comparison data_manager/data_manager.py @ 39:2ab076cf69df draft

planemo upload for repository https://scottx611x@toolshed.g2.bx.psu.edu/repos/scottx611x/data_manager_fetch_gene_annotation
author scottx611x
date Fri, 08 Jul 2016 11:17:50 -0400
parents
children
comparison
equal deleted inserted replaced
38:d27c122c2424 39:2ab076cf69df
1 import os
2 import sys
3 import uuid
4 import json
5 import argparse
6 import requests
7 from requests.exceptions import ContentDecodingError
8
9
10 def url_download(url):
11 """Attempt to download gene annotation file from a given url
12 :param url: full url to gene annotation file
13 :type url: str.
14 :returns: name of downloaded gene annotation file
15 :raises: ContentDecodingError, IOError
16 """
17 response = requests.get(url=url, stream=True)
18
19 # Generate file_name
20 file_name = response.url.split("/")[-1]
21
22 block_size = 10 * 1024 * 1024 # 10MB chunked download
23 with open(file_name, 'w+') as f:
24 try:
25 # Good to note here that requests' iter_content() will
26 # automatically handle decoding "gzip" and "deflate" encoding
27 # formats
28 for buf in response.iter_content(block_size):
29 f.write(buf)
30 except (ContentDecodingError, IOError) as e:
31 sys.stderr.write("Error occured downloading reference file: %s"
32 % e)
33 os.remove(file_name)
34
35 return file_name
36
37
38 def main():
39
40 # Generate and parse command line args
41 parser = argparse.ArgumentParser(description='Create data manager JSON.')
42 parser.add_argument('--out', dest='output', action='store',
43 help='JSON filename')
44 parser.add_argument('--name', dest='name', action='store',
45 default=uuid.uuid4(), help='Data table entry unique ID'
46 )
47 parser.add_argument('--url', dest='url', action='store',
48 help='Url to download gtf file from')
49
50 args = parser.parse_args()
51
52 work_dir = os.getcwd()
53
54 # Attempt to download gene annotation file from given url
55 gene_annotation_file_name = url_download(args.url)
56
57 # Update Data Manager JSON and write to file
58 data_manager_entry = {
59 'data_tables': {
60 'gene_annotation': {
61 'value': str(args.name),
62 'dbkey': str(args.name),
63 'name': gene_annotation_file_name,
64 'path': os.path.join(work_dir, gene_annotation_file_name)
65 }
66 }
67 }
68
69 with open(os.path.join(args.output), "w+") as f:
70 f.write(json.dumps(data_manager_entry))
71
72 if __name__ == '__main__':
73 main()