Created
June 8, 2025 08:58
-
-
Save pospi/0df6db3d2769e248388232a32a690460 to your computer and use it in GitHub Desktop.
Convert Pocket export CSV to chunked Omnivore backup JSON files
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/** | |
* Convert CSV from Pocket export file to chunked JSON files in | |
* Omnivore format. | |
* For import into Wallabag with minimal data loss. | |
*/ | |
const { readFileSync, writeFileSync } = require('fs') | |
const { parse } = require('csv/sync') | |
const { format } = require('fecha') | |
const INPUT_FILENAME = './part_000000.csv' | |
const OUTPUT_FILE_PREFIX = './pocket2omnivore' | |
const CHUNK_LEN = 100 | |
const data = parse(readFileSync(INPUT_FILENAME)).slice(1) | |
const formatted = data.map(row => ({ | |
title: row[0], | |
url: row[1], | |
savedAt: format(new Date(parseInt(row[2], 10) * 1000), 'YYYY-MM-DDTHH:mm:ss.SSS000') + 'Z', | |
labels: row[3].split('|'), | |
state: row[4] === 'archive' ? 'Archived' : 'Unread', | |
author: null, | |
publishedAt: null, | |
})) | |
for (let i = 0, l = Math.ceil(formatted.length / CHUNK_LEN); i < l; ++i) { | |
writeFileSync( | |
`${OUTPUT_FILE_PREFIX}-${i}.json`, | |
JSON.stringify(formatted.slice(i * CHUNK_LEN, i * CHUNK_LEN + CHUNK_LEN), null, 2), | |
) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment