Mercurial > repos > scottx611x > data_manager_fetch_gene_annotation

comparison data_manager_gene_annotation/data_manager/data_manager.py @ 37:7af38f95bc8d draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload
author scottx611x
date Thu, 23 Jun 2016 17:56:47 -0400
parents f38beb0743d5
children
comparison
equal deleted inserted replaced
36:f38beb0743d5 37:7af38f95bc8d
5 import argparse 5 import argparse
6 import datetime 6 import datetime
7 import requests 7 import requests
8 from requests.exceptions import ContentDecodingError 8 from requests.exceptions import ContentDecodingError
9 9
10 parser = argparse.ArgumentParser(description='Create data manager json.')
11 parser.add_argument('--out',
12 dest='output',
13 action='store',
14 help='JSON filename',
15 )
16 parser.add_argument('--name',
17 dest='name',
18 action='store',
19 default=uuid.uuid4(),
20 help='Data table entry unique ID'
21 )
22 parser.add_argument('--url',
23 dest='url',
24 action='store',
25 help='Download URL'
26 )
27
28 args = parser.parse_args()
29
30 10
31 def url_download(url): 11 def url_download(url):
12 """Attempt to download gene annotation file from a given url
13 :param url: NodeSet UUID.
14 :type url: str.
15 :returns: name of downloaded gene annotation file
16 :raises: ContentDecodingError, IOError
17 """
32 response = requests.get(url=url, stream=True) 18 response = requests.get(url=url, stream=True)
33 19
34 # Generate file_name 20 # Generate file_name
35 file_name = response.url.split("/")[-1] 21 file_name = response.url.split("/")[-1]
36 22
37 block_size = 10 * 1024 * 1024 # 10MB chunked download 23 block_size = 10 * 1024 * 1024 # 10MB chunked download
38 with open(file_name, 'w+') as f: 24 with open(file_name, 'w+') as f:
39 try: 25 try:
40 # Good to note here that requests' iter_content() will 26 # Good to note here that requests' iter_content() will
41 # automatically handle decoding "gzip" and "deflate" formats 27 # automatically handle decoding "gzip" and "deflate" encoding
28 # formats
42 for buf in response.iter_content(block_size): 29 for buf in response.iter_content(block_size):
43 f.write(buf) 30 f.write(buf)
44 except (ContentDecodingError, IOError) as e: 31 except (ContentDecodingError, IOError) as e:
45 sys.stderr.write("Error occured downloading reference file: %s" 32 sys.stderr.write("Error occured downloading reference file: %s"
46 % e) 33 % e)
47 os.remove(file_name) 34 os.remove(file_name)
48 35
49 with open("/Users/scott/Desktop/cool.txt", "w+") as f:
50 f.write(os.path.join(os.getcwd(), file_name))
51 f.write("\n")
52
53 return file_name 36 return file_name
54 37
55 38
56 def main(args): 39 def main():
40
41 # Generate and parse command line args
42 parser = argparse.ArgumentParser(description='Create data manager JSON.')
43 parser.add_argument('--out', dest='output', action='store',
44 help='JSON filename')
45 parser.add_argument('--name', dest='name', action='store',
46 default=uuid.uuid4(), help='Data table entry unique ID'
47 )
48 parser.add_argument('--url', dest='url', action='store',
49 help='Url to download gtf file from')
50
51 args = parser.parse_args()
57 52
58 work_dir = os.getcwd() 53 work_dir = os.getcwd()
59 54
60 # Attempt to download gene annotation file from given url 55 # Attempt to download gene annotation file from given url
61 gene_annotation_file_name = url_download(args.url) 56 gene_annotation_file_name = url_download(args.url)
74 69
75 with open(os.path.join(args.output), "w+") as f: 70 with open(os.path.join(args.output), "w+") as f:
76 f.write(json.dumps(data_manager_entry)) 71 f.write(json.dumps(data_manager_entry))
77 72
78 if __name__ == '__main__': 73 if __name__ == '__main__':
79 main(args) 74 main()