def test_update():
data = {"foo": "bar", "case_num": 1}
data2 = {"baz": "bang"}
case_info = CaseInfo(data)
case_info.update(data2)
assert case_info.data["baz"] == "bang"
assert case_info.baz == "bang"
def test_update():
data = {'foo': 'bar', 'case_num': 1}
data2 = {'baz': 'bang'}
case_info = CaseInfo(data)
case_info.update(data2)
assert case_info.data['baz'] == 'bang'
assert case_info.baz == 'bang'
def test_merge():
data = {"foo": "bar", "case_num": 1}
data2 = {"baz": "bang", "case_num": 1}
case_info = CaseInfo(data)
case_info2 = CaseInfo(data2)
case_info.merge(case_info2)
assert case_info.case_num == 1
assert case_info.foo == "bar"
assert case_info.baz == "bang"
def test_merge():
data = {'foo': 'bar', 'case_num': 1}
data2 = {'baz': 'bang', 'case_num': 1}
case_info = CaseInfo(data)
case_info2 = CaseInfo(data2)
case_info.merge(case_info2)
assert case_info.case_num == 1
assert case_info.foo == 'bar'
assert case_info.baz == 'bang'
def results(self):
"""Data from Search Results page
Returns:
List of CaseInfo instances
"""
# Search results contain an entry for every party
# to a case, so we need to deduplicate
results = {}
# Only grab result rows (i.e. skip header)
for row in self.soup.table.find_all("tr", class_="resultTableRow"):
case_id_cell, filing_date, case_name, found_party = row.find_all("td")
case_id = case_id_cell.a.text.strip()
try:
case_info = results[case_id]
except KeyError:
data = {
"place_id": self.place_id,
"number": case_id,
"filing_date": filing_date.text.strip(),
"name": case_name.text.strip(),
"parties": [],
}
case_info = CaseInfo(data)
results[case_id] = case_info
case_info.parties.append(found_party.text.strip())
return list(results.values())
def test_attribute_mapping():
mapping = {"case_num": "number"}
data = {"foo": "bar", "case_num": "1"}
CaseInfo._map = mapping
ci = CaseInfo(data)
assert hasattr(ci, "case_num") is False
assert ci.number == "1"
assert ci.foo == "bar"
def test_attribute_mapping():
mapping = {'case_num': 'number'}
data = {'foo': 'bar', 'case_num': '1'}
CaseInfo._map = mapping
ci = CaseInfo(data)
assert hasattr(ci, 'case_num') is False
assert ci.number == '1'
assert ci.foo == 'bar'
def search(self, case_numbers=[]):
results = []
for case_number in case_numbers:
page = CaseDetailPage(self.place_id, case_number)
# Prepare CaseInfo class instances
# for any valid case detail pages
data = {"place_id": self.place_id}
data.update(page.data)
case = CaseInfo(data)
results.append(case)
return results
def _get_by_case_number(self, case_number) -> CaseInfo:
"""
Scrapes the data for the provided case number.
Returns a CaseInfo object ready to be archived.
"""
# Open the homepage
home_page = HomePage(self.driver)
home_page.open()
# Open the search selection page
home_page.start_search()
search_selection_page = SearchSelectionPage(self.driver)
# Open the trial court search page
search_selection_page.open_trial_court_search()
# Switch to the case number search tab
search_trial_court_page = SearchTrialCourtPage(self.driver)
search_trial_court_page.open_case_number_search_tab()
# Parse the the id and type out of the case number
case_dict = parsers.case_numbers.parse(case_number)
# Convert our place_id into the county id that the form expects
county_dict = parsers.counties.parse(self.place_id)
# Search for the case
search_trial_court_page.search_for_case_by_number(
county_dict['id'], case_dict['type_id'], case_dict['id'])
# Open the case detail page
search_results_page = SearchResultsPage(self.driver)
search_results_page.open_case_detail_page(case_number)
# Parse the case detail page
case_detail_page = CaseDetailPage(self.driver)
case_detail_page.open()
# Parse the case detail page
obj = CaseInfo({
'place_id': self.place_id,
'number': case_number,
'page_source': self.driver.page_source,
'url': case_detail_page.url
})
# Return the result
return obj
def _extract_case_data(self, table):
# Get section header
data = []
# Section headers precede table tag and
# contain generic case types, e.g. 'Civil Misc. (CV)'
case_type = table.find_previous('font').text.strip()
for row in table.find_all('tr'):
# Get case data
cell1, cell2 = row.find_all('td')
row_data = {
'place_id': self.place_id,
'type_short': case_type,
'number': cell1.a.text.strip(),
'parties_short': cell2.text.strip(),
}
case_info = CaseInfo(row_data)
data.append(case_info)
return data
def _extract_case_data(self, table):
