def make_objects(self, item, court, sha1_hash, content):
blocked = item['blocked_statuses']
if blocked:
date_blocked = date.today()
else:
date_blocked = None
case_name_short = (item.get('case_name_shorts') or
self.cnt.make_case_name_short(item['case_names']))
docket = Docket(
docket_number=item.get('docket_numbers', ''),
case_name=item['case_names'],
case_name_short=case_name_short,
court=court,
blocked=blocked,
date_blocked=date_blocked,
date_argued=item['case_dates'],
source=Docket.SCRAPER,
)
audio_file = Audio(
judges=item.get('judges', ''),
source='C',
case_name=item['case_names'],
case_name_short=case_name_short,
sha1=sha1_hash,
download_url=item['download_urls'],
blocked=blocked,
date_blocked=date_blocked,
)
error = False
try:
cf = ContentFile(content)
extension = get_extension(content)
if extension not in ['.mp3', '.wma']:
extension = '.' + item['download_urls'].lower().rsplit('.',
1)[1]
# See bitbucket issue #215 for why this must be
# lower-cased.
file_name = trunc(item['case_names'].lower(), 75) + extension
audio_file.file_with_date = docket.date_argued
audio_file.local_path_original_file.save(file_name, cf, save=False)
except:
msg = 'Unable to save binary to disk. Deleted audio file: %s.\n ' \
'%s' % (item['case_names'], traceback.format_exc())
logger.critical(msg.encode('utf-8'))
ErrorLog(log_level='CRITICAL', court=court, message=msg).save()
error = True
return docket, audio_file, error
def make_objects(item, court, sha1_hash, content):
blocked = item["blocked_statuses"]
if blocked:
date_blocked = date.today()
else:
date_blocked = None
case_name_short = item.get("case_name_shorts") or cnt.make_case_name_short(
item["case_names"])
docket = Docket(
docket_number=item.get("docket_numbers", ""),
case_name=item["case_names"],
case_name_short=case_name_short,
court=court,
blocked=blocked,
date_blocked=date_blocked,
date_argued=item["case_dates"],
source=item.get("source") or Docket.SCRAPER,
)
audio_file = Audio(
judges=item.get("judges", ""),
source=item.get("cluster_source") or "C",
case_name=item["case_names"],
case_name_short=case_name_short,
sha1=sha1_hash,
download_url=item["download_urls"],
blocked=blocked,
date_blocked=date_blocked,
)
error = False
try:
cf = ContentFile(content)
extension = get_extension(content)
if extension not in [".mp3", ".wma"]:
extension = "." + item["download_urls"].lower().rsplit(".", 1)[1]
# See bitbucket issue #215 for why this must be
# lower-cased.
file_name = trunc(item["case_names"].lower(), 75) + extension
audio_file.file_with_date = docket.date_argued
audio_file.local_path_original_file.save(file_name, cf, save=False)
except:
msg = ("Unable to save binary to disk. Deleted audio file: %s.\n "
"%s" % (item["case_names"], traceback.format_exc()))
logger.critical(msg.encode())
ErrorLog(log_level="CRITICAL", court=court, message=msg).save()
error = True
return docket, audio_file, error
def make_objects(self, item, court, sha1_hash, content):
blocked = item['blocked_statuses']
if blocked:
date_blocked = date.today()
else:
date_blocked = None
case_name_short = (item.get('case_name_shorts') or
self.cnt.make_case_name_short(item['case_names']))
docket = Docket(
docket_number=item.get('docket_numbers', ''),
case_name=item['case_names'],
case_name_short=case_name_short,
court=court,
blocked=blocked,
date_blocked=date_blocked,
date_argued=item['case_dates'],
source=Docket.SCRAPER,
)
audio_file = Audio(
judges=item.get('judges', ''),
source='C',
case_name=item['case_names'],
case_name_short=case_name_short,
sha1=sha1_hash,
download_url=item['download_urls'],
blocked=blocked,
date_blocked=date_blocked,
)
error = False
try:
cf = ContentFile(content)
extension = get_extension(content)
if extension not in ['.mp3', '.wma']:
extension = '.' + item['download_urls'].lower().rsplit('.', 1)[1]
# See bitbucket issue #215 for why this must be
# lower-cased.
file_name = trunc(item['case_names'].lower(), 75) + extension
audio_file.file_with_date = docket.date_argued
audio_file.local_path_original_file.save(file_name, cf, save=False)
except:
msg = 'Unable to save binary to disk. Deleted audio file: %s.\n ' \
'%s' % (item['case_names'], traceback.format_exc())
logger.critical(msg.encode('utf-8'))
ErrorLog(log_level='CRITICAL', court=court, message=msg).save()
error = True
return docket, audio_file, error
def make_objects(self, item, court, sha1_hash, content):
"""Takes the meta data from the scraper and associates it with objects.
Returns the created objects.
