-
Notifications
You must be signed in to change notification settings - Fork 0
/
server.py
66 lines (50 loc) · 2.01 KB
/
server.py
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
import re
import nltk
from flask import Flask, request
from flask_cors import cross_origin
app = Flask(__name__)
# TODO: Clean up
def summarize(article_text):
article_text = re.sub(r"\[[0-9]*\]", " ", article_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_frequencies = {}
for word in nltk.word_tokenize(formatted_article_text):
if word not in stopwords:
if word not in word_frequencies.keys():
word_frequencies[word] = 1
else:
word_frequencies[word] += 1
maximum_frequency = max(word_frequencies.values())
for word in word_frequencies.keys():
word_frequencies[word] = word_frequencies[word] / maximum_frequency
sentence_scores = {}
for sent in sentence_list:
for word in nltk.word_tokenize(sent.lower()):
if word in word_frequencies.keys():
if len(sent.split(" ")) < 30:
if sent not in sentence_scores.keys():
sentence_scores[sent] = word_frequencies[word]
else:
sentence_scores[sent] += word_frequencies[word]
import heapq
summary_sentences = heapq.nlargest(7, sentence_scores, key=sentence_scores.get)
return " ".join(summary_sentences)
def check_nltk_resources():
try:
nltk.data.find("tokenizers/punkt")
nltk.data.find("corpora/stopwords")
except LookupError:
print("Downloading NLTK resources....")
nltk.download("punkt")
nltk.download("stopwords")
@app.route("/summarize", methods=["POST"])
@cross_origin(origins=["*"])
def text_summarize():
article_text = request.get_json()
check_nltk_resources()
summary = summarize(article_text)
return dict(data=summary)