# importing required modules
import sys
from urllib.parse import urlparse
import requests
import io
import os
from pypdf import PdfReader
# Reciving paramater

n = len(sys.argv)
url = sys.argv[1] #'https://mmlorders.s3.ap-south-1.amazonaws.com/orders/3/TNCH010048222020/TNCH010048222020-2022-04-01-1.pdf'
a = urlparse(url)
file_name = os.path.basename(a.path)
file_name = file_name.replace("pdf","txt")

# loading file content from external file
response = requests.get(url)
f = io.BytesIO(response.content)

# creating a pdf reader object
reader = PdfReader(f)
text = ''
for page_num in range(len(reader.pages)):
    page = reader.pages[page_num]
    text += page.extract_text()

# Saving pdf content to text file
f = open("/var/www/html/web/files/order_text/"+file_name, "w")
f.write(text)
f.close()
#print(text)