def test_append():
html_path = Config.test_resource("daikoku1.html")
parser = Parser("daikoku").parse_html(html_path)
html_path2 = Config.test_resource("isogo1.html")
parser2 = Parser("isogo").parse_html(html_path2)
parser.append(parser2)
timestamps = parser.get_timestamps()
print(timestamps)
assert timestamps['choka']
assert timestamps['newsline']
def test_cleansing_comment():
comment_path = Config.test_resource("comment1.txt")
f = open(comment_path, encoding='utf-8')
comment = f.read()
f.close()
comment = Converter.clensing_summary_comment(comment)
assert comment
print(comment)
comment_path = Config.test_resource("comment2.txt")
f = open(comment_path, encoding='utf-8')
comment = f.read()
f.close()
comment2 = Converter.clensing_summary_comment(comment)
assert comment2
print(comment2)
def test_html_no_data():
html_path = Config.test_resource("not_found1.html")
f = open(html_path, encoding='euc_jp', errors='ignore')
html = f.read()
f.close()
download = Download().load_config().check_html_no_data(html)
assert not download.page_found
def test_honmoku_html_parseer():
html_path = Config.test_resource("honmoku1.html")
parser = Parser("honmoku").parse_html(html_path)
timestamps = parser.get_timestamps()
print(timestamps)
assert timestamps['choka']
assert timestamps['newsline']
def test_get_path():
assert Config.get_datastore_path("choka.csv")
assert Config.get_download_path("choka_daikoku_2021_04_001.html")
assert Config.test_resource("daikoku1.html")
assert Config.get_url("daikoku")
assert Config.get_download_file("daikoku", 2021, 4)
assert Config.get_db_path()
assert Config.get_config_path("config.toml")
def test_append_load():
datastore = Datastore(TEST_DB).reset_database()
parser = Parser("daikoku").parse_html(
Config.test_resource("daikoku1.html"))
parser.export('csv')
datastore.csv_import()
parser2 = Parser("isogo").parse_html(Config.test_resource("isogo1.html"))
parser2.export('csv')
datastore.csv_import()
assert datastore.load_counts['choka.csv'] == 19
parser3 = Parser("honmoku").parse_html(
Config.test_resource("honmoku1.html"))
parser3.export('csv')
datastore.csv_import()
assert datastore.load_counts['choka.csv'] == 54
def test_daikoku_html_parser():
html_path = Config.test_resource("daikoku1.html")
parser = Parser("daikoku").parse_html(html_path)
timestamps = parser.get_timestamps()
print(parser.choka.columns)
print(parser.comment.columns)
print(parser.newsline.columns)
assert timestamps['choka']
assert timestamps['newsline']
def test_initial_export():
datastore = Datastore(TEST_DB).reset_database()
html_path = Config.test_resource("daikoku1.html")
parser = Parser("daikoku").parse_html(html_path)
parser.export('csv')
datastore.csv_import()
assert datastore.load_counts == {
'choka.csv': 12,
'comment.csv': 1,
'newsline.csv': 9
}
def test_not_found():
html_path = Config.test_resource("not_found1.html")
assert not Parser("daikoku").parse_html(html_path)
def test_export():
html_path = Config.test_resource("daikoku1.html")
parser = Parser("daikoku").parse_html(html_path)
parser.export('csv')
def test_daikoku_only_newsline_parser():
html_path = Config.test_resource("daikoku1_newsline.html")
parser = Parser("daikoku").parse_html(html_path)
timestamps = parser.get_timestamps()
assert not timestamps['choka']
assert timestamps['newsline']