|
0
|
1 import argparse
|
|
|
2 import datetime
|
|
|
3 import json
|
|
|
4 import os
|
|
|
5 import sys
|
|
|
6
|
|
|
7 from urllib.request import Request, urlopen
|
|
|
8
|
|
|
9
|
|
|
10 def url_download(url, workdir):
|
|
|
11 file_path = os.path.abspath(os.path.join(workdir, os.path.basename(url)))
|
|
|
12 src = None
|
|
|
13 dst = None
|
|
|
14 try:
|
|
|
15 req = Request(url)
|
|
|
16 src = urlopen(req)
|
|
|
17 with open(file_path, 'wb') as dst:
|
|
|
18 while True:
|
|
|
19 chunk = src.read(2**10)
|
|
|
20 if chunk:
|
|
|
21 dst.write(chunk)
|
|
|
22 else:
|
|
|
23 break
|
|
|
24 except Exception as e:
|
|
|
25 sys.exit(str(e))
|
|
|
26 finally:
|
|
|
27 if src:
|
|
|
28 src.close()
|
|
|
29 return file_path
|
|
|
30
|
|
|
31
|
|
|
32 def download(url, out_file):
|
|
|
33 today = datetime.datetime.utcnow().strftime("%Y-%m-%d")
|
|
|
34
|
|
|
35 with open(out_file) as fh:
|
|
|
36 params = json.load(fh)
|
|
|
37
|
|
|
38 workdir = params['output_data'][0]['extra_files_path']
|
|
|
39 os.makedirs(workdir)
|
|
|
40 file_path = url_download(url, workdir)
|
|
|
41 value = '%s_pima_plasmids_and_values' % today
|
|
|
42 name = '%s %s' % (today, os.path.basename(file_path))
|
|
|
43
|
|
|
44 data_manager_json = {"data_tables": {}}
|
|
|
45 data_manager_entry = {}
|
|
|
46 data_manager_entry['value'] = value
|
|
|
47 data_manager_entry['name'] = name
|
|
|
48 data_manager_entry['path'] = file_path
|
|
|
49 data_manager_json["data_tables"]["vsnp_genbank"] = data_manager_entry
|
|
|
50
|
|
|
51 with open(out_file, 'w') as fh:
|
|
|
52 json.dump(data_manager_json, fh, sort_keys=True)
|
|
|
53
|
|
|
54
|
|
|
55 parser = argparse.ArgumentParser()
|
|
|
56
|
|
|
57 parser.add_argument('--url', dest='url', help='URL to download plasmids_and_vectors.fasta file')
|
|
|
58 parser.add_argument('--out_file', dest='out_file', help='JSON output file')
|
|
|
59
|
|
|
60 args = parser.parse_args()
|
|
|
61
|
|
|
62 download(args.url, args.out_file)
|
