PDF Skill

PdfInspect { action: "summary", filePath: "…" }

import PDFDocument from 'pdfkit'
import fs from 'node:fs'

const doc = new PDFDocument({ size: 'A4', margin: 48 })
doc.pipe(fs.createWriteStream('invoice.pdf'))

doc.fontSize(22).text('INVOICE', { align: 'right' })
doc.moveDown()
doc.fontSize(10).text('Acme Corp', { align: 'right' })
doc.text('Invoice #2026-042   Date: 2026-04-20', { align: 'right' })
doc.moveDown()

// 简易表格
const rows = [
  ['Widget', 1, 50.00],
  ['Gadget', 2, 30.00],
]
doc.fontSize(12).text('Description     Qty     Unit     Total')
doc.moveTo(48, doc.y).lineTo(547, doc.y).stroke()
let total = 0
for (const [name, qty, unit] of rows) {
  const line = qty * unit
  total += line
  doc.text(`${name.padEnd(14)} ${qty}       $${unit.toFixed(2)}   $${line.toFixed(2)}`)
}
doc.moveDown().fontSize(14).text(`Total: $${total.toFixed(2)}`, { align: 'right' })

doc.end()
await new Promise(r => doc.on('end', r))
console.log('invoice.pdf written')

import { PDFDocument, rgb, degrees, StandardFonts } from 'pdf-lib'
import fs from 'node:fs/promises'

const src = await fs.readFile(process.argv[2] ?? 'input.pdf')
const pdf = await PDFDocument.load(src)
const font = await pdf.embedFont(StandardFonts.HelveticaBold)

for (const page of pdf.getPages()) {
  const { width, height } = page.getSize()
  page.drawText('CONFIDENTIAL', {
    x: width / 2 - 140,
    y: height / 2,
    size: 64,
    font,
    color: rgb(0.9, 0.1, 0.1),
    opacity: 0.25,
    rotate: degrees(-30),
  })
}

const out = await pdf.save()
await fs.writeFile('watermarked.pdf', out)
console.log(`watermarked ${pdf.getPageCount()} pages`)

import { PDFDocument } from 'pdf-lib'
import fs from 'node:fs/promises'

const merged = await PDFDocument.create()
for (const p of ['a.pdf', 'b.pdf', 'c.pdf']) {
  const src = await PDFDocument.load(await fs.readFile(p))
  const pages = await merged.copyPages(src, src.getPageIndices())
  pages.forEach(pg => merged.addPage(pg))
}
await fs.writeFile('merged.pdf', await merged.save())
console.log(`merged → ${merged.getPageCount()} pages`)

import { PDFDocument } from 'pdf-lib'
import fs from 'node:fs/promises'

const pdf = await PDFDocument.load(await fs.readFile('form.pdf'))
const form = pdf.getForm()
form.getTextField('full_name').setText('张三')
form.getCheckBox('agree').check()          // 若 PdfInspect 给出 checkedValue='Y'，用 setValue('Y')
form.getRadioGroup('gender').select('M')
// form.flatten() // 想锁表单就 flatten
await fs.writeFile('filled.pdf', await pdf.save())
console.log('form filled')

// 解密
import { PDFDocument } from 'pdf-lib'
const pdf = await PDFDocument.load(buf, { password: 'secret', ignoreEncryption: false })
await fs.writeFile('unlocked.pdf', await pdf.save())

// 旋转第 1 页 90°
pdf.getPage(0).setRotation(degrees(90))

// 抽出第 3、5 页到新 PDF
const out = await PDFDocument.create()
const [p3, p5] = await out.copyPages(pdf, [2, 4])
out.addPage(p3); out.addPage(p5)

PdfInspect(summary)              // textType == 'scanned'
PdfInspect(render, pageRange)    // 得到 [<asset>/render-p1.png, ...]
CloudImageUnderstand(image=<上面每张 png>, question='精确识别并提取中文文字')

DocConvert(from="pdf", to="docx", sourcePath="…")   # PDF → Word 编辑
DocConvert(from="docx", to="pdf", sourcePath="…")   # Word → PDF 分发