# Get section header
data = []
# Section headers precede table tag and
# contain generic case types, e.g. 'Civil Misc. (CV)'
case_type = table.find_previous("font").text.strip()
for row in table.find_all("tr"):
# Get case data
cell1, cell2 = row.find_all("td")
row_data = {
"place_id": self.place_id,
"type_short": case_type,
"number": cell1.a.text.strip(),
"parties_short": cell2.text.strip(),
}
case_info = CaseInfo(row_data)
data.append(case_info)
return data
def test_standardized_data():
mapping = {
'case_num': 'number',
}
data = {
'place_id': 'ga_dekalb',
'case_num': '1',
'status': 'Open',
'foo': 'bar',
}
# Number should be standardized,
# and foo should not appear
expected = {
'place_id': 'ga_dekalb',
'number': '1',
'status': 'Open',
}
CaseInfo._map = mapping
ci = CaseInfo(data)
assert ci.standard_data == expected
def test_standardized_data():
mapping = {
"case_num": "number",
}
data = {
"place_id": "ga_dekalb",
"case_num": "1",
"status": "Open",
"foo": "bar",
}
# Number should be standardized,
# and foo should not appear
expected = {
"place_id": "ga_dekalb",
"number": "1",
"status": "Open",
"filing_date": None,
}
CaseInfo._map = mapping
ci = CaseInfo(data)
assert ci.standard_data == expected
def test_scraper_caching(court_scraper_dir, monkeypatch):
data = [
CaseInfo({
'number': '20A123',
'status': 'Open',
'page_source': '<html>foo</html>'
})
]
# Need to monkeypatch because Configs class is instanstiated
# in global scope of cli.py, and the import at top of this
# test file executes cli.py before this test runs (therefore
# standard patching doesn't work b/c it occurs too late)
monkeypatch.setattr(cli.configs, 'cache_dir', court_scraper_dir)
with patch('court_scraper.runner.Runner.search') as mock_method:
mock_method.return_value = data
runner = CliRunner()
runner.invoke(cli.cli, ['search', '-p', 'ga_dekalb', '-s', '20A123'])
cache_file = Path(court_scraper_dir)\
.joinpath('cache/ga_dekalb/20A123.html')
expected = data[0].page_source
actual = file_contents(cache_file)
assert expected == actual
"download_dir": court_scraper_dir,
"headless": True,
}
# Get the args and kwargs (2nd and 3rd items) from the
# first call which is Site instantiation
args, kwargs = site_class.mock_calls[0][1:]
assert args == expected_args
assert kwargs == expected_kwargs
login_call, search_call = site_class.mock_calls[1:3]
assert login_call == call().login(username, password)
assert search_call == call().search(case_numbers=["foo"])
@pytest.mark.usefixtures("create_scraper_dir", "create_config")
def test_page_source_caching(court_scraper_dir, config_path):
case = CaseInfo({"number": "20A123", "page_source": "<html>foo</html>"})
r = Runner(court_scraper_dir, config_path, "ga_dekalb")
# Supply CaseInfo instances in a list
r.cache_detail_pages([case])
cache_file = Path(court_scraper_dir).joinpath(
"cache/ga_dekalb/20A123.html")
actual = file_contents(cache_file)
assert case.page_source == actual
@pytest.mark.usefixtures("create_scraper_dir", "create_config")
def test_multiword_county(court_scraper_dir, config_path):
"Multiword counties should not raise errors"
site_class = Mock(name="OdysseySite")
to_patch = "court_scraper.platforms.odyssey.runner.Runner._get_site_class"
with patch(to_patch) as mock_method:
mock_method.return_value = site_class
r = Runner(court_scraper_dir, config_path, 'ga_dekalb')
r.search(search_terms=['foo'])
username = '******'
password = '******'
expected_args = (
'https://ody.dekalbcountyga.gov/portal/Home/Dashboard/29',
court_scraper_dir,
)
expected_kwargs = {'headless': True}
# Get the args and kwargs (2nd and 3rd items) from the
# first call which is Site instantiation
args, kwargs = site_class.mock_calls[0][1:]
assert args == expected_args
assert kwargs == expected_kwargs
login_call, search_call = site_class.mock_calls[1:3]
assert login_call == call().login(username, password)
assert search_call == call().search(search_terms=['foo'])
@pytest.mark.usefixtures('create_scraper_dir', 'create_config')
def test_page_source_caching(court_scraper_dir, config_path):
case = CaseInfo({'number': '20A123', 'page_source': '<html>foo</html>'})
r = Runner(court_scraper_dir, config_path, 'ga_dekalb')
# Supply CaseInfo instances in a list
r.cache_detail_pages([case])
cache_file = Path(court_scraper_dir)\
.joinpath('cache/ga_dekalb/20A123.html')
actual = file_contents(cache_file)
assert case.page_source == actual
