gistfile1.txt

#!/usr/bin/python

"""

0. This script demonstrates to download data files of project with name "project_name" from your basespace account.

1. Get your access token from here by creating an application: https://developer.basespace.illumina.com/dashboard
The access token is a 32-bit long string.

2. For demonstration only this script only considers that you have less than 1000 projects in your account because of "Offset=0&Limit=1000"
If you have more than 1000 projects, use a loop with combination of "Offset" and "Limit".

3. No error handling. DIY if you want.

"""

import sys
import os
import urllib2
import json
import multiprocessing

ACCESS_TOKEN="thisisa32bitlongstringasyouraccesstoken"
BASE_URI = 'http://api.basespace.illumina.com/v1pre3/'
RESOURCE_COLLECTION_REQUESTS="?Offset=0&Limit=1024&access_token={}".format(ACCESS_TOKEN)
PROJECTS_GET_URI = 'users/current/projects'
SAMPLES_GET_URI = 'projects/{Id}/samples'
FILES_GET_URI='samples/{Id}/files'


def get_request(req):
    request = urllib2.Request(req)
    response = urllib2.urlopen(request)
    return json.loads(response.read())

def list_items(req):
    return iter(req['Response']['Items'])

def download_file(tuple_uri):
    
    request_uri,project_name,file_name = tuple_uri 
    output_file_name = os.path.abspath(os.path.join(project_name,file_name))
    output_dir_name = os.path.dirname(output_file_name)
    try:
        if not os.path.exists(output_dir_name):
            os.makedirs(output_dir_name)
    except:
        pass 
    print '%s ---> %s' % (file_name,output_file_name) 
    with open(output_file_name,'wb') as outfile:
        response = urllib2.urlopen((request_uri),timeout=3)
        outfile.write(response.read())
    
def download_project(project_name="project1"):
    
    request_uri= '{0}{1}{2}'.format(BASE_URI,PROJECTS_GET_URI,RESOURCE_COLLECTION_REQUESTS)
    files_uris = []
    for i in list_items(get_request(request_uri)):
        if i['Name'] == project_name:
            request_uri= '{0}{1}{2}'.format(BASE_URI,SAMPLES_GET_URI.format(Id=i['Id']),RESOURCE_COLLECTION_REQUESTS)
            for j in list_items(get_request(request_uri)):
                request_uri= '{0}{1}{2}'.format(BASE_URI,FILES_GET_URI.format(Id=j['Id']),RESOURCE_COLLECTION_REQUESTS)
                for k in list_items(get_request(request_uri)):
                    files_uris.append(['http://api.basespace.illumina.com/{0}/content?access_token={1}'.format(k['Href'],ACCESS_TOKEN),
                                       project_name,
                                       k['Path']
                                       ])
            break
        
    ppool = multiprocessing.Pool(multiprocessing.cpu_count())
    ppool.map(download_file,files_uris)
    ppool.close()
    

if __name__=='__main__':
    download_project(project_name=sys.argv[1])