def download_archives(self, begin_year, end_year):
     self.logger.info("downloading archives")
     downloader = Downloader('https://www.google.com/googlebooks/uspto-patents-grants-text.html')
     downloader.download_archives(self.working_dir, begin_year, end_year)
Exemple #2
0
 def test_url_matcher_matches_only_zip_files(self):
     downloader = Downloader('')
     url = 'http://somedomain/2012/patent.tgz'
     matched = downloader.url_matcher(url, 2012, 2013)
     assert not matched
Exemple #3
0
 def test_url_matcher_matches_url_from_given_period(self):
     downloader = Downloader('')
     url = 'http://somedomain/2012/patent.zip'
     matched = downloader.url_matcher(url, 2012, 2013)
     assert matched
Exemple #4
0
 def test_url_matcher_doesnt_match_url_out_of_given_period(self):
     downloader = Downloader('')
     url = 'http://somedomain/2011/patent.zip'
     matched = downloader.url_matcher(url, 2012, 2013)
     assert not matched
 def test_url_matcher_matches_url_from_given_period(self):
     downloader = Downloader("")
     url = "http://somedomain/2012/patent.zip"
     matched = downloader.url_matcher(url, 2012, 2013)
     assert matched
 def test_url_matcher_matches_only_zip_files(self):
     downloader = Downloader("")
     url = "http://somedomain/2012/patent.tgz"
     matched = downloader.url_matcher(url, 2012, 2013)
     assert not matched
 def test_url_matcher_doesnt_match_url_out_of_given_period(self):
     downloader = Downloader("")
     url = "http://somedomain/2011/patent.zip"
     matched = downloader.url_matcher(url, 2012, 2013)
     assert not matched
 def download_archives(self, begin_year, end_year):
     self.logger.info("downloading archives")
     downloader = Downloader(
         'https://www.google.com/googlebooks/uspto-patents-grants-text.html'
     )
     downloader.download_archives(self.working_dir, begin_year, end_year)