Sunday, July 28, 2024

Display PDF text on Python terminal

# pip install pypdf


def extractFromPage1(innFile, pageNumbers):

    reader = PdfReader(innFile)

    for pageNumber in pageNumbers:

      if pageNumber < len(reader.pages):

        page = reader.pages[pageNumber]

        text = page.extract_text()

        print(text)

        input("Press any key to continue\n")

      else: # If page does not exist

        print(f"page {pageNumber} does not exist")

        input("Press any key to continue\n")


innFile = 'US_Declaration.pdf'

extractFromPage1(innFile, [7, 2]) # Page 7 does not exist in file

No comments:

Post a Comment