Skip to content

Instantly share code, notes, and snippets.

View benmccloskey's full-sized avatar

Benjamin McCloskey benmccloskey

View GitHub Profile
import re
import PyPDF2
import spacy
class PdfParser():
def __init__(self, file_path):
self.file_path = file_path
def pdf_reader(self) -> str:
content = ''
opener = open(self.file_path, 'rb')