# HG changeset patch
# User jingchunzhu
# Date 1439422692 25200
# Node ID 3167c1a26101ec60e7cf5bc5a05541972acf1ace
# Parent 8da6920a39ac6e35db2c6bf6190deab3101956fa
fix
diff -r 8da6920a39ac -r 3167c1a26101 getXenaData.py
--- a/getXenaData.py Sun Aug 09 23:23:58 2015 -0700
+++ b/getXenaData.py Wed Aug 12 16:38:12 2015 -0700
@@ -6,66 +6,75 @@
print "python getXenaData.py hub datasetId outputfile\n"
sys.exit(1)
-url = sys.argv[1]
-dataset = sys.argv[2]
-output = sys.argv[3]
+def main():
+ url = sys.argv[1]
+ dataset = sys.argv[2]
+ output = sys.argv[3]
-fout = open(output,'w')
+ fout = open(output,'w')
-if string.find(url,"galaxyxena") !=-1 and string.find(url,"ucsc.edu")!=-1:
- url = "https://galaxyxena.soe.ucsc.edu:443/xena"
+ contactUrl = url
+ if string.find(url,"galaxyxena") !=-1 and string.find(url,"ucsc.edu")!=-1:
+ contactUrl = "https://galaxyxena.soe.ucsc.edu:443/xena"
-#testing if the url is reachable
-try:
- r =json.loads(xena.post(url, "(+ 1 2)"))
- if r!=3.0:
- print "The hub seems can not be reached, either it is not running, the url has a typo, or it is not accessible to you."
+ #testing if the url is reachable
+ try:
+ r =json.loads(xena.post(contactUrl, "(+ 1 2)"))
+
+ if r!=3.0:
+ print "The hub seems can not be reached, either it is not running, the url has a typo, or it is not accessible to this galaxy instance."
+ print "You entered hub: %s" % (url)
+ fout.write("The hub seems can not be reached, either it is not running, the url has a typo, or it is not accessible to this galaxy instance.\n")
+ fout.write("You entered hub: %s\n" % (url))
+ fout.close()
+ sys.exit(1)
+
+ except:
+ print "The hub seems can not be reached, either it is not running, the url has a typo, or it is not accessible to this galaxy instance."
print "You entered hub: %s" % (url)
- fout.write("The hub seems can not be reached, either it is not running, the url has a typo, or it is not accessible to you.\n")
- fout.write("You entered hub: %s\n" % (url))
- fout.close()
- sys.exit(1)
-except:
- print "The hub seems can not be reached, either it is not running, the url has a typo, or it is not accessible to you."
- print "You entered hub: %s" % (url)
- fout.write("The hub seems can not be reached, either it is not running, the url has a typo, or it is not accessible to you.\n")
+ fout.write("The hub seems can not be reached, either it is not running, the url has a typo, or it is not accessible to this galaxy instance.\n")
fout.write("You entered hub: %s\n" % (url))
fout.close()
sys.exit(1)
-samples = xena.dataset_samples (url, dataset)
-if not samples:
- print "Dataset does not exist"
- print "You entered dataset id: %s" % (dataset)
- fout.write("Dataset does not exists\n")
- fout.write("You entered dataset id: %s\n" % (dataset))
- fout.close()
- sys.exit(1)
+ samples = xena.dataset_samples (contactUrl, dataset)
+ if not samples:
+ print "Dataset does not exist"
+ print "You entered dataset id: %s" % (dataset)
+ fout.write("Dataset does not exists\n")
+ fout.write("You entered dataset id: %s\n" % (dataset))
+ fout.close()
+ sys.exit(1)
-type = xena.dataset_type(url, dataset)
-if type[0] not in ["genomicMatrix", "clinicalMatrix"]:
- print "The type of data is not supported"
- print "datatype=%s" % (type[0])
- fout.write("The type of data is not supported\n")
- fout.write("datatype=%s\n" % (type[0]))
- fout.close()
- sys.exit(1)
+ type = xena.dataset_type(contactUrl, dataset)
+ if type[0] not in ["genomicMatrix", "clinicalMatrix"]:
+ print "The type of data is not supported"
+ print "datatype=%s" % (type[0])
+ fout.write("The type of data is not supported\n")
+ fout.write("datatype=%s\n" % (type[0]))
+ fout.close()
+ sys.exit(1)
+
+ writer = csv.writer(fout, delimiter='\t')
+ writer.writerow(["sample"]+samples)
-writer = csv.writer(fout, delimiter='\t')
-writer.writerow(["sample"]+samples)
+ probes = xena.dataset_field(contactUrl, dataset)
+ start=0
+ size =100
+ N= len(probes)
+ for i in range (start, N,size):
+ results = xena.dataset_probe_values (contactUrl, dataset, samples, probes[i:i+size])
+ print ".",
+ for j in range (0, size):
+ if i+j == N:
+ break
+ writer.writerow([probes[i+j]]+results[j])
-probes = xena.dataset_field(url, dataset)
-start=0
-size =100
-N= len(probes)
-for i in range (start, N,size):
- results = xena.dataset_probe_values (url, dataset, samples, probes[i:i+size])
- print ".",
- for j in range (0, size):
- if i+j == N:
- break
- writer.writerow([probes[i+j]]+results[j])
+ fout.close()
+ print "done"
+ sys.exit(0)
-fout.close()
-print "done"
-sys.exit(0)
+
+if __name__ == "__main__":
+ main()
+
diff -r 8da6920a39ac -r 3167c1a26101 xenaGetDataset.py
--- a/xenaGetDataset.py Sun Aug 09 23:23:58 2015 -0700
+++ b/xenaGetDataset.py Wed Aug 12 16:38:12 2015 -0700
@@ -9,26 +9,25 @@
parser = argparse.ArgumentParser()
parser.add_argument("dataHub", type=str)
parser.add_argument("datasetId", type=str)
- #parser.add_argument("metadatafile", type=str)
parser.add_argument("datafile", type=str)
args = parser.parse_args()
datasetUrlHost = re.sub("/proj/", "/download/", args.dataHub)
datasetIdTokens = re.split("/", args.datasetId)
datasetUrl = datasetUrlHost + "/" + "/".join(datasetIdTokens[1:])
- print datasetUrl
- """
- metadataUrl = datasetUrl + ".json"
- mm = urllib2.urlopen(metadataUrl)
- with open(args.metadatafile, "w") as metadata:
- metadata.write(mm.read())
- mm.close()
- """
- dd = urllib2.urlopen(datasetUrl)
- with open(args.datafile, "w") as data:
+
+ data = open(args.datafile, "w")
+
+ try:
+ dd = urllib2.urlopen(datasetUrl)
data.write(dd.read())
- dd.close()
-
+ dd.close()
+ data.close()
+ except:
+ data.wriet("You entered dataset id: %s\n" % (args.datasetId))
+ data.write("Dataset does not exist. check typo.")
+ data.close()
+ sys.exit(1)
if __name__ == "__main__":
main()