diff --git a/static/files/.DS_Store b/static/files/.DS_Store
index b1d674c..b10cdea 100644
Binary files a/static/files/.DS_Store and b/static/files/.DS_Store differ
diff --git a/static/files/00. Pushing Scores/00.json b/static/files/00. Pushing Scores/00.json
deleted file mode 100644
index 9bc2eff..0000000
--- a/static/files/00. Pushing Scores/00.json	
+++ /dev/null
@@ -1,13 +0,0 @@
-{
-  "id": "00.",
-  "name": "Yes",
-  "email": "sure@whynot.com",
-  "friend": "Y",
-  "content": "A sound file.",
-  "files":[
-  	"files/00. Pushing Scores/Participants.txt",
-    "files/00. Pushing Scores/PushingScores.html",
-    "files/00. Pushing Scores/events.txt"
-
-  ]
-}
diff --git a/textedit.py b/textedit.py
new file mode 100644
index 0000000..dbd29b1
--- /dev/null
+++ b/textedit.py
@@ -0,0 +1,26 @@
+# this code is split in two parts:
+# going through the description html files and gathering the interesting words in a json file;
+# and going through the files again to replace words that also appear in the json with an a href version
+
+import sys, os
+import nltk
+from nltk import word_tokenize
+from nltk.util import trigrams
+
+# text analysis
+def analysis(file):
+    # print("yes")
+    file_trigrams = trigrams(content)
+    print(file_trigrams)
+
+
+
+# reading each individual html file
+path = "static/files/"
+for path, subdirs, files in os.walk(path):
+    for name in files:
+        if name.endswith('html'):
+            file = os.path.join(path, name)
+            with open(file) as f:
+                content = f.read()
+            analysis(content)