책에 있는 예제입니다.
import twitter import os import sys import json twitter_search = twitter.Twitter(domain="search.twitter.com",secure=None) trends = twitter_search.trends() print [ trend['name'] for trend in trends['trends'] ] search_results=[] for page in range(1,2): search_results.append( twitter_search.search(q="SNL", rpp=100, page=page) ) # print json.dumps(search_results, sort_keys=True, indent=1) tweets = [ r['text'] for result in search_results for r in result['results'] ] #print tweets words = [] for t in tweets: words += [ w for w in t.split() ] print len(words) print len(set(words)) print 1.0*len(set(words))/len(words) print 1.0*sum([ len(t.split()) for t in tweets ])/len(tweets) import nltk freq_dist = nltk.FreqDist(words) import re rt_patterns = re.compile(r"(RT|via)((?:bW*@w+)+)", re.IGNORECASE) for t in tweets: print rt_patterns.findall(t)