Return to 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))

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

Takes 2.02 minutes

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

startTime = datetime.now()
# process Text
def  processText(f):
    file = open(f, 'rb')
    pdfDoc = PdfFileReader(file)
    d = {}
    for i in range(pdfDoc.getNumPages()):
        content = pdfDoc.getPage(i).extractText().lower()
        d[i] = content
    return d


# find pages
def  findText(d, slist):
    pages = []
    for key, value in d.items():
        for s in slist:
            if re.search(s.lower(), value) is not None:
                if key not in pages:
                    pages.append(key)
    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_new.pdf")
    stringList = ["String1", "String2"]
    extractPage(pdfFile, outPdfFile, findText(processText(pdfFile), stringList))
print (datetime.now() - startTime)

Takes 2 minutes