Extract Text from Multipage Attachment PDF Using Google Apps Script - pdf

Question

I have a Gmail attachment PDF with multiple scanned pages. When I use Google Apps Script to save the blob from the attachment to a Drive file, open the PDF manually from Google Drive, then select Open With Google Docs, all of the text from the PDF is displayed as a Google Doc. However, when I save the blob as a Google Doc with OCR, only the text from the image on the first page is saved to a Doc, accessed either manually or by code.
The code to get the blob and process it is:
function getAttachments(desiredLabel, processedLabel, emailQuery){
// Find emails
var threads = GmailApp.search(emailQuery);
if(threads.length > 0){
// Iterate through the emails
for(var i in threads){
var mesgs = threads[i].getMessages();
for(var j in mesgs){
var processingMesg = mesgs[j];
var attachments = processingMesg.getAttachments();
var processedAttachments = 0;
// Iterate through attachments
for(var k in attachments){
var attachment = attachments[k];
var attachmentName = attachment.getName();
var attachmentType = attachment.getContentType();
// Process PDFs
if (attachmentType.includes('pdf')) {
processedAttachments += 1;
var pdfBlob = attachment.copyBlob();
var filename = attachmentName + " " + processedAttachments;
processPDF(pdfBlob, filename);
}
}
}
}
}
}
function processPDF(pdfBlob, filename){
// Saves the blob as a PDF.
// All pages are displayed if I click on it from Google Drive after running this script.
let pdfFile = DriveApp.createFile(pdfBlob);
pdfFile.setName(filename);
// Saves the blob as an OCRed Doc.
let resources = {
title: filename,
mimeType: "application/pdf"
};
let options = {
ocr: true,
ocrLanguage: "en"
};
let file = Drive.Files.insert(resources, pdfBlob, options);
let fileID = file.getId();
// Open the file to get the text.
// Only the text of the image on the first page is available in the Doc.
let doc = DocumentApp.openById(fileID);
let docText = doc.getBody().getText();
}
If I try to use Google Docs to read the PDF without OCR directly, I get Exception: Invalid argument, for example:
DocumentApp.openById(pdfFile.getId());
How do I get the text from all of the pages of the PDF?

Answer 1

DocumentApp.openById is a method that can only be used for Google Docs documents
pdfFile can only be "opened" with the DriveApp - DriveApp.getFileById(pdfFile.getId());
Opening a file with DriveApp allows you to use the following methods on the file
When it comes to OCR conversion, your code works for me correctly to convert all pages of a PDF document to Google Docs, so you error source is likely come from the attachment itself / the way you retrieve the blob
Mind that OCR conversion is not good at preserving formatting, so a two page PDF might be collapsed into a one-page Docs - depneding on the formatting of the PDF