Export pdf with puppeteer

Signed-off-by: Yukai Huang <yukaihuangtw@gmail.com>
2020-03-09 10:09:38 +08:00 · 2020-03-09 10:09:38 +08:00 · c8462c72b3
parent 42ae89cc72
commit c8462c72b3
7 changed files with 236 additions and 52 deletions
--- a/lib/config/default.js
+++ b/lib/config/default.js
@ -1,6 +1,7 @@
 'use strict'

 const os = require('os')
+const uuid = require('uuid/v4')

 module.exports = {
  domain: '',
@ -186,5 +187,6 @@ module.exports = {
  //    2nd appearance: "31-good-morning-my-friend---do-you-have-5-1"
  //    3rd appearance: "31-good-morning-my-friend---do-you-have-5-2"
  linkifyHeaderStyle: 'keep-case',
-  autoVersionCheck: true
+  autoVersionCheck: true,
+  codimdSignKey: uuid()
 }
--- a/lib/note/index.js
+++ b/lib/note/index.js
@ -1,5 +1,7 @@
 'use strict'

+const jwt = require('jsonwebtoken')
+
 const config = require('../config')
 const logger = require('../logger')

@ -77,6 +79,24 @@ async function showNote (req, res) {
  return responseCodiMD(res, note)
 }

+async function authenticateUser (req) {
+  const authHeader = req.header('Authorization')
+  const token = authHeader && authHeader.replace('Bearer ', '')
+
+  if (token) {
+    const { userId } = jwt.verify(token, config.codimdSignKey)
+    const user = await User.findOne({ id: userId })
+
+    if (user) {
+      return [true, user]
+    } else {
+      return [false]
+    }
+  } else {
+    return [req.isAuthenticated(), req.user]
+  }
+}
+
 function canViewNote (note, isLogin, userId) {
  if (note.permission === 'private') {
    return note.ownerId === userId
@ -87,6 +107,26 @@ function canViewNote (note, isLogin, userId) {
  return true
 }

+async function findNote (req, res, next) {
+  const noteId = req.params.noteId
+
+  const note = await getNoteById(noteId)
+
+  if (!note) {
+    return errorNotFound(req, res)
+  }
+
+  const [isAuthenticated, user] = await authenticateUser(req)
+
+  if (!canViewNote(note, isAuthenticated, user ? user.id : null)) {
+    return errorForbidden(req, res)
+  }
+
+  res.locals.note = note
+
+  next()
+}
+
 async function showPublishNote (req, res) {
  const shortid = req.params.shortid

@ -141,18 +181,9 @@ async function showPublishNote (req, res) {
 }

 async function noteActions (req, res) {
+  const { note } = res.locals
  const noteId = req.params.noteId

-  const note = await getNoteById(noteId)
-
-  if (!note) {
-    return errorNotFound(req, res)
-  }
-
-  if (!canViewNote(note, req.isAuthenticated(), req.user ? req.user.id : null)) {
-    return errorForbidden(req, res)
-  }
-
  const action = req.params.action
  switch (action) {
    case 'publish':
@ -191,3 +222,5 @@ async function noteActions (req, res) {
 exports.showNote = showNote
 exports.showPublishNote = showPublishNote
 exports.noteActions = noteActions
+exports.actionPDF = actionPDF
+exports.findNote = findNote
--- a/lib/note/noteActions.js
+++ b/lib/note/noteActions.js
@ -1,8 +1,8 @@
 'use strict'

 const fs = require('fs')
-const path = require('path')
-const markdownpdf = require('markdown-pdf')
+const jwt = require('jsonwebtoken')
+const puppeteer = require('puppeteer')
 const shortId = require('shortid')
 const querystring = require('querystring')
 const moment = require('moment')
@ -10,7 +10,7 @@ const { Pandoc } = require('@hackmd/pandoc.js')

 const config = require('../config')
 const logger = require('../logger')
-const { Note, Revision } = require('../models')
+const { Note, Revision, User } = require('../models')
 const { errorInternalError, errorNotFound } = require('../response')

 function actionPublish (req, res, note) {
@ -64,43 +64,67 @@ function actionInfo (req, res, note) {
  res.send(data)
 }

-function actionPDF (req, res, note) {
-  const url = config.serverURL || 'http://' + req.get('host')
-  const body = note.content
-  const extracted = Note.extractMeta(body)
-  let content = extracted.markdown
-  const title = Note.decodeTitle(note.title)
-
-  const highlightCssPath = path.join(config.appRootPath, '/node_modules/highlight.js/styles/github-gist.css')
-
-  if (!fs.existsSync(config.tmpPath)) {
-    fs.mkdirSync(config.tmpPath)
-  }
-  const pdfPath = config.tmpPath + '/' + Date.now() + '.pdf'
-  content = content.replace(/\]\(\//g, '](' + url + '/')
-  const markdownpdfOptions = {
-    highlightCssPath: highlightCssPath
-  }
-  markdownpdf(markdownpdfOptions).from.string(content).to(pdfPath, function () {
-    if (!fs.existsSync(pdfPath)) {
-      logger.error('PDF seems to not be generated as expected. File doesn\'t exist: ' + pdfPath)
-      return errorInternalError(req, res)
-    }
-    const stream = fs.createReadStream(pdfPath)
-    let filename = title
-    // Be careful of special characters
-    filename = encodeURIComponent(filename)
-    // Ideally this should strip them
-    res.setHeader('Content-disposition', 'attachment; filename="' + filename + '.pdf"')
-    res.setHeader('Cache-Control', 'private')
-    res.setHeader('Content-Type', 'application/pdf; charset=UTF-8')
-    res.setHeader('X-Robots-Tag', 'noindex, nofollow') // prevent crawling
-    stream.on('end', () => {
-      stream.close()
-      fs.unlinkSync(pdfPath)
-    })
-    stream.pipe(res)
+async function printPDF (noteUrl, headers = {}) {
+  const browser = await puppeteer.launch({
+    headless: true,
+    args: ['--disable-dev-shm-usage']
  })
+
+  const page = await browser.newPage()
+  await page.setExtraHTTPHeaders(headers)
+  await page.goto(noteUrl, { waitUntil: 'networkidle0' })
+  const pdf = await page.pdf({ format: 'A4' })
+
+  await browser.close()
+  return pdf
+}
+
+function actionPDF (req, res, note) {
+  const noteId = req.params.noteId
+
+  if (req.method === 'POST') {
+    const token = jwt.sign({ userId: req.user.id.toString() }, config.codimdSignKey, { expiresIn: 5 * 60 })
+
+    const noteURL = `${config.serverURL}/${noteId}/pdf`
+
+    return printPDF(noteURL, {
+      Authorization: `Bearer ${token}`
+    }).then(pdf => {
+      res.set({ 'Content-Type': 'application/pdf', 'Content-Length': pdf.length })
+      res.send(pdf)
+    })
+  } else {
+    const body = note.content
+    const extracted = Note.extractMeta(body)
+    const markdown = extracted.markdown
+    const meta = Note.parseMeta(extracted.meta)
+    const createTime = note.createdAt
+    const updateTime = note.lastchangeAt
+    const title = Note.generateWebTitle(meta.title || Note.decodeTitle(note.title))
+
+    const data = {
+      title: title,
+      description: meta.description || (markdown ? Note.generateDescription(markdown) : null),
+      viewcount: note.viewcount,
+      createtime: createTime,
+      updatetime: updateTime,
+      body: body,
+      owner: note.owner ? note.owner.id : null,
+      ownerprofile: note.owner ? User.getProfile(note.owner) : null,
+      lastchangeuser: note.lastchangeuser ? note.lastchangeuser.id : null,
+      lastchangeuserprofile: note.lastchangeuser ? User.getProfile(note.lastchangeuser) : null,
+      robots: meta.robots || false, // default allow robots
+      GA: meta.GA,
+      disqus: meta.disqus,
+      cspNonce: res.locals.nonce
+    }
+
+    res.set({
+      'Cache-Control': 'private' // only cache by client
+    })
+
+    return res.render('pretty.ejs', data)
+  }
 }

 const outputFormats = {
--- a/lib/routes.js
+++ b/lib/routes.js
@ -74,7 +74,8 @@ appRouter.get('/p/:shortid/:action', response.publishSlideActions)
 // get note by id
 appRouter.get('/:noteId', wrap(noteController.showNote))
 // note actions
-appRouter.get('/:noteId/:action', noteController.noteActions)
+appRouter.get('/:noteId/:action', noteController.findNote, noteController.noteActions)
+appRouter.post('/:noteId/:action', noteController.findNote, noteController.noteActions)
 // note actions with action id
 appRouter.get('/:noteId/:action/:actionId', noteController.noteActions)

--- a/package-lock.json
+++ b/package-lock.json
@ -586,6 +586,11 @@
      "resolved": "https://registry.npmjs.org/@types/mime/-/mime-2.0.1.tgz",
      "integrity": "sha512-FwI9gX75FgVBJ7ywgnq/P7tw+/o1GUbtP0KzbtusLigAOgIgNISRK0ZPl4qertvXSIE8YbsVJueQ90cDt9YYyw=="
    },
+    "@types/mime-types": {
+      "version": "2.1.0",
+      "resolved": "https://registry.npmjs.org/@types/mime-types/-/mime-types-2.1.0.tgz",
+      "integrity": "sha1-nKUs2jY/aZxpRmwqbM2q2RPqenM="
+    },
    "@types/node": {
      "version": "10.17.14",
      "resolved": "https://registry.npmjs.org/@types/node/-/node-10.17.14.tgz",
@ -8699,6 +8704,23 @@
      "resolved": "https://registry.npmjs.org/jsonparse/-/jsonparse-1.2.0.tgz",
      "integrity": "sha1-XAxWhRBxYOcv50ib3eoLRMK8Z70="
    },
+    "jsonwebtoken": {
+      "version": "8.5.1",
+      "resolved": "https://registry.npmjs.org/jsonwebtoken/-/jsonwebtoken-8.5.1.tgz",
+      "integrity": "sha512-XjwVfRS6jTMsqYs0EsuJ4LGxXV14zQybNd4L2r0UvbVnSF9Af8x7p5MzbJ90Ioz/9TI41/hTCvznF/loiSzn8w==",
+      "requires": {
+        "jws": "^3.2.2",
+        "lodash.includes": "^4.3.0",
+        "lodash.isboolean": "^3.0.3",
+        "lodash.isinteger": "^4.0.4",
+        "lodash.isnumber": "^3.0.3",
+        "lodash.isplainobject": "^4.0.6",
+        "lodash.isstring": "^4.0.1",
+        "lodash.once": "^4.0.0",
+        "ms": "^2.1.1",
+        "semver": "^5.6.0"
+      }
+    },
    "jsprim": {
      "version": "1.4.1",
      "resolved": "https://registry.npmjs.org/jsprim/-/jsprim-1.4.1.tgz",
@ -9046,11 +9068,36 @@
      "resolved": "https://registry.npmjs.org/lodash.foreach/-/lodash.foreach-4.5.0.tgz",
      "integrity": "sha1-Gmo16s5AEoDH8G3d7DUWWrJ+PlM="
    },
+    "lodash.includes": {
+      "version": "4.3.0",
+      "resolved": "https://registry.npmjs.org/lodash.includes/-/lodash.includes-4.3.0.tgz",
+      "integrity": "sha1-YLuYqHy5I8aMoeUTJUgzFISfVT8="
+    },
+    "lodash.isboolean": {
+      "version": "3.0.3",
+      "resolved": "https://registry.npmjs.org/lodash.isboolean/-/lodash.isboolean-3.0.3.tgz",
+      "integrity": "sha1-bC4XHbKiV82WgC/UOwGyDV9YcPY="
+    },
+    "lodash.isinteger": {
+      "version": "4.0.4",
+      "resolved": "https://registry.npmjs.org/lodash.isinteger/-/lodash.isinteger-4.0.4.tgz",
+      "integrity": "sha1-YZwK89A/iwTDH1iChAt3sRzWg0M="
+    },
+    "lodash.isnumber": {
+      "version": "3.0.3",
+      "resolved": "https://registry.npmjs.org/lodash.isnumber/-/lodash.isnumber-3.0.3.tgz",
+      "integrity": "sha1-POdoEMWSjQM1IwGsKHMX8RwLH/w="
+    },
    "lodash.isplainobject": {
      "version": "4.0.6",
      "resolved": "https://registry.npmjs.org/lodash.isplainobject/-/lodash.isplainobject-4.0.6.tgz",
      "integrity": "sha1-fFJqUtibRcRcxpC4gWO+BJf1UMs="
    },
+    "lodash.isstring": {
+      "version": "4.0.1",
+      "resolved": "https://registry.npmjs.org/lodash.isstring/-/lodash.isstring-4.0.1.tgz",
+      "integrity": "sha1-1SfftUVuynzJu5XV2ur4i6VKVFE="
+    },
    "lodash.map": {
      "version": "4.6.0",
      "resolved": "https://registry.npmjs.org/lodash.map/-/lodash.map-4.6.0.tgz",
@ -9067,6 +9114,11 @@
      "resolved": "https://registry.npmjs.org/lodash.merge/-/lodash.merge-4.6.2.tgz",
      "integrity": "sha512-0KpjqXRVvrYyCsX1swR/XTK0va6VQkQM6MNo7PqW77ByjAhoARA8EfrP1N4+KlKj8YS0ZUCtRT/YUuhyYDujIQ=="
    },
+    "lodash.once": {
+      "version": "4.1.1",
+      "resolved": "https://registry.npmjs.org/lodash.once/-/lodash.once-4.1.1.tgz",
+      "integrity": "sha1-DdOXEhPHxW34gJd9UEyI+0cal6w="
+    },
    "lodash.pick": {
      "version": "4.4.0",
      "resolved": "https://registry.npmjs.org/lodash.pick/-/lodash.pick-4.4.0.tgz",
@ -12694,6 +12746,11 @@
        "ipaddr.js": "1.9.0"
      }
    },
+    "proxy-from-env": {
+      "version": "1.1.0",
+      "resolved": "https://registry.npmjs.org/proxy-from-env/-/proxy-from-env-1.1.0.tgz",
+      "integrity": "sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg=="
+    },
    "prr": {
      "version": "1.0.1",
      "resolved": "https://registry.npmjs.org/prr/-/prr-1.0.1.tgz",
@ -12761,6 +12818,60 @@
      "resolved": "https://registry.npmjs.org/punycode/-/punycode-2.1.1.tgz",
      "integrity": "sha512-XRsRjdf+j5ml+y/6GKHPZbrF/8p2Yga0JPtdqTIY2Xe5ohJPD9saDJJLPvp9+NSBprVvevdXZybnj2cv8OEd0A=="
    },
+    "puppeteer": {
+      "version": "2.1.1",
+      "resolved": "https://registry.npmjs.org/puppeteer/-/puppeteer-2.1.1.tgz",
+      "integrity": "sha512-LWzaDVQkk1EPiuYeTOj+CZRIjda4k2s5w4MK4xoH2+kgWV/SDlkYHmxatDdtYrciHUKSXTsGgPgPP8ILVdBsxg==",
+      "requires": {
+        "@types/mime-types": "^2.1.0",
+        "debug": "^4.1.0",
+        "extract-zip": "^1.6.6",
+        "https-proxy-agent": "^4.0.0",
+        "mime": "^2.0.3",
+        "mime-types": "^2.1.25",
+        "progress": "^2.0.1",
+        "proxy-from-env": "^1.0.0",
+        "rimraf": "^2.6.1",
+        "ws": "^6.1.0"
+      },
+      "dependencies": {
