def test_search_nologin_no_captcha(test_input, headless, court_scraper_dir):
place_id, url, case_ids = test_input
site = OdysseySite(place_id,
url=url,
download_dir=court_scraper_dir,
headless=headless)
results = site.search(case_numbers=case_ids)
assert len(results) == 1
def test_maximize_displayed_results(test_input, headless, court_scraper_dir):
"should automatically maximize the number of results displayed on results page"
place_id, url, case_ids = test_input
site = OdysseySite(place_id,
url=url,
download_dir=court_scraper_dir,
headless=headless)
results = site.search(case_numbers=case_ids)
assert len(results) == 91
def test_login(webdriver_mock, login_page_mock):
site = OdysseySite('http://somesite.com', '/tmp/some_path/')
# Web driver instantiated during Site class initialization
assert webdriver_mock.Chrome.called
# Login requires password
site.login('user', 'pass')
# login method goes to login page and submits user creds
expected_calls = [call().go_to(), call().login()]
actual_calls = login_page_mock.mock_calls
for expected in expected_calls:
assert expected in actual_calls
def test_search(test_input, headless, live_configs, court_scraper_dir):
auth = live_configs['ga_dekalb']
username = auth['username']
password = auth['password']
place_id, url, case_ids = test_input
site = OdysseySite(place_id,
url=url,
download_dir=court_scraper_dir,
headless=headless)
site.login(username, password)
results = site.search(case_numbers=case_ids)
assert len(results) == 1
# Does *not* scrape Case Detail page (HTML) by default
assert 'page_source' not in results[0].data.keys()
def test_malformed_result_listing(test_input, headless, live_configs,
court_scraper_dir):
"should handle result listings that have an extra leading blank cell"
auth = live_configs['ga_dekalb']
username = auth['username']
password = auth['password']
place_id, url, case_ids = test_input
site = OdysseySite(place_id,
url=url,
download_dir=court_scraper_dir,
headless=headless)
site.login(username, password)
results = site.search(case_numbers=case_ids)
assert len(results) == 1
assert results[0].data['File Date'] == '10/02/2019'
def test_scrape_case_details(test_input, headless, live_configs,
court_scraper_dir):
"should support optional scraping of case details"
auth = live_configs['ga_dekalb']
username = auth['username']
password = auth['password']
place_id, url, case_ids = test_input
site = OdysseySite(place_id,
url=url,
download_dir=court_scraper_dir,
headless=headless)
site.login(username, password)
results = site.search(case_numbers=case_ids, case_details=True)
# Should have case detail HTML stored on return object
assert len(results) == 1
assert 'page_source' in results[0].data.keys()