EMLOG

使用方法

安装插件，访问人民日报电子版网页，点击右上角的下载按钮，耐心等一会

代码

// ==UserScript==
// @name         人民日报 PDF 批量下载 + 合并
// @namespace    http://blog.liyunhe.wang/
// @version      1.0
// @description  自动抓取人民日报当前日期所有版面 PDF 并可合并下载
// @author       liyunhe && ChatGPT
// @match        https://paper.people.com.cn/rmrb/html/*
// @match        https://paper.people.com.cn/rmrb/pc/*
// @match        http://paper.people.com.cn/rmrb/html/*
// @match        http://paper.people.com.cn/rmrb/pc/*
// @grant        none
// @require      https://cdn.jsdelivr.net/npm/pdf-lib/dist/pdf-lib.min.js
// ==/UserScript==

(function() {
  'use strict';

  // 添加按钮
  const btn = document.createElement('button');
  btn.textContent = '📥 下载全部 PDF（含合并）';
  btn.style = 'position:fixed;top:20px;right:20px;z-index:9999;padding:10px;background:#007bff;color:white;border:none;border-radius:5px;cursor:pointer;';
  document.body.appendChild(btn);

  btn.onclick = async () => {
    btn.disabled = true;
    btn.textContent = '⏳ 正在抓取数据...';

    try {
      const { date, detailedLinks } = await getPDFLinks(location.href);
      const validLinks = detailedLinks.filter(link => link.pdfUrl);

      if (validLinks.length === 0) {
        alert('❌ 未找到任何 PDF 链接');
        return;
      }

      const pdfBlobs = [];

      for (let i = 0; i < validLinks.length; i++) {
        const { title, pdfUrl } = validLinks[i];
        btn.textContent = `⬇️ 下载中：${title} (${i + 1}/${validLinks.length})`;

        const res = await fetch(pdfUrl);
        const blob = await res.blob();
        pdfBlobs.push({ title, blob });
      }

      btn.textContent = '📚 合并 PDF 中...';

      const mergedBlob = await mergePDFs(pdfBlobs.map(p => p.blob));
      const mergedFilename = `人民日报-${date}.pdf`;
      triggerDownload(mergedBlob, mergedFilename);

      btn.textContent = `✅ 下载完成：${mergedFilename}`;
    } catch (err) {
      console.error(err);
      alert('❌ 出错：' + err.message);
    } finally {
      setTimeout(() => {
        btn.disabled = false;
        btn.textContent = '📥 下载全部 PDF（含合并）';
      }, 5000);
    }
  };

  // 抓取当前页面所有 PDF 链接
  async function getPDFLinks(mainUrl) {
    const res = await fetch(mainUrl);
    const html = await res.text();
    const parser = new DOMParser();
    const doc = parser.parseFromString(html, 'text/html');

    const dateMatch = doc.querySelector('.date')?.textContent.match(/(\d{4})年(\d{2})月(\d{2})日/);
    const date = dateMatch ? `${dateMatch[1]}-${dateMatch[2]}-${dateMatch[3]}` : 'unknown';

    const pageLinks = [...doc.querySelectorAll('#pageLink')]
      .map(el => ({
        title: el.textContent.trim(),
        url: new URL(el.getAttribute('href'), mainUrl).href
      }));

    const detailedLinks = await Promise.all(pageLinks.map(async ({ title, url }) => {
      try {
        const res = await fetch(url);
        const html = await res.text();
        const subDoc = new DOMParser().parseFromString(html, 'text/html');
        const href = subDoc.querySelector('.paper-bot a')?.getAttribute('href');
        const pdfUrl = href ? new URL(href, mainUrl).href : null;
        return { title, pdfUrl };
      } catch {
        return { title, pdfUrl: null };
      }
    }));

    return { date, detailedLinks };
  }

  // 合并多个 PDF Blob
  async function mergePDFs(blobs) {
    const mergedPdf = await PDFLib.PDFDocument.create();

    for (const blob of blobs) {
      const arrayBuffer = await blob.arrayBuffer();
      const pdf = await PDFLib.PDFDocument.load(arrayBuffer);
      const pages = await mergedPdf.copyPages(pdf, pdf.getPageIndices());
      pages.forEach(p => mergedPdf.addPage(p));
    }

    const mergedBytes = await mergedPdf.save();
    return new Blob([mergedBytes], { type: 'application/pdf' });
  }

  // 触发浏览器下载
  function triggerDownload(blob, filename) {
    const a = document.createElement('a');
    a.href = URL.createObjectURL(blob);
    a.download = filename;
    a.click();
    URL.revokeObjectURL(a.href);
  }

})();