Added support for google scholar citations (#2193)

Closes #1809, but there are caveats:
1 - it only works at build time, which means it won't update the numbers
unless you build your site again
2 - Google might block the request if it receives lots of it, failing
the whole process.

This is how it looks like when it can fetch the information:

![Screenshot from 2024-02-13
00-37-52](https://github.com/alshedivat/al-folio/assets/31376482/646d1f3c-1294-491b-bc13-9013e38918b4)

And this when it fails:


![image](https://github.com/alshedivat/al-folio/assets/31376482/516eefff-d394-44ad-8702-8982233f8c4f)

Signed-off-by: George Araujo <[email protected]>

Author: george-gca

_bibliography/papers.bib

@@ -44,6 +44,7 @@ @article{PhysRev.47.777
   pdf={example_pdf.pdf},
   altmetric={248277},
   dimensions={true},
+  google_scholar_id={qyhmnyLat1gC},
   selected={true}
 }
 

_config.yml

@@ -73,7 +73,7 @@ x_username: # your X handle
 mastodon_username: # your mastodon instance+username in the format instance.tld/@username
 linkedin_username: # your LinkedIn user name
 telegram_username: # your Telegram user name
-scholar_userid: # your Google Scholar ID
+scholar_userid: qc6CJjYAAAAJ # your Google Scholar ID
 semanticscholar_id: # your Semantic Scholar ID
 whatsapp_number: # your WhatsApp number (full phone number in international format. Omit any zeroes, brackets, or dashes when adding the phone number in international format.)
 orcid_id: # your ORCID ID
@@ -311,6 +311,7 @@ scholar:
 enable_publication_badges:
   altmetric: true # Altmetric badge (https://www.altmetric.com/products/altmetric-badges/)
   dimensions: true # Dimensions badge (https://badge.dimensions.ai/)
+  google_scholar: true # Google Scholar badge (https://scholar.google.com/intl/en/scholar/citations.html)
 
 # Filter out certain bibtex entry keywords used internally from the bib output
 filtered_bibtex_keywords:

_layouts/bib.liquid

@@ -211,7 +211,8 @@
     {% if site.enable_publication_badges %}
       {% assign entry_has_altmetric_badge = entry.altmetric or entry.doi or  entry.eprint or entry.pmid or entry.isbn %}
       {% assign entry_has_dimensions_badge = entry.dimensions or entry.doi or entry.pmid %}
-      {% if entry_has_altmetric_badge or entry_has_dimensions_badge %}
+      {% assign entry_has_google_scholar_badge = entry.google_scholar_id %}
+      {% if entry_has_altmetric_badge or entry_has_dimensions_badge or entry_has_google_scholar_badge %}
         <div class="badges">
           {% if site.enable_publication_badges.altmetric and entry_has_altmetric_badge %}
             <span
@@ -249,6 +250,11 @@
               style="margin-bottom: 3px;"
             ></span>
           {% endif %}
+          {% if site.enable_publication_badges.google_scholar and entry_has_google_scholar_badge %}
+            <a href="https://scholar.google.com/citations?view_op=view_citation&hl=en&user={{ site.scholar_userid }}&citation_for_view={{ site.scholar_userid }}:{{ entry.google_scholar_id }}">
+              <img src="https://img.shields.io/badge/scholar-{% google_scholar_citations site.scholar_userid entry.google_scholar_id %}-4285F4?logo=googlescholar&labelColor=beige">
+            </a>
+          {% endif %}
         </div>
       {% endif %}
     {% endif %}

_plugins/google-scholar-citations.rb

@@ -0,0 +1,78 @@
+require "active_support/all"
+require 'nokogiri'
+require 'open-uri'
+
+module Helpers
+    extend ActiveSupport::NumberHelper
+end
+
+module Jekyll
+    class GoogleScholarCitationsTag < Liquid::Tag
+        Citations = { }
+
+        def initialize(tag_name, params, tokens)
+            super
+            splitted = params.split(" ").map(&:strip)
+            @scholar_id = splitted[0]
+            @article_id = splitted[1]
+        end
+
+        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 (\d+[,\d]*)/)
+
+                    if matches
+                        citation_count = matches[1].to_i
+                    end
+
+                elsif !og_description_meta.empty?
+                    cited_by_text = og_description_meta[0]['content']
+                    matches = cited_by_text.match(/Cited by (\d+[,\d]*)/)
+
+                    if matches
+                        citation_count = matches[1].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}: #{e.class} - #{e.message}"
+            end
+
+
+            GoogleScholarCitationsTag::Citations[article_id] = citation_count
+            return "#{citation_count}"
+        end
+    end
+end
+
+Liquid::Template.register_tag('google_scholar_citations', Jekyll::GoogleScholarCitationsTag)