I need to read the contents of a pdf one page at a time and feed it on Chatgpt. Now I need to fetch the results and store in a word, with heading Page followed by the response of chatgpt. How do I do this for each page? Currently I’m using do-while and read pdf text
*with heading as page number
Welcome to the community
Do while and read pdf is what you would do…
And for writing use append text activity in word activities to write responses to word
Cheers
Check this video
Extract pages from a PDF file - RPA Component | UiPath Marketplace | Overview
Extract selected page(s) from a PDF file
Hi @NAVNEETH ,
You can read the entire page and then segment each page into 1 value
it will be an array of String
From here you can use it one after another
When reading pdf, you can extract pages or have a regex way to get each page out
Regards,
Hi @NAVNEETH
You can try this
- Assign:
currentPageNumber = 1
- Do While: Condition is
currentPageNumber <= totalPages
- Read PDF Text: Range is
currentPageNumber.ToString
- HTTP Request (if using API) or Your Method of Sending to ChatGPT: Send the extracted text and receive the response.
- Word Application Scope: Specify the file path for the Word document.
- If: Condition is
currentPageNumber = 1
- Add Word Document activity (if it doesn’t exist)
- Add Heading: Text is
"Page " + currentPageNumber.ToString
- Append Text: Text is the response from ChatGPT.
- If: Condition is
- Assign:
currentPageNumber = currentPageNumber + 1
- Read PDF Text: Range is
- End Do While
Hope this helps