+        "agent-base": {
+          "version": "5.1.1",
+          "resolved": "https://registry.npmjs.org/agent-base/-/agent-base-5.1.1.tgz",
+          "integrity": "sha512-TMeqbNl2fMW0nMjTEPOwe3J/PRFP4vqeoNuQMG0HlMrtm5QxKqdvAkZ1pRBQ/ulIyDD5Yq0nJ7YbdD8ey0TO3g=="
+        },
+        "debug": {
+          "version": "4.1.1",
+          "resolved": "https://registry.npmjs.org/debug/-/debug-4.1.1.tgz",
+          "integrity": "sha512-pYAIzeRo8J6KPEaJ0VWOh5Pzkbw/RetuzehGM7QRRX5he4fPHx2rdKMB256ehJCkX+XRQm16eZLqLNS8RSZXZw==",
+          "requires": {
+            "ms": "^2.1.1"
+          }
+        },
+        "https-proxy-agent": {
+          "version": "4.0.0",
+          "resolved": "https://registry.npmjs.org/https-proxy-agent/-/https-proxy-agent-4.0.0.tgz",
+          "integrity": "sha512-zoDhWrkR3of1l9QAL8/scJZyLu8j/gBkcwcaQOZh7Gyh/+uJQzGVETdgT30akuwkpL8HTRfssqI3BZuV18teDg==",
+          "requires": {
+            "agent-base": "5",
+            "debug": "4"
+          }
+        },
+        "mime": {
+          "version": "2.4.4",
+          "resolved": "https://registry.npmjs.org/mime/-/mime-2.4.4.tgz",
+          "integrity": "sha512-LRxmNwziLPT828z+4YkNzloCFC2YM4wrB99k+AV5ZbEyfGNWfG8SO1FUXLmLDBSo89NrJZ4DIWeLjy1CHGhMGA=="
+        },
+        "ws": {
+          "version": "6.2.1",
+          "resolved": "https://registry.npmjs.org/ws/-/ws-6.2.1.tgz",
+          "integrity": "sha512-GIyAXC2cB7LjvpgMt9EKS2ldqr0MTrORaleiOno6TweZ6r3TKtoFQWay/2PceJ3RuBasOHzXNn5Lrw1X0bEjqA==",
+          "requires": {
+            "async-limiter": "~1.0.0"
+          }
+        }
+      }
+    },
    "q": {
      "version": "1.5.1",
      "resolved": "https://registry.npmjs.org/q/-/q-1.5.1.tgz",
--- a/package.json
+++ b/package.json
@ -78,6 +78,7 @@
    "js-cookie": "~2.2.0",
    "js-yaml": "~3.13.1",
    "jsdom-nogyp": "~0.8.3",
+    "jsonwebtoken": "^8.5.1",
    "keymaster": "~1.6.2",
    "list.js": "~1.5.0",
    "lodash": "~4.17.15",
@ -124,6 +125,7 @@
    "pg-hstore": "~2.3.2",
    "plantuml-encoder": "^1.2.5",
    "prismjs": "~1.17.1",
+    "puppeteer": "^2.1.1",
    "randomcolor": "~0.5.4",
    "raphael": "~2.2.8",
    "readline-sync": "~1.4.7",
--- a/public/js/index.js
+++ b/public/js/index.js
@ -951,7 +951,18 @@ ui.toolbar.download.rawhtml.click(function (e) {
  exportToRawHTML(ui.area.markdown)
 })
 // pdf
-ui.toolbar.download.pdf.attr('download', '').attr('href', noteurl + '/pdf')
+ui.toolbar.download.pdf.click(function (e) {
+  // TODO: using ajax
+
+  const form = document.createElement('form')
+  form.method = 'POST'
+  form.target = '_blank'
+  form.action = `${noteurl}/pdf`
+
+  document.body.appendChild(form)
+
+  form.submit()
+})

 ui.modal.pandocExport.find('#pandoc-export-download').click(function (e) {
  e.preventDefault()