pacnpal/iron_ebooks
1
0
Fork 0
mirror of https://github.com/thewesker/iron_ebooks.git synced 2025-12-22 21:31:12 -05:00
Code Issues Packages Projects Releases Wiki Activity

Some tweaks to the algorithm

Browse Source
This commit is contained in:
Jacob Harris
2013-07-11 07:49:21 -04:00
parent ca71d20d80
commit ff3472390c
1 changed files with 13 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
ebook.rb
View File

@@ -15,20 +15,24 @@ unless params.key?("tweet")
params["tweet"] = true params["tweet"] = true
end end
rand_key = rand($rand_limit)
# randomly running only about 1 in $rand_limit times # randomly running only about 1 in $rand_limit times
unless rand($rand_limit) == 0 || params["force"] unless rand_key == 0 || params["force"]
puts "Not running this time" puts "Not running this time (key: #{rand_key})"
else else
# Fetch a thousand tweets # Fetch a thousand tweets
begin begin
user_tweets = Twitter.user_timeline($source_account, :count => 200, :trim_user => true, :exclude_replies => false, :include_replies => true) user_tweets = Twitter.user_timeline($source_account, :count => 200, :trim_user => true, :exclude_replies => true, :include_rts => false)
max_id = user_tweets.last.id max_id = user_tweets.last.id
source_tweets += user_tweets.reject {|t| t.text =~ /(http:\/\/)|(\bRT\b)|(\bMT\b)|@/ } source_tweets += user_tweets.reject {|t| t.text =~ /(https?:\/\/)/ }.map {|t| t.text.gsub(/\b(RT|MT) .+/, '') }
25.times do # Twitter only returns up to 3200 of a user timeline, includes retweets.
user_tweets = Twitter.user_timeline($source_account, :count => 200, :trim_user => true, :max_id => max_id - 1, :exclude_replies => false, :include_replies => true) 17.times do
user_tweets = Twitter.user_timeline($source_account, :count => 200, :trim_user => true, :max_id => max_id - 1, :exclude_replies => true, :include_rts => false)
puts "MAX_ID #{max_id} TWEETS: #{user_tweets.length}"
max_id = user_tweets.last.id max_id = user_tweets.last.id
source_tweets += user_tweets.reject {|t| t.text =~ /(http:\/\/)|(\bRT\b)|(\bMT\b)|@/ } source_tweets += user_tweets.reject {|t| t.text =~ /(https?:\/\/)/ }.map {|t| t.text.gsub(/\b(RT|MT) .+/, '') }
end end
rescue rescue
end end
@@ -38,7 +42,7 @@ else
markov = MarkovChainer.new(2) markov = MarkovChainer.new(2)
source_tweets.each do |twt| source_tweets.each do |twt|
text = twt.text text = twt
text.gsub!(/\#[\w\d]+/, '') # remove hashtags text.gsub!(/\#[\w\d]+/, '') # remove hashtags
markov.add_text(text) markov.add_text(text)
end end
@@ -47,7 +51,7 @@ else
5.times do 5.times do
tweet = markov.generate_sentence tweet = markov.generate_sentence
break if !tweet.nil? && tweet.length < 140 && !source_tweets.any? {|t| t.text != tweet } break if !tweet.nil? && tweet.length < 110 && !source_tweets.any? {|t| t =~ /#{tweet}/ }
end end
if params["tweet"] if params["tweet"]