Class: Repos::StackOverflow

Inherits:
Object
  • Object
show all
Defined in:
lib/repocrawler/crawler.rb

Instance Method Summary collapse

Constructor Details

#initialize(gem_name) ⇒ StackOverflow

Returns a new instance of StackOverflow.



242
243
244
 
# File 'lib/repocrawler/crawler.rb', line 242

def initialize(gem_name)
  @STACKOVERFLOW_API = "https://api.stackexchange.com/2.2/search/advanced?order=desc&sort=creation&q=#{gem_name}&site=stackoverflow&key=#{ENV['stackoverflow_token']}"
end

Instance Method Details

#get_questions ⇒ Object

get questions from stackexchange



247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
 
# File 'lib/repocrawler/crawler.rb', line 247

def get_questions

  stop_words = []
  File.open(File.expand_path("../../public/stop_words.txt",  File.dirname(__FILE__)), "r") do |f|
    f.each_line do |line|
      stop_words << line.gsub(/\n/,"")
    end
  end

  questions = []
  fetch_questions = HTTParty.get(@STACKOVERFLOW_API)
  fetch_questions['items'].each do |q|
    #don't store stop words
    good_words = []
    q['title'].split(' ').map do |word|
      if !stop_words.include?(word.downcase)
        good_words << word
      end
    end

    questions << {
      'creation_date' => q['creation_date'],
      'title' => good_words,
      'views' => q['view_count']
    }
  end

  questions_word_count = Hash.new(0)
  questions.each do |question|
    question['title'].each do |word|
      questions_word_count[word] += 1
    end
  end

  questions_word_count = questions_word_count.sort_by { |word, freq| freq }.reverse!
  [questions, questions_word_count]
end