def test_retrieve_hierarchy(self):
scrapper = NCBITaxonomyScrapper(self.file)
expected_list = [{
'name': 'cellular organisms',
'rank': 'no rank',
'tax_id': '131567'
}, {
'name': 'Bacteria',
'rank': 'superkingdom',
'tax_id': '2'
}, {
'name': 'Terrabacteria group',
'rank': 'clade',
'tax_id': '1783272'
}, {
'name': 'Firmicutes',
'rank': 'phylum',
'tax_id': '1239'
}, {
'name': 'Bacilli',
'rank': 'class',
'tax_id': '91061'
}, {
'name': 'Lactobacillales',
'rank': 'order',
'tax_id': '186826'
}]
tested_list = scrapper.retrieve_hierarchy()
self.assertListEqual(tested_list, expected_list)
def test_retrieve_current_item(self):
scrapper = NCBITaxonomyScrapper(self.file)
expected_dict = {
'rank': 'family',
'tax_id': '33958',
'name': 'Lactobacillaceae'
}
tested_dict = scrapper.retrieve_current_item()
self.assertDictEqual(tested_dict, expected_dict)
def get(self, tax_id: int, get_model: bool = True) -> Union[NCBITaxonomyScrapper.model, dict]:
"""
:param tax_id: NCBI taxonomy ID to retrieve data from
:param get_model: return pydantic model (return dict if False)
"""
full_url = f"https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id={tax_id}&mode=info"
response = self.session.get(full_url)
self.last_url_requested = full_url
response.raise_for_status()
scrapper = NCBITaxonomyScrapper(response.content)
if not scrapper.result_found():
raise requests.exceptions.HTTPError(f"{tax_id} not found in NCBI taxonomy db.")
if get_model:
return scrapper.validated_entry
return scrapper.validated_entry.dict()
def test_retrieve_current_item_variant_1(self):
"""
Some entry has different display and more information, for instance tax_id 12345
"""
file_path = os.path.join(os.path.dirname(__file__),
'data/tax_12345.html')
tax_file = open(file_path, "rb")
scrapper = NCBITaxonomyScrapper(tax_file)
expected_dict = {
'rank': 'species',
'tax_id': '12345',
'name': 'Bacillus virus GA1'
}
tested_dict = scrapper.retrieve_current_item()
self.assertDictEqual(tested_dict, expected_dict)
def test_retrieve_current_item_no_link(self):
"""
Some entry has their names without a link, for instance tax_id 339588
"""
file_path = os.path.join(os.path.dirname(__file__),
'data/tax_339588.html')
tax_file = open(file_path, "rb")
scrapper = NCBITaxonomyScrapper(tax_file)
expected_dict = {
'rank': 'species',
'tax_id': '339588',
'name': 'Peyssonnelia inamoena'
}
tested_dict = scrapper.retrieve_current_item()
self.assertDictEqual(tested_dict, expected_dict)
def test_extract_tax_id_from_url(self):
tested_url = "wwwtax.cgi?mode=Undef&id=131567&lvl=3&keep=1&srchmode=1&unlock"
expected_id = "131567"
tested_id = NCBITaxonomyScrapper.extract_tax_id_from_url(tested_url)
self.assertEqual(tested_id, expected_id)
def test_result_found_error_page(self):
file_path = os.path.join(os.path.dirname(__file__),
'data/error_page.html')
tax_file = open(file_path, "rb")
scrapper = NCBITaxonomyScrapper(tax_file)
self.assertFalse(scrapper.result_found())
def test_result_found(self):
scrapper = NCBITaxonomyScrapper(self.file)
self.assertTrue(scrapper.result_found())