extract pages from pdf python code example
Example 1: how to loop through pages of pdf using python
import PyPDF2
import re
for k in range(1,100):
object = PyPDF2.PdfFileReader("C:/my_path/file%s.pdf"%(k))
NumPages = object.getNumPages()
String = "New York State Real Property Law"
for i in range(0, NumPages):
PageObj = object.getPage(i)
print("this is page " + str(i))
Text = PageObj.extractText()
ResSearch = re.search(String, Text)
print(ResSearch)
Example 2: python split pdf pages
from PyPDF2 import PdfFileWriter, PdfFileReader
inputpdf = PdfFileReader(open("document.pdf", "rb"))
for i in range(inputpdf.numPages):
output = PdfFileWriter()
output.addPage(inputpdf.getPage(i))
with open("document-page%s.pdf" % i, "wb") as outputStream:
output.write(outputStream)