extract_text_in_pdf.py

import sys
import time
import PyPDF2
import shutil
from pdfrw import PdfReader, PdfWriter

file = sys.argv[1]

get_name_file = file.split('.')

pdfFileObj = open(file, 'rb')
pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
num_pages = pdfReader.getNumPages()

print (num_pages)

def extractPages():
	print('Extraindo txt das paginas...\nAguarde, essa etapa pode demorar um pouco\n')
	for page in range(1, num_pages+1):
		pdfFileObj = open(file, 'rb')
		pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
		file_txt = open(get_name_file[0]+'.txt', 'a')
		pageObj = pdfReader.getPage(page)
		print('Extraindo pagina {}'.format(page))
		pageObj_ = pageObj.extractText().strip()
		file_txt.write((pageObj_+'\n').encode("utf-8"))
		file_txt.close()

print('---Texto extraido---\n')

extractPages()