編寫Ruby腳本來(lái)對(duì)Twitter用戶的數(shù)據(jù)進(jìn)行深度挖掘

$ sudo apt-get install ruby1.9.1-full 

$ sudo gem install twitter 

$ irb 
irb(main):001:0> require "rubygems" 
=> true 
irb(main):002:0> require "twitter" 
=> true 
 
irb(main):003:0> puts Twitter.user_timeline("developerworks").first.text 
dW Twitter is saving #IBM over $600K per month: will #Google+ add to that?> 
http://t.co/HiRwir7 #Tech #webdesign #Socialmedia #webapp #app 
=> nil 
 
irb(main):004:0> puts Twitter.user("MTimJones").location 
Colorado, USA 
=> nil 
 
irb(main):005:0> search = Twitter::Search.new 
=> #Twitter::Search:0xb7437e04 @oauth_token_secret=nil, 
@endpoint="https://api.twitter.com/1/", 
@user_agent="Twitter Ruby Gem 1.6.0", 
@oauth_token=nil, @consumer_secret=nil, 
@search_endpoint="https://search.twitter.com/", 
@query={:tude=>[], :q=>[]}, @cache=nil, @gateway=nil, @consumer_key=nil, 
@proxy=nil, @format=:json, @adapter=:net_http 
irb(main):006:0> search.containing("why").to("LulzSec"). 
result_type("recent").each do |r| puts r.text end 
@LulzSec why not stop posting bleep> and get a full time job! MYSQLi isn't 
hacking you bleep>. 
... 
irb(main):007:0> 

irb(main):007:0> puts Twitter.user("MTimJones") 
#Hashie::Mash 
contributors_enabled=false 
created_at="Wed Oct 08 20:40:53 +0000 2008" 
default_profile=false default_profile_image=false 
description="Platform Architect and author (Linux, Embedded, Networking, AI)." 
favourites_count=1 
follow_request_sent=nil 
followers_count=148 
following=nil 
friends_count=96 
geo_enabled=true 
id=16655901 id_str="16655901" 
is_translator=false 
lang="en" 
listed_count=10 
location="Colorado, USA" 
name="M. Tim Jones" 
notifications=nil 
profile_background_color="1A1B1F" 
profile_background_image_url="..." 
profile_background_image_url_https="..." 
profile_background_tile=false 
profile_image_url="http://a0.twimg.com/profile_images/851508584/bio_mtjones_normal.JPG" 
profile_image_url_https="..." 
profile_link_color="2FC2EF" 
profile_sidebar_border_color="181A1E" profile_sidebar_fill_color="252429" 
profile_text_color="666666" 
profile_use_background_image=true 
protected=false 
screen_name="MTimJones" 
show_all_inline_media=false 
status=#Hashie::Mash 
contributors=nil coordinates=nil 
created_at="Sat Jul 02 02:03:24 +0000 2011" 
favorited=false 
geo=nil 
id=86978247602094080 id_str="86978247602094080" 
in_reply_to_screen_name="AnonymousIRC" 
in_reply_to_status_id=nil in_reply_to_status_id_str=nil 
in_reply_to_user_id=225663702 in_reply_to_user_id_str="225663702" 
place=#Hashie::Mash 
attributes=#Hashie::Mash> 
bounding_box=#Hashie::Mash 
coordinates=[[[-105.178387, 40.12596], 
[-105.034397, 40.12596], 
[-105.034397, 40.203495], 
[-105.178387, 40.203495]]] 
type="Polygon" 
> 
country="United States" country_code="US" 
full_name="Longmont, CO" 
id="2736a5db074e8201" 
name="Longmont" place_type="city" 
url="http://api.twitter.com/1/geo/id/2736a5db074e8201.json" 
> 
retweet_count=0 
retweeted=false 
source="web" 
text="@AnonymousIRC @anonymouSabu @LulzSec @atopiary @Anonakomis Practical reading 
for future reference... LULZ \"Prison 101\" http://t.co/sf8jIH9" truncated=false 
> 
statuses_count=79 
time_zone="Mountain Time (US  Canada)" 
url="http://www.mtjones.com" 
utc_offset=-25200 
verified=false 
> 
=> nil 
irb(main):008:0> 

