genSum.py

import spacy
from spacy.lang.en.stop_words import STOP_WORDS
from string import punctuation
from heapq import nlargest
import spacy.cli
import sys

def summarize(text, per):
    nlp = spacy.load("en_core_web_md")
    f = open(text, "r")
    texts = f.read()
    doc = nlp(texts)

    tokens = [token.text for token in doc]
    word_frequencies = {}
    for word in doc:
        if word.text.lower() not in list(STOP_WORDS):
            if word.text.lower() not in punctuation:
                if word.text not in word_frequencies.keys():
                    word_frequencies[word.text] = 1
                else:
                    word_frequencies[word.text] += 1
    max_frequency=max(word_frequencies.values())

    for word in word_frequencies.keys():
        word_frequencies[word] = word_frequencies[word]/max_frequency

    sentence_tokens = []
    for sent in doc.sents:
        sentence_tokens.append(sent)
    
    sentence_scores = {}
    for sent in sentence_tokens:
        for word in sent:
            if word.text.lower() in word_frequencies.keys():
                if sent not in sentence_scores.keys():
                    sentence_scores[sent]=word_frequencies[word.text.lower()]
                else:
                    sentence_scores[sent]+=word_frequencies[word.text.lower()]
    select_length=int(len(sentence_tokens)*per)
    if select_length < 1:
        select_length = 1
    summary=nlargest(select_length, sentence_scores,key=sentence_scores.get)
    final_summary=[word.text for word in summary]
    summary=''.join(final_summary)
    return summary

if __name__ == '__main__':
    summary = summarize(sys.argv[1], 0.05)
    with open(f"{sys.argv[2]}/summary.txt", "w") as f:
        f.write(summary)