smcl · June 19, 2011 15:28 · Jun 19, 2011 · Jun 19, 2011
diff --git a/gistfile1.py b/gistfile1.py
@@ -88,7 +88,8 @@ def fetch(user):
 m = Markov()
 
 def tweet():
-    msg = m.generate_markov_text(20)
+    msg = m.generate_markov_text(random.randint(5,20))
     while len(msg) > 140:
-        msg = m.generate_markov_text(20)
+        msg = m.generate_markov_text(random.randint(5,20))
     api.PostUpdate(msg)
+
diff --git a/gistfile1.py b/gistfile1.py
@@ -0,0 +1,94 @@
+#!/usr/bin/python
+
+import random
+import oauth2 as oauth
+import sys
+import twitter
+
+class Markov(object):
+
+    def __init__(self):
+        self.cache = {}
+        self.words = fetch("profbriancox")
+        self.word_size = len(self.words)
+        self.database()
+
+    def triples(self):
+        """ Generates triples from the given data string. So if our string were
+        "What a lovely day", we'd generate (What, a, lovely) and then
+        (a, lovely, day).
+        """
+
+        if len(self.words) < 3:
+            return
+
+        for i in range(len(self.words) - 2):
+            yield (self.words[i], self.words[i+1], self.words[i+2])
+
+    def database(self):
+        for w1, w2, w3 in self.triples():
+            key = (w1, w2)
+            if key in self.cache:
+                self.cache[key].append(w3)
+            else:
+                self.cache[key] = [w3]
+
+    def generate_markov_text(self, size=20):
+        seed = random.randint(0, self.word_size-3)
+        seed_word, next_word = self.words[seed], self.words[seed+1]
+        w1, w2 = seed_word, next_word
+        gen_words = []
+        for i in xrange(size):
+            gen_words.append(w1)
+            w1, w2 = w2, random.choice(self.cache[(w1, w2)])
+        gen_words.append(w2)
+        return ' '.join(gen_words)
+
+ACCESS_TOKEN_KEY="accesstokenkey"
+ACCESS_TOKEN_SECRET="accesstokenkeysecret"
+CONSUMER_KEY="consumerkey"
+CONSUMER_SECRET="consumersecret"
+
+api = twitter.Api(
+    consumer_key=CONSUMER_KEY,
+    consumer_secret=CONSUMER_SECRET,
+    access_token_key=ACCESS_TOKEN_KEY,
+    access_token_secret=ACCESS_TOKEN_SECRET)
+
+######
+def fetch(user):
+    data = {}
+    api = twitter.Api()
+    max_id = None
+    total = 0
+    words = []
+    while True:
+        try:
+            statuses = api.GetUserTimeline(user, count=200, max_id=max_id)
+            newCount = ignCount = 0
+            for s in statuses:
+                if s.id in data:
+                    ignCount += 1
+                else:
+                    data[s.id] = s
+                    newCount += 1
+            total += newCount
+            print >>sys.stderr, "Fetched %d/%d/%d new/old/total." % (
+                newCount, ignCount, total)
+            if newCount == 0:
+                break
+            max_id = min([s.id for s in statuses]) - 1
+            for s in statuses:
+                words.extend(s.text.split())
+        except:
+            return words        
+    return words
+
+
+m = Markov()
+
+def tweet():
+    msg = m.generate_markov_text(20)
+    while len(msg) > 140:
+        msg = m.generate_markov_text(20)
+    api.PostUpdate(msg)