#!/usr/bin/env ruby 
require "rubygems" 
require "twitter" 
 
screen_name = String.new ARGV[0] 
 
a_user = Twitter.user(screen_name) 
 
if a_user.protected != true 
 
puts "Username : " + a_user.screen_name.to_s 
puts "Name : " + a_user.name 
puts "Id : " + a_user.id_str 
puts "Location : " + a_user.location 
puts "User since : " + a_user.created_at.to_s 
puts "Bio : " + a_user.description.to_s 
puts "Followers : " + a_user.followers_count.to_s 
puts "Friends : " + a_user.friends_count.to_s 
puts "Listed Cnt : " + a_user.listed_count.to_s 
puts "Tweet Cnt : " + a_user.statuses_count.to_s 
puts "Geocoded : " + a_user.geo_enabled.to_s 
puts "Language : " + a_user.lang 
puts "URL : " + a_user.url.to_s 
puts "Time Zone : " + a_user.time_zone 
puts "Verified : " + a_user.verified.to_s 
puts 
 
tweet = Twitter.user_timeline(screen_name).first 
 
puts "Tweet time : " + tweet.created_at 
puts "Tweet ID : " + tweet.id.to_s 
puts "Tweet text : " + tweet.text 
 
end 

$ ./user.rb developerworks 
Username : developerworks 
Name : developerworks 
Id : 16362921 
Location : 
User since : Fri Sep 19 13:10:39 +0000 2008 
Bio : IBM's premier Web site for Java, Android, Linux, Open Source, PHP, Social, 
Cloud Computing, Google, jQuery, and Web developer educational resources 
Followers : 48439 
Friends : 46299 
Listed Cnt : 3801 
Tweet Cnt : 9831 
Geocoded : false 
Language : en 
URL : http://bit.ly/EQ7te 
Time Zone : Pacific Time (US  Canada) 
Verified : false 
 
Tweet time : Sun Jul 17 01:04:46 +0000 2011 
Tweet ID : 92399309022167040 
Tweet text : dW Twitter is saving #IBM over $600K per month: will #Google+ add to that? > 
http://t.co/HiRwir7 #Tech #webdesign #Socialmedia #webapp #app 

#!/usr/bin/env ruby 
require "rubygems" 
require "twitter" 
 
name = String.new ARGV[0] 
 
user = Hash.new 
 
# Iterate friends, hash their followers 
Twitter.friends(name).users.each do |f| 
 
# Only iterate if we can see their followers 
if (f.protected.to_s != "true") 
user[f.screen_name.to_s] = f.followers_count 
end 
 
end 
 
user.sort_by {|k,v| -v}.each { |user, count| puts "#{user}, #{count}" } 

$ ./friends.rb MTimJones 
RWW, 1096862 
PlayStation, 1026634 
HarvardBiz, 541139 
tedtalks, 526886 
lifehacker, 146162 
wandfc, 121683 
AnonymousIRC, 117896 
iTunesPodcasts, 82581 
adultswim, 76188 
forrester, 72945 
googleresearch, 66318 
Gartner_inc, 57468 
developerworks, 48518 

$ gem install gchartrb 

#!/usr/bin/env ruby 
require "rubygems" 
require "twitter" 
require 'google_chart' 
 
screen_name = String.new ARGV[0] 
 
tweetlocation = Hash.new 
timezones = 0.0 
 
# Authenticate 
Twitter.configure do |config| 
config.consumer_key = '' 
config.consumer_secret = '' 
config.oauth_token = ' 
config.oauth_token_secret = '' 
end 
 
# Iterate followers, hash their location 
followers = Twitter.followers.users.each do |f| 
 
loc = f.time_zone.to_s 
 
if (loc.length > 0) 
 
if tweetlocation.has_key?(loc) 
tweetlocation[loc] = tweetlocation[loc] + 1 
else 
tweetlocation[loc] = 1 
end 
 
timezones = timezones + 1.0 
 
end 
 
end 
 
# Create a pie chart 
GoogleChart::PieChart.new('650x350', "Time Zones", false ) do |pc| 
 
tweetlocation.each do |loc,count| 
pc.data loc.to_s.delete(""), (count/timezones*100).round 
end 
 
puts pc.to_url 
 
end 

$ ./followers-location.rb MTimJones 
http://chart.apis.google.com/chart?chl=Seoul|Santiago|Paris|Mountain+Time+(US++Canada)| 
Madrid|Central+Time+(US++Canada)|Warsaw|Kolkata|London|Pacific+Time+(US++Canada)| 
New+Delhi|Pretoria|Quito|Dublin|Moscow|Istanbul|Taipei|Casablanca|Hawaii|Mumbai| 
International+Date+Line+West|Tokyo|Ulaan+Bataar|Vienna|Osaka|Alaska|Chennai|Bern| 
Brasilia|Eastern+Time+(US++Canada)|Rome|Perth|La+Paz 
chs=650x350chtt=Time+Zoneschd=s:KDDyKcKDOcKDKDDDDDKDDKDDDDOKK9DDDcht=p 
$ 

#!/usr/bin/env ruby 
require "rubygems" 
require "twitter" 
require "google_chart" 
 
screen_name = String.new ARGV[0] 
 
dayhash = Hash.new 
 
timeline = Twitter.user_timeline(screen_name, :count => 200 ) 
timeline.each do |t| 
 
tweetday = t.created_at.to_s[0..2] 
 
if dayhash.has_key?(tweetday) 
dayhash[tweetday] = dayhash[tweetday] + 1 
else 
dayhash[tweetday] = 1 
end 
 
end 
 
GoogleChart::BarChart.new('300x200', screen_name, :vertical, false) do |bc| 
bc.data "Sunday", [dayhash["Sun"]], '00000f' 
bc.data "Monday", [dayhash["Mon"]], '0000ff' 
bc.data "Tuesday", [dayhash["Tue"]], '00ff00' 
bc.data "Wednesday", [dayhash["Wed"]], '00ffff' 
bc.data "Thursday", [dayhash["Thu"]], 'ff0000' 
bc.data "Friday", [dayhash["Fri"]], 'ff00ff' 
bc.data "Saturday", [dayhash["Sat"]], 'ffff00' 
puts bc.to_url 
end 

#!/usr/bin/env ruby 
require "rubygems" 
require "twitter" 
require 'google_chart' 
 
screen_name = String.new ARGV[0] 
 
tweetsource = Hash.new 
 
timeline = Twitter.user_timeline(screen_name, :count => 200 ) 
timeline.each do |t| 
 
if (t.source.rindex('blackberry')) then 
src = 'Blackberry' 
elsif (t.source.rindex('snaptu')) then 
src = 'Snaptu' 
elsif (t.source.rindex('tweetmeme')) then 
src = 'Tweetmeme' 
elsif (t.source.rindex('android')) then 
src = 'Android' 
elsif (t.source.rindex('LinkedIn')) then 
src = 'LinkedIn' 
elsif (t.source.rindex('twitterfeed')) then 
src = 'Twitterfeed' 
elsif (t.source.rindex('twitter.com')) then 
src = 'Twitter.com' 
else 
src = t.source 
end 
 
if tweetsource.has_key?(src) 
tweetsource[src] = tweetsource[src] + 1 
else 
tweetsource[src] = 1 
end 
 
end 
 
GoogleChart::PieChart.new('320x200', "Tweet Source", false) do |pc| 
 
tweetsource.each do|source,count| 
pc.data source.to_s, count 
end 
 
puts "\nPie Chart" 
puts pc.to_url 
end 

$ sudo apt-get install graphviz 

#!/usr/bin/env ruby 
require "rubygems" 
require "twitter" 
require 'google_chart' 
 
screen_name = String.new ARGV[0] 
 
tweetlocation = Hash.new 
 
# Authenticate 
Twitter.configure do |config| 
config.consumer_key = '' 
config.consumer_secret = '' 
config.oauth_token = '' 
config.oauth_token_secret = '' 
end 
 
my_file = File.new("graph.dot", "w") 
 
my_file.puts "graph followers {" 
my_file.puts " node [ fontname=Arial, fontsize=6 ];" 
 
# Iterate followers, hash their location 
followers = Twitter.followers(screen_name, :count=>10 ).users.each do |f| 
 
# Only iterate if we can see their followers 
if (f.protected.to_s != "true") 
 
my_file.puts " \"" + screen_name + "\" -- \"" + f.screen_name.to_s + "\"" 
 
followers2 = Twitter.followers(f.screen_name, :count =>10 ).users.each do |f2| 
 
my_file.puts " \"" + f.screen_name.to_s + "\" -- \"" + 
f2.screen_name.to_s + "\"" 
 
end 
 
end 
 
end 
 
my_file.puts "}" 

