Home | History | Annotate | Download | only in tools 
      1 #!/usr/bin/env python
      2 # Copyright (c) 2011 The Chromium Authors. All rights reserved.
      3 # Use of this source code is governed by a BSD-style license that can be
      4 # found in the LICENSE file.
      5 
      6 import os
      7 import tempfile
      8 import unittest
      9 
     10 import webforms_aggregator
     11 
     12 
     13 class WebformsAggregatorTest(unittest.TestCase):
     14   """Unit tests for the webforms_aggregator module."""
     15 
     16   def setUp(self):
     17     self.cookie_file = 'test.cookie'
     18     self.url1 = 'http://www.google.com'
     19     self.url2 = 'http://www.macys.com'
     20     self.domain = 'google.com'
     21     self.url_file = tempfile.NamedTemporaryFile(suffix='.txt', delete=False)
     22     self.url_file.file.write(
     23         'URLs to crawl:\n%s\n%s\n' % (self.url1, self.url2))
     24     self.url_file.close()
     25 
     26   def tearDown(self):
     27     if os.path.isfile(self.cookie_file):
     28       os.unlink(self.cookie_file)
     29     if os.path.isfile(self.url_file.name):
     30       self.url_file.close()
     31       os.unlink(self.url_file.name)
     32 
     33   def testRetrieverDownloadsPage(self):
     34     """Verify the retriever can download a page."""
     35     r = webforms_aggregator.Retriever(self.url1, self.domain, self.cookie_file)
     36     self.assertTrue(r.Download(),
     37                     msg='Retriever could not download "%s"' % self.url1)
     38 
     39   def testCrawlerFindsRegPageFromUrl(self):
     40     """Verify that the crawler is able to find a reg page from the given URL."""
     41     c = webforms_aggregator.Crawler(self.url2)
     42     self.assertTrue(
     43         c.Run(), msg='Crawler could not find the reg page of "%s"' % self.url2)
     44 
     45   def testThreadedCrawlerFindsRegPageFromUrlsFile(self):
     46     """Verify the threaded crawler finds reg page from a file of URLs."""
     47     c = webforms_aggregator.ThreadedCrawler(self.url_file.name)
     48     self.assertNotEqual(
     49         c.Run(), -1,
     50         msg='Threaded crawler could not find the reg page from the URLs file')
     51 
     52 
     53 if __name__ == '__main__':
     54   suite = unittest.TestLoader().loadTestsFromTestCase(
     55       WebformsAggregatorTest)
     56   unittest.TextTestRunner(verbosity=2).run(suite)
     57