ids_please 2.2.5 → 2.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 3ffc9292346271435345f61a1d78b0445ae9665a
-  data.tar.gz: e804bf4bdc53f5b9fc6dad8cabac4a8896a3d45f
+  metadata.gz: c35bb69a59551448eae6824e7899412d17316913
+  data.tar.gz: 9eea7ffb29a6e31b774a79097fc7433acd6b3f65
 SHA512:
-  metadata.gz: 2cf37f10598ec5c12cbb69a26dcc1b34d0419dffc0fa63095406032aec85c880e76d6d7e2fc1e5a2fbc811eab4aa1f4aade2ac8c490ae9ab7b7f84958de39d03
-  data.tar.gz: fe7b94b2cc2218ef2667293499b44d43660653478743de11b80f06f76aa6b44c9439b43fd6fde24aed9c9ca55513aa6df7c3f9fd1a5ed196f80066be0121d8ee
+  metadata.gz: da397514835d00919f038b35b02baca683bb3696c3d75a52497ab95d4182cc574e36f4fbc2834e0fbedff50747418b9360c7fdf85282ceb035276fc2192473f7
+  data.tar.gz: c5f74ba3b93a4178407e0ba550325a665eba5da83d211547eea6e3a36844042267a6cf56ea42ad85f13a93a563fe9d2e8c85dac1c4f093e73df8f8a5602bca2f

data/.gitignore

@@ -1,6 +1,7 @@
 .DS_Store
 *.gem
 *.rbc
+.byebug_history
 /.config
 /coverage/
 /InstalledFiles

data/lib/ids_please/grabbers/facebook.rb

@@ -1,7 +1,6 @@
 class IdsPlease
   module Grabbers
     class Facebook < IdsPlease::Grabbers::Base
-
       def grab_link
         @network_id   = find_network_id
         @avatar       = find_avatar
@@ -35,9 +34,9 @@ class IdsPlease
       end
 
       def find_avatar
-        CGI.unescapeHTML(
-          find_by_regex(/profilePic\simg"\salt=[^=]+="([^"]+)/).encode('utf-8')
-        )
+        _avatar = find_by_regex(/profilePic\simg"\salt=[^=]+="([^"]+)/) ||
+                  find_by_regex(/id="entity_sidebar".+img".+src="([^"]+)/)
+        CGI.unescapeHTML(_avatar.gsub(/amp\;/, '').encode('utf-8')) if _avatar
       rescue => e
         record_error __method__, e.message
         return nil
@@ -61,7 +60,7 @@ class IdsPlease
       end
 
       def find_type
-        find_by_regex(/type":"Person/) ? 'perosnal' : 'group'
+        find_by_regex(/type":"Person/) ? 'personal' : 'group'
       rescue => e
         record_error __method__, e.message
         return nil

data/lib/ids_please/grabbers/google_plus.rb

@@ -31,7 +31,9 @@ class IdsPlease
       end
 
       def find_avatar
-        "https:#{find_by_regex(/guidedhelpid="profile_photo"><img src="([^"]+)"/)}"
+        _avatar = find_by_regex(/meta itemprop="image" content="([^"]+)/).encode('utf-8')
+        _avatar = "http:#{_avatar}" unless _avatar =~ /\Ahttps?:\/\//
+        _avatar
       rescue => e
         record_error __method__, e.message
         return nil

data/lib/ids_please/grabbers/instagram.rb

@@ -30,21 +30,21 @@ class IdsPlease
       private
 
       def find_network_id
-        find_by_regex(/"id":"(\d+)","biography"/)
+        find_by_regex(/"id":\s?"(\d+)"/)
       rescue => e
         record_error __method__, e.message
         return nil
       end
 
       def find_avatar
-        find_by_regex(/"user":{.+"profile_pic_url":"([^"]+)"/).gsub('\\', '')
+        find_by_regex(/"user":\s?{.+"profile_pic_url":\s?"([^"]+)"/).gsub('\\', '')
       rescue => e
         record_error __method__, e.message
         return nil
       end
 
       def find_display_name
-        _display_name = find_by_regex(/"user":{.+"full_name":"([^"]+)"/)
+        _display_name = find_by_regex(/"user":\s?{.+"full_name":\s?"([^"]+)"/)
         _display_name.gsub(/\\u([\da-fA-F]{4})/) { |_m|
           [Regexp.last_match(1)].pack('H*').unpack('n*').pack('U*')
         }
@@ -54,42 +54,42 @@ class IdsPlease
       end
 
       def find_username
-        find_by_regex(/"user":{"username":"([^"]+)"/).to_s.gsub('\\', '')
+        find_by_regex(/"username":\s?"([^"]+)"/).to_s.gsub('\\', '')
       rescue => e
         record_error __method__, e.message
         return nil
       end
 
       def find_bio
-        CGI.unescapeHTML(find_by_regex(/"biography":"([^"]+)"/).to_s).strip
+        CGI.unescapeHTML(find_by_regex(/"biography":\s?"([^"]+)"/).to_s).strip
       rescue => e
         record_error __method__, e.message
         return nil
       end
 
