Python lsa.LsaSummarizer类代码示例

def summarizeFile(inputFile):
	summarizer = LsaSummarizer(stem_word)
	summarizer.stop_words = get_stop_words("english")
	url = findURLS(inputFile)
	if url != None:
		if url[-1] == '.':
			url = url[0:-1]
		#print (url)
		#urlContent = 'Summary from URL ['+url+']: \n'
		urlContent = ''
		try:
			parser = HtmlParser.from_url(url, Tokenizer("english"))		
			for sentence in summarizer(parser.document, 3):
				urlContent = urlContent + str(sentence) + '\n'
		except:
			#print (sys.exc_info()[0])
			urlContent = ''
	content = inputFile.read()
	parser = PlaintextParser.from_string(content, Tokenizer(LANGUAGE))
	#summarizer = LsaSummarizer(stem_word)
	#summarizer.stop_words = get_stop_words(LANGUAGE)
	#summary = 'Event Summary: \n'
	summary = ''
	try:
		for sentence in summarizer(parser.document, SENTENCES_COUNT_1):
			summary = summary + str(sentence) + '\n'
	except AssertionError:
		return None
	if url != None:
		return summary + urlContent
	return summary

    def test_single_sentence(self):
        document = build_document(("I am the sentence you like",))
        summarizer = LsaSummarizer()
        summarizer.stopwords = ("I", "am", "the",)

        sentences = summarizer(document, 10)
        self.assertEqual(len(sentences), 1)
        self.assertEqual(to_unicode(sentences[0]), "I am the sentence you like")

def test_single_sentence():
    document = build_document(("I am the sentence you like",))
    summarizer = LsaSummarizer()
    summarizer.stopwords = ("I", "am", "the",)

    sentences = summarizer(document, 10)
    assert len(sentences) == 1
    assert to_unicode(sentences[0]) == "I am the sentence you like"

def lsa(comment,parser,num):
	summarizer = LsaSummarizer(stemmer)
	summarizer.stop_words = get_stop_words(LANGUAGE)

	LSAstr = ''
	for sentence in summarizer(parser.document,num):
		LSAstr += str(sentence)

	return LSAstr

def summarize(filename, num_sentences):
    with open (filename, "r") as myfile:
        data=myfile.read()
    parser = PlaintextParser.from_string(data, Tokenizer('english')) 
    summarizer = LsaSummarizer(stem_word)
    summarizer.stop_words = get_stop_words("english")
    summary = ""
    for sentence in summarizer(parser.document, num_sentences):
        summary += sentence.__unicode__().encode('ascii', 'ignore').replace('\"', '').replace('\'', '').strip() + " " 
    return summary

 def summary(self, int1, int2):
     # int1, int2 are the places between which to look for
     # the summary to be taken (slicing the corpus as a string)
     parser = PlaintextParser(self.corpus[int1:int2], Tokenizer("english"))
     summarizer = LsaSummarizer(stem_word)
     summarizer.stop_words = get_stop_words("english")
     self.summary_text = " ".join(
         map(lambda x:x._text,
             summarizer(parser.document, 20)))
     return self.summary_text

    def test_issue_5_sigma_can_multiply_matrix_v(self):
        """Source: https://github.com/miso-belica/sumy/issues/5"""
        parser = PlaintextParser.from_string(
            load_resource("articles/sigma_can_multiply_matrix_v.txt"),
            Tokenizer("english")
        )
        summarizer = LsaSummarizer(english_stemmer)
        summarizer.stop_words = get_stop_words("english")

        sentences = summarizer(parser.document, 20)
        self.assertEqual(len(sentences), 20)

def test_article_example():
    """Source: http://www.prevko.cz/dite/skutecne-pribehy-deti"""
    parser = PlaintextParser.from_string(
        load_resource("articles/prevko_cz_1.txt"),
        Tokenizer("czech")
    )
    summarizer = LsaSummarizer(Stemmer("czech"))
    summarizer.stop_words = get_stop_words("czech")

    sentences = summarizer(parser.document, 20)
    assert len(sentences) == 20

    def test_real_example(self):
        """Source: http://www.prevko.cz/dite/skutecne-pribehy-deti"""
        parser = PlaintextParser.from_string(
            load_resource("snippets/prevko.txt"),
            Tokenizer("czech")
        )
        summarizer = LsaSummarizer(Stemmer("czech"))
        summarizer.stop_words = get_stop_words("czech")

        sentences = summarizer(parser.document, 2)
        self.assertEqual(len(sentences), 2)

def main(url, num_sentences=10, language='english'):
	parser = HtmlParser.from_url(url, Tokenizer(language))
	stemmer = Stemmer(language)
	summarizer = Summarizer(stemmer)
	summarizer.stop_words = get_stop_words(language)
	for sentence in summarizer(parser.document, num_sentences):
		print(sentence)

def summarize(text, n_sentences, sep='\n'):
    '''
    Args:
        text (str or file): text itself or file in memory of text
        n_sentences (int): number of sentences to include in summary

    Kwargs:
        sep (str): separator to join summary sentences

    Returns:
        (str) n_sentences-long, automatically-produced summary of text
    '''

    if isinstance(text, str):
        parser = PlaintextParser.from_string(text, Tokenizer(LANGUAGE))
    elif isinstance(text, file):
        parser = PlaintextParser.from_file(text, Tokenizer(LANGUAGE))
    else:
        raise TypeError('text must be either str or file')

    stemmer = Stemmer(LANGUAGE)

    summarizer = Summarizer(stemmer)
    summarizer.stop_words = get_stop_words(LANGUAGE)

    return '\n'.join(str(s) for s in summarizer(parser.document, n_sentences))

def summarize(string, summary_length = 1, language = "english"):
    string = string.lower() if string.isupper() else string
    parser = PlaintextParser.from_string(string, Tokenizer(language))
    stemmer = Stemmer(language)
    summarizer = Summarizer(stemmer)
    summarizer.stop_words = get_stop_words(language)

    return ". ".join([str(sentence) for sentence in summarizer(parser.document, summary_length)]) 

def summarize(text):
    total = ""
    parser = PlaintextParser.from_string(text, Tokenizer(LANGUAGE))
    stemmer = Stemmer(LANGUAGE)
    summarizer = Summarizer(stemmer)
    summarizer.stop_words = get_stop_words(LANGUAGE)
    for sentence in summarizer(parser.document, SENTENCES_COUNT):
        total += str(sentence)
    return total

 def summarizeText(self, body, numSentences = 10):
     """Summarizes body of text to numSentences
     """
     #parser = PlaintextParser.from_string(body, Tokenizer(self.LANG))
     parser = PlaintextParser.from_string(body, Tokenizer(self.LANG))        
     stemmer = Stemmer(self.LANG)
     summarizer = SumySummarizer(stemmer)
     summarizer.stop_words = get_stop_words(self.LANG)
     summary = ' '.join([str(sentence).decode('utf-8') for sentence in summarizer(parser.document, numSentences)])
     return summary

def summarize(content):
    parser = PlaintextParser.from_string(content.body, Tokenizer(LANGUAGE))
    stemmer = Stemmer(LANGUAGE)
    summarizer = Summarizer(stemmer)
    summarizer.stop_words = get_stop_words(LANGUAGE)
    text = '\n'.join(
        [str(sentence) for sentence in summarizer(parser.document, COUNT)]
    )
    summary = Summary(content=content, summary=text)
    summary.save()