process-content.py

import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.stem import PorterStemmer
from nltk.stem import LancasterStemmer


class PlagiarismChecker:
    def prepare_content(self, content):
        # STOP WORDS
        stop_words = set(stopwords.words('english'))
        # TOKENIZE
        word_tokens = word_tokenize(content)
        filtered_content = []
        # STEMMING
        porter = PorterStemmer()
        for w in word_tokens:
            if w not in stop_words:
                w = w.lower()
                word = porter.stem(w)
                filtered_content.append(word)

        return filtered_content