gentle-scholar 1.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: a376293e4fa94ea7d9e02be8b1c481a82d662384
+  data.tar.gz: 1c0739ae9eb14ed3e15fcb45f86d47b0d85330a4
+SHA512:
+  metadata.gz: 05a400e3f02cec668146bf5ae377631478586883f779a4026a2ed61a6bb18008875a402279c0fa9eaf02d78b77a9817d7b6d6aea3581125c98284f33deb778b2
+  data.tar.gz: 6773cb9144c86bee17eff3b3e48b23bf8a4f6bf0da11cd6907e836b49cb807c04db4a1d41b4723c47005e620bc035d4e22328034eb79d728f609edd9e59f7f7c

data/lib/publication.rb

@@ -0,0 +1,78 @@
+# Author::       Soumya Ray (mailto: soumya.ray@gmail.com)
+# License::      MIT
+
+require 'typhoeus'
+require 'nokogiri'
+require 'date'
+
+# This class loads a single publication from Google scholar and returns
+# all its attributes, including dynamic attributes like number of citations
+class GScholarPub
+  GSCHOLAR_HOST_URL = 'http://scholar.google.com'
+  GSCHOLAR_CIT_URL =
+      'http://scholar.google.com/citations?view_op=view_citation&hl=en'
+
+  attr_reader :title, :cites, :cites_url, :chart_url, :article_url
+  attr_reader :authors, :date, :journal, :volume, :issue, :pages, :publisher
+  attr_reader :description, :gscholar_url
+  # TODO: @doc only for development, testing modes
+  attr_reader :doc
+
+  SCAN_STR = {
+    gscholar_url:
+      "//div[contains(@class,'g-section cit-dgb')]/div/table/tr/td/a",
+    cites: "//div[contains(@id,'scholar_sec')]/div/a",
+    title: '//div[@id="title"]/a',
+    article_url: '//div[@id="title"]/a',
+    chart_url: '//div[contains(@class,"cit-dd")]/img'
+  }
+
+  TABLE_ATTR = {
+    authors: 'Authors',
+    date: 'Publication date',
+    journal: 'Journal name',
+    volume: 'Volume',
+    issue: 'Issue',
+    pages: 'Pages',
+    publisher: 'Publisher',
+    description: 'Description'
+  }
+
+  def initialize(scholar_pub_id)
+    auth_id, pub_id = scholar_pub_id.split(/:/)
+    url = GSCHOLAR_CIT_URL + '&user=' + auth_id \
+                           + '&citation_for_view=' + auth_id + ':' + pub_id
+    res = Typhoeus::Request.new(url).run
+    @doc = Nokogiri::HTML(res.response_body)
+
+    extract_html_elements
+    extract_html_table
+  end
+
+  def extract_html_elements
+    @cites = @doc.xpath(SCAN_STR[:cites]).text[/\d+/].to_i
+    @cites_url = @doc.xpath(SCAN_STR[:cites])[0].attributes['href'].value
+
+    @title = @doc.xpath(SCAN_STR[:title]).text
+    @article_url = @doc.xpath(SCAN_STR[:article_url]).attr('href').value
+
+    @chart_url = @doc.xpath(SCAN_STR[:chart_url]).attr('src').value
+
+    @gscholar_url = GSCHOLAR_HOST_URL + @doc.xpath(
+                                  SCAN_STR[:gscholar_url]).attr('href').value
+  end
+
+  def extract_html_table
+    # lambda gets text from right html column given name in left column
+    table_pick = lambda do |name|
+      @doc.xpath("//div[starts-with(.,'#{name}')]")[0].children[1].text
+    end
+
+    TABLE_ATTR.each do |k, v|
+      instance_variable_set("@#{k}", table_pick.call(v))
+    end
+
+    @authors = @authors.split(/,/).map { |a| a.split(' ') }
+    @date = Date.strptime(@date, '%Y/%m/%d')
+  end
+end

metadata

@@ -0,0 +1,100 @@
+--- !ruby/object:Gem::Specification
+name: gentle-scholar
+version: !ruby/object:Gem::Version
+  version: 1.0.1
+platform: ruby
+authors:
+- Soumya Ray
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-05-25 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: minitest-rg
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.6.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.6.2
+- !ruby/object:Gem::Dependency
+  name: typhoeus
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.6.8
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.6.8
+description: Extract author/paper info from Google Scholar
+email: soumya.ray@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/publication.rb
+homepage: https://github.com/soumyaray/gentle-scholar
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.1.11
+signing_key: 
+specification_version: 4
+summary: Google Scholar infor extractor
+test_files: []