rubyscholar 0.0.5 → 0.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 68cc9491e42d735441cfd82e8e18c108a84ec05d
+  data.tar.gz: 5cc483aa8e259775a599b588cf658a219d5389f9
+SHA512:
+  metadata.gz: de91f4aa92392ce239fe9e093ca804f6725fa0ae05a1c6419ff49022cb3f12888961a8ea2f65c9fb35590b8b446620e5694385e2e35cf159b8beab632fc8e76d
+  data.tar.gz: face85b2e90f71e9d6c37e281a81a4e78011975e1ae820449fb2b995863d7195219ad4794fd7137a5420d2ae5a2f6b19433bc90a51f55883ea70a50d4d4b47f9

data/README.md

@@ -13,16 +13,6 @@ Some features:
 
 # How to use:
 
-### As a Ruby Gem:
-1. Install the gem using: `[sudo] gem install rubyscholar`
-2. Create and configure a `config.yml` file.
-      To create a `config.yml` file, run `$ rubyscholar init`
-      Edit the file, filling in your details.
-3. Run as `$ rubyscholar scrape --out file.html `.
-4. A `file.html` file is created containing your citations all formatted
-and ready to use.
-5. Done!
-
 ### As a ruby script:
 1. Configure "config.yml"
    If you want DOI retreival to work (including Altmetrics), you need to be 
@@ -35,8 +25,10 @@ and ready to use.
 
  * uses author list as visible on your main Google Scholar page. Sometimes this 
    means names are chopped in two or just a single author is missing. This could
-   be made smarter. 
- * flexible output
+   be made smarter (by following the link to get the full author list). 
+ * output format could be more flexible. (e.g. change order (eg title before authors), or change formatting (e.g. remove first initial)). Perhaps this could be done with by providing a regexp search/replace configuration option within each field.
+ * Ensure that a true email is entered. 
+ * right now only works from "user profile" pages. Not from "articles citing article" pages. 
  * flexible use of DOIs
 
 # Technologies

data/bin/rubyscholar

@@ -1,76 +1,50 @@
 #!/usr/bin/env ruby
 
-require 'optparse'
 require 'rubygems'
+require 'optparse'  # YW is this needed or redundant with commander?
 require 'commander/import'
-require 'rubyscholar'
 require 'yaml'
+require 'rubyscholar-main'
 
 
-program :name, 'rubysholar'
-program :version, '0.0.2'
+program :name, 'rubyscholar'
+program :version, Rubyscholar::VERSION
 program :description, 'Rubyscholar scrapes google scholar and formats it into a scholar.html file.'
 
 default_command :scrape
 
 command :scrape do |c|
   c.syntax = 'rubyscholar scrape [options]'
-  c.summary = '' 
-  c.description = "Scape google scholar for new publications"
+  c.description = "Scrape Google Scholar for new publications"
 
   c.option '--config [Config File]', 'Config file to use'
-  c.option '--out [Output File]', 'File to output the scrapes to'
-
-  c.action do |args, options|
-   options.default :config => "config.yml", :out  => "scholar.html"
-   configFile= "#{options.config}"
-   config    = YAML.load_file(configFile)
-   parsed    = Rubyscholar::Parser.new(config["url"], 
-                                config["email"])
-   formatter = Rubyscholar::Formatter.new(parsed, 
-                                        config["highlight"], 
-                                        config["pdfs"], 
-                                        config["altmetricDOIs"], 
-                                        config["minCitations"].to_i)
-
-   html = formatter.to_html
-       config["italicize"].each do |term|
-       html.gsub!( term , '<em>' + term + '</em>')
-   end
-   outFile="#{options.out}"
-   f= File.open(outFile,'w')
-   f.write html
-   f.close()
-end
-end
-
-command :init do |c|
-  c.syntax = 'rubyscholar init'
-  c.description = 'Creates a sample config.yml file for Scraping.'
+  c.option '--output [Output File]',  'HTML output for publication list'
+  
   c.action do |args, options|
-    say '# Intialising a configuration file for Rubyscholar.'
-    if File.exist?("config.yml")
-      abort("Initialisation aborted!") if ask("config.yml already exists. Do you want to overwrite?", ['y', 'n']) == 'n'
+    options.default \
+    :config => 'config.yaml',
+    :output  => 'publications.html'
+    #rest stays in this block bc we need to access options
+
+    raise IOError, "You must specify config file via --config\n" if options.config.nil?
+    config    = YAML.load_file(options.config) 
+    parsed    = Rubyscholar::Parser.new(config["url"], 
+                                        config["email"])
+    html = Rubyscholar::Formatter.new(parsed, 
+                                      config["highlight"], 
+                                      config["pdfs"], 
+                                      config["altmetricDOIs"], 
+                                      config["minCitations"].to_i
+                                      ).to_html
+    
+    config["italicize"].each do |term|
+      html.gsub!( term , '<em>' + term + '</em>')
     end
-    puts "# Creating config.yml."
-    open("config.yml", 'w') do |page|
-      page.puts "# Google Scholar page (you can choose how you sort it)"
-      page.puts "url: "
-      page.puts "\n\n# Name to highlight (withing \" and \")"
-      page.puts "highlight: "
-      page.puts "\n\n# Need an Email address that has been registered with CrossRef to obtain DOIs using their OpenURL service. "
-      page.puts "# e.g. the following should provide an XML file: "
-      page.puts "# http://www.crossref.org/openurl?redirect=false&pid=YOUR@EMAIL>COM&aulast=Wurm&atitle=Behavioral%20Genomics:%20A,%20Bee,%20C,%20G,%20T"
-      page.puts "email: your@email.com"
-      page.puts "\n\n# Show \"[Cited Nx]\" if N > the following number"
-      page.puts "minCitations: 5 "
-      page.puts "\n\n# Words to italicize (emphasize). These will have \"<em>\" around them. "
-      page.puts "italicize: "
-      page.puts "\n\n# DOIs of articles for which we should show altmetric.org badges. "
-      page.puts "altmetricDOIs:  "
-      page.puts "\n\n# Article titles for which we have urls to PDFs in \"name\" : \"url\" format"
-      page.puts "pdfs:"
-    end
-  end
+
+    STDERR << "Outputting to #{options.output}\n."
+    f = File.open(options.output,'w')
+    f.write html
+    f.close
+  end 
 end
 

