class OpinionsDownloader():
# TK: Add a param to set where to download files to?
def __init__(self, username, password):
self.pacer_client = PacerClient(username, password)
self.connection = pika.BlockingConnection(
pika.ConnectionParameters('localhost'))
self.channel = self.connection.channel()
# set up the queue for later
self.channel.queue_declare(queue='dockets')
def reinit_pacer_client(self, username, password):
# we have to log into each new court separately
self.pacer_client = PacerClient(username, password)
def get_opinions(self, court, start_date, end_date):
html = self.pacer_client.get_opinions_html(court, start_date, end_date)
dockets = PP.parse_opinions(html, court)
logger.info(' Downloaded %d dockets for court %s between %s and %s',
len(dockets), court, start_date, end_date)
#if len(dockets) == 0:
# logger.debug(' 0 dockets downloaded. HTML response: %s', html)
return dockets
def get_document(self, court, casenum, de_seq_num, dm_id, doc_num):
return self.pacer_client.get_pdf_show_doc(court, casenum, de_seq_num,
dm_id, doc_num)
def enqueue_opinions(self, court, start_date, end_date):
for docket in self.get_opinions(court, start_date, end_date):
docmap = {}
for key, doc in docket.documents.items():
logger.info(' Downloading document %s.%s.%s.0', court,
docket.get_casenum(), doc['doc_num']),
pdfbits = self.get_document(court, docket.get_casenum(),
doc['pacer_de_seq_num'],
doc['pacer_dm_id'], doc['doc_num'])
logger.info(' Downloaded document %s.%s.%s.0', court,
docket.get_casenum(), doc['doc_num']),
# pickle the document into a file
# map the docnum-subdocnum to the filename
docmap[key] = _pickle_object(pdfbits)
# pickle file
filename = _pickle_object(docket)
# create message
upload_message = {
'docket_filename': filename,
'docnums_to_filename': docmap,
'court': docket.get_court(),
'casenum': docket.get_casenum()
}
# energize!
self.channel.basic_publish(exchange='',
routing_key='dockets',
body=pickle.dumps(upload_message))
logger.info(' Sent upload message for %s.%s', court,
docket.get_casenum())
def __init__(self, username, password):
self.pacer_client = PacerClient(username, password)
self.connection = pika.BlockingConnection(
pika.ConnectionParameters('localhost'))
self.channel = self.connection.channel()
# set up the queue for later
self.channel.queue_declare(queue='dockets')
def __init__(self, username, password) :
self.pacer_client = PacerClient(username, password)
self.connection = pika.BlockingConnection(pika.ConnectionParameters(
'localhost'))
self.channel = self.connection.channel()
# set up the queue for later
self.channel.queue_declare(queue='dockets')
def reinit_pacer_client(self, username, password):
# we have to log into each new court separately
self.pacer_client = PacerClient(username, password)
class OpinionsDownloader():
# TK: Add a param to set where to download files to?
def __init__(self, username, password) :
self.pacer_client = PacerClient(username, password)
self.connection = pika.BlockingConnection(pika.ConnectionParameters(
'localhost'))
self.channel = self.connection.channel()
# set up the queue for later
self.channel.queue_declare(queue='dockets')
def reinit_pacer_client(self, username, password):
# we have to log into each new court separately
self.pacer_client = PacerClient(username, password)
def get_opinions(self, court, start_date, end_date):
html = self.pacer_client.get_opinions_html(court,
start_date,
end_date)
dockets = PP.parse_opinions(html, court)
logger.info(' Downloaded %d dockets for court %s between %s and %s', len(dockets),
court,
start_date,
end_date)
#if len(dockets) == 0:
# logger.debug(' 0 dockets downloaded. HTML response: %s', html)
return dockets
def get_document(self, court, casenum, de_seq_num, dm_id, doc_num):
return self.pacer_client.get_pdf_show_doc(court, casenum, de_seq_num, dm_id, doc_num)
def enqueue_opinions(self, court, start_date, end_date):
for docket in self.get_opinions(court, start_date, end_date):
docmap = {}
for key, doc in docket.documents.items():
logger.info(' Downloading document %s.%s.%s.0', court,
docket.get_casenum(),
doc['doc_num']),
pdfbits = self.get_document(court,
docket.get_casenum(),
doc['pacer_de_seq_num'],
doc['pacer_dm_id'],
doc['doc_num'])
logger.info(' Downloaded document %s.%s.%s.0', court,
docket.get_casenum(),
doc['doc_num']),
# pickle the document into a file
# map the docnum-subdocnum to the filename
docmap[key] = _pickle_object(pdfbits)
# pickle file
filename = _pickle_object(docket)
# create message
upload_message = {'docket_filename': filename,
'docnums_to_filename': docmap,
'court': docket.get_court(),
'casenum': docket.get_casenum()}
# energize!
self.channel.basic_publish(exchange='',
routing_key='dockets',
body=pickle.dumps(upload_message))
logger.info(' Sent upload message for %s.%s', court, docket.get_casenum())
def reinit_pacer_client(self, username, password):
# we have to log into each new court separately
self.pacer_client = PacerClient(username, password)