Reads a page from a PDF by page number and cleans the contents

pdf_page_cleaner.py

import re
import string

import PyPDF2

def clean_pdf_text(pdfobj, page_num):
    # Get text from PDF object by page number
    page_text = pdfobj.getPage(page_num).extractText()
    # Remove double-spaces
    page_text = page_text.replace("  ", " ")
    # Remove non-ASCII chars
    page_text = filter(
        lambda x: x in set(string.printable), page_text)
    # Remove page-broken hyphens and all newlines
    page_text = page_text.replace("-\n", "").replace("\n", "")
    # Split at InDesign filename and remove .indd
    terminus = "\d+_.*_.*\.indd"
    page_text = re.sub(terminus, "", re.split(terminus, page_text)[0])
    return page_text

# Example
pdf = PyPDF2.PdfFileReader(open("my.pdf", "rb"))
print(clean_pdf_text(pdf, 5))