data/example.config.yml

@@ -0,0 +1,51 @@
+# Google Scholar page (you can choose how you sort it)
+url: "http://scholar.google.com/citations?hl=en&user=k6y0EGsAAAAJ&sortby=pubdate&view_op=list_works&pagesize=100"
+
+#### Everything below this line is OPTIONAL ####
+
+# Name to highlight 
+highlight: "Y Wurm"
+
+
+# Need an Email address that has been registered with CrossRef to obtain DOIs 
+# using their OpenURL service. 
+# e.g. the following should provide an XML file: 
+# http://www.crossref.org/openurl?redirect=false&pid=YOUR@EMAIL>COM&aulast=Wurm&atitle=Behavioral%20Genomics:%20A,%20Bee,%20C,%20G,%20T
+email: your@email.com
+
+
+# Show "[Cited Nx]" if N > the following number
+minCitations: 5
+
+# Words to italicize (emphasize). These will have "<em>" around them. 
+italicize: 
+ - Solenopsis invicta
+ - Acromyrmex echinatior
+ - de novo
+
+# DOIs of articles for which we should show altmetric.org badges. 
+altmetricDOIs: 
+ - "10.1038/nature11832"
+ - "10.1101/gr.121392.111"
+ - "10.1073/pnas.1009690108"
+ - "10.1073/pnas.1104825108"
+
+# Article titles for which we have urls to PDFs
+pdfs:
+  "A Y-like social chromosome causes alternative colony organization in fire ants" : "/publications/wangwurm2013socialChromosome.pdf"
+  "Duplication and concerted evolution in a master sex determiner under balancing selection" : "/publications/procb2013.pdf"
+  "Comparative genomics of chemosensory protein genes reveals rapid evolution and positive selection in ant-specific duplicates" : "/publications/hdy2012122a.pdf"
+  "The Molecular Clockwork of the Fire Ant Solenopsis invicta" : "/publications/ingram2012-fireAntClockGenes.pdf"
+  "Epigenetics: The Making of Ant Castes" : "/publications/2012CurrBiolAntepigenetics.pdf"
+  "Visualization and quality assessment of de novo genome assemblies" : "/publications/Bioinformatics-2011-Riba-Grognuz-3425-6"
+  "The genomic impact of 100 million years of social evolution in seven ant species" : "/publications/TiG2011.pdf"
+  "Relaxed selection is a precursor to the evolution of phenotypic plasticity" : "/publications/hunt2011phenotypicPlasticity.pdf"
+  "The genome of the leaf-cutting ant Acromyrmex echinatior suggests key adaptations to advanced social life and fungus farming" : "/publications/nygaard2011-acromyrmex-genome.pdf"
+  "Behind the Scenes of an Ant Genome Project" : "/publications/wurm2011antGenomeBehindTheScenes.pdf"
+  "The genome of the fire ant Solenopsis invicta" : "/publications/wurm2011fireAntGenome.pdf"
+  "Odorant Binding Proteins of the Red Imported Fire Ant, Solenopsis invicta: An Example of the Problems Facing the Analysis of Widely Divergent Proteins" : "/publications/gotzek2011obps.pdf"
+  "Parasitoid Wasps: From Natural History to Genomic Studies" : "/publications/wurm2010wasps.pdf"
+  "Changes in reproductive roles are associated with changes in gene expression in fire ant queens" : "/publications/wurm2010fireAntQueenDealationExpression.pdf"
+  "Fourmidable: a database for ant genomics" : "/publications/wurm2009antDatabase.pdf"
+  "Behavioral Genomics: A, Bee, C, G, T" : "/publications/wurm2007bees.pdf"
+  "An annotated cDNA library and microarray for large-scale gene-expression studies in the ant Solenopsis invicta" : "/publications/wang2007fireAntMicroarrays.pdf"

