yatesconsulting
yatesconsulting
/ parsepdf.py
Created
May 19, 2021 14:21
— forked from gchristian/parsepdf.py
parse pdf into smaller pdfs based on key value
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #separate pdf based on a phrase that can be used to delineate break points and names files by first word after that break point | |
| import PyPDF2 | |
| import pdfplumber | |
| if __name__ == '__main__': | |
| pdf_path = 'MBA Report Creator.pdf' | |
| pdf_break_point = 'Student_Number ' | |
| base_pdf = PyPDF2.PdfFileReader(pdf_path) | |
| new_pdf = PyPDF2.PdfFileWriter() |