def main():
parser = argparse.ArgumentParser()
parser.add_argument("--scheme_name",
"-s",
dest="scheme_name",
help="scheme name",
required=True)
parser.add_argument("--scheme_id",
"-i",
dest="scheme_id",
default="1",
help="scheme id")
parser.add_argument("--outdir",
"-o",
dest="outdir",
default='.',
help="output directory")
args = parser.parse_args()
if not os.path.exists(args.outdir):
os.mkdir(args.outdir)
api_url_base = 'http://rest.pubmlst.org/db'
scheme_url = '/'.join([
api_url_base, 'pubmlst_' + args.scheme_name + '_seqdef', 'schemes',
args.scheme_id
])
scheme_response = json.loads(get(scheme_url))
for locus_url in scheme_response['loci']:
locus = json.loads(get(locus_url))
plaintext_header = {'Content-Type': 'text/plain'}
alleles_fasta = get(locus['alleles_fasta'],
headers=plaintext_header).decode('utf-8')
output_filename = os.path.join(args.outdir, locus['id'] + '.fasta')
with open(output_filename, 'w') as f:
f.write(alleles_fasta)
log_msg = {
'timestamp': str(datetime.datetime.now().isoformat()),
'event': 'file_downloaded',
'filename': output_filename,
}
print(json.dumps(log_msg), file=sys.stderr)
def main():
parser = argparse.ArgumentParser()
parser.add_argument("--scheme_name", "-s", dest="scheme_name", help="scheme name", required=True)
parser.add_argument("--scheme_id", "-i", dest="scheme_id", default="1", help="scheme id")
parser.add_argument("--outdir", "-o", dest="outdir", default='.', help="output directory")
parser.add_argument("--base-url", "-b", dest="base_url", default='http://rest.pubmlst.org/db', help="Base URL for the API. Suggested values are: http://rest.pubmlst.org/db (default), https://bigsdb.pasteur.fr/api/db")
parser.add_argument("--proxy", "-p", dest="proxy", default='', help="Proxy URL: http://yourProxy:8080")
args = parser.parse_args()
if not os.path.exists(args.outdir):
os.mkdir(args.outdir)
api_url_base = args.base_url
scheme_url = '/'.join([
api_url_base,
'pubmlst_' + args.scheme_name + '_seqdef',
'schemes',
args.scheme_id
])
scheme_response = json.loads(get(api_url=scheme_url, proxy=args.proxy))
if args.proxy == '':
pd.read_csv(scheme_response['profiles_csv'], sep='\t', index_col=False).to_csv(os.path.join(args.outdir, os.path.basename(args.outdir) + ".txt"), sep='\t', index=None)
else:
proxy_dict = {"http": args.proxy,
"https": args.proxy}
s = requests.get(scheme_response['profiles_csv'], proxies=proxy_dict).text
pd.read_csv(io.StringIO(s), sep='\t', index_col=False).to_csv(os.path.join(args.outdir, os.path.basename(args.outdir) + ".txt"), sep='\t', index=None)
for locus_url in scheme_response['loci']:
locus = json.loads(get(locus_url))
plaintext_header = {'Content-Type': 'text/plain'}
alleles_fasta = get(locus['alleles_fasta'], headers=plaintext_header).decode('utf-8')
output_filename = os.path.join(args.outdir, locus['id'] + '.tfa')
with open(output_filename, 'w') as f:
f.write(alleles_fasta)
log_msg = {
'timestamp': str(datetime.datetime.now().isoformat()),
'event': 'file_downloaded',
'filename': output_filename,
}
print(json.dumps(log_msg), file=sys.stderr)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--pattern',
'-p',
default="",
help="regex pattern to filter scheme names")
parser.add_argument('--exclude_pattern',
'-e',
default="",
help="regex pattern to filter scheme names")
parser.add_argument('--names_only',
'-n',
default="",
action='store_true',
help="Only show scheme names")
args = parser.parse_args()
details_fields = [
'id',
'description',
'locus_count',
'records',
'last_added',
'last_updated',
]
if args.names_only:
print('name')
else:
print('\t'.join(['name'] + details_fields))
api_url_base = 'http://rest.pubmlst.org/db'
url_base_response = json.loads(get(api_url_base))
for db in url_base_response:
databases = db['databases']
for database in databases:
if args.exclude_pattern != "":
if re.search(
'pubmlst_(' + '.*' + args.exclude_pattern + '.*' +
')_seqdef$', database['name']):
continue
scheme_match = re.search(
'pubmlst_(' + '.*' + args.pattern + '.*' + ')_seqdef$',
database['name'])
if scheme_match:
scheme_name = scheme_match.group(1)
if args.names_only:
print(scheme_name)
break
seqdef_response = get(database['href'])
if seqdef_response:
schemes_response = get(
json.loads(seqdef_response)['schemes'])
if schemes_response:
for scheme in json.loads(schemes_response)['schemes']:
scheme_details_response = get(scheme['scheme'])
if scheme_details_response:
details = {}
for field in details_fields:
try:
details[field] = json.loads(
scheme_details_response)[field]
except KeyError:
details[field] = None
print('\t'.join(
map(str, [scheme_name] +
list(details.values()))),
flush=True)