"""
blocked = item['blocked_statuses']
if blocked:
date_blocked = date.today()
else:
date_blocked = None
case_name_short = (item.get('case_name_shorts') or
self.cnt.make_case_name_short(item['case_names']))
docket = Docket(
docket_number=item.get('docket_numbers', ''),
case_name=item['case_names'],
case_name_short=case_name_short,
court=court,
blocked=blocked,
date_blocked=date_blocked,
source=Docket.SCRAPER,
)
west_cite_str = item.get('west_citations', '')
state_cite_str = item.get('west_state_citations', '')
neutral_cite_str = item.get('neutral_citations', '')
cluster = OpinionCluster(
judges=item.get('judges', ''),
date_filed=item['case_dates'],
date_filed_is_approximate=item['date_filed_is_approximate'],
case_name=item['case_names'],
case_name_short=case_name_short,
source='C',
precedential_status=item['precedential_statuses'],
nature_of_suit=item.get('nature_of_suit', ''),
blocked=blocked,
date_blocked=date_blocked,
# These three fields are replaced below.
federal_cite_one=west_cite_str,
state_cite_one=state_cite_str,
neutral_cite=neutral_cite_str,
syllabus=item.get('summaries', ''),
)
citations = []
cite_types = [
(west_cite_str, Citation.WEST),
(state_cite_str, Citation.STATE),
(neutral_cite_str, Citation.NEUTRAL),
]
for cite_str, cite_type in cite_types:
if cite_str:
citations.append(make_citation(cite_str, cluster, cite_type))
opinion = Opinion(
type='010combined',
sha1=sha1_hash,
download_url=item['download_urls'],
)
error = False
try:
cf = ContentFile(content)
extension = get_extension(content)
file_name = trunc(item['case_names'].lower(), 75) + extension
opinion.file_with_date = cluster.date_filed
opinion.local_path.save(file_name, cf, save=False)
except:
msg = ('Unable to save binary to disk. Deleted '
'item: %s.\n %s' %
(item['case_names'], traceback.format_exc()))
logger.critical(msg.encode('utf-8'))
ErrorLog(log_level='CRITICAL', court=court, message=msg).save()
error = True
return docket, opinion, cluster, citations, error
def handle(self, *args, **options):
super(Command, self).handle(*args, **options)
global die_now
# this line is used for handling SIGTERM (CTRL+4), so things can die
# safely
signal.signal(signal.SIGTERM, signal_handler)
module_strings = build_module_list(options['court_id'])
if not len(module_strings):
raise CommandError('Unable to import module or package. Aborting.')
logger.info("Starting up the scraper.")
num_courts = len(module_strings)
wait = (options['rate'] * 60) / num_courts
i = 0
while i < num_courts:
# this catches SIGTERM, so the code can be killed safely.
if die_now:
logger.info("The scraper has stopped.")
sys.exit(1)
package, module = module_strings[i].rsplit('.', 1)
mod = __import__("%s.%s" % (package, module), globals(), locals(),
[module])
# noinspection PyBroadException
try:
self.parse_and_scrape_site(mod, options['full_crawl'])
except Exception as e:
# noinspection PyBroadException
try:
msg = ('********!! CRAWLER DOWN !!***********\n'
'*****scrape_court method failed!*****\n'
'********!! ACTION NEEDED !!**********\n%s' %
traceback.format_exc())
logger.critical(msg)
# opinions.united_states.federal.ca9_u --> ca9
court_str = mod.Site.__module__.split('.')[-1].split(
'_')[0]
court = Court.objects.get(pk=court_str)
ErrorLog(log_level='CRITICAL', court=court,
message=msg).save()
except Exception as e:
# This is very important. Without this, an exception
# above will crash the caller.
pass
finally:
time.sleep(wait)
last_court_in_list = (i == (num_courts - 1))
if last_court_in_list and options['daemon']:
# Start over...
logger.info(
"All jurisdictions done. Looping back to "
"the beginning because daemon mode is enabled.")
i = 0
else:
i += 1
logger.info("The scraper has stopped.")
sys.exit(0)
def make_objects(item, court, sha1_hash, content):
"""Takes the meta data from the scraper and associates it with objects.
Returns the created objects.
"""
blocked = item["blocked_statuses"]
if blocked:
date_blocked = date.today()
else:
date_blocked = None
case_name_short = item.get("case_name_shorts") or cnt.make_case_name_short(
item["case_names"])
docket = Docket(
docket_number=item.get("docket_numbers", ""),
case_name=item["case_names"],
case_name_short=case_name_short,
court=court,
blocked=blocked,
date_blocked=date_blocked,
source=item.get("source") or Docket.SCRAPER,
)
west_cite_str = item.get("west_citations", "")
state_cite_str = item.get("west_state_citations", "")
neutral_cite_str = item.get("neutral_citations", "")
cluster = OpinionCluster(
judges=item.get("judges", ""),
date_filed=item["case_dates"],
date_filed_is_approximate=item["date_filed_is_approximate"],
case_name=item["case_names"],
case_name_short=case_name_short,
source=item.get("cluster_source") or "C",
precedential_status=item["precedential_statuses"],
nature_of_suit=item.get("nature_of_suit", ""),
blocked=blocked,
date_blocked=date_blocked,
syllabus=item.get("summaries", ""),
)
citations = []
cite_types = [
(west_cite_str, Citation.WEST),
(state_cite_str, Citation.STATE),
(neutral_cite_str, Citation.NEUTRAL),
]
for cite_str, cite_type in cite_types:
if cite_str:
citations.append(make_citation(cite_str, cluster, cite_type))
opinion = Opinion(
type=Opinion.COMBINED,
sha1=sha1_hash,
download_url=item["download_urls"],
)
error = False
try:
cf = ContentFile(content)
extension = get_extension(content)
file_name = trunc(item["case_names"].lower(), 75) + extension
opinion.file_with_date = cluster.date_filed
opinion.local_path.save(file_name, cf, save=False)
except:
msg = "Unable to save binary to disk. Deleted " "item: %s.\n %s" % (
item["case_names"],
traceback.format_exc(),
)
logger.critical(msg.encode("utf-8"))
ErrorLog(log_level="CRITICAL", court=court, message=msg).save()
error = True
return docket, opinion, cluster, citations, error
def make_objects(self, item, court, sha1_hash, content):
"""Takes the meta data from the scraper and associates it with objects.
