def test_num_of_links(self, soup, expected):
extractor = DocumentObjectFeature(
lp_url="https://felp_dummy_internal.com", soup=soup)
num_of_links = extractor.get_num_of_links()
assert num_of_links == expected
def test_get_text_size_links_ratio(self, soup, expected):
extractor = DocumentObjectFeature(
lp_url="https://felp_dummy_internal.com", soup=soup)
text_size_links_ratio = extractor.get_text_size_links_ratio()
assert round(text_size_links_ratio, 2) == expected
def test_number_of_external_total_links_ratio(self, soup, expected):
extractor = DocumentObjectFeature(
lp_url="https://felp_dummy_internal.com", soup=soup)
number_of_external_total_links_ratio = (
extractor.get_number_of_external_total_links_ratio())
assert round(number_of_external_total_links_ratio, 2) == expected
def test_get_links(self, soup, expected_internal, expected_external):
extractor = DocumentObjectFeature(
lp_url="https://felp_dummy_internal.com", soup=soup)
links = extractor.get_links()
assert len(links.internal) == expected_internal
assert len(links.external) == expected_external
def test_get_main_text(self, soup, expected_main_text_num):
extractor = DocumentObjectFeature(
lp_url="https://felp_dummy_internal.com", soup=soup)
main_text = extractor.get_main_text()
expected_path = self.FIXTURES_ROOT / expected_main_text_num / "main_text.txt"
with expected_path.open("r") as rf:
expected_text = rf.read()
assert main_text == expected_text
def test_get_external_links(self, soup, expected):
extractor = DocumentObjectFeature(
lp_url="https://felp_dummy_internal.com", soup=soup)
external_links = extractor.get_external_links()
print(external_links)
raise NotImplementedError
def __init__(self, lp_url: str, soup: BeautifulSoup) -> None:
self._soup = soup
self._doc_feat_extractor = DocumentObjectFeature(lp_url, soup)