Created
December 16, 2016 02:09
-
-
Save actsasflinn/a2b67d28308ee00cf5cf4c29ff64fdfa to your computer and use it in GitHub Desktop.
PDF Split using PDFBox
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
require 'java' | |
require './pdfbox-1.8.13.jar' | |
require './fontbox-1.8.13.jar' | |
require './commons-logging-1.2.jar' | |
input = java.io.File.new("example.pdf") | |
inputDocument = org.apache.pdfbox.pdmodel.PDDocument::loadNonSeq(input, nil) | |
stripper = org.apache.pdfbox.util.PDFTextStripper.new | |
outputDocument = org.apache.pdfbox.pdmodel.PDDocument.new | |
for page in (1..inputDocument.getNumberOfPages) | |
stripper.setStartPage(page) | |
stripper.setEndPage(page) | |
text = stripper.getText(inputDocument) | |
p = java.util.regex.Pattern::compile("Growing Faster Than PCs") | |
m = p.matcher(text) | |
if m.find | |
pdPage = inputDocument.getDocumentCatalog.getAllPages.get(page - 1) | |
outputDocument.importPage(pdPage) | |
end | |
end | |
f = java.io.File.new("extract.pdf") | |
outputDocument.save(f) | |
outputDocument.close() | |
inputDocument.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment