Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix: invalid date when parsing it from html #16

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
+37 −21
Open

fix: invalid date when parsing it from html #16

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Update timeout value and add function to get month and year from meta… 
…data or HTML
  • Loading branch information
@jaikathuria
jaikathuria committed Feb 10, 2024
commit c55333b8cb52748cfb505777ea6fe8d10a507552
58 changes: 37 additions & 21 deletions index.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ import { exiftool } from 'exiftool-vendored'

chromium.use(stealth())

const timeoutValue = 30000
const timeoutValue = 300000
const userDataDir = './session'
const downloadPath = './download'

Expand Down Expand Up @@ -39,6 +39,39 @@ const saveProgress = async (page) => {
console.log('Current URL does not start with https://photos.google.com, not saving progress.');
}
}
const getMonthAndYear = async (metadata, page) => {
let year = 1970
let month = 1
let dateType = "default"
if (metadata.DateTimeOriginal) {
year = metadata.DateTimeOriginal.year
month = metadata.DateTimeOriginal.month
dateType = "DateTimeOriginal"
} else if (metadata.CreateDate) {
year = metadata.CreateDate.year
month = metadata.CreateDate.month
dateType = "CreateDate"
} else {
// if metadata is not available, we try to get the date from the html
console.log('Metadata not found, trying to get date from html')
const data = await page.request.get(page.url())
const html = await data.text()

const regex = /aria-label="(Photo|Video) - (Landscape|Portrait|Square) - ([A-Za-z]{3} \d{1,2}, \d{4}, \d{1,2}:\d{2}:\d{2} [APM]{2})"/
const match = regex.exec(html)

if (match) {
const dateString = match[3].replace(/\u202F/g, ' ') // Remove U+202F character
const date = new Date(dateString)
if (date.toString() !== 'Invalid Date') {
year = date.getFullYear()
month = date.getMonth() + 1
dateType = "HTML"
}
}
}
return { year, month, dateType }
}

(async () => {
const startLink = await getProgress()
Expand Down Expand Up @@ -118,26 +151,9 @@ const downloadPhoto = async (page, overwrite = false) => {

const metadata = await exiftool.read(temp)

let year = metadata.DateTimeOriginal?.year || 1970
let month = metadata.DateTimeOriginal?.month || 1

if (year === 1970 && month === 1) {
// if metadata is not available, we try to get the date from the html
console.log('Metadata not found, trying to get date from html')
const data = await page.request.get(page.url())
const html = await data.text()

const regex = /aria-label="(Photo . Landscape|Photo . Portrait|Video . Landscape|Video . Portrait|Video|Photo) . ([^"]+)"/
const match = regex.exec(html)

if (match) {
const dateString = match[1]
const date = new Date(dateString)
year = date.getFullYear()
month = date.getMonth() + 1
}
}

const date = await getMonthAndYear(metadata, page)
const year = date.year
const month = date.month
try {
await moveFile(temp, `${downloadPath}/${year}/${month}/${fileName}`, { overwrite })
console.log('Download Complete:', `${year}/${month}/${fileName}`)
Expand Down