Returns the created objects.
"""
blocked = item['blocked_statuses']
if blocked:
date_blocked = date.today()
else:
date_blocked = None
case_name_short = (item.get('case_name_shorts') or
self.cnt.make_case_name_short(item['case_names']))
docket = Docket(
docket_number=item.get('docket_numbers', ''),
case_name=item['case_names'],
case_name_short=case_name_short,
court=court,
blocked=blocked,
date_blocked=date_blocked,
source=Docket.SCRAPER,
)
west_cite_str = item.get('west_citations', '')
state_cite_str = item.get('west_state_citations', '')
neutral_cite_str = item.get('neutral_citations', '')
cluster = OpinionCluster(
judges=item.get('judges', ''),
date_filed=item['case_dates'],
date_filed_is_approximate=item['date_filed_is_approximate'],
case_name=item['case_names'],
case_name_short=case_name_short,
source='C',
precedential_status=item['precedential_statuses'],
nature_of_suit=item.get('nature_of_suit', ''),
blocked=blocked,
date_blocked=date_blocked,
# These three fields are replaced below.
federal_cite_one=west_cite_str,
state_cite_one=state_cite_str,
neutral_cite=neutral_cite_str,
syllabus=item.get('summaries', ''),
)
citations = []
cite_types = [
(west_cite_str, Citation.WEST),
(state_cite_str, Citation.STATE),
(neutral_cite_str, Citation.NEUTRAL),
]
for cite_str, cite_type in cite_types:
if cite_str:
citations.append(make_citation(cite_str, cluster, cite_type))
opinion = Opinion(
type='010combined',
sha1=sha1_hash,
download_url=item['download_urls'],
)
error = False
try:
cf = ContentFile(content)
extension = get_extension(content)
file_name = trunc(item['case_names'].lower(), 75) + extension
opinion.file_with_date = cluster.date_filed
opinion.local_path.save(file_name, cf, save=False)
except:
msg = ('Unable to save binary to disk. Deleted '
'item: %s.\n %s' %
(item['case_names'], traceback.format_exc()))
logger.critical(msg.encode('utf-8'))
ErrorLog(log_level='CRITICAL', court=court, message=msg).save()
error = True
return docket, opinion, cluster, citations, error
def handle(self, *args, **options):
super(Command, self).handle(*args, **options)
global die_now
# this line is used for handling SIGTERM (CTRL+4), so things can die
# safely
signal.signal(signal.SIGTERM, signal_handler)
module_strings = build_module_list(options['court_id'])
if not len(module_strings):
raise CommandError('Unable to import module or package. Aborting.')
logger.info("Starting up the scraper.")
num_courts = len(module_strings)
wait = (options['rate'] * 60) / num_courts
i = 0
while i < num_courts:
# this catches SIGTERM, so the code can be killed safely.
if die_now:
logger.info("The scraper has stopped.")
sys.exit(1)
package, module = module_strings[i].rsplit('.', 1)
mod = __import__(
"%s.%s" % (package, module),
globals(),
locals(),
[module]
)
# noinspection PyBroadException
try:
self.parse_and_scrape_site(mod, options['full_crawl'])
except Exception as e:
# noinspection PyBroadException
try:
msg = ('********!! CRAWLER DOWN !!***********\n'
'*****scrape_court method failed!*****\n'
'********!! ACTION NEEDED !!**********\n%s' %
traceback.format_exc())
logger.critical(msg)
# opinions.united_states.federal.ca9_u --> ca9
court_str = mod.Site.__module__.split('.')[-1].split('_')[0]
court = Court.objects.get(pk=court_str)
ErrorLog(
log_level='CRITICAL',
court=court,
message=msg
).save()
except Exception as e:
# This is very important. Without this, an exception
# above will crash the caller.
pass
finally:
time.sleep(wait)
last_court_in_list = (i == (num_courts - 1))
if last_court_in_list and options['daemon']:
# Start over...
logger.info("All jurisdictions done. Looping back to "
"the beginning because daemon mode is enabled.")
i = 0
else:
i += 1
logger.info("The scraper has stopped.")
sys.exit(0)
