def nyt():
nyt_file = File("nytimes.html")
nyt_url = ("https://bites-data.s3.us-east-2.amazonaws.com/"
"2020-03-10_nytimes.html")
nyt_web = Web(nyt_url, nyt_file)
yield NYTimes(nyt_web)
if CLEAN_UP:
if nyt_web.file.path.exists():
nyt_web.file.path.unlink()
def rcp():
rcp_file = File("realclearpolitics.html")
rcp_url = ("https://bites-data.s3.us-east-2.amazonaws.com/"
"2020-03-10_realclearpolitics.html")
rcp_web = Web(rcp_url, rcp_file)
yield RealClearPolitics(rcp_web)
if CLEAN_UP:
if rcp_web.file.path.exists():
rcp_web.file.path.unlink()
def test_web_bad_url():
file = File("clamytoe.html")
url = "https://clamytoe.dev"
test_web = Web(url, file)
with pytest.raises(URLError) as e:
test_web.data
error = str(e.value)
assert 'urlopen error' in error
assert ('Name or service not known' in error
or 'nodename nor servname provided, or not known' in error)
def test_site(test_file):
Site.__abstractmethods__ = set()
@dataclass
class Dummy(Site):
web: Web
url = "https://projects.fivethirtyeight.com/polls/"
test_web = Web(url, test_file)
d = Dummy(test_web)
table = d.find_table()
rows = d.parse_rows(table)
polls = d.polls()
stats = d.stats()
assert d.web.file.name == "test.html"
assert isinstance(Site, ABCMeta)
assert rows is None
assert polls is None
assert stats is None
def test_web(test_file):
url = "https://projects.fivethirtyeight.com/polls/"
test_web = Web(url, test_file)
assert test_web.url == url
assert isinstance(test_web.file, File)
assert isinstance(test_web.soup, Soup)