def test_replacement(self, s):
output = to_storage_name(s)
self.assertNotIn('..', output)
j = 0
if output == '':
self.assertTrue(set(s) <= set(removables + endottables + ['.']))
return
for c in s:
if c in removables or (c in endottables + ['.'] and (
j == 0 or j == len(output))):
# removables get removed - should not compare
# leading and trailing dots also get removed
continue
elif c in endottables + ['.']:
# either the current should be dot or the prev should be
if output[j] == '.':
j += 1
else:
self.assertEqual(output[j-1], '.')
# do not increment j, we haven't moved on yet
else:
self.assertEqual(output[j], c.lower(),
'from %r got %r removing %r and %r[%r] != %r' % (
s, output, removables, output, j, c))
j += 1
def load_page(content):
by_series = defaultdict(lambda: defaultdict(dict))
by_name = defaultdict(lambda: defaultdict(dict))
soup = BeautifulSoup(content, 'lxml')
rows = soup.findAll('tr')[5:-4]
for row in rows:
tds = row.findAll('td')
year_tvdbepno = tds[0].getText()
epname_eng = tds[1].getText().strip()
year = year_tvdbepno.split('x')[0].strip()
tvdb_epno = year_tvdbepno.split('x')[1].strip()
by_series[year][tvdb_epno] = epname_eng
by_name[to_storage_name(epname_eng)] = EpInfo(year, tvdb_epno, epname_eng)
return by_series, by_name
def test_removal(self, s):
self.assertEqual(to_storage_name(s), '')