$ ./followers-graph.rb MTimJones 
$ circo graph.dot -Tpng -o graph.png 

#!/usr/bin/env ruby 
require "rubygems" 
require "twitter" 
 
Twitter.configure do |config| 
config.consumer_key = 'consumer_key> 
config.consumer_secret = 'consumer_secret> 
config.oauth_token = 'oauth_token> 
config.oauth_token_secret = 'token_secret> 
end 
 
screen_name = String.new ARGV[0] 
 
a_user = Twitter.user(screen_name) 
 
if a_user.geo_enabled == true 
 
long = a_user.status.place.bounding_box.coordinates[0][0][0]; 
lat = a_user.status.place.bounding_box.coordinates[0][0][1]; 
 
my_file = File.new("test.html", "w") 
 
my_file.puts "!DOCTYPE html> 
my_file.puts "html> head> 
my_file.puts "meta name=\"viewport\" content=\"initial-scale=1.0, user-scalable=no\"/>" 
my_file.puts "style type=\"text/css\">" 
my_file.puts "html { height: 100% }" 
my_file.puts "body { height: 100%; margin: 0px; padding: 0px }" 
my_file.puts "#map_canvas { height: 100% }" 
my_file.puts "/style>" 
my_file.puts " script type=\"text/javascript\"" 
my_file.puts "src=\"http://maps.google.com/maps/api/js?sensor=false\">" 
my_file.puts "/script>" 
my_file.puts "script type=\"text/javascript\">" 
my_file.puts "function initialize() {" 
my_file.puts "var latlng = new google.maps.LatLng(" + lat.to_s + ", " + long.to_s + ");" 
my_file.puts "var myOptions = {" 
my_file.puts "zoom: 12," 
my_file.puts "center: latlng," 
my_file.puts "mapTypeId: google.maps.MapTypeId.HYBRID" 
my_file.puts "};" 
my_file.puts "var map = new google.maps.Map(document.getElementById(\"map_canvas\")," 
my_file.puts "myOptions);" 
my_file.puts "}" 
my_file.puts "/script>" 
my_file.puts "/head>" 
my_file.puts "body onload=\"initialize()\">" 
my_file.puts "div id=\"map_canvas\" style=\"width:100%; height:100%\">/div>" 
my_file.puts "/body>" 
my_file.puts "/html>" 
 
else 
 
puts "no geolocation data available." 
 
end 

$ ./where-am-i.rb MTimJones 

$ firefox test.html 

#!/usr/bin/env ruby 
require "rubygems" 
require "twitter" 
 
Twitter.configure do |config| 
config.consumer_key = '' 
config.consumer_secret = '' 
config.oauth_token = '' 
config.oauth_token_secret = '' 
end 
 
screen_name = String.new ARGV[0] 
 
a_user = Twitter.user(screen_name) 
 
if a_user.geo_enabled == true 
 
long = a_user.status.place.bounding_box.coordinates[0][0][0] 
lat = a_user.status.place.bounding_box.coordinates[0][0][1] 
 
Array tweets = Twitter::Search.new.geocode(lat, long, "5mi").fetch 
 
tweets.each do |t| 
 
puts t.from_user + " | " + t.text 
 
end 
 
end 

$ ./tweets-local.rb MTimJones 
Breesesummer | @DaltonOls did he answer u 
LongmontRadMon | 60 CPM, 0.4872 uSv/h, 0.6368 uSv/h, 2 time(s) over natural radiation 
graelston | on every street there is a memory; a time and place we can never be again. 
Breesesummer | #I'minafight with @DaltonOls to see who will marry @TheCodySimpson I will 
marry him!!! :/ 
_JennieJune_ | ok I'm done, goodnight everyone! 
Breesesummer | @DaltonOls same 
_JennieJune_ | @sylquejr sleep well! 
Breesesummer | @DaltonOls ok let's see what he says 
LongmontRadMon | 90 CPM, 0.7308 uSv/h, 0.7864 uSv/h, 2 time(s) over natural radiation 
Breesesummer | @TheCodySimpson would u marry me or @DaltonOls 
natcapsolutions | RT hlovins: The scientific rebuttal to the silly Forbes release this 
morning: Misdiagnosis of Surface Temperatu... http://bit.ly/nRpLJl 
$