def test_in_the_news(self):
from tablib import Dataset, Databook
data = Dataset()
mention = Mention("http://www.lvbusinesspress.com/articles/2011/11/28/news/iq_49033368.txt")
mention.append(data)
mention = Mention("http://www.lasvegasgleaner.com/las_vegas_gleaner/2011/12/unwitting-local-tools-of-corporate-overlords-hire-a-lawyer.html - NPRI in the News")
mention.append(data)
self.assertEqual(len(data), 2)
self.assertEqual(len(data.filter(['in-the-news'])), 1)
from core import HEADERS
from core.parsers.mention import Mention
date_prefix = datetime.date.today().strftime("%Y%m%d")
parser = ArgumentParser()
parser.add_argument("input", metavar="INPUT", type=open)
parser.add_argument("-o", "--output", default="%s-newsclips.xls" % date_prefix)
args = parser.parse_args()
logging.basicConfig(level=logging.DEBUG)
log = logging.getLogger("newsclips.main")
data = tablib.Dataset(headers=HEADERS)
for line in args.input:
item = {}
line = line.strip()
if not line:
continue
mention = Mention(line)
mention.append(data)
book = tablib.Databook((data, data.filter(["in-the-news"])))
with open(args.output, "wb") as fp:
fp.write(book.xls)
