PDF input to Cloud Vision OCR to output text

[Philippe_Ravix]

What are you trying to achieve?

To parse the text of a PDF file that I received from a mailhook.

Steps taken so far

I have been able to grab the file from the attachment, it is stored into a google drive.

TEST 1 : I have tried to pass the Google drive pdf file URL : Web view Link into the Cloud Vision module but I receive this error : The operation failed with an error. The URL does not appear to be accessible by us. Please double check or download the content and pass it in.

TEST 2 : same as test 1 but with the Web Content Link from the drive module. The operation failed with an error. We’re not allowed to access the URL on your behalf. Please download the content and pass it in.

TEST3 : with the agregator data , but then the error is : The operation failed with an error. Bad image data.

Not sure how to iput the right pdf data to cloud vision

Screenshots: scenario setup, module configuration, errors

[Jonathan_Quarics]

Hi Philippe_Ravix, if you want to extract the text of a PDF file, you have to use the Run Text Detection (OCR) within a File and Iterate the Result Array module and the Download a File module to get the PDF’s data

Map the Files data in Google Cloud Vision

Integration Google Drive, Google Cloud Vision.blueprint.json (10.1 KB)

[Philippe_Ravix]

Thanks a lot this is exactly what I needed !