Created
March 9, 2024 15:43
-
-
Save bishabosha/de064673e486e339c09694f51f5ffa1f to your computer and use it in GitHub Desktop.
scala script to convert PDF to plain text
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
//> using repository "https://repo.e-iceblue.com/nexus/content/groups/public/" | |
//> using dep "e-iceblue:spire.pdf:9.10.3" | |
//> using dep "jakarta.xml.bind:jakarta.xml.bind-api:4.0.0" | |
//> using scala 3.4.0 | |
//> using toolkit default | |
import com.spire.pdf.PdfDocument | |
import scala.util.Using, Using.Releasable | |
import scala.util.chaining.given | |
val path = os.Path(args(0)) | |
given Releasable[PdfDocument] = _.close() | |
Using | |
.resource(PdfDocument(path.toString)): pdf => | |
val limit = pdf.getPages().nn.getCount() | |
Iterator | |
.iterate(0)(_ + 1) | |
.takeWhile(_ < limit) | |
.map(pdf.getPages().nn.get(_).nn) | |
.map(_.extractText().nn) | |
.mkString("\n\n") | |
.pipe(println) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment