def setUp(self):
super(DupcheckerWithFixturesTest, self).setUp()
self.court = Court.objects.get(pk='test')
# Set the dup_threshold to zero for these tests
self.dup_checkers = [
DupChecker(self.court, full_crawl=True, dup_threshold=0),
DupChecker(self.court, full_crawl=False, dup_threshold=0),
]
# Set up the hash value using one in the fixture.
self.content_hash = 'asdfasdfasdfasdfasdfasddf'
def scrape_court(self, site, full_crawl=False, backscrape=False):
download_error = False
# Get the court object early for logging
# opinions.united_states.federal.ca9_u --> ca9
court_str = site.court_id.split(".")[-1].split("_")[0]
court = Court.objects.get(pk=court_str)
dup_checker = DupChecker(court, full_crawl=full_crawl)
abort = dup_checker.abort_by_url_hash(site.url, site.hash)
if not abort:
if site.cookies:
logger.info("Using cookies: %s" % site.cookies)
for i, item in enumerate(site):
msg, r = get_binary_content(
item["download_urls"],
site.cookies,
site._get_adapter_instance(),
method=site.method,
)
if msg:
logger.warning(msg)
ErrorLog(
log_level="WARNING", court=court, message=msg
).save()
continue
content = site.cleanup_content(r.content)
current_date = item["case_dates"]
try:
next_date = site[i + 1]["case_dates"]
except IndexError:
next_date = None
# request.content is sometimes a str, sometimes unicode, so
# force it all to be bytes, pleasing hashlib.
sha1_hash = sha1(force_bytes(content))
onwards = dup_checker.press_on(
Audio,
current_date,
next_date,
lookup_value=sha1_hash,
lookup_by="sha1",
)
if dup_checker.emulate_break:
break
if onwards:
# Not a duplicate, carry on
logger.info(
"Adding new document found at: %s"
% item["download_urls"].encode("utf-8")
)
dup_checker.reset()
docket, audio_file, error = make_objects(
item, court, sha1_hash, content
)
if error:
download_error = True
continue
save_everything(
items={"docket": docket, "audio_file": audio_file},
index=False,
backscrape=backscrape,
)
process_audio_file.apply_async(
(audio_file.pk,), countdown=random.randint(0, 3600)
)
logger.info(
"Successfully added audio file {pk}: {name}".format(
pk=audio_file.pk,
name=item["case_names"].encode("utf-8"),
)
)
# Update the hash if everything finishes properly.
logger.info(
"%s: Successfully crawled oral arguments." % site.court_id
)
if not download_error and not full_crawl:
# Only update the hash if no errors occurred.
dup_checker.update_site_hash(site.hash)
def setUp(self):
self.court = Court.objects.get(pk='test')
self.dup_checkers = [DupChecker(self.court, full_crawl=True),
DupChecker(self.court, full_crawl=False)]
def scrape_court(self, site, full_crawl=False):
download_error = False
# Get the court object early for logging
# opinions.united_states.federal.ca9_u --> ca9
court_str = site.court_id.split('.')[-1].split('_')[0]
court = Court.objects.get(pk=court_str)
dup_checker = DupChecker(court, full_crawl=full_crawl)
abort = dup_checker.abort_by_url_hash(site.url, site.hash)
if not abort:
if site.cookies:
logger.info("Using cookies: %s" % site.cookies)
for i, item in enumerate(site):
msg, r = get_binary_content(
item['download_urls'],
site.cookies,
site._get_adapter_instance(),
method=site.method
)
if msg:
logger.warn(msg)
ErrorLog(log_level='WARNING',
court=court,
message=msg).save()
continue
content = site.cleanup_content(r.content)
current_date = item['case_dates']
try:
next_date = site[i + 1]['case_dates']
except IndexError:
next_date = None
# request.content is sometimes a str, sometimes unicode, so
# force it all to be bytes, pleasing hashlib.
sha1_hash = hashlib.sha1(force_bytes(content)).hexdigest()
onwards = dup_checker.press_on(
Audio,
current_date,
next_date,
lookup_value=sha1_hash,
lookup_by='sha1'
)
if dup_checker.emulate_break:
break
if onwards:
# Not a duplicate, carry on
logger.info('Adding new document found at: %s' %
item['download_urls'].encode('utf-8'))
dup_checker.reset()
docket, audio_file, error = self.make_objects(
item, court, sha1_hash, content,
)
if error:
download_error = True
continue
self.save_everything(
items={
'docket': docket,
'audio_file': audio_file,
},
index=False,
)
process_audio_file.apply_async(
(audio_file.pk,),
countdown=random.randint(0, 3600)
)
logger.info(
"Successfully added audio file {pk}: {name}".format(
pk=audio_file.pk,
name=item['case_names'].encode('utf-8')
)
)
# Update the hash if everything finishes properly.
logger.info("%s: Successfully crawled oral arguments." %
site.court_id)
if not download_error and not full_crawl:
# Only update the hash if no errors occurred.
dup_checker.update_site_hash(site.hash)
def scrape_court(self, site, full_crawl=False):
download_error = False
# Get the court object early for logging
# opinions.united_states.federal.ca9_u --> ca9
court_str = site.court_id.split('.')[-1].split('_')[0]
court = Court.objects.get(pk=court_str)
dup_checker = DupChecker(court, full_crawl=full_crawl)
abort = dup_checker.abort_by_url_hash(site.url, site.hash)
if not abort:
if site.cookies:
logger.info("Using cookies: %s" % site.cookies)
for i, item in enumerate(site):
msg, r = get_binary_content(item['download_urls'],
site.cookies,
site._get_adapter_instance(),
method=site.method)
if msg:
logger.warn(msg)
ErrorLog(log_level='WARNING', court=court,
message=msg).save()
continue
content = site.cleanup_content(r.content)
current_date = item['case_dates']
try:
next_date = site[i + 1]['case_dates']
except IndexError:
next_date = None
# request.content is sometimes a str, sometimes unicode, so
# force it all to be bytes, pleasing hashlib.
sha1_hash = sha1(force_bytes(content))
if (court_str == 'nev'
and item['precedential_statuses'] == 'Unpublished'):
# Nevada's non-precedential cases have different SHA1
# sums every time.
lookup_params = {
'lookup_value': item['download_urls'],
'lookup_by': 'download_url'
}
else:
lookup_params = {
'lookup_value': sha1_hash,
'lookup_by': 'sha1'
}
onwards = dup_checker.press_on(Opinion, current_date,
next_date, **lookup_params)
if dup_checker.emulate_break:
break
if onwards:
# Not a duplicate, carry on
logger.info('Adding new document found at: %s' %
item['download_urls'].encode('utf-8'))
dup_checker.reset()
docket, opinion, cluster, citations, error = self.make_objects(
item, court, sha1_hash, content)
if error:
download_error = True
continue
self.save_everything(items={
'docket': docket,
'opinion': opinion,
'cluster': cluster,
'citations': citations,
},
index=False)
extract_doc_content.delay(
opinion.pk,
do_ocr=True,
citation_jitter=True,
)
logger.info("Successfully added doc {pk}: {name}".format(
pk=opinion.pk,
name=item['case_names'].encode('utf-8'),
))
# Update the hash if everything finishes properly.
logger.info("%s: Successfully crawled opinions." % site.court_id)
if not download_error and not full_crawl:
# Only update the hash if no errors occurred.
dup_checker.update_site_hash(site.hash)
def scrape_court(self, site, full_crawl=False, ocr_available=True):
# Get the court object early for logging
# opinions.united_states.federal.ca9_u --> ca9
court_str = site.court_id.split(".")[-1].split("_")[0]
court = Court.objects.get(pk=court_str)
dup_checker = DupChecker(court, full_crawl=full_crawl)
if dup_checker.abort_by_url_hash(site.url, site.hash):
return
if site.cookies:
logger.info(f"Using cookies: {site.cookies}")
for i, item in enumerate(site):
msg, r = get_binary_content(
item["download_urls"],
site.cookies,
method=site.method,
)
if msg:
logger.warning(msg)
ErrorLog(log_level="WARNING", court=court, message=msg).save()
continue
content = site.cleanup_content(r.content)
current_date = item["case_dates"]
try:
next_date = site[i + 1]["case_dates"]
except IndexError:
next_date = None
# request.content is sometimes a str, sometimes unicode, so
# force it all to be bytes, pleasing hashlib.
sha1_hash = sha1(force_bytes(content))
if (
court_str == "nev"
and item["precedential_statuses"] == "Unpublished"
):
# Nevada's non-precedential cases have different SHA1 sums
# every time.
lookup_params = {
"lookup_value": item["download_urls"],
"lookup_by": "download_url",
}
else:
lookup_params = {
"lookup_value": sha1_hash,
"lookup_by": "sha1",
}
proceed = dup_checker.press_on(
Opinion, current_date, next_date, **lookup_params
)
if dup_checker.emulate_break:
break
if not proceed:
continue
# Not a duplicate, carry on
logger.info(
f"Adding new document found at: {item['download_urls'].encode()}"
)
dup_checker.reset()
docket, opinion, cluster, citations = make_objects(
item, court, sha1_hash, content
)
save_everything(
items={
"docket": docket,
"opinion": opinion,
"cluster": cluster,
"citations": citations,
},
index=False,
)
extract_doc_content.delay(
opinion.pk, ocr_available=ocr_available, citation_jitter=True
)
logger.info(
f"Successfully added doc {opinion.pk}: {item['case_names'].encode()}"
)
# Update the hash if everything finishes properly.
logger.info(f"{site.court_id}: Successfully crawled opinions.")
if not full_crawl:
# Only update the hash if no errors occurred.
dup_checker.update_site_hash(site.hash)
def scrape_court(self, site, full_crawl=False):
download_error = False
# Get the court object early for logging
# opinions.united_states.federal.ca9_u --> ca9
court_str = site.court_id.split('.')[-1].split('_')[0]
court = Court.objects.get(pk=court_str)
dup_checker = DupChecker(court, full_crawl=full_crawl)
abort = dup_checker.abort_by_url_hash(site.url, site.hash)
if not abort:
if site.cookies:
logger.info("Using cookies: %s" % site.cookies)
for i, item in enumerate(site):
msg, r = get_binary_content(
item['download_urls'],
site.cookies,
site._get_adapter_instance(),
method=site.method
)
if msg:
logger.warn(msg)
ErrorLog(log_level='WARNING',
court=court,
message=msg).save()
continue
content = site.cleanup_content(r.content)
current_date = item['case_dates']
try:
next_date = site[i + 1]['case_dates']
except IndexError:
next_date = None
# request.content is sometimes a str, sometimes unicode, so
# force it all to be bytes, pleasing hashlib.
sha1_hash = hashlib.sha1(force_bytes(content)).hexdigest()
if (court_str == 'nev' and
item['precedential_statuses'] == 'Unpublished'):
# Nevada's non-precedential cases have different SHA1
# sums every time.
lookup_params = {'lookup_value': item['download_urls'],
'lookup_by': 'download_url'}
else:
lookup_params = {'lookup_value': sha1_hash,
'lookup_by': 'sha1'}
onwards = dup_checker.press_on(Opinion, current_date, next_date,
**lookup_params)
if dup_checker.emulate_break:
break
if onwards:
# Not a duplicate, carry on
logger.info('Adding new document found at: %s' %
item['download_urls'].encode('utf-8'))
dup_checker.reset()
docket, opinion, cluster, citations, error = self.make_objects(
item, court, sha1_hash, content
)
if error:
download_error = True
continue
self.save_everything(
items={
'docket': docket,
'opinion': opinion,
'cluster': cluster,
'citations': citations,
},
index=False
)
extract_doc_content.delay(
opinion.pk, do_ocr=True,
citation_jitter=True,
)
logger.info("Successfully added doc {pk}: {name}".format(
pk=opinion.pk,
name=item['case_names'].encode('utf-8'),
))
# Update the hash if everything finishes properly.
logger.info("%s: Successfully crawled opinions." % site.court_id)
if not download_error and not full_crawl:
# Only update the hash if no errors occurred.
dup_checker.update_site_hash(site.hash)
def setUp(self) -> None:
self.court = Court.objects.get(pk="test")
self.dup_checkers = [
DupChecker(self.court, full_crawl=True),
DupChecker(self.court, full_crawl=False),
]
