2 files changed, 56 insertions, 0 deletions
diff --git a/.gitignore b/.gitignore
index eaf0161..fe1d8a4 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,2 +1,3 @@
 errors
 data/
+run.txt
diff --git a/run.py b/run.py
new file mode 100755
index 0000000..7f0fea9
--- /dev/null
+++ b/run.py
@@ -0,0 +1,55 @@
+#!/usr/bin/env python3
+
+import fileinput
+import json
+import os
+from urllib.parse import quote_plus
+from urllib.request import urlopen, Request
+
+DATADIR = 'data'
+ERRORFILE = 'errors'
+
+def get(dbpediaid):
+    outfile = os.path.join(DATADIR, quote_plus(dbpediaid) + '.json')
+    if not os.path.isfile(outfile):
+        url = 'http://api.nordlys.cc/ec/lookup_id/{}'.format(
+                quote_plus(dbpediaid.replace('/', '___SLASH')).replace('___SLASH', '/'))
+        print(url)
+        result = urlopen(Request(url,
+            headers={'User-Agent': 'Radboud University'})).read()
+        with open(outfile, 'w') as f:
+            f.write(result.decode(encoding='UTF-8'))
+    with open(outfile) as f:
+        return json.load(f)
+
+def match(value, terms):
+    for v in value.split():
+        if v in terms:
+            return True
+    return False
+
+def run(queries, line, outfile):
+    query, _, dbpediaid, _, relevance, method = line.split('\t')
+    terms = queries[query].split()
+    try:
+        result = get(dbpediaid)
+        for field, values in result.items():
+            matches = 0
+            for value in values:
+                if match(value, terms):
+                    matches += 1
+            outfile.write('{}\t{}\t{}\t{}\t{}\n'.format(
+                query, dbpediaid, field, len(values), matches))
+    except Exception as e:
+        print(dbpediaid)
+        print(e)
+        with open(ERRORFILE, 'a') as f:
+            f.write(dbpediaid + '\t' + e + '\n')
+
+if __name__ == '__main__':
+    with open('queries_stopped.json') as f:
+        queries = json.load(f)
+
+        with open('run.txt', 'w') as out:
+            for line in fileinput.input():
+                run(queries, line, out)