pocketmags.js

// This tool downloads PDF from pocketmags.com
//
// HOWTO:
// Open an issue like this: https://pocketmags.com/magazine/reader/1234567?pageNumber=1
// Stick this code into DevTools Console and run.
// Downloading JPEGs takes a little time, but jsPDF is waaaaaay too slow. Go make a coffee.
// Once it's ready PDF Print preview will pop, save result as a PDF using browsers feature.
// 

async function loadJsPDF() {
  return new Promise((resolve) => {
    if (window.jspdf?.jsPDF) {
      console.log("[jsPDF] Already loaded.");
      resolve();
      return;
    }

    console.log("[jsPDF] Loading...");
    const script = document.createElement("script");
    script.src = "https://cdnjs.cloudflare.com/ajax/libs/jspdf/2.5.1/jspdf.umd.min.js";
    script.onload = () => {
      if (window.jspdf?.jsPDF) {
        console.log("[jsPDF] Loaded successfully!");
        resolve();
      } else {
        console.error("[jsPDF] Failed to load!");
      }
    };
    document.head.appendChild(script);
  });
}

async function generatePDF(images) {
  await loadJsPDF(); // Ensure jsPDF is loaded before proceeding
  const { jsPDF } = window.jspdf; // Correct way to access jsPDF from UMD build

  console.log(`[PDF] Generating PDF with ${images.length} images...`);

  if (images.length === 0) {
    console.warn("[PDF] No images found, skipping PDF generation.");
    return;
  }

  const pdf = new jsPDF();

  for (let i = 0; i < images.length; i++) {
    const imgBlob = images[i].blob;
    const imgData = await blobToBase64(imgBlob);

    console.log(`[PDF] Processing image ${i + 1}/${images.length}`);

    const img = new Image();
    img.src = imgData;
    await new Promise((resolve) => (img.onload = resolve));

    const imgWidth = 210; // A4 width in mm
    const imgHeight = (img.height / img.width) * imgWidth;

    if (i !== 0) {
      pdf.addPage();
    }
    pdf.addImage(imgData, "JPEG", 0, 0, imgWidth, imgHeight);
  }

  console.log("[PDF] Saving PDF as combined.pdf");
  pdf.save("combined.pdf");
}

var known = [];

async function fetchImageBlob(url) {
  try {
    console.log(`[Fetch] Downloading: ${url}`);
    const response = await fetch(url);
    const blob = await response.blob();
    console.log(`[Fetch] Successfully downloaded: ${url}`);
    return blob;
  } catch (error) {
    console.error(`[Fetch] Error fetching image: ${url}`, error);
    return null;
  }
}

async function scrapeAndCombinePDF() {
  await loadJsPDF(); // Ensure jsPDF is loaded before processing pages

  let pageNum = 0;
  let images = [];

  console.log("[Scraper] Starting page scan...");

  while (document.getElementById("right_navigation")?.style.display !== "none") {
    console.log("[Scraper] Checking current page...");

    const nextPageButton = document.getElementById("btnNextPage");
    if (!nextPageButton) {
      console.warn("[Scraper] Next page button not found. Stopping.");
      break;
    }

    const pdfViewers = document.getElementsByClassName("pdfViewer");
    for (let item of pdfViewers) {
      let urls = item.style.backgroundImage;
      if (!urls || urls.length === 0) {
        console.warn("[Scraper] No background images found.");
        continue;
      }

      let parts = urls.split('"');
      for (let part of parts) {
        if (part.includes("transparent.png")) {
          console.log(`[Scraper] Skipping: ${part}`);
          continue;
        }
        if (part.includes("https://")) {
          if (known.includes(part)) {
            console.log(`[Scraper] Skipping (already processed): ${part}`);
            continue;
          }
          known.push(part);

          console.log(`[Scraper] Fetching new image: ${part}`);
          const blob = await fetchImageBlob(part);
          if (blob) {
            images.push({ blob, pageNum });
            console.log(`[Scraper] Image added to processing queue. PageNum: ${pageNum}`);
            pageNum++;
          }
        }
      }
    }

    nextPageButton.click();
    console.log("[Scraper] Going to next page...");

    console.log("[Scraper] Sleeping for 1 second...");
    await new Promise(resolve => setTimeout(resolve, 1000));
    console.log("[Scraper] Waking up.");
  }

  console.log(`[Scraper] Finished scanning. Total images found: ${images.length}`);

  if (images.length > 0) {
    console.log("[Scraper] Generating PDF...");
    generatePDF(images);
  } else {
    console.warn("[Scraper] No images found to generate PDF.");
  }
}

function blobToBase64(blob) {
  return new Promise((resolve, reject) => {
    const reader = new FileReader();
    reader.onloadend = () => resolve(reader.result);
    reader.onerror = reject;
    reader.readAsDataURL(blob);
  });
}

// Start script **ONLY AFTER** jsPDF is fully loaded
loadJsPDF().then(() => {
  console.log("[Main] Starting PDF processing...");
  scrapeAndCombinePDF();
});