def cli():
parser = argparse.ArgumentParser(
description="Get summary and key points from text")
parser.add_argument('-f', '--file', \
type=argparse.FileType('r'), help="filename containing text")
parser.add_argument('-t', '--text', help="text string")
parser.add_argument('-u', '--url', help="url string")
parser.add_argument('-l', '--lines', type=int, help="number of sentences")
args = vars(parser.parse_args())
num_sentences = 4 if not args['lines'] else args['lines']
if args['file']:
try:
text = args['file'].read()
print "\n".join(summarize_text(text, \
num_sentences=num_sentences))
except Exception as e:
print "error: ", e
elif args['text']:
print "\n".join(summarize_text(args['text'], \
num_sentences=num_sentences))
elif args['url']:
res = summarize_url(args['url'], num_sentences=num_sentences)
print "Summary: ", res[0]
print "\nKey Points\n==========\n*", "\n* ".join(res[1])
def cli():
parser = argparse.ArgumentParser(
description="Get summary and key points from text")
parser.add_argument('-f', '--file', \
type=argparse.FileType('r'), help="filename containing text")
parser.add_argument('-t', '--text', help="text string")
parser.add_argument('-u', '--url', help="url string")
parser.add_argument('-l', '--lines', type=int, help="number of sentences")
args = vars(parser.parse_args())
num_sentences = 4 if not args['lines'] else args['lines']
if args['file']:
try:
text = args['file'].read()
print "\n".join(summarize_text(text, \
num_sentences=num_sentences))
except Exception as e:
print "error: ", e
elif args['text']:
print "\n".join(summarize_text(args['text'], \
num_sentences=num_sentences))
elif args['url']:
res = summarize_url(args['url'],num_sentences=num_sentences)
print "Summary: ", res[0]
print "\nKey Points\n==========\n*", "\n* ".join(res[1])
def __init__(self, url, num_sentences=4, fmt='default', extractor=None):
self.url = url
if not extractor:
from core import goose_extractor
self._extr = goose_extractor
else:
from core import newspaper_extractor
self._extr = newspaper_extractor
self.title, self.meta, self.text = self._extr(url)
self.summary, self.keypoints = \
summarize_url(self.url, num_sentences, fmt)
def __init__(self, url, num_sentences=4,
fmt='default', extractor=None):
self.url = url
if not extractor:
from core import goose_extractor
self._extr = goose_extractor
else:
from core import newspaper_extractor
self._extr = newspaper_extractor
self.title, self.meta, self.text = self._extr(url)
self.summary, self.keypoints = \
summarize_url(self.url, num_sentences, fmt)
