jcsalterego

#!/usr/bin/env python
#
# Generates non-unique word list from Twitter Search meeting certain
# criteria (as set in the configuration, below).
#
# EXAMPLE (word wrap inserted for ease of reading):
#
# $ python hashtag_wordle.py 
# Fetching http://search.twitter.com/search.json?q=%23spinuzzi-project&rpp=30&page=1...
# Fetching http://search.twitter.com/search.json?q=%23spinuzzi-project&rpp=30&page=2...

taboularasa

http://search.twitter.com/search.json?q=%40human_bot


{
    "results": [{
        "text": "@human_bot Are you feeling okay? Sounds like you've been smoking some crack with the way you've been talking lately.",
        "to_user_id": 5740619,
        "to_user": "human_bot",
        "from_user": "taboularasa",
        "id": 1306533155,

storborg

"""
walk through related tags on twitter.

start it with something like python twitterwalk.py sxsw
"""

import sys, re
from twitter import Twitter

if len(sys.argv) > 1:

agiliq

import random

class Markov(object):
	
	def __init__(self, open_file):
		self.cache = {}
		self.open_file = open_file
		self.words = self.file_to_words()
		self.word_size = len(self.words)
		self.database()

mnot

#!/usr/bin/env python

"""
RSS.py

Classes for working with RSS channels as arbitrary data structures.
Requires Python 2.2 or newer and PyXML 0.7.1 or newer.

  ChannelBase - Base class for RSS Channels.
  CollectionChannel - RSS Channel modeled as a URI-per-entry 

endolith

function [maxtab, mintab]=peakdet(v, delta, x)
%PEAKDET Detect peaks in a vector
%        [MAXTAB, MINTAB] = PEAKDET(V, DELTA) finds the local
%        maxima and minima ("peaks") in the vector V.
%        MAXTAB and MINTAB consists of two columns. Column 1
%        contains indices in V, and column 2 the found values.
%      
%        With [MAXTAB, MINTAB] = PEAKDET(V, DELTA, X) the indices
%        in MAXTAB and MINTAB are replaced with the corresponding
%        X-values.

criccomini

# print a user's tweets
import simplejson
import re
import urllib2
import string

me = urllib2.urlopen('http://twitter.com/statuses/user_timeline/peteskomoroch.json?count=200')

for tweet in simplejson.loads(me.read()):
	print tweet['text'].encode('utf-8')

criccomini

# poll a search term every 60 seconds and print tweets out
import time
import simplejson
import re
import urllib2
import urllib

last_id = False

while True:

code

import gaerun

from google.appengine.ext import db 
from google.appengine.api import urlfetch
from google.appengine.api import memcache
import simplejson
import logging

class User(db.Model):
    name = db.StringProperty()

NaiveBayesClassifier.py

import nltk
import random

class Categorizer(object):
    def __init__(self, categories):
        self.categories = categories

    def prep_seed(self, content):
        """Convert seed content into nltk.Text"""
        raw = nltk.clean_html(content)