Class: Jekyll::GoogleScholarCitationsTag

Inherits:
Liquid::Tag
  • Object
show all
Defined in:
lib/al_citations/google_scholar.rb

Constant Summary collapse

Citations = 
{ }
CITED_BY_REGEX = 
/Cited by (\d+[,\d]*)/

Instance Method Summary collapse

Constructor Details

#initialize(tag_name, params, tokens) ⇒ GoogleScholarCitationsTag

Returns a new instance of GoogleScholarCitationsTag.



10
11
12
13
14
15
16
17
18
19
20
21
22
23
 
# File 'lib/al_citations/google_scholar.rb', line 10

def initialize(tag_name, params, tokens)
  super
  splitted = params.split(" ").map(&:strip)
  @scholar_id = splitted[0]
  @article_id = splitted[1]

  if @scholar_id.nil? || @scholar_id.empty?
    puts "Invalid scholar_id provided"
  end

  if @article_id.nil? || @article_id.empty?
    puts "Invalid article_id provided"
  end
end

Instance Method Details

#render(context) ⇒ Object 



25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
 
# File 'lib/al_citations/google_scholar.rb', line 25

def render(context)
  article_id = context[@article_id.strip]
  scholar_id = context[@scholar_id.strip]
  article_url = "https://scholar.google.com/citations?view_op=view_citation&hl=en&user=#{scholar_id}&citation_for_view=#{scholar_id}:#{article_id}"

  begin
      # If the citation count has already been fetched, return it
      if GoogleScholarCitationsTag::Citations[article_id]
        return GoogleScholarCitationsTag::Citations[article_id]
      end

      # Sleep for a random amount of time to avoid being blocked
      sleep(rand(1.5..3.5))

      # Fetch the article page
      doc = Nokogiri::HTML(URI.open(article_url, "User-Agent" => "Ruby/#{RUBY_VERSION}"))

      # Attempt to extract the "Cited by n" string from the meta tags
      citation_count = 0

      # Look for meta tags with "name" attribute set to "description"
      description_meta = doc.css('meta[name="description"]')
      og_description_meta = doc.css('meta[property="og:description"]')

      if !description_meta.empty?
        cited_by_text = description_meta[0]['content']
        matches = cited_by_text.match(CITED_BY_REGEX)

        if matches
          citation_count = matches[1].sub(",", "").to_i
        end

      elsif !og_description_meta.empty?
        cited_by_text = og_description_meta[0]['content']
        matches = cited_by_text.match(CITED_BY_REGEX)

        if matches
          citation_count = matches[1].sub(",", "").to_i
        end
      end

    citation_count = Helpers.number_to_human(citation_count, :format => '%n%u', :precision => 2, :units => { :thousand => 'K', :million => 'M', :billion => 'B' })

  rescue Exception => e
    # Handle any errors that may occur during fetching
    citation_count = "N/A"

    # Print the error message including the exception class and message
    puts "Error fetching citation count for #{article_id} in #{article_url}: #{e.class} - #{e.message}"
  end

  GoogleScholarCitationsTag::Citations[article_id] = citation_count
  return "#{citation_count}"
end