data/lib/rubyscholar-main.rb

@@ -0,0 +1,138 @@
+require 'nokogiri'
+require 'open-uri'
+require 'rubyscholar-version'
+
+
+class String
+  def clean
+    # removes leading and trailing whitespace, commas
+    self.gsub!(/(^[\s,]+)|([\s,]+$)/, '')
+    return self
+  end
+end
+
+module Rubyscholar
+  class Paper < Struct.new(:title, :url, :authors, :journalName, :journalDetails, :year, :citationCount, :citingPapers, :doi)
+  end  
+  
+  class Parser
+    attr_accessor :parsedPapers, :crossRefEmail
+    
+    def initialize(url, crossRefEmail = "")
+      @parsedPapers  = []
+      @crossRefEmail = crossRefEmail # if nil doesn't return any DOI
+      parse(url)
+    end
+
+    def parse(url)
+      STDERR << "Will check #{url}.\n"
+      page = Nokogiri::HTML(open(url,
+                                 'User-Agent' => 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.121 Safari/535.2'), nil, 'utf-8')
+      papers = page.css(".gsc_a_tr")
+      STDERR << "Found #{papers.length} papers.\n"
+      papers.each do |paper|
+        title          = paper.css(".gsc_a_at").text rescue ''
+        title.gsub!(/\.$/, '')
+
+        googleUrl      = paper.children[0].children[0].attribute('href').text rescue ''
+        authors        = paper.children[0].children[1].text.clean rescue ''
+        authors.gsub!("...", "et al")
+
+        journal        = paper.children[0].children[2].text rescue '' 
+        journalName    = journal.split(/,|\d/).first.clean   rescue ''
+        journalDetails = journal.gsub(journalName, '').clean 
+        year           = journalDetails.match(/, \d+$/)[0]
+        journalDetails = journalDetails.gsub(year, '').clean
+        year           = year.clean
+
+        #citations
+        citeInfo      = paper.css('.gsc_a_ac')
+        citationCount = citeInfo.text
+        citationUrl   = citationCount.empty?  ? nil : citeInfo.attribute('href').to_s 
+
+        # get DOI: needs last name of first author, no funny chars
+        lastNameFirstAuthor = ((authors.split(',').first ).split(' ').last ).gsub(/[^A-Za-z\-]/, '')
+        doi                 = getDoi( lastNameFirstAuthor, title, @crossRefEmail)
+
+        @parsedPapers.push(Paper.new( title, googleUrl, authors, journalName, journalDetails, year, citationCount, citationUrl, doi))
+      end
+      STDERR << "Scraped #{parsedPapers.length} from Google Scholar.\n"
+    end
+
+    # Scholar doesn't provide DOI. 
+    # But if registered at crossref (its free), DOI can be retreived. 
+    def getDoi(lastNameFirstAuthor, title, crossRefEmail)
+      return '' if @crossRefEmail.nil?
+      sleep(1) # to reduce risk 
+      STDERR << "Getting DOI for paper by #{lastNameFirstAuthor}: #{title}.\n"
+      url = 'http://www.crossref.org/openurl?redirect=false' +  
+        '&pid='    + crossRefEmail + 
+        '&aulast=' + lastNameFirstAuthor   +
+        '&atitle=' + URI.escape(title)
+      crossRefXML = Nokogiri::XML(open(url)) 
+      crossRefXML.search("doi").children.first.content rescue ''
+    end
+  end
+  
+  class Formatter
+    attr_accessor :parser, :nameToHighlight, :pdfLinks, :altmetricDOIs
+    
+    def initialize(parser, nameToHighlight = nil, pdfLinks = {}, altmetricDOIs = [], minCitationCount = 1)
+      @parser          = parser
+      @nameToHighlight = nameToHighlight
+      @pdfLinks        = pdfLinks
+      @altmetricDOIs   = altmetricDOIs
+      @minCitations    = minCitationCount
+    end
+
+    def to_html
+      builder = Nokogiri::HTML::Builder.new do |doc|
+        doc.div( :class => "publication") {
+          doc.ol {	
+            @parser.parsedPapers.each_with_index do |paper, index|
+              doc.li( :value=> ( (@parser.parsedPapers).length - index).to_s)  {
+                doc.b paper[:title] + '.'
+                doc.text ' (' + paper[:year] + '). '
+                if paper[:authors].include?(@nameToHighlight)
+                  doc.text( paper[:authors].sub(Regexp.new(@nameToHighlight + '.*'), '') )
+                  doc.span( :class => "label") { doc.text @nameToHighlight }
+                  doc.text( paper[:authors].sub(Regexp.new('.*' + @nameToHighlight), '') )
+                else
+                  doc.text( paper[:authors]) + '.'
+                end
+                
+                doc.em   ' ' + paper[:journalName]
+                doc.text ' ' + paper[:journalDetails]
+                unless paper[ :doi].empty?
+                  doc.text(' ')
+                  doc.a( :href => URI.join("http://dx.doi.org/", paper[ :doi]))  { 
+                    doc.text "[DOI]" 
+                  } 
+                end
+                if @pdfLinks.keys.include?(paper[:title])
+                  doc.text(' ')
+                  doc.a( :href => @pdfLinks[paper[:title]])  { 
+                    doc.text "[PDF]"
+                  } 
+                end
+                if paper[ :citationCount].to_i > @minCitations
+                  doc.text(' ')
+                  doc.a( :href => paper[ :citingPapers], :title => "Citations") { 
+                    doc.span( :class => "badge badge-inverse") { doc.test("#{paper[ :citationCount]}x") }
+                  } 
+                end
+                if altmetricDOIs.include?( paper[ :doi])
+                  doc.text(' ')
+                  doc.span( :class                => 'altmetric-embed',
+                            :'data-badge-popover' => 'bottom',
+                            :'data-doi'           => paper[ :doi]        )
+                end
+              }
+            end
+          }
+        }
+      end
+      return builder.to_html
+    end
+  end
+end

data/lib/{rubyscholar/version.rb → rubyscholar-version.rb}

@@ -1,3 +1,3 @@
 module Rubyscholar
-  VERSION = "0.0.5"
+  VERSION = "0.2"
 end

data/lib/rubyscholar-version.rb~

@@ -0,0 +1,3 @@
+module Rubyscholar
+  VERSION = "0.0.1"
+end

data/lib/{rubyscholar.rb → rubyscholar.rb~}

@@ -1,32 +1,31 @@
-require "rubyscholar/version"
 require "nokogiri"
 require "open-uri"
 
-
+module Rubyscholar
  class String
   def clean
     # removes leading and trailing whitespace, commas
     self.gsub!(/(^[\s,]+)|([\s,]+$)/, '')
     return self
   end
- end
+end
 
-module Rubyscholar
-  class Paper < Struct.new(:title, :url, :authors, :journalName, :journalDetails, :year, :citationCount, :citingPapers, :doi)
-  end
 
+  class Paper < Struct.new(:title, :url, :authors, :journalName, :journalDetails, :year, :citationCount, :citingPapers, :doi)
+  end  
+  
   class Parser
     attr_accessor :parsedPapers, :crossRefEmail
-
+    
     def initialize(url, crossRefEmail = "")
       @parsedPapers  = []
-      @crossRefEmail = crossRefEmail # if nil doesn't retursn any DOI
+      @crossRefEmail = crossRefEmail # if nil doesn't return any DOI
       parse(url)
     end
 
     def parse(url)
       papers = Nokogiri::HTML(open(url)).css(".cit-table .item")
-      STDOUT << "Found #{papers.length} papers.\n"
+      STDERR << "Found #{papers.length} papers.\n"
       papers.each do |paper|
         paperDetails   = paper.css("#col-title")
         title          = paperDetails[0].children[0].content.clean
@@ -43,7 +42,7 @@ module Rubyscholar
         #citations
         citeInfo      = paper.css(".cit-dark-link")
         citationCount = citeInfo.text
-        citationUrl   = citationCount.empty?  ? nil : citeInfo.attribute('href').to_s
+        citationUrl   = citationCount.empty?  ? nil : citeInfo.attribute('href').to_s 
 
         # get DOI: needs last name of first author, no funny chars
         lastNameFirstAuthor = ((authors.split(',').first ).split(' ').last ).gsub(/[^A-Za-z\-]/, '')
@@ -51,27 +50,27 @@ module Rubyscholar
 
         @parsedPapers.push(Paper.new( title, googleUrl, authors, journalName, journalDetails, year, citationCount, citationUrl, doi))
       end
-      STDOUT << "Scraped #{parsedPapers.length} from Google Scholar.\n"
+      STDERR << "Scraped #{parsedPapers.length} from Google Scholar.\n"
     end
 
-    # Scholar doesn't provide DOI.
-    # But if registered at crossref (its free), DOI can be retreived.
+    # Scholar doesn't provide DOI. 
+    # But if registered at crossref (its free), DOI can be retreived. 
     def getDoi(lastNameFirstAuthor, title, crossRefEmail)
       return '' if @crossRefEmail.nil?
-      sleep(1) # to reduce risk
+      sleep(1) # to reduce risk 
       STDERR << "Getting DOI for paper by #{lastNameFirstAuthor}: #{title}.\n"
-      url = 'http://www.crossref.org/openurl?redirect=false' +
-        '&pid='    + crossRefEmail +
+      url = 'http://www.crossref.org/openurl?redirect=false' +  
+        '&pid='    + crossRefEmail + 
         '&aulast=' + lastNameFirstAuthor   +
         '&atitle=' + URI.escape(title)
-      crossRefXML = Nokogiri::XML(open(url))
+      crossRefXML = Nokogiri::XML(open(url)) 
       crossRefXML.search("doi").children.first.content rescue ''
     end
   end
-
+  
   class Formatter
     attr_accessor :parser, :nameToHighlight, :pdfLinks, :altmetricDOIs
-
+    
     def initialize(parser, nameToHighlight = nil, pdfLinks = {}, altmetricDOIs = [], minCitationCount = 1)
       @parser          = parser
       @nameToHighlight = nameToHighlight
@@ -81,14 +80,14 @@ module Rubyscholar
     end
 
