hi all, I want to read pdf document line by line and translate it to a different language. below code works sometimes for couple of pages and sometimes it doesn’t works at all. please can you let me know what changes I need to make
# Importing required modules
import PyPDF2
from googletrans import Translator
# Loop for reading all the Pages
URL_COM = 'translate.google.com'
URL_LV = 'translate.google.da'
LANG = "da"
file = open('C:/Users/ambar/OneDrive/Desktop/dummy/a1.pdf', 'rb')
reader = PyPDF2.PdfFileReader(file)
num_pages = reader.numPages
for p in range(num_pages):
page = reader.getPage(p)
print("Page No: ", p)
text = page.extractText()
translator = Translator(service_urls=[URL_COM, URL_LV])
translation = translator.translate(text, dest=LANG)
result_text = translation.text.replace("\n", " ").replace("W", "")
print ( result_text)