diff uniprotxml_downloader.py @ 2:e1abc9a35c64 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/uniprotxml_downloader commit 15c2d28359584bcee25cdb456cff50892fff7347

--- a/uniprotxml_downloader.py	Wed Dec 07 16:44:14 2016 -0500
+++ b/uniprotxml_downloader.py	Fri Dec 16 17:33:05 2016 -0500
@@ -15,19 +15,32 @@
 import re
 import optparse
 import urllib
+import urllib2
 
 
 def __main__():
     # Parse Command Line
     parser = optparse.OptionParser()
+    parser.add_option('-i', '--input', dest='input', default=None, help='Tabular file containing a column of NCBI Taxon IDs')
+    parser.add_option('-c', '--column', dest='column', type='int', default=0, help='The column (zero-based) in the tabular file that contains Taxon IDs' )
     parser.add_option('-t', '--taxon', dest='taxon', action='append', default=[], help='NCBI taxon ID to download')
-    parser.add_option('-r', '--reviewed', dest='reviewed', help='file path for th downloaed uniprot xml')
+    parser.add_option('-r', '--reviewed', dest='reviewed', help='Only uniprot reviewed entries')
+    parser.add_option('-f', '--format', dest='format', choices=['xml', 'fasta'], default='xml',help='output format')
     parser.add_option('-o', '--output', dest='output', help='file path for th downloaed uniprot xml')
     parser.add_option('-v', '--verbose', dest='verbose', action='store_true', default=False, help='Print UniProt Info')
     parser.add_option('-d', '--debug', dest='debug', action='store_true', default=False, help='Turn on wrapper debugging to stderr')
     (options, args) = parser.parse_args()
-
-    taxids = options.taxon if options.taxon else ['9606']
+    taxids = set(options.taxon)
+    if options.input:
+        with open(options.input,'r') as inputFile:
+            for linenum,line in enumerate(inputFile):
+                if line.startswith('#'):
+                    continue
+                fields = line.rstrip('\r\n').split('\t')
+                if len(fields) > abs(options.column):
+                    taxid = fields[options.column].strip()
+                    if taxid:
+                      taxids.add(taxid)
     taxon_queries = ['taxonomy:"%s"' % taxid for taxid in taxids]
     taxon_query = ' OR '.join(taxon_queries)
     if options.output:
@@ -35,26 +48,31 @@
     else:
         dest_path = "uniprot_%s.xml" % '_'.join(taxids)
     reviewed = " reviewed:%s" % options.reviewed if options.reviewed else ''
-    url = 'http://www.uniprot.org/uniprot/?query=%s%s&force=yes&format=xml' % (taxon_query, reviewed)
-    if options.debug:
-        print >> sys.stderr, url
     try:
-        (fname, msg) = urllib.urlretrieve(url, dest_path)
+        def reporthook(n1,n2,n3):
+            pass   
+        url = 'http://www.uniprot.org/uniprot/'
+        query = "%s%s" % (taxon_query, reviewed)
+        params = {'query' : query, 'force' : 'yes' , 'format' : options.format}
+        if options.debug:
+            print >> sys.stderr, "%s ? %s" % (url,params)
+        data = urllib.urlencode(params)
+        (fname, msg) = urllib.urlretrieve(url, dest_path,reporthook,data)
         headers = {j[0]: j[1].strip() for j in [i.split(':', 1) for i in str(msg).strip().splitlines()]}
         if 'Content-Length' in headers and headers['Content-Length'] == 0:
             print >> sys.stderr, url
             print >> sys.stderr, msg
             exit(1)
-        elif True:
-            pass
-        else:
+        if options.format == 'xml':
             with open(dest_path, 'r') as contents:
                 while True:
                     line = contents.readline()
                     if options.debug:
                         print >> sys.stderr, line
-                    if line is None or not line.startswith('<?'):
+                    if line is None:
                         break
+                    if line.startswith('<?'):
+                        continue
                     # pattern match <root or <ns:root for any ns string
                     pattern = '^<(\w*:)?uniprot'
                     if re.match(pattern, line):
@@ -62,7 +80,6 @@
                     else:
                         print >> sys.stderr, "failed: Not a uniprot xml file"
                         exit(1)
-
         if options.verbose:
             print >> sys.stdout, "NCBI Taxon ID:%s" % taxids
             if 'X-UniProt-Release' in headers: