Extract text from a PDF given its URL

pdf_url_text.py

import requests
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from io import StringIO, BytesIO

def convert_pdf_to_txt(url, pages=None):
    if not pages:
        pagenums = set()
    else:
        pagenums = set(pages)
    output = StringIO()
    manager = PDFResourceManager()
    converter = TextConverter(manager, output, laparams=LAParams())
    interpreter = PDFPageInterpreter(manager, converter)

    r = requests.get(url)
    infile = BytesIO(r.content)

    for page in PDFPage.get_pages(infile, pagenums):
        interpreter.process_page(page)
    infile.close()
    converter.close()
    text = output.getvalue()
    output.close()
    return text

if __name__ == '__main__':
    url = input("Enter URL of PDF from which to extract text: ")
    # Example URL: https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf
    # Output: 
    # >>> Dummy PDF file

    output = convert_pdf_to_txt(url)
    print(output)