fixed MPRT

.gitignore

@@ -0,0 +1,2 @@
+.venv
+*.txt

python/MPRT.py

@@ -1,44 +1,53 @@
 #!/usr/bin/python
-#MPRT - Finding a Protein Motif Solution
+# MPRT - Finding a Protein Motif Solution
-#Problem can be found at http://rosalind.info/problems/mprt/
+# Problem can be found at http://rosalind.info/problems/mprt/
-#Author: Peter Vlasveld
+# Author: Peter Vlasveld
 
-import urllib2
 import re
+from time import sleep
 
-#declare motif
+import requests
+
+# declare motif
 motif = "N[^P][ST][^P]"
 
-#read in file
+# read in file
 f0 = open("rosalind_mprt.txt", "r")
 content = f0.read().splitlines()
 f0.close()
 
-#open output file
+# open output file
 f1 = open("output.txt", "w+")
-#loop through each accession ID
+# loop through each accession ID
 for i in content:
-	#get fasta from url
+    # get fasta from url
-	url = "http://www.uniprot.org/uniprot/" + i + ".fasta"
+    url = "http://www.uniprot.org/uniprot/" + i.split("_")[0] + ".fasta"
-	response = urllib2.urlopen(url)
+    response = requests.get(url)
-	fasta = response.read().splitlines()
 
-	#format protein string
+    if response.status_code != 200:
+        print(f"uniprot request failed for {i}")
+        print(f"detail: {response.text}")
+
+    fasta = response.text.splitlines()
+
+    # format protein string
     protStr = ""
     for j in fasta:
-		if not j.startswith('>'):
+        if not j.startswith(">"):
             protStr += j
-	#construct output strings
+    # construct output strings
     outStr = ""
-	for j in range(0, len(protStr)-4):
+    for j in range(0, len(protStr) - 4):
-		if re.match(motif,protStr[j:j+4]):
+        if re.match(motif, protStr[j: j + 4]):
-			outStr += str(j+1) + " "
+            outStr += str(j + 1) + " "
 
-	#output
+    # output
     if not outStr == "":
-		print i
+        print(i)
         f1.write(i + "\n")
-		print outStr
+        print(outStr)
         f1.write(outStr + "\n")
-#close output file
+
+    sleep(1)
+# close output file
 f1.close()