def test_get_by_place_id(sites_csv_text):
to_patch = "court_scraper.sites_meta.SitesMeta._get_sites_csv_text"
with patch(to_patch) as mock_method:
mock_method.return_value = sites_csv_text
meta = SitesMeta()
row = meta.get("ca_san_mateo")
assert row["site_type"] == "odyssey"
def test_get_by_place_id(sites_csv_text):
to_patch = 'court_scraper.sites_meta.SitesMeta._get_sites_csv_text'
with patch(to_patch) as mock_method:
mock_method.return_value = sites_csv_text
meta = SitesMeta()
row = meta.get('ca_san_mateo')
assert row['site_type'] == 'odyssey'
def test_url_lookup_by_state_county(sites_csv_text):
to_patch = "court_scraper.sites_meta.SitesMeta._get_sites_csv_text"
with patch(to_patch) as mock_method:
mock_method.return_value = sites_csv_text
meta = SitesMeta()
actual = meta.get_url(state="ga", county="dekalb")
expected = "https://ody.dekalbcountyga.gov/portal/Home/Dashboard/29"
assert actual == expected
def test_url_lookup_by_state_county(sites_csv_text):
to_patch = 'court_scraper.sites_meta.SitesMeta._get_sites_csv_text'
with patch(to_patch) as mock_method:
mock_method.return_value = sites_csv_text
s = SitesMeta()
actual = s.get_url(state='ga', county='dekalb')
expected = 'https://ody.dekalbcountyga.gov/portal/Home/Dashboard/29'
assert actual == expected
def test_url_lookup_multiname_county(sites_csv_text):
to_patch = 'court_scraper.sites_meta.SitesMeta._get_sites_csv_text'
with patch(to_patch) as mock_method:
mock_method.return_value = sites_csv_text
meta = SitesMeta()
actual = meta.get_url(state='ca', county='san mateo')
expected = 'https://odyportal-ext.sanmateocourt.org/Portal-External/Home/Dashboard/29'
assert actual == expected
def _get_runner(place_id):
# Site types for one-off scrapers should live in the scrapers
# namespace in a module named by state and county, e.g. ny_westchester.
# Platform site classes should live in platforms namespace
# in a snake_case module (e.g. odyssey).
# In both cases, sites_meta.csv should specify the module name
# in the site_type field as a snake_case value (ny_westchester, odyssey).
meta = SitesMeta()
site_type = meta.get(place_id)["site_type"]
if place_id == site_type:
parent_mod = "scrapers"
else:
parent_mod = "platforms"
target_module = "court_scraper.{}.{}.runner".format(parent_mod, site_type)
mod = importlib.import_module(target_module)
return getattr(mod, "Runner")
def get_site_meta(cls, place_id):
sm = SitesMeta()
state = place_id[0:2]
county = place_id[3:].replace('_', ' ').strip()
key = (state, county)
site_info = sm.data[key]
cls._site_meta = site_info
return cls._site_meta
def info():
msg = "\nAvailable scrapers:\n\n"
meta = SitesMeta()
for state, county in meta.data.keys():
entry = " * {} - {} ({})\n".format(state.upper(), county.title(),
'_'.join((state, county)))
msg += entry
end_note = "\nNOTE: Scraper IDs (in parentheses) should be " +\
"used with the search command's --place-id argument."
msg += end_note
click.echo(msg)
def site_meta(self):
try:
return self._site_meta
except AttributeError:
sm = SitesMeta()
state = self.place_id[0:2]
county = self.place_id[3:].replace("_", " ").strip()
key = (state, county)
site_info = sm.data[key]
self._site_meta = site_info
return self._site_meta