# number of new records collected
new_records_processed = 0
with open(OUTPUT_FILE, 'a') as o:
with open(OSF_PREPRINT_FILE, 'r') as f:
for line in f:
records = json.loads(line)
for record in records['data']:
if record['id'] not in records_processed:
contributor_url = record['relationships']['contributors']['links']['related']['href']
contributor_data = { 'id' : record['id'], 'data' : [] }
while True:
status, data = util.download_from_url(contributor_url)
if status == 'SUCCESS':
contributor_data['data'].append(data)
if data['links']['next'] is None:
break
# get link to next set of records to download
contributor_url = data['links']['next']
else:
break
json.dump(contributor_data, o)
o.write('\n')
o.flush()
def download_cash_flow(symbol, force=True):
url = cash_flow_url.format(symbol)
filename = os.path.join(data_dir, symbol + '.cash_flow.xlsx')
return download_from_url(url, filename, overwrite=force)
def download_income_stmt(symbol, force=True):
url = income_statement_url.format(symbol)
filename = os.path.join(data_dir, symbol + '.income_stmt.xlsx')
return download_from_url(url, filename, overwrite=force)
def download_balance_sheet(symbol, force=True):
url = balance_sheet_url.format(symbol)
filename = os.path.join(data_dir, symbol + '.balance_sheet.xlsx')
return download_from_url(url, filename, overwrite=force)
if record['id'] not in records_processed:
institution_data = {'id': record['id'], 'data': {}}
for author_list in record['data']:
for author in author_list['data']:
try:
institution_url = author['embeds']['users'][
'data']['relationships']['institutions'][
'links']['related']['href']
except:
institution_url = None
if institution_url is not None:
institution_list = []
while True:
status, data = util.download_from_url(
institution_url)
if status == 'SUCCESS':
institution_list.append(data)
if data['links']['next'] is None:
break
# get link to next set of records to download
institution_url = data['links']['next']
else:
break
institution_data[author['id']] = institution_list
json.dump(institution_data, o)
