extract_text_from_pdf

# pip install PyPDF2 - > Read and parse your content pdf
# pip install requests - > request for get the pdf
# pip install BeautifulSoup - > for parse the html

from PyPDF2 import PdfFileReader
import requests
import io
from bs4 import BeautifulSoup

def getPdfMeta(pdfLink):
  response = requests.get(pdfLink)
  with io.BytesIO(response.content) as f:
    pdf = PdfFileReader(f)
    information = pdf.getDocumentInfo()
    number_of_pages = pdf.getNumPages()
    txt = f"""
    Author: {information.author}\n
    Creator: {information.creator}\n
    Producer: {information.producer}\n
    Subject: {information.subject}\n
    Title: {information.title}\n
    Number of pages: {number_of_pages}
    """
    # Here the metadata of your pdf
    print(f'Metadata:\n {txt}')


def getPdfContent(pdfLink, numpage):
  response = requests.get(pdfLink)
  with io.BytesIO(response.content) as f:
    pdf = PdfFileReader(f)
    numpage=numpage
    page = pdf.getPage(numpage)
    page_content = page.extractText()
    #page_content = page_content.replace('\n', '')
    #page_content = page_content.replace('˜', 'fi')
    #page_content = page_content.replace('˚', 'ff')
    #tokenized_content = nltk.sent_tokenize(page_content)
      
  return page_content

pdfLink1 = "https://www.osce.org/files/f/documents/9/d/499420.pdf"
getPdfMeta(pdfLink1)
getPdfContent(pdfLink1, 0)