parse pdf into smaller pdfs based on key value

parsepdf.py

#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()
	next_student_file = None
	page_count = 0
	
	with pdfplumber.open(pdf_path) as pdf:
		
		for page in pdf.pages:
			page_text= page.extract_text()
			if pdf_break_point in page_text:
				
				if new_pdf.getNumPages() > 0 and next_student_file is not None:
					with open(next_student_file + ".pdf", 'wb') as fh:
							new_pdf.write(fh)
							
					new_pdf = PyPDF2.PdfFileWriter()
					new_pdf.addPage(base_pdf.getPage(page_count))
				else:
					new_pdf.addPage(base_pdf.getPage(page_count))
					
				next_student_file = page_text.split(pdf_break_point)[1].split("\n")[0].strip()
			else:
				new_pdf.addPage(base_pdf.getPage(page_count))
			
			page_count = page_count + 1
	
	if new_pdf.getNumPages() > 0 and next_student_file is not None:
		with open(next_student_file + ".pdf", 'wb') as fh:
				new_pdf.write(fh)