       def find_website
-        CGI.unescapeHTML(find_by_regex(/"user":{.+"external_url":"([^"]+)"/).to_s.gsub('\\', '')).strip
+        CGI.unescapeHTML(find_by_regex(/"user":\s?{.+"external_url":\s?"([^"]+)"/).to_s.gsub('\\', '')).strip
       rescue => e
         record_error __method__, e.message
         return nil
       end
 
       def find_media
-        find_by_regex(/"media":{"count":(\d+)/).to_i
+        find_by_regex(/"media":\s?{"count":\s?(\d+)/).to_i
       rescue => e
         record_error __method__, e.message
         return nil
       end
 
       def find_followed_by
-        find_by_regex(/"followed_by":{"count":(\d+)/).to_i
+        find_by_regex(/"followed_by":\s?{"count":\s?(\d+)/).to_i
       rescue => e
         record_error __method__, e.message
         return nil
       end
 
       def find_follows
-        find_by_regex(/"follows":{"count":(\d+)/).to_i
+        find_by_regex(/"follows":\s?{"count":\s?(\d+)/).to_i
       rescue => e
         record_error __method__, e.message
         return nil

data/lib/ids_please/grabbers/vkontakte.rb

@@ -2,28 +2,65 @@ class IdsPlease
   module Grabbers
     class Vkontakte < IdsPlease::Grabbers::Base
       def grab_link
-        prepare_link
         agent          = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36'
         @page_source ||= open(link, 'User-Agent' => agent).read.encode('utf-8')
-        @network_id    = find_by_regex(/href="\/wall(-\d+)_/)
-        @username      = @link.to_s.split('vk.com/').last.gsub('/', '')
-        @avatar        = find_by_regex(/page_avatar.+\n.+src="([^"]+)/)
-        @avatar        = CGI.unescapeHTML(@avatar) if @avatar
-        @display_name  = find_by_regex(/page_name">([^<]+)/)
-        @display_name  = CGI.unescapeHTML(@display_name) if @display_name
+
+        @network_id    = find_network_id
+        @username      = find_username
+        @avatar        = find_avatar
+        @display_name  = find_display_name
+
         @data = {
-          description: find_by_regex(/description" content="([^"]+)/)
+          description: find_description
         }
-        @data[:description] = CGI.unescapeHTML(@data[:description]) if @data[:description]
         self
       rescue => e
         record_error __method__, e.message
         return self
       end
 
-      def prepare_link
-        id = @link.to_s.split('/').last
-        @link = URI("https://new.vk.com/#{id}")
+      private
+
+      def find_avatar
+        CGI.unescapeHTML(
+          find_by_regex(/page_avatar_img" src="([^"]+)/) ||
+          find_by_regex(/<img src="([^"]+).+class="post_img"/)
+        )
+      rescue => e
+        record_error __method__, e.message
+        return nil
+      end
+
+      def find_network_id
+        find_by_regex(/href="\/wall(-\d+)_/)
+      rescue => e
+        record_error __method__, e.message
+        return nil
+      end
+
+      def find_display_name
+        CGI.unescapeHTML(
+          find_by_regex(/page_name">([^<]+)/)
+        )
+      rescue => e
+        record_error __method__, e.message
+        return nil
+      end
+
+      def find_username
+        @link.to_s.split('vk.com/').last.gsub('/', '')
+      rescue => e
+        record_error __method__, e.message
+        return nil
+      end
+
+      def find_description
+        CGI.unescapeHTML(
+          find_by_regex(/description" content="([^"]+)/)
+        )
+      rescue => e
+        record_error __method__, e.message
+        return nil
       end
     end
   end

data/lib/ids_please/version.rb

@@ -1,5 +1,5 @@
 class IdsPlease
 
-  VERSION = '2.2.5'
+  VERSION = '2.3.0'
 
 end

data/spec/ids_please/grab_spec.rb

@@ -0,0 +1,144 @@
+require 'spec_helper'
+
+describe IdsPlease do
+  describe 'grab' do
+    context 'from external', external: true do
+      let!(:recognizer) do
+        recognizer = IdsPlease.new(*recognazible_links)
+        recognizer.grab
+        recognizer
+      end
+
+      let(:recognazible_links) do
+        %w(
+          https://twitter.com/amplifr
+          https://www.instagram.com/instagram/
+          https://my.mail.ru/community/test-group-102/
+          https://my.mail.ru/mail/gazay/
+          https://plus.google.com/+VladimirBokov
+          https://plus.google.com/communities/109254488709825102030
+        )
+      end
+
+      describe 'vk grabber' do
+        context 'vk public page' do
+          let(:grabbed) do
+            recognizer = IdsPlease.new('https://vk.com/amplifr')
+            recognizer.grab[:vkontakte].first
+          end
+
+          it "does return correct data set for public" do
+            expect(grabbed.errors).to be_empty
+            expect(URI.parse(grabbed.avatar)).to be_truthy
+            expect(grabbed.display_name).to be_truthy
+            expect(grabbed.username).to be_truthy
+            expect(grabbed.network_id).to be_truthy
+            expect(grabbed.link).to be_truthy
+            expect(grabbed.data).to be_truthy
+          end
+        end
+
+        context 'vk user page' do
+          let(:grabbed) do
+            recognizer = IdsPlease.new('https://vk.com/id1')
+            recognizer.grab[:vkontakte].first
+          end
+          it "does return correct data set for user page" do
+            expect(grabbed.errors).to be_empty
+            expect(URI.parse(grabbed.avatar)).to be_truthy
+            expect(grabbed.display_name).to be_truthy
+            expect(grabbed.username).to be_truthy
+            expect(grabbed.link).to be_truthy
+            expect(grabbed.data).to be_truthy
+          end
+        end
+      end
+
+      describe 'fb grabber' do
+        context 'fb public page' do
+          let(:grabbed) do
+            recognizer = IdsPlease.new('https://www.facebook.com/amplifr/')
+            recognizer.grab[:facebook].first
+          end
+
+          it "does return correct data set for public" do
+            expect(grabbed.errors).to be_empty
+            expect(URI.parse(grabbed.avatar)).to be_truthy
+            expect(grabbed.display_name).to be_truthy
+            expect(grabbed.username).to be_truthy
+            expect(grabbed.network_id).to be_truthy
+            expect(grabbed.link).to be_truthy
+            expect(grabbed.data).to be_truthy
+            expect(grabbed.data[:type]).to be_truthy
+            expect(grabbed.data[:description]).to be_truthy
+          end
+        end
+
+        context 'fb user page' do
+          let(:grabbed) do
+            recognizer = IdsPlease.new('https://www.facebook.com/zuck')
+            recognizer.grab[:facebook].first
+          end
+
+          it "does return correct data set for user page" do
+            expect(grabbed.errors).to be_empty
+            expect(URI.parse(grabbed.avatar)).to be_truthy
+            expect(grabbed.display_name).to be_truthy
+            expect(grabbed.username).to be_truthy
+            expect(grabbed.link).to be_truthy
+            expect(grabbed.data[:type]).to be_truthy
+            expect(grabbed.data[:description]).to be_truthy
+          end
+        end
+      end
+
+      it 'does return correct set of data for twitter' do
+        recognizer.grabbed[:twitter].each do |g|
+          expect(g.errors).to be_empty
+          expect(URI.parse(g.avatar)).to be_truthy
+          expect(g.display_name).to be_truthy
+          expect(g.username).to be_truthy
+          expect(g.link).to be_truthy
+          expect(g.network_id).to be_truthy
+          expect(g.data).to be_truthy
+        end
+      end
+
+      it 'does return correct set of data for instagram' do
+        recognizer.grabbed[:instagram].each do |g|
+          expect(g.errors).to be_empty
+          expect(URI.parse(g.avatar)).to be_truthy
+          expect(g.display_name).to be_truthy
+          expect(g.username).to be_truthy
+          expect(g.link).to be_truthy
+          expect(g.network_id).to be_truthy
+          expect(g.data).to be_truthy
+        end
+      end
+
+      it 'does return correct set of data for mail' do
+        recognizer.grabbed[:mail].each do |g|
+          expect(g.errors).to be_empty
+          expect(URI.parse(g.avatar)).to be_truthy
+          expect(g.display_name).to be_truthy
+          expect(g.username).to be_truthy
+          expect(g.link).to be_truthy
+          expect(g.network_id).to be_truthy
+          expect(g.data).to be_truthy
+        end
+      end
+
+      it 'does return correct set of data for google' do
+        recognizer.grabbed[:google].each do |g|
+          expect(g.errors).to be_empty
+          expect(URI.parse(g.avatar)).to be_truthy
+          expect(g.display_name).to be_truthy
+          expect(g.username).to be_truthy
+          expect(g.link).to be_truthy
+          expect(g.network_id).to be_truthy
+          expect(g.data).to be_truthy
+        end
+      end
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -1 +1,5 @@
 require 'ids_please'
+
+RSpec.configure do |c|
+  c.filter_run_excluding external: true
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ids_please
 version: !ruby/object:Gem::Version
-  version: 2.2.5
+  version: 2.3.0
 platform: ruby
 authors:
 - gazay
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-08-10 00:00:00.000000000 Z
+date: 2017-07-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -101,6 +101,7 @@ files:
 - lib/ids_please/parsers/youtube.rb
 - lib/ids_please/version.rb
 - spec/ids_please/basic_spec.rb
+- spec/ids_please/grab_spec.rb
 - spec/spec_helper.rb
 homepage: http://github.com/gazay/ids_please
 licenses:
@@ -123,10 +124,11 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.5.1
+rubygems_version: 2.5.2
 signing_key: 
 specification_version: 4
 summary: Helps to get ids or screen names from links to social network accounts
 test_files:
 - spec/ids_please/basic_spec.rb
+- spec/ids_please/grab_spec.rb
 - spec/spec_helper.rb