def usingTitleAlgorithm(userinput): #nltk's english stopword list stop = ['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', 'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', 'himself', 'she', 'her', 'hers', 'herself', 'it', 'its', 'itself', 'they', 'them', 'their', 'theirs', 'themselves', 'what', 'which', 'who', 'whom', 'this', 'that', 'these', 'those', 'am', 'is', 'are', 'was', 'were', 'be', 'been', 'being', 'have', 'has', 'had', 'having', 'do', 'does', 'did', 'doing', 'a', 'an', 'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while', 'of', 'at', 'by', 'for', 'with', 'about', 'against', 'between', 'into', 'through', 'during', 'before', 'after', 'above', 'below', 'to', 'from', 'up', 'down', 'in', 'out', 'on', 'off', 'over', 'under', 'again', 'further', 'then', 'once', 'here', 'there', 'when', 'where', 'why', 'how', 'all', 'any', 'both', 'each', 'few','more', 'most', 'other', 'some', 'such', 'no', 'nor', 'not', 'only', 'own', 'same', 'so', 'than', 'too', 'very', 'can', 'will', 'just', 'don', 'should', 'now'] url = str(userinput) title, htmlText = web_crawler(url) qry = PunktWordTokenizer().tokenize(title) #tokenize title qry = [words for words in qry if words.lower() not in stop] #Run Query through stopwords totalText = PunktSentenceTokenizer().tokenize(htmlText) textList = [] for i in totalText: i = PunktWordTokenizer().tokenize(i.strip('.')) textList.append(i) sentenceRanks = summarizer(qry, textList) finalResults = [] for num in range(1,4): #skipping the first sentence because it's just going to be the title ind = sentenceRanks[num][0] finalResults.append(' '.join(textList[ind])) finalResults.append(title) return finalResults
def usingSentenceIntersectionAlgorithm(userinput): url = userinput title, htmlText = web_crawler(url) qry = PunktWordTokenizer().tokenize(title) #tokenize title totalText = PunktSentenceTokenizer().tokenize(htmlText) textList = [] for i in totalText: i = PunktWordTokenizer().tokenize(i.strip('.')) textList.append(i) ranks = sentence_ranks(textList) ranks_sorted = sorted(ranks.items(), key = operator.itemgetter(1)) ranks_sorted.reverse() finalResults = [] for num in range(1,4): #skipping the first sentence because it's just going to be the title finalResults.append(ranks_sorted[num][0]) finalResults.append(title) return finalResults