Text-Summarization/api.py at master · ab93/Text-Summarization · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
#!/usr/bin/python

from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.kl import KLSummarizer
from sumy.summarizers.lex_rank import LexRankSummarizer
from sumy.summarizers.lsa import LsaSummarizer
from sumy.summarizers.luhn import LuhnSummarizer
from sumy.summarizers.sum_basic import SumBasicSummarizer
from sumy.summarizers.text_rank import TextRankSummarizer


from sumy.nlp.stemmers import Stemmer
from sumy.utils import get_stop_words


LANGUAGE = "spanish"
SENTENCES_COUNT = 10


#if __name__ == "__main__":

def klReferenceSummary(path):
	sentencesList=[]
	parser = PlaintextParser.from_file(path, Tokenizer(LANGUAGE))
	stemmer = Stemmer(LANGUAGE)
	summarizer = KLSummarizer(stemmer)
	summarizer.stop_words = get_stop_words(LANGUAGE)


	for sentence in summarizer(parser.document, SENTENCES_COUNT):
		#print(sentence._text)
		sentencesList.append(sentence._text)

	return sentencesList

def lexrankReferenceSummary(path):
	sentencesList=[]
	parser = PlaintextParser.from_file(path, Tokenizer(LANGUAGE))
	stemmer = Stemmer(LANGUAGE)
	summarizer = LexRankSummarizer(stemmer)
	summarizer.stop_words = get_stop_words(LANGUAGE)


	for sentence in summarizer(parser.document, SENTENCES_COUNT):
		#print(sentence._text)
		sentencesList.append(sentence._text)

	return sentencesList

def lsaReferenceSummary(path):
	sentencesList=[]
	parser = PlaintextParser.from_file(path, Tokenizer(LANGUAGE))
	stemmer = Stemmer(LANGUAGE)
	summarizer = LsaSummarizer(stemmer)
	summarizer.stop_words = get_stop_words(LANGUAGE)


	for sentence in summarizer(parser.document, SENTENCES_COUNT):
		#print(sentence._text)
		sentencesList.append(sentence._text)

	return sentencesList

def luhnReferenceSummary(path):
	sentencesList=[]
	parser = PlaintextParser.from_file(path, Tokenizer(LANGUAGE))
	stemmer = Stemmer(LANGUAGE)
	summarizer = LuhnSummarizer(stemmer)
	summarizer.stop_words = get_stop_words(LANGUAGE)


	for sentence in summarizer(parser.document, SENTENCES_COUNT):
		#print(sentence._text)
		sentencesList.append(sentence._text)

	return sentencesList

def sumbasicReferenceSummary(path):
	sentencesList=[]
	parser = PlaintextParser.from_file(path, Tokenizer(LANGUAGE))
	stemmer = Stemmer(LANGUAGE)
	summarizer = SumBasicSummarizer(stemmer)
	summarizer.stop_words = get_stop_words(LANGUAGE)


	for sentence in summarizer(parser.document, SENTENCES_COUNT):
		#print(sentence._text)
		sentencesList.append(sentence._text)

	return sentencesList

def textrankReferenceSummary(path):
	sentencesList=[]
	parser = PlaintextParser.from_file(path, Tokenizer(LANGUAGE))
	stemmer = Stemmer(LANGUAGE)
	summarizer = TextRankSummarizer(stemmer)
	summarizer.stop_words = get_stop_words(LANGUAGE)


	for sentence in summarizer(parser.document, SENTENCES_COUNT):
		#print(sentence._text)
		sentencesList.append(sentence._text)

	return sentencesList