Extracting email address from PDF files

(0) Share

Report

Posted on by michaelshparber

111

I have a folder full of pdf files (requests from customers).

In each pdf file there is only one email address, and it can be located anywhere on the page.

I would like to scan all the files in this folder and extract these email addresses and insert them in Excel file in OneDrive.

I can recognize the email addresses by "@".

I've seen several tools: Docparse, AI builder... and they seem to be somewhat complicated.

Is there something simple and straightforward?

What would you recommend?

Please help

Thank you

Categories:

Building flows

I have the same question (0)

All responses (4)

Answers (1)

Verified answer

CedrickB Microsoft Employee on at

Like (2)

Report
Copy link

Link copied!

Hi,

Here is a proposal presuming your PDFs are not too big.

First you will use AI Builder Text Recognition https://docs.microsoft.com/en-us/ai-builder/prebuilt-text-recognition to extract texts from your PDF. (Check the size limitation)

Then you will pass the output to the entity extraction prebuilt which is able to extract several entities from a text including emails https://docs.microsoft.com/en-us/ai-builder/prebuilt-entity-extraction (You will have to split by chunk of 5K characters)

Then you will insert the output entities of type "email" from previous model to your Excel.

This is something that can be easilly performed with Power Automate.

See https://docs.microsoft.com/en-us/ai-builder/flow-text-recognition and https://docs.microsoft.com/en-us/ai-builder/prebuilt-entity-extraction-pwr-automate

Was this reply helpful? Yes No
Amanthaper 441 on at

Like (0)

Report
Copy link

Link copied!

@CedrickBexcellent suggestion!

Was this reply helpful? Yes No
Jaimatadi 6 on at

Like (1)

Report
Copy link

Link copied!

A quick and smooth PDF email addresses extractor software program. It extracts mail addresses from PDF record and store in excel, csv documents. PDF File Email Extractor - An high-quality pdf email addresses grabber software program perfectly extract email address without any trouble.

Was this reply helpful? Yes No
mrrosenthal85 53 on at

Like (0)

Report
Copy link

Link copied!

how would we do this if we wanted to download a pdf from an email, extract the email address inside the pdf, then send an email to the email address extracted from the pdf

Was this reply helpful? Yes No