def initialize(self, article):
similarity_array = []
# similarity_array.append(article)
test = self.articleSummerization(article, 1) # in one line
# for i in summerizedSentence:
# test=str(i)
print('-------Summerized Title-------')
print(test)
sitesContainingArticle, scrapId = self.googleSearch(article)
print('sites_length_after_google search', len(sitesContainingArticle))
for index, url in enumerate(sitesContainingArticle):
print('URL ', url, scrapId[index], '\n')
raw_html = self.simple_get(url) #full page site content
try:
soup = BeautifulSoup(
raw_html, 'html.parser') #proper formattinh raw_html
# print('hua idhar')
# print(soup)
except Exception as e:
print(e)
return 0, []
_ = [s.extract() for s in soup('script')]
soup_article = soup.find_all('div', {"class": scrapId[index]})
# print(soup_article)
article_string = ''
for data in soup_article:
# print(data)
article_string += data.text
# article_string += data.text
# print(article_string)
if not article_string == '':
# print('aaya\n')
similarity_array.append(
self.articleSummerization(article_string, 5))
else:
print('nahi aaya\n')
pass
# for c in similarity_array:
# print('\n\n\n',c)
mylsa = LSA()
wmdinit = WordMoverDistance()
length = len(similarity_array)
# print(length)
if length == 0:
return 0, sitesContainingArticle
else:
count = 0
score_array = []
while (count < length):
print('\n\n', similarity_array[count])
lsa_similarity = mylsa.start([article + ' ' + article] +
similarity_array, count + 1)
wmdinit.data_accept(similarity_array[count], article)
wmddistance = wmdinit.model()
print('wordmover distance is', wmddistance)
fuzzy = Fuzzy(lsa_similarity, wmddistance)
score = fuzzy.get_score_data()
# score = score/10
print('final score ', score)
score_array.append(score)
count = count + 1
score_array = sorted(score_array, key=lambda x: x, reverse=True)
return min(100,
np.around(sum(score_array[:2]), decimals=2) *
100), sitesContainingArticle
# wmdinit=wordmover.WordMoverDistance(titles[count],titles[0])
# wmddistance=wmdinit.model()
