Moved result files to a directory

jvilaplana · Apr 27, 2017 · 4683b83 · 4683b83
1 parent 3d79f17
commit 4683b83
Show file tree

Hide file tree

Showing 29 changed files with 25 additions and 4 deletions.
diff --git a/README.md b/README.md
@@ -30,14 +30,28 @@ To execute the program run the following commands in your terminal:
 source venv/bin/activate
 python vademecum_export.py
 ```
+If the executing is successful, you should see something like:
+```
+$ python vademecum_export.py
+
+Going for letter a
+	Getting drug 614537 (a-1)
+	Getting drug 686580 (a-1)
+	Getting drug 614560 (a-2)
+	Getting drug 672905 (a-2)
+	Getting drug 712249 (a-3)
+  ...
+```
 
 ## Analyze results
 To check how many drugs were successfully retrieved run:
 ```
+cd results/
 find . -name 'vademecum-*' | xargs wc -l
 ```
 
 To combine all the CSV files into a single one run:
 ```
+cd results/
 cat vademecum-* > vademecum.csv
 ```
diff --git a/vademecum-a.csv → results/vademecum-a.csv b/vademecum-a.csv → results/vademecum-a.csv
diff --git a/vademecum-b.csv → results/vademecum-b.csv b/vademecum-b.csv → results/vademecum-b.csv
diff --git a/vademecum-c.csv → results/vademecum-c.csv b/vademecum-c.csv → results/vademecum-c.csv
diff --git a/vademecum-d.csv → results/vademecum-d.csv b/vademecum-d.csv → results/vademecum-d.csv
diff --git a/vademecum-e.csv → results/vademecum-e.csv b/vademecum-e.csv → results/vademecum-e.csv
diff --git a/vademecum-f.csv → results/vademecum-f.csv b/vademecum-f.csv → results/vademecum-f.csv
diff --git a/vademecum-g.csv → results/vademecum-g.csv b/vademecum-g.csv → results/vademecum-g.csv
diff --git a/vademecum-h.csv → results/vademecum-h.csv b/vademecum-h.csv → results/vademecum-h.csv
diff --git a/vademecum-i.csv → results/vademecum-i.csv b/vademecum-i.csv → results/vademecum-i.csv
diff --git a/vademecum-j.csv → results/vademecum-j.csv b/vademecum-j.csv → results/vademecum-j.csv
diff --git a/vademecum-k.csv → results/vademecum-k.csv b/vademecum-k.csv → results/vademecum-k.csv
diff --git a/vademecum-l.csv → results/vademecum-l.csv b/vademecum-l.csv → results/vademecum-l.csv
diff --git a/vademecum-m.csv → results/vademecum-m.csv b/vademecum-m.csv → results/vademecum-m.csv
diff --git a/vademecum-n.csv → results/vademecum-n.csv b/vademecum-n.csv → results/vademecum-n.csv
diff --git a/vademecum-o.csv → results/vademecum-o.csv b/vademecum-o.csv → results/vademecum-o.csv
diff --git a/vademecum-p.csv → results/vademecum-p.csv b/vademecum-p.csv → results/vademecum-p.csv
diff --git a/vademecum-q.csv → results/vademecum-q.csv b/vademecum-q.csv → results/vademecum-q.csv
diff --git a/vademecum-r.csv → results/vademecum-r.csv b/vademecum-r.csv → results/vademecum-r.csv
diff --git a/vademecum-s.csv → results/vademecum-s.csv b/vademecum-s.csv → results/vademecum-s.csv
diff --git a/vademecum-t.csv → results/vademecum-t.csv b/vademecum-t.csv → results/vademecum-t.csv
diff --git a/vademecum-u.csv → results/vademecum-u.csv b/vademecum-u.csv → results/vademecum-u.csv
diff --git a/vademecum-v.csv → results/vademecum-v.csv b/vademecum-v.csv → results/vademecum-v.csv
diff --git a/vademecum-w.csv → results/vademecum-w.csv b/vademecum-w.csv → results/vademecum-w.csv
diff --git a/vademecum-x.csv → results/vademecum-x.csv b/vademecum-x.csv → results/vademecum-x.csv
diff --git a/vademecum-y.csv → results/vademecum-y.csv b/vademecum-y.csv → results/vademecum-y.csv
diff --git a/vademecum-z.csv → results/vademecum-z.csv b/vademecum-z.csv → results/vademecum-z.csv
diff --git a/vademecum.csv → results/vademecum.csv b/vademecum.csv → results/vademecum.csv
diff --git a/vademecum_export.py b/vademecum_export.py
@@ -1,19 +1,26 @@
 # -*- coding: utf-8 -*-
 
-import urllib2
-from bs4 import BeautifulSoup
 import re
-import string
+import os
 import csv
 import time
+import string
+import urllib2
+from bs4 import BeautifulSoup
+
 
 # We are going to iterate through all leters (a - z).
 letter_list = string.lowercase[:26]
 
+# We check if the results directory exists
+if not os.path.exists('results'):
+    # If it's not there, we create it
+    os.makedirs('results')
+
 # Each letter has its own page with its drug list.
 # We will be saving a CSV file for each starting letter.
 for letter in letter_list:
-    with open('vademecum-' + str(letter) + '.csv', 'wb') as csvfile:
+    with open('results/vademecum-' + str(letter) + '.csv', 'wb') as csvfile:
         # We will be saving the drug code, name and URL.
         fieldnames = ['cod_nacion', 'nombre', 'url']
         writer = csv.DictWriter(csvfile, fieldnames=fieldnames)