def import_resource_org_item(case_location):
"""Using the path to a case, import it, gathering all needed meta data.
Path is any valid URI that the requests library can handle.
"""
def get_file(location):
if location.startswith('/'):
with open(location) as f:
r = requests.Session()
r.content = f.read()
else:
r = requests.get(location)
return fromstring(r.content), get_clean_body_content(r.content)
# Get trees and text for the opinion itself and for the index page
# that links to it. Each has useful data.
case_tree, case_text = get_file(case_location)
vol_location = case_location.rsplit('/', 1)[-2] + '/index.html'
vol_tree, vol_text = get_file(vol_location)
html, blocked = anonymize(get_case_body(case_tree))
case_location_relative = case_location.rsplit('/', 1)[1]
case_name, status = get_case_name_and_status(vol_tree,
case_location_relative)
docket = Docket(
docket_number=get_docket_number(case_location),
court=Court.objects.get(pk=get_court_id(case_tree)),
case_name=case_name,
)
doc = Document(
case_name=case_name,
federal_cite_one=get_west_cite(vol_tree, case_location_relative),
date_filed=get_date_filed(vol_tree, case_location_relative),
source='R',
sha1=hashlib.sha1(case_text).hexdigest(),
docket=docket,
download_url=case_location,
html=html,
precedential_status=status,
)
if blocked:
doc.blocked = True
docket.blocked = True
doc.date_blocked = datetime.date.today()
docket.date_blocked = datetime.date.today()
docket.save()
doc.docket = docket
doc.save()
# Update the citation graph
from cl.citations.tasks import update_document_by_id
update_document_by_id(doc.pk)
return doc
def import_resource_org_item(case_location):
"""Using the path to a case, import it, gathering all needed meta data.
Path is any valid URI that the requests library can handle.
"""
def get_file(location):
if location.startswith('/'):
with open(location) as f:
r = requests.Session()
r.content = f.read()
else:
r = requests.get(location)
return fromstring(r.content), get_clean_body_content(r.content)
# Get trees and text for the opinion itself and for the index page
# that links to it. Each has useful data.
case_tree, case_text = get_file(case_location)
vol_location = case_location.rsplit('/', 1)[-2] + '/index.html'
vol_tree, vol_text = get_file(vol_location)
html, blocked = anonymize(get_case_body(case_tree))
case_location_relative = case_location.rsplit('/', 1)[1]
case_name, status = get_case_name_and_status(
vol_tree, case_location_relative)
docket = Docket(
docket_number=get_docket_number(case_location),
court=Court.objects.get(pk=get_court_id(case_tree)),
case_name=case_name,
)
doc = Document(
case_name=case_name,
federal_cite_one=get_west_cite(vol_tree, case_location_relative),
date_filed=get_date_filed(vol_tree, case_location_relative),
source='R',
sha1=hashlib.sha1(case_text).hexdigest(),
docket=docket,
download_url=case_location,
html=html,
precedential_status=status,
)
if blocked:
doc.blocked = True
docket.blocked = True
doc.date_blocked = datetime.date.today()
docket.date_blocked = datetime.date.today()
docket.save()
doc.docket = docket
doc.save()
# Update the citation graph
from cl.citations.tasks import update_document_by_id
update_document_by_id(doc.pk)
return doc
def test_auto_blocking_small_bankr_docket(self):
"""Do we properly set small bankruptcy dockets to private?"""
d = Docket()
d.court = Court.objects.get(pk='akb')
blocked, date_blocked = get_blocked_status(d)
self.assertTrue(blocked, msg="Bankruptcy dockets with few entries "
"should be blocked.")
blocked, date_blocked = get_blocked_status(d, count_override=501)
self.assertFalse(blocked, msg="Bankruptcy dockets with many entries "
"should not be blocked")
# This should stay blocked even though it's a big bankruptcy docket.
d.blocked = True
blocked, date_blocked = get_blocked_status(d, count_override=501)
self.assertTrue(blocked, msg="Bankruptcy dockets that start blocked "
"should stay blocked.")
def test_auto_blocking_small_bankr_docket(self):
"""Do we properly set small bankruptcy dockets to private?"""
d = Docket()
d.court = Court.objects.get(pk='akb')
blocked, date_blocked = get_blocked_status(d)
self.assertTrue(blocked,
msg="Bankruptcy dockets with few entries "
"should be blocked.")
blocked, date_blocked = get_blocked_status(d, count_override=501)
self.assertFalse(blocked,
msg="Bankruptcy dockets with many entries "
"should not be blocked")
# This should stay blocked even though it's a big bankruptcy docket.
d.blocked = True
blocked, date_blocked = get_blocked_status(d, count_override=501)
self.assertTrue(blocked,
msg="Bankruptcy dockets that start blocked "
"should stay blocked.")
def update_docket_metadata(d: Docket, docket_data: Dict[str, Any]) -> Docket:
"""Update the Docket object with the data from Juriscraper.
Works on either docket history report or docket report (appellate
or district) results.
"""
d = update_case_names(d, docket_data["case_name"])
mark_ia_upload_needed(d, save_docket=False)
d.docket_number = docket_data["docket_number"] or d.docket_number
d.date_filed = docket_data.get("date_filed") or d.date_filed
d.date_last_filing = (
docket_data.get("date_last_filing") or d.date_last_filing
)
d.date_terminated = docket_data.get("date_terminated") or d.date_terminated
d.cause = docket_data.get("cause") or d.cause
d.nature_of_suit = docket_data.get("nature_of_suit") or d.nature_of_suit
d.jury_demand = docket_data.get("jury_demand") or d.jury_demand
d.jurisdiction_type = (
docket_data.get("jurisdiction") or d.jurisdiction_type
)
d.mdl_status = docket_data.get("mdl_status") or d.mdl_status
judges = get_candidate_judges(
docket_data.get("assigned_to_str"),
d.court_id,
docket_data.get("date_filed"),
)
if judges is not None and len(judges) == 1:
d.assigned_to = judges[0]
d.assigned_to_str = docket_data.get("assigned_to_str") or ""
judges = get_candidate_judges(
docket_data.get("referred_to_str"),
d.court_id,
docket_data.get("date_filed"),
)
if judges is not None and len(judges) == 1:
d.referred_to = judges[0]
d.referred_to_str = docket_data.get("referred_to_str") or ""
d.blocked, d.date_blocked = get_blocked_status(d)
return d