     def to_html
-      ##@doc = Nokogiri::HTML::DocumentFragment.parse ""
+      ##@doc = Nokogiri::HTML::DocumentFragment.parse "" 
       builder = Nokogiri::HTML::Builder.new do |doc|
         doc.html {
           doc.body {
             @parser.parsedPapers.each_with_index { |paper, index|
               doc.div( :class => "publication") {
                 doc.p {
-                  doc.text ((@parser.parsedPapers).length - index).to_s + '. '
+                  doc.text ((@parser.parsedPapers).length - index).to_s + '. ' 
 
                   doc.b    paper[:title] + '.'
                   doc.text ' (' + paper[:year] + '). '
@@ -107,21 +106,21 @@ module Rubyscholar
                   doc.text paper[:journalDetails]
                   unless paper[ :doi].empty?
                     doc.text(' ')
-                    doc.a( :href => URI.join("http://dx.doi.org/", paper[ :doi]))  {
-                      doc.text "[DOI]"
-                    }
+                    doc.a( :href => URI.join("http://dx.doi.org/", paper[ :doi]))  { 
+                      doc.text "[DOI]" 
+                    } 
                   end
                   if @pdfLinks.keys.include?(paper[:title])
                     doc.text(' ')
-                    doc.a( :href => @pdfLinks[paper[:title]])  {
+                    doc.a( :href => @pdfLinks[paper[:title]])  { 
                       doc.text "[PDF]"
-                    }
+                    } 
                   end
                   if paper[ :citationCount].to_i > @minCitations
                     doc.text(' ')
-                    doc.a( :href => paper[ :citingPapers]) {
-                      doc.text("[Cited #{paper[ :citationCount]}x]")
-                    }
+                    doc.a( :href => paper[ :citingPapers]) { 
+                      doc.text("[Cited #{paper[ :citationCount]}x]") 
+                    } 
                   end
                   if altmetricDOIs.include?( paper[ :doi])
                     doc.text(' ')

data/rubyscholar.gemspec

@@ -1,23 +1,40 @@
-# -*- encoding: utf-8 -*-
-lib = File.expand_path('../lib', __FILE__)
-$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
-require 'rubyscholar/version'
+require './lib/rubyscholar-version.rb'
 
 Gem::Specification.new do |gem|
-  gem.name          = "rubyscholar"
+  gem.name          = 'rubyscholar'
   gem.version       = Rubyscholar::VERSION
-  gem.authors       = ["Yannick Wurm","Gaurav Koley"]
-  gem.email         = ["y.wurm@qmul.ac.uk","arkokoley@live.in"]
-  gem.description   = %q{Scrape Google Scholar}
-  gem.summary       = %q{Rubyscholar scrapes google scholar and formats it into a scholar.html file.}
-  gem.homepage      = "http://github.com/yannickwurm/rubyscholar"
-  gem.license       = "MIT"
-
-  gem.add_dependency "nokogiri", "~>1.6.0"
-  gem.add_dependency "commander", "~>4.1.5"
-
-  gem.files         = `git ls-files`.split($/)
-  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
-  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
-  gem.require_paths = ["lib"]
+  gem.authors       = ['Yannick Wurm','Gaurav Koley']
+  gem.email         = ['y.wurm@qmul.ac.uk','arkokoley@live.in']
+  gem.description   = %q{Scrape Google Scholar Profile page}
+  gem.summary       = %q{Rubyscholar scrapes one google scholar and formats it into a scholar.html file listing publications.}
+  gem.homepage      = 'http://yannick.poulet.org/'
+  gem.license       = 'MIT'
+
+
+  gem.add_runtime_dependency 'nokogiri',  '~> 1.6', '>= 1.6.0'
+  gem.add_runtime_dependency 'commander', '~> 4.1', '>= 4.1.5'
+
+  gem.files         = Dir['lib/**/*'] + Dir['views/**/*'] + Dir['public/**/*'] + Dir['tests/**/*']
+  gem.files         = gem.files + ['example.config.yml']
+  gem.files         = gem.files + ['LICENSE.txt', 'README.md']
+  gem.files         = gem.files + ['Gemfile',     'rubyscholar.gemspec']
+
+  gem.executables   = ['rubyscholar']
+  gem.require_paths = ['lib']
+
+  gem.post_install_message = <<INFO
+
+-----
+Thanks for installing rubyscholar. 
+If something isn't working, this may be due to Google's changing the format of Scholar pages
+(they do this regularly with no warning). 
+
+If you can have a shot at fixing it, please go ahead - pull requests are most welcome.
+
+All the best,  
+
+Yannick  -  http://yannick.poulet.org
+----
+
+INFO
 end

