Code Template Read PDF File from URL by Python

pdf.reader.py

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

def download_pdf(url):
    response = requests.get(url)
    return response.content

def extract_text_from_pdf(pdf_content):
    resource_manager = PDFResourceManager()
    string_io = io.StringIO()
    converter = TextConverter(resource_manager, string_io, laparams=LAParams())
    page_interpreter = PDFPageInterpreter(resource_manager, converter)

    text = ''
    pdf_io = BytesIO(pdf_content)
    for page in PDFPage.get_pages(pdf_io, caching=True, check_extractable=True):
        page_interpreter.process_page(page)
        text += string_io.getvalue()
        string_io.truncate(0)
        string_io.seek(0)

    converter.close()
    string_io.close()

    return text

if __name__ == '__main__':
    url = 'http://www.host.com/assets/file.pdf'
    pdf_content = download_pdf(url)
    text = extract_text_from_pdf(pdf_content)
    print(text)