def Random(rsc_file, dst_file, count):
language = "chinese"
parser = PlaintextParser.from_file(rsc_file,
Tokenizer(language),
encoding='utf-8')
stemmer = Stemmer(language) # 语言容器
summarizer = RandomSummarizer(stemmer) # LSA算法
summarizer.stop_words = get_stop_words(language)
with open(dst_file, 'w', encoding='utf-8') as f:
for sentence in summarizer(parser.document, count):
f.write(str(sentence))
f.write('\n')
print(sentence)
import os
#create folder
def createFolder(directory):
try:
if not os.path.exists(directory):
os.makedirs(directory)
except OSError:
print('Error: Creating directory. ' + directory)
LANGUAGE = "bangla"
SENTENCES_COUNT = 2
if __name__ == "__main__":
createFolder('Dataset/NCTB/RandomSummary/')
for i in range(1, 140):
serial_no = str(i)
path = "Dataset/NCTB/Source/" + serial_no + ".txt"
parser = PlaintextParser.from_file(path, Tokenizer(LANGUAGE))
stemmer = Stemmer(LANGUAGE)
summarizer = Summarizer(stemmer)
summarizer.stop_words = get_stop_words(LANGUAGE)
summary = ""
for sentence in summarizer(parser.document, SENTENCES_COUNT):
summary = summary + " " + str(sentence)
fi = open('Dataset/NCTB/RandomSummary/' + serial_no + '.txt', '+w')
fi.write(summary)