metadata

@@ -1,8 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rubyscholar
 version: !ruby/object:Gem::Version
-  version: 0.0.5
-  prerelease: 
+  version: '0.2'
 platform: ruby
 authors:
 - Yannick Wurm
@@ -10,84 +9,93 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-10-12 00:00:00.000000000 Z
+date: 2014-09-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.6.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.6.0
 - !ruby/object:Gem::Dependency
   name: commander
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.1'
+    - - ">="
       - !ruby/object:Gem::Version
         version: 4.1.5
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.1'
+    - - ">="
       - !ruby/object:Gem::Version
         version: 4.1.5
-description: Scrape Google Scholar
+description: Scrape Google Scholar Profile page
 email:
 - y.wurm@qmul.ac.uk
 - arkokoley@live.in
 executables:
 - rubyscholar
-- scrape.rb
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
-- CHANGELOG.md
 - Gemfile
 - LICENSE.txt
 - README.md
-- Rakefile
 - bin/rubyscholar
-- bin/scrape.rb
-- lib/rubyscholar.rb
-- lib/rubyscholar/version.rb
+- example.config.yml
+- lib/rubyscholar-main.rb
+- lib/rubyscholar-version.rb
+- lib/rubyscholar-version.rb~
+- lib/rubyscholar.rb~
 - rubyscholar.gemspec
-homepage: http://github.com/yannickwurm/rubyscholar
+homepage: http://yannick.poulet.org/
 licenses:
 - MIT
-post_install_message: 
+metadata: {}
+post_install_message: "\n-----\nThanks for installing rubyscholar. \nIf something
+  isn't working, this may be due to Google's changing the format of Scholar pages\n(they
+  do this regularly with no warning). \n\nIf you can have a shot at fixing it, please
+  go ahead - pull requests are most welcome.\n\nAll the best,  \n\nYannick  -  http://yannick.poulet.org\n----\n\n"
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.23
+rubygems_version: 2.2.2
 signing_key: 
-specification_version: 3
-summary: Rubyscholar scrapes google scholar and formats it into a scholar.html file.
+specification_version: 4
+summary: Rubyscholar scrapes one google scholar and formats it into a scholar.html
+  file listing publications.
 test_files: []

data/.gitignore

@@ -1,18 +0,0 @@
-*.gem
-*.rbc
-.bundle
-.config
-coverage
-InstalledFiles
-lib/bundler/man
-pkg
-rdoc
-spec/reports
-test/tmp
-test/version_tmp
-tmp
-
-# YARD artifacts
-.yardoc
-_yardoc
-doc/

data/CHANGELOG.md

@@ -1,6 +0,0 @@
-## Changelog
-
-version 0.0.4
-
-* Support for custom config files and output file in commands.
-* Command for creating a config.yml file using `rubyscholar init`. 

data/Rakefile

@@ -1 +0,0 @@
-require "bundler/gem_tasks"

data/bin/scrape.rb

@@ -1,20 +0,0 @@
-require_relative '../lib/rubyscholar'
-require 'yaml'
-
-    config    = YAML.load_file('config.yml')
-    parsed    = Rubyscholar::Parser.new(config["url"], 
-                                    config["email"])
-    formatter = Rubyscholar::Formatter.new(parsed, 
-                                       config["highlight"], 
-                                       config["pdfs"], 
-                                       config["altmetricDOIs"], 
-                                       config["minCitations"].to_i)
-
-    html = formatter.to_html
-        config["italicize"].each do |term|
-    html.gsub!( term , '<em>' + term + '</em>')
-    end
-
-    f= File.open('scholar.html','w')
-    f.write html
-    f.close