def test_arias_model(self):
cutoff_percent = 60
window = 2
a = Arias(cutoff_percent, window)
content_arias = a.analyze(big_html_doc)
# now compute the actual content
blocks = Blockifier.blockify(big_html_doc)
actual_content_indices = [1, 2, 3]
actual_content = ' '.join([blocks[k].text for k in actual_content_indices])
self.assertEqual(actual_content, content_arias)
def test_arias_model(self):
cutoff_percent = 60
window = 2
a = Arias(cutoff_percent, window)
content_arias = a.analyze(big_html_doc)
# now compute the actual content
blocks = Blockifier.blockify(big_html_doc)
actual_content_indices = [1, 2, 3]
actual_content = ' '.join(
[blocks[k].text for k in actual_content_indices])
self.assertEqual(actual_content, content_arias)
#! /usr/bin/env python
# Run a particular algorithm on the entire set of documents
from dragnet import Arias as technique
import os
for site in os.listdir('documents'):
sitepath = os.path.join('documents', site)
for document in os.listdir(sitepath):
# Make sure the output directory exists
try:
os.makedirs(os.path.join('output', site))
except:
pass
# Read in, analyze, write out
inpath = os.path.join(sitepath, document)
outpath = os.path.join('output', site, document)
print 'Working on %s' % inpath
with open(inpath) as inf:
with open(outpath, 'w+') as outf:
outf.write(technique.analyze(inf.read(), inpath))