Check in CSV generator and Handle Extractor (basically the same thing in two different versions)

datecsv.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+DATAFILE=Database.db
+OUTFILE=output.csv
+
+SQLITE="sqlite3 -csv -header"
+
+QUERY="SELECT SUBSTR(t.timestamp,0,11) AS 'Date', (SELECT COUNT(*) FROM tweets e WHERE SUBSTR(e.timestamp,0,11) = SUBSTR(t.timestamp,0,11)) AS 'Tweets'"
+
+for i in $@;
+ do QUERY="$QUERY, (SELECT COUNT(*) FROM tweets e WHERE SUBSTR(e.timestamp,0,11) = SUBSTR(t.timestamp,0,11) AND LOWER(e.text) LIKE '%${i,,}%') AS '$i'"
+done
+
+QUERY="$QUERY FROM tweets t GROUP BY SUBSTR(t.timestamp,0,11);"
+
+$SQLITE $DATAFILE "$QUERY" > $OUTFILE

gethandles.py

@@ -0,0 +1,28 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import operator, re, sqlite3
+
+def getTweets(database_filename = "Database.db"):
+ sql_conn = sqlite3.connect(database_filename)
+ cur = sql_conn.cursor()
+ 
+ handles = dict()
+ tweets = cur.execute("SELECT text FROM tweets")
+ 
+ for tweet in tweets:
+  for word in tweet[0].split():
+   if word[0] == "@":
+    handle = "@" + re.split('[\\W]',word[1:])[0].lower()
+    if handle != "@":
+     try:
+      handles[handle] += 1
+     except KeyError:
+      handles[handle] = 1
+
+ return handles
+
+if __name__ == "__main__":
+ data = sorted(getTweets().items(), key=operator.itemgetter(1), reverse=True)
+ for handle, tweets in data:
+  print handle + "," + str(tweets)