Last active
February 25, 2023 09:36
-
-
Save benmccloskey/bf6aaee84327d4270922a53e9ee23d7f to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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') | |
pdf = PyPDF2.PdfFileReader(opener) | |
num_pages = pdf.numPages | |
for i in range(0,num_pages): | |
content+= pdf.getPage(i).extractText() + '\n' | |
content = ' '.join(content.replace(u'\xa0', ' ').strip().split()) | |
page_number_removal = r"\d{1,3} of \d{1,3}" | |
page_number_removal_pattern = re.compile(page_number_removal, re.IGNORECASE) | |
content = re.sub(page_number_removal_pattern, '',content) | |
return content | |
def date_extractor(self) -> set: | |
text = self.pdf_reader() | |
date_label = ['DATE'] | |
nlp = spacy.load('en_core_web_lg') | |
doc = nlp(text) | |
dates_pattern = re.compile(r'(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})') | |
dates = set((ent.text) for ent in doc.ents if ent.label_ in date_label) | |
filtered_dates = set(date for date in dates if not dates_pattern.match(date)) | |
sorted_dates = sorted(list(filtered_dates),reverse=True) | |
return sorted_dates |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment