extractiveAlgorithm.py

#This code is written and tested in python 2.7
#The library NLTK has to be installed first.
import re, nltk, heapq 
class Summary:
	def summary(self, article_text, n=5): # n indicates the number of lines of summary required 
		# article_text = re.sub(r'\[[0-9]*\]', ' ', text)
		# article_text = re.sub(r'\s+', ' ', article_text)
		formatted_article_text = re.sub('[^a-zA-Z]', ' ', article_text )  
		formatted_article_text = re.sub(r'\s+', ' ', formatted_article_text)  
		sentence_list = nltk.sent_tokenize(article_text)  
		stopwords = nltk.corpus.stopwords.words('english')
		word_freq = {}
		for word in nltk.word_tokenize(formatted_article_text):
			if word not in stopwords:
				if word not in word_freq.keys():
					word_freq[word] = 1 
				else:
					word_freq[word] += 1 
		maximum_freq = max(word_freq.values())
		for word in word_freq.keys():
			word_freq[word] = (word_freq[word]/float(maximum_freq))
		sentence_scores = {}
		for sent in sentence_list:
			for word in nltk.word_tokenize(sent.lower()):
				if word in word_freq.keys():
					if len(sent.split(' ')) < 30:
						if sent not in sentence_scores.keys():
							sentence_scores[sent] = word_freq[word]
						else:
							sentence_scores[sent] += word_freq[word]
		summary_sents = heapq.nlargest(n, sentence_scores, key=sentence_scores.get)
		summary = ' '.join(summary_sents)
		return summary

article_text = raw_input('Enter The Input Article Text: ')
S = Summary()
print(S.summary(article_text))