linkedindata 0.0.5 → 0.0.6

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: bfd623725b05bee10c9876abb55628a0a2e28a06
+  data.tar.gz: 1a4b6a558e726171b2ac9171af396e5de836c3cf
+SHA512:
+  metadata.gz: b71648311c07547c5fabcb1461581c8835e3ab38cab52e6f9c64828361bb27cf047d2cb3ae9dee609479bff34cd678e26d47a883df69c8bdc5019c470577a220
+  data.tar.gz: 27eed0c38444ca889ca331443aa4d78702bc21a07f47603ec66f39e1ad811f5a7d10633f5919bb7603cba322c45039198abd1e8e46ba48bba5d2d656fc397b18

data/lib/linkedindata.rb

@@ -1,12 +1,20 @@
 require 'mechanize'
 require 'linkedin-scraper'
 require 'json'
+require 'nokogiri'
+require 'open-uri'
 
 class LinkedinData
-  def initialize(input)
-   @input = input
-   @output = Array.new
-   @startindex = 10
+  def initialize(input, todegree)
+    @input = input
+    @output = Array.new
+    @startindex = 10
+    @degree = 0
+    if todegree == nil
+      @to_degree = 0
+    else
+      @to_degree = todegree
+    end
   end
 
   # Searches for links on Google
@@ -47,17 +55,75 @@ class LinkedinData
 
   # Scrapes profile and makes JSON
   def scrape(url)
+    flag = 0
+    @output.each do |o|
+      if o[:profile_url] == url
+        flag = 1
+        if @degree < o[:degree]
+          o[:degree] = @degree
+        end
+      end
+    end
+
     profile = Linkedin::Profile.get_profile(url)
     
     if profile
       profile.current_companies.each do |c|
-        c.merge!(:skills => profile.skills, :certifications => profile.certifications, :languages => profile.languages, :name => profile.first_name + " " + profile.last_name)
+        c.merge!(:skills => profile.skills, :certifications => profile.certifications, :languages => profile.languages, :name => profile.first_name + " " + profile.last_name, :location => profile.location, :area => profile.country, :industry => profile.industry, :picture => profile.picture, :organizations => profile.organizations, :groups => profile.groups, :education => profile.education, :websites => profile.websites, :profile_url => url, :degree => @degree, :current => "Yes")
+
+        if profile.picture
+          path = profile.picture.split("/")
+          if !File.file?("public/uploads/pictures/" + path[path.length-1].chomp.strip)
+            `wget -P public/uploads/pictures #{profile.picture}`
+          end
+          c.merge!(:pic_path => "public/uploads/pictures/" + path[path.length-1].chomp.strip)
+        end
+
         @output.push(c)
       end
       
       profile.past_companies.each do |c|
-        c.merge!(:skills => profile.skills, :certifications => profile.certifications, :languages => profile.languages, :name => profile.first_name + " " + profile.last_name)
+        c.merge!(:skills => profile.skills, :certifications => profile.certifications, :languages => profile.languages, :name => profile.first_name + " " + profile.last_name, :location => profile.location, :area => profile.country, :industry => profile.industry, :picture => profile.picture, :organizations => profile.organizations, :groups => profile.groups, :education => profile.education, :websites => profile.websites, :profile_url => url, :degree => @degree, :current => "No")
         @output.push(c)
+
+        if profile.picture
+          path = profile.picture.split("/")
+          if !File.file?("public/uploads/pictures/" + path[path.length-1].chomp.strip)
+            `wget -P public/uploads/pictures #{profile.picture}`
+          end
+          c.merge!(:pic_path => "public/uploads/pictures/" + path[path.length-1].chomp.strip)
+        end
+      end
+
+      # Clean up directories
+      pics = Dir["public/uploads/*.jpg.*"]
+      pics.each do |p|
+        File.delete(p)
+      end
+      getRelated(url)
+    end
+  end
+
+  # Gets related profiles listed on side of the page
+  def getRelated(url) 
+    if @degree < @to_degree
+      html = Nokogiri::HTML(open(url))
+      html.css("li.with-photo").each do |l|
+        plink = l.css("a")[0]['href'].split("?")
+
+        # Check to be sure not already saved
+        flag = 0
+        @output.each do |o|
+          if o[:profile_url] == plink[0]
+            flag = 1
+          end
+        end
+
+        if flag == 0
+          @degree += 1
+          scrape(plink[0])
+          @degree -= 1
+        end
       end
     end
   end
@@ -68,4 +134,3 @@ class LinkedinData
     return JSON.pretty_generate(@output)
   end
 end
-

metadata

@@ -1,15 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: linkedindata
 version: !ruby/object:Gem::Version
-  version: 0.0.5
-  prerelease: 
+  version: 0.0.6
 platform: ruby
 authors:
 - M. C. McGrath
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-02-25 00:00:00.000000000 Z
+date: 2014-05-24 00:00:00.000000000 Z
 dependencies: []
 description: Scrapes all LinkedIn profiles including terms you specify.
 email: shidash@shidash.com
@@ -18,30 +17,29 @@ extensions: []
 extra_rdoc_files: []
 files:
 - lib/linkedindata.rb
-homepage: https://github.com/Shidash/LinkedInData
+homepage: https://github.com/transparencytoolkit/linkedindata
 licenses:
 - GPL
+metadata: {}
 post_install_message: 
 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: 2.0.14
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Get all LinkedIn profiles including terms you specify
 test_files: []
 has_rdoc: