def test_cez():
cez_path = pathlib.Path('samples/cez.html')
with open(cez_path) as f:
bs = BeautifulSoup(f, 'html.parser')
result = parse.parse_page('výroba elektřiny', '110100146', bs)
assert result.id == '110100146'
assert result.pocet_zdroju == 72
assert result.vykony[0].lic_id == '110100146'
assert result.vykony[0].druh == 'Elektrický'
assert result.vykony[0].technologie == 'Celkový'
assert result.vykony[0].mw == 9716.003
assert result.provozovny[0].vykony[0].technologie == 'Celkový'
assert result.provozovny[0].vykony[0].druh == 'Elektrický'
assert result.provozovny[0].vykony[0].mw == 7.3
assert result.provozovny[0].vykony[3].technologie == 'Parní'
assert result.provozovny[0].vykony[3].mw == 49.8
assert result.provozovny[0].pocet_zdroju == 2
assert result.provozovny[-1].pocet_zdroju == 1
assert result.provozovny[-1].nazev == 'Elektrárna Ledvice IV B6'
assert result.provozovny[-1].vykony[-1].technologie == 'Parní'
assert result.provozovny[-1].vykony[-1].mw == 1288.130
def get_data(
business: str, lic_ids: List, url: str, start: int, end: int
) -> List[parse.Licence]:
count = 0
lic_list = []
for lic_id in lic_ids[start:end]:
params = {'lic-id': lic_id}
try:
soup = parse.request_soup(url, count, params=params)
parsed_lic = parse.parse_page(business, lic_id, soup)
except Error as e:
print(e)
print(f'Error occured when parsing id {lic_id}')
print(f'for {business} at index {lic_ids.index(lic_id)}')
raise SystemExit
lic_list.append(parsed_lic)
count += 1
if count % 500 == 0:
print(f'Parsed {count} licenses')
return lic_list
def test_plzen():
plzen_path = pathlib.Path('samples/plzen.html')
with open(plzen_path) as f:
bs = BeautifulSoup(f, 'html.parser')
result = parse.parse_page('výroba elektřiny', '110100054', bs)
assert result.provozovny[0].vykony[0].technologie == 'Celkový'
assert result.provozovny[0].vykony[0].druh == 'Elektrický'
assert result.provozovny[0].vykony[0].mw == 90.0
assert result.provozovny[0].vykony[3].technologie == 'Parní'
assert result.provozovny[0].vykony[3].mw == 430.1
def test_plzen_export_to_csv():
oleska_path = pathlib.Path('samples/plzen.html')
with open(oleska_path) as f:
bs = BeautifulSoup(f, 'html.parser')
result = parse.parse_page('výroba elektřiny', '110100054', bs)
# Export csvs within tests directory
output_dir = pathlib.Path('tests/licenses/electricity/')
result.to_csv(output_dir, 'licenses.csv')
output_dir_list = list(output_dir.iterdir())
sub_path = 'tests/licenses/electricity'
assert pathlib.Path(f'{sub_path}/licenses.csv') in output_dir_list
assert pathlib.Path(f'{sub_path}/capacities.csv') in output_dir_list
assert pathlib.Path(f'{sub_path}/facilities.csv') in output_dir_list
assert pathlib.Path(
f'{sub_path}/facilities_capacities.csv') in output_dir_list
with open(f'{sub_path}/facilities.csv') as csvf:
reader = csv.DictReader(csvf)
data = [row for row in reader]
assert len(data) == 1
assert data[0]['id'] == '1'
assert data[0]['lic_id'] == '110100054'
assert data[0]['nazev'] == 'ELÚ 3'
with open(f'{sub_path}/licenses.csv') as csvf:
reader = csv.DictReader(csvf)
data = [row for row in reader]
assert len(data) == 1
assert data[0]['id'] == '110100054'
assert data[0]['pocet_zdroju'] == '3'
with open(f'{sub_path}/capacities.csv') as csvf:
reader = csv.DictReader(csvf)
data = [row for row in reader]
assert len(data) == 4
assert data[0]['mw'] == '90.0'
assert data[0]['druh'] == 'Elektrický'
assert data[1]['mw'] == '430.1'
assert data[1]['druh'] == 'Tepelný'
assert data[2]['technologie'] == 'Parní'
# Cleanup
for csvfile in [
'capacities.csv', 'facilities.csv', 'facilities_capacities.csv',
'licenses.csv'
]:
pathlib.Path(f'{sub_path}/{csvfile}').unlink()
pathlib.Path(f'{sub_path}').rmdir()
pathlib.Path('tests/licenses').rmdir()
def test_oleska():
oleska_path = pathlib.Path('samples/oleska.html')
with open(oleska_path) as f:
bs = BeautifulSoup(f, 'html.parser')
result = parse.parse_page('výroba elektřiny', '110100010', bs)
assert result.id == '110100010'
assert len(result.provozovny) == 1
assert result.pocet_zdroju == 2
assert result.vykony[0].mw == 0.013
assert 'Tepelný' not in [vykon.druh for vykon in result.vykony]
assert result.provozovny[0].kod_katastru == '670936'
assert result.provozovny[0].vykony[0].technologie == 'Celkový'
assert result.provozovny[0].vykony[0].druh == 'Elektrický'
assert result.provozovny[0].vykony[0].mw == 0.013
assert result.provozovny[0].vykony[1].technologie == 'Vodní'
assert result.provozovny[0].vykony[1].mw == 0.013