diff --git a/snark-document-builder/src/main/python/SnarkParser.py b/snark-document-builder/src/main/python/SnarkParser.py
new file mode 100644
index 0000000..fb71d7f
--- /dev/null
+++ b/snark-document-builder/src/main/python/SnarkParser.py
@@ -0,0 +1,26 @@
+import sys
+import re
+import json
+
+assert(len(sys.argv) >= 2)
+
+string = sys.argv[1]
+
+outputfile = sys.argv[2] if len(sys.argv) >= 3 else None
+
+pattern = r'^([\n|\t| ]*@include\([a-z|0-9|.|_]*.md\)[\n|\t| ]*)*$'
+
+files = []
+
+if re.search("@include", string, re.IGNORECASE):
+    if re.match(pattern, string):
+        matches = re.findall(r'@include\((.*?)\)', string)
+        files.extend(matches)
+    else:
+        sys.exit("Illformed string")
+
+if outputfile is None:
+    print(json.dumps(files))
+else:
+    with open(outputfile, 'w+') as f:
+        json.dump(files, f)
\ No newline at end of file