http_reader 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 342e596f1ce05595886d576288111a8d873e5d06
-  data.tar.gz: d1bb9056c0e5ef44fa9185fbb8b97943fffa6639
+  metadata.gz: 5d7bf3d80028e3d8d30021fa2a5f5e9e8bbc045d
+  data.tar.gz: 0f2d2d21c8406d9c82fd0342360a7140d0bae1fe
 SHA512:
-  metadata.gz: 9983010f18f2bee05fadc9a7583c4c1d1740a173191a5bab70129e2d55fdc6da6da2d061a70e39c4fa6daed91337e366a058b6ccebc74a2666fb8d0ef2690d6a
-  data.tar.gz: af912964ef1658a387989e177c4be500a4938aca5df004fc6d203dfcdf469c4f8fe8e7614ccf89cae4d7f67dd89d13835ee7ef0d9c01258110d36275d53135a3
+  metadata.gz: e21c2d5c8c5d0e2fbe21eff99dd4db77d8a591eb5592d0ccf6ae8985fb9ff23bfa54f5ffa2c3ea7af7bf5a2628b49c4c44b06742cbf6d4cf663b6886cdca948d
+  data.tar.gz: 9fcf04a7fbbb4395b8cd197d90f7d3c21eefeeafdf3c717678574511546df2b6fbc5cb14f84b8d34983c76d7219dcb8616f214af75f39019fc47256e69050736

data/README.md

@@ -1,4 +1,8 @@
 # HttpReader
+[![Gem Version](https://badge.fury.io/rb/http_reader.svg)](http://badge.fury.io/rb/http_reader)
+[![Build Status](https://secure.travis-ci.org/pniemczyk/http_reader.png?branch=master)](https://travis-ci.org/pniemczyk/http_reader) 
+[![Dependency Status](https://gemnasium.com/pniemczyk/http_reader.png)](https://gemnasium.com/pniemczyk/http_reader)
+[![Code Climate](https://codeclimate.com/github/pniemczyk/http_reader/badges/gpa.svg)](https://codeclimate.com/github/pniemczyk/http_reader)
 
 Read any document on internet and parse to your own format :D
 
@@ -100,9 +104,10 @@ Or install it yourself as:
 - httparty
 - headless
 - watir-webdriver
+
 ### System components
 - xvfb
-instalation on ubuntu: sudo apt-get install xvfb
+*instalation on ubuntu: sudo apt-get install xvfb*
 
 
 ## Contributing

data/lib/http_reader/engine.rb

@@ -8,7 +8,7 @@ module HttpReader
   class Engine
     ReadError       = Class.new(StandardError)
     DefaultResponse = Struct.new(:body, :code, :message, :headers)
-    attr_reader :parsers, :default_parser, :http_client, :browser, :logger
+    attr_reader :parsers, :default_parser, :http_client, :browser, :logger, :browser_keep_running
 
     def initialize(config = {})
       @parsers        = config.fetch(:parsers, [])
@@ -16,6 +16,7 @@ module HttpReader
       @http_client    = config.fetch(:http_client, HTTParty)
       @browser        = config.fetch(:browser, Watir::Browser)
       @logger         = config.fetch(:logger, Logger.new(STDOUT))
+      @browser_keep_running = config.fetch(:browser_keep_running, true)
     end
 
     def read(url, opts = {})
@@ -35,6 +36,12 @@ module HttpReader
       raise ReadError.new(e.message)
     end
 
+    def close_browser
+      active_browser.close
+      headless.destroy
+      @active_browser = nil
+    end
+
     private
 
     def find_parser(url)
@@ -46,12 +53,9 @@ module HttpReader
     end
 
     def browse(url, parser, opts = {})
-      html = nil
-      headless.start
-      b    = browser.start(url)
-      html = parser.browse_actions_for_html(b, opts)
-      b.close
-      headless.destroy
+      active_browser.goto(url)
+      html = parser.browse_actions_for_html(active_browser, opts)
+      close_browser unless browser_keep_running
       DefaultResponse.new(html, 200, opts[:message] || "success")
     rescue => e
       log_error('browse', e)
@@ -67,8 +71,17 @@ module HttpReader
       DefaultResponse.new(nil, 500, e.message)
     end
 
+    def active_browser
+      @active_browser ||= new_browser
+    end
+
+    def new_browser
+      headless.start
+      browser.new
+    end
+
     def headless
-      @headless ||= Headless.new
+      @headless ||= Headless.new(display: 100, reuse: true, destroy_at_exit: true)
     end
 
     def log_error(method, ex, info = nil)

data/lib/http_reader/version.rb

@@ -1,3 +1,3 @@
 module HttpReader
-  VERSION = "0.0.1"
+  VERSION = "0.0.2"
 end

data/spec/unit/lib/http_reader/engine_spec.rb

@@ -164,25 +164,44 @@ describe HttpReader::Engine do
       subject.read(test_url, request_opts: request_opts)
     end
 
-    it 'should provide request_opts to request method' do
+    it 'should provide browse_opts to request method' do
       message      = 'done'
       browse_opts  = { process: :continue, message: message}
       browser_body = "body"
       response = described_class::DefaultResponse.new(browser_body, 200, message)
-      expect(Headless).to receive(:new).and_return(headless)
+      expect(Headless).to receive(:new).with(display: 100, reuse: true, destroy_at_exit: true).and_return(headless)
       expect(headless).to receive(:start)
       expect(default_parser).to receive(:use_browser).and_return(true)
-      expect(browser).to receive(:start).with(test_url).and_return(active_browser)
+      expect(browser).to receive(:new).and_return(active_browser)
+      expect(active_browser).to receive(:goto).with(test_url)
       expect(default_parser).to receive(:browse_actions_for_html)
                                 .with(active_browser, browse_opts)
                                 .and_return(browser_body)
-      expect(active_browser).to receive(:close)
-      expect(headless).to receive(:destroy)
       expect(default_parser).to receive(:parse).with(response, {})
 
       subject.read(test_url, browse_opts: browse_opts)
     end
 
+    it 'should close browser and destroy headless after browse' do
+      message      = 'done'
+      browse_opts  = { process: :continue, message: message}
+      browser_body = "body"
+      response = described_class::DefaultResponse.new(browser_body, 200, message)
+      expect(Headless).to receive(:new).with(display: 100, reuse: true, destroy_at_exit: true).and_return(headless)
+      expect(headless).to receive(:start)
+      expect(default_parser).to receive(:use_browser).and_return(true)
+      expect(browser).to receive(:new).and_return(active_browser)
+      expect(active_browser).to receive(:goto).with(test_url)
+      expect(default_parser).to receive(:browse_actions_for_html)
+                                .with(active_browser, browse_opts)
+                                .and_return(browser_body)
+      expect(default_parser).to receive(:parse).with(response, {})
+      subject.instance_variable_set(:@browser_keep_running,false)
+      expect(active_browser).to receive(:close)
+      expect(headless).to receive(:destroy)
+      subject.read(test_url, browse_opts: browse_opts)
+    end
+
     context 'on raise errors' do
 
       it 'raise ReadError' do
@@ -206,7 +225,7 @@ describe HttpReader::Engine do
         error_msg = 'HttpReader::Engine#browse - Bad '
         response  = described_class::DefaultResponse.new(nil, 500, 'Bad')
         expect(default_parser).to receive(:use_browser).and_return(true)
-        expect(browser).to receive(:start).with(test_url).and_raise('Bad')
+        expect(browser).to receive(:new).and_raise('Bad')
         expect(default_parser).to receive(:parse).with(response, {})
         expect(logger).to receive(:error).with(error_msg)
         subject.read(test_url)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: http_reader
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - Paweł Niemczyk
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-09-20 00:00:00.000000000 Z
+date: 2014-09-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: httparty