content = content.replace('.', ' ')
content = content.replace('∙', ' ')
content = content.replace('˚', '°')
content = content.replace('~', ' ')
content = content.replace('=', ' ')
content = content.replace('≤', ' ')
content = content.replace('−', '-')
content = content.replace('α', 'a')
content = content.replace('δ', 'b')
return content
#get row data from database
data = Database()
stopwords = nltk.corpus.stopwords.words('english')
synopses = data.getAbstract()
#initial abstract list
abstract_list=[]
TotalCountList = []
for i in synopses:
abstract_id = i[0]
abstract_list.append(str(abstract_id))
content = normalizeString(i[1])
allwords_stemmed = tokenize_and_stem(content)
allwords_stemmed = [word for word in allwords_stemmed if word not in stopwords]
count_list = count_words(allwords_stemmed)
#print(tuple_count)
TotalCountList.append(count_list)
