Advanced Search

Extract citations from Google Scholar

/ Published in: Ruby
Save to your folder(s)

Expand | Embed | Plain Text

Copy this code and paste it in your HTML 
  1. #!/usr/local/bin/ruby
  2. require 'net/http'
  3. require 'uri'
  4.  
  5.  
  6. def escape_title(s)
  7.     s = s.gsub(/(<\/a>)|(&nbsp;)/i,'')
  8.     s = s.gsub(/&hellip;/i,'...')
  9.     return s
  10. end
  11.  
  12. def get_citation_list(id, start=0, max_num=10)
  13.     str = '/scholar?start=%d&cites=%s'%[start,id]
  14.     enc_uri = URI.escape(str)
  15.     papers = []
  16.     Net::HTTP.start('scholar.google.com') do |http|
  17.         req = Net::HTTP::Get.new(enc_uri)
  18.         s = http.request(req).body
  19.         localizer = s.index('</b> citing <b>')
  20.         s = s[localizer+20,s.length()-localizer+20]
  21.         s = s.gsub(/(<b>)|(<\/b>)/i,'')
  22.         start = 0
  23.         1.upto(max_num){
  24.             pos2 = s.index('</h3>', start)
  25.             pos1 = s.rindex('>', pos2-5)
  26.             title =  s[pos1+1, pos2-pos1-1]
  27.             title = escape_title(title)
  28.             #puts title
  29.             papers << title
  30.             start = pos2 + 10
  31.         }
  32.     end
  33.     return papers
  34. end
  35.  
  36.  
  37. puts ' *** Googling paper "%s" *** '%ARGV[0]
  38. enc_uri = URI.escape('/scholar?q="'+ARGV[0]+'"&num=1')
  39.  
  40. Net::HTTP.start('scholar.google.com') do |http|
  41.     req = Net::HTTP::Get.new(enc_uri)
  42.     s = http.request(req).body
  43.     pos1 = s.index('Cited by ')
  44.     if pos1
  45.         pos2 = s.index('</a>', pos1+9)
  46.         citation_num = Integer(s[pos1+9, pos2-pos1-9])
  47.         pos3 = s.rindex('cites', pos1)
  48.         pos4 = s.index('amp', pos3)
  49.         citation_id = s[pos3+6, pos4-pos3-7]
  50.         puts " -- Google Scholar Citation ID: %s"%citation_id
  51.         puts " -- Cited by the following %d papers:"%citation_num
  52.         pages = citation_num / 10
  53.         papers = []
  54.         0.upto(pages-1){ |num|
  55.             papers += get_citation_list(citation_id, num*10)
  56.         }
  57.         num_in_last_page = citation_num - pages*10
  58.         papers += get_citation_list(citation_id, pages*10, num_in_last_page)
  59.         papers.each_with_index {|p,i|
  60.             puts "[#{i+1}] #{p}"
  61.         }
  62.     else
  63.         puts "no citation found!"
  64.     end
  65. end

Report this snippet


Comments

RSS Icon Subscribe to comments

You need to login to post a comment.