Extract Pages from PDF based on search in python

Question

Everything is working fine except timing. it takes lot time for my file containing 1000 pages and having 100 pages of interest.

import re
from PyPDF2 import PdfFileReader, PdfFileWriter
import glob, os

# find pages
def  findText(f, slist):
    file = open(f, 'rb')
    pdfDoc = PdfFileReader(file)
    pages = []
    for i in range(pdfDoc.getNumPages()):
        content = pdfDoc.getPage(i).extractText().lower()
        for s in slist:
            if re.search(s.lower(), content) is not None:
                if i not in pages:
                    pages.append(i)
    return pages

#extract pages
def extractPage(f, fOut, pages):
    file = open(f, 'rb')
    output = PdfFileWriter()
    pdfOne = PdfFileReader(file)
    for i in pages:
        output.addPage(pdfOne.getPage(i))
    outputStream = open(fOut, "wb")
    output.write(outputStream)
    outputStream.close()
    return

os.chdir(r"path\to\mydir")
for pdfFile in glob.glob("*.pdf"):
    print(pdfFile)
    outPdfFile = pdfFile.replace(".pdf","_searched_extracted.pdf")
    stringList = ["string1", "string2"]
    extractPage(pdfFile, outPdfFile, findText(pdfFile, stringList))

Updated code after suggestions is at:

https://gist.github.com/pra007/099f10b07be5b7126a36438c67ad7a1f

Answer 1

You could try profiling but the code is simple enough that I think you're spending most of the time in PyPDF2 code. Two options:

• You can preprocess your PDF files to store their text somewhere, which will make the search phase much faster, especially if you run multiples queries on the same PDF files
• You can try another parser such as a Python 3 version of PDFMiner, or even a parser written in a faster language

Answer 2

One thing that might help a lot is to compile your regexs just once. Instead of

def findText(f, slist):
    file = open(f, 'rb')
    pdfDoc = PdfFileReader(file)
    pages = []
    for i in range(pdfDoc.getNumPages()):
        content = pdfDoc.getPage(i).extractText().lower()
        for s in slist:
            if re.search(s.lower(), content) is not None:
                if i not in pages:
                    pages.append(i)
    return pages

try:

def  findText(f, slist):
    file = open(f, 'rb')
    pdfDoc = PdfFileReader(file)
    pages = []
    searches = [ re.compile(s.lower()) for s in slist ]
    for i in range(pdfDoc.getNumPages()):
        content = pdfDoc.getPage(i).extractText().lower()
        for s in searches:
            if s.search(content) is not None:
                if i not in pages:
                    pages.append(i)
    return pages

Also, you can short-circuit out a lot faster than you're doing:

def  findText(f, slist):
    file = open(f, 'rb')
    pdfDoc = PdfFileReader(file)
    pages = []
    searches = [ re.compile(s.lower()) for s in slist ]
    for i in range(pdfDoc.getNumPages()):
        content = pdfDoc.getPage(i).extractText().lower()
        for s in searches:
            if s.search(content) is not None:
                pages.append(i)
                break
    return pages