        body { font-family: -apple-system, BlinkMacSystemFont, "Helvetica Neue", "PingFang SC", "Microsoft YaHei", sans-serif; max-width: 900px; margin: 0 auto; padding: 20px; line-height: 1.7; color: #121212; background-color: #f6f6f6; }
        .container { background: #fff; padding: 40px; border-radius: 8px; box-shadow: 0 1px 3px rgba(26,26,26,.1); }
        h1.main-title { text-align: center; margin-bottom: 30px; color: #1772f6; }
        #toc { background: #f9f9f9; padding: 20px; border-radius: 6px; margin-bottom: 40px; border: 1px solid #eee; max-height: 400px; overflow-y: auto; }
        #toc ul { list-style: none; padding: 0; }
        #toc li { margin-bottom: 8px; border-bottom: 1px dashed #eee; padding-bottom: 4px; }
        #toc a { text-decoration: none; color: #333; font-size: 14px; }
        #toc a:hover { color: #1772f6; }
        .article-item { margin-bottom: 60px; }
        .article-header h2 { margin-bottom: 10px; font-size: 22px; }
        .article-header a { text-decoration: none; color: #121212; }
        .article-header a:hover { color: #1772f6; }
        .meta { font-size: 13px; color: #8590a6; margin-bottom: 20px; }
        .article-content img { max-width: 100%; height: auto; display: block; margin: 10px auto; border-radius: 4px; cursor: zoom-in; }
        .article-content blockquote { border-left: 3px solid #dfe3eb; color: #646464; padding-left: 15px; margin: 1em 0; }
        .article-content p { margin-bottom: 1.2em; text-align: justify; }

        /* 评论区样式 */
        .comments-section { margin-top: 30px; background: #f6f6f6; padding: 15px; border-radius: 4px; border: 1px solid #eee; }
        .comments-title { font-weight: bold; margin-bottom: 10px; font-size: 14px; color: #666; }
        .comment-item { padding: 10px 0; border-bottom: 1px dashed #e0e0e0; }
        .comment-item:last-child { border-bottom: none; }
        .comment-meta { font-size: 12px; color: #999; margin-bottom: 4px; }
        .comment-author { color: #444; font-weight: bold; }
        .comment-vote { margin-left: 10px; color: #1772f6; }
        .comment-content { font-size: 13px; color: #333; line-height: 1.5; }

        .separator { border: 0; height: 1px; background: #ebebeb; margin: 40px 0; }
        .back-to-top { text-align: right; margin-top: 10px; }
        .back-to-top a { color: #8590a6; font-size: 12px; text-decoration: none; }
    </style>
</head>
<body>
    <div class="container">
        <h1 class="main-title">${title}</h1>
        <div id="toc">
            <h3>目录 (共 ${STATE.items.length} 条)</h3>
            <ul>${tocHtml}</ul>
        </div>
        <div id="main-content">
            ${contentHtml}
        </div>
    </div>
</body>
</html>
        `;

        const blob = new Blob([finalHtml], { type: "text/html;charset=utf-8" });
        saveAs(blob, `${title}.html`);
        log('HTML 文件已导出！');
    }

    function exportJSON() {
        const title = `知乎数据_${STATE.currentType}_${STATE.id}`;
        const blob = new Blob([JSON.stringify(STATE.items, null, 2)], { type: "application/json;charset=utf-8" });
        saveAs(blob, `${title}.json`);
        log('JSON 文件已导出！');
    }

    // 启动
    initUI();

})();