Last active
January 13, 2023 00:10
-
-
Save Pazzilivo/302ef71ebbba9a5929c9942b96e5f152 to your computer and use it in GitHub Desktop.
This file contains 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
const fs = require('fs'); | |
const pdfParse = require('pdf-parse'); | |
let content = [] | |
const readPdf = async (uri) => { | |
const buffer = fs.readFileSync(uri); | |
try { | |
const data = await pdfParse(buffer); | |
content = data.text.split('\n') | |
console.log(readLine(content).join('\n')) | |
}catch(err){ | |
throw new Error(err); | |
} | |
} | |
const readLine = (content) => { | |
let currentLine = 0 | |
let total = content.length | |
let lines = [] | |
let lastLineValid = false | |
while (currentLine < total) { | |
const regex = /(\d{4}-\d{2}-\d{2})(CNY)/g; | |
const valid = regex.test(content[currentLine]) | |
if (valid) { | |
lines.push(content[currentLine]) | |
lastLineValid = true | |
} else { | |
if (lastLineValid) { | |
if (content[currentLine]) { | |
const l = lines.length | |
lines[l - 1] = lines[l - 1] + content[currentLine] | |
} else { | |
lastLineValid = false | |
} | |
} | |
} | |
currentLine += 1 | |
} | |
return lines.map((line) => { | |
const r = /(\d{4}-\d{2}-\d{2})(CNY)(-?[0-9,]*.\d{2})(-?[0-9,]*.\d{2})(\S*)/g | |
const part = r.exec(line) | |
if (part) { | |
const [, date, , amount, balance, payee] = part | |
return `${date},${amount},${balance},${payee}` | |
} | |
return [] | |
}) | |
} | |
// Testing | |
const DUMMY_PDF = './cmb.pdf'; | |
readPdf(DUMMY_PDF); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment