screencap 0.0.3 → 0.1.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 9b7624dd53d821906855cf7ae58dd10655313d48
+  data.tar.gz: c8200b69557b17fb185aafe9b60caf9c45c9fb5e
+SHA512:
+  metadata.gz: 3e7760a49fb7eb9a09b82b0d2b064ca1d53da0ac74464c6f711c6d4f41824326e9578c2e283723efa383e54228a9259c6af4de127704d72500b785ffab2605e4
+  data.tar.gz: 7a0ac0b9fe08fedcfec07d11b91fd955dfe4d7e6c34c7d6066309a9344bd037a23a87451ebefe752df11ef86ee59656d3ba0184a675340dac98394d039faf56f

data/Gemfile

@@ -4,5 +4,4 @@ source 'https://rubygems.org'
 gem 'guard'
 gem 'guard-rspec'
 gem 'guard-bundler'
-gem 'phantomjs.rb', :git => 'git://github.com/westoque/phantomjs.rb.git'
 gemspec

data/README.md

@@ -29,14 +29,17 @@ it also currently supports a couple of options
 
 ```ruby
   f = Screencap::Fetcher.new('http://google.com')
-  screenshot = f.fetch(:div => '.header', :output => '~/my_directory.png') #dont forget the extension!
-```
+  screenshot = f.fetch(
+  	:output => '~/my_directory.png', # don't forget the extension!
+  	# optional:
+  	:div => '.header', # selector for a specific element to take screenshot of
+  	:width => 1024,
+    :height => 768,
+  	:top => 0, :left => 0, :width => 100, :height => 100 # dimensions for a specific area
+  )
 
-## To-do
+```
 
-more tests
-better configuration
-expose more options
 ## Contributing
 
 1. Fork it

data/lib/screencap.rb

@@ -5,14 +5,9 @@ require 'pathname'
 
 module Screencap
   SCREENCAP_ROOT = Pathname.new(File.dirname(__FILE__))
-  TMP_DIRECTORY = SCREENCAP_ROOT.join('..', 'tmp')
-end
-
-#config
 
-#tmp directory to store files
-
-#should return a file handle to tmp director where it is stored
+  class Error < StandardError; end
+end
 
 require 'screencap/fetcher'
 require 'screencap/phantom'

data/lib/screencap/fetcher.rb

@@ -6,7 +6,7 @@ module Screencap
 
     def fetch(opts = {})
       @filename = opts.fetch(:output, clean_filename)
-      raster(@url, @filename, opts[:div])
+      raster(@url, @filename, opts)
       fetched_file
     end
 
@@ -15,7 +15,9 @@ module Screencap
     end
 
     def fetched_file
-      File.open(filename)
+      if File.exists?(filename)
+        File.open(filename)
+      end
     end
 
     def raster(*args)
@@ -23,7 +25,7 @@ module Screencap
     end
 
     def clean_filename
-      "#{TMP_DIRECTORY}/#{@url.delete('/.:?!')}.png"
+      "#{@url.delete('/.:?!')}.png"
     end
   end
 end

data/lib/screencap/phantom.rb

@@ -2,12 +2,17 @@ module Screencap
   class Phantom
     RASTERIZE = SCREENCAP_ROOT.join('screencap', 'raster.js')
 
-    def self.rasterize(url, path, *args)
-      # puts RASTERIZE.to_s, url, path, *args  # Your code goes here...
-      Phantomjs.run(RASTERIZE.to_s, url, path, *args) 
+    def self.rasterize(url, path, args = {})
+      params = {
+        url: CGI::escape(url),
+        output: path
+      }.merge(args).collect {|k,v| "#{k}=#{v}"}
+      puts RASTERIZE.to_s, params
+      result = Phantomjs.run(RASTERIZE.to_s, *params)
+      puts result if(args[:debug])
+      raise Screencap::Error, "Could not load URL #{url}" if result.match /Unable to load/
     end
 
-
     def quoted_args(args)
       args.map{|x| quoted_arg(x)}
     end

data/lib/screencap/raster.js

@@ -1,52 +1,182 @@
-var page = new WebPage(),
-    address, output, div;
+//
+// Takes a screenshot of the given URL, uses named arguments passed in like so: phantomjs raster.js arg=value arg2=value2
+//
+// Arguments:
+// - url                      - URL to screenshot
+// - output                   - page to output (e.g. /tmp/output.png)
+// - width         [optional] - default 1024 - viewport width
+// - height        [optional] - viewport height (see note below on using height)
+// - debug         [optional] - default false - whether to do some extra debugging
+// - div           [optional] - a selector to use to screenshot to a specific element
+// - resourceWait  [optional] - default 300 - the time to wait after the last resource has loaded in MS before taking the screenshot
+// - maxRenderWait [optional] - default 10000 - the maximum time to wait before taking the screenshot, regardless of whether resources are waiting to be loaded
+// - top, left, width, height [optional] - dimensions to use to screenshot a specific area of the screen
+//
+// == Important notice when providing height ==
+//
+// If you provide a height then we resize the html & body tags otherwise render() renders the entire page
+// changing the viewport height does not affect this behaviour of render(), see https://github.com/ariya/phantomjs/issues/10619
+//
+var page           = new WebPage(),
+    resourceWait   = 300,
+    maxRenderWait  = 10000,
+    args           = {},
+    resourceCount  = 0,
+    debug          = false,
+    mask           = null,
+    forcedRenderTimeout,
+    renderTimeout;
 
-if (phantom.args.length < 2 || phantom.args.length > 4) {
-    console.log('Usage: rasterize.js URL filename div(optional)');
-    phantom.exit();
-} 
+//
+// Functions
+//
+function pickupNamedArguments() {
+    var i, pair;
+    for(i = 0; i < phantom.args.length; i++) {
+        pair = phantom.args[i].split(/=(.*)/);
+        args[pair[0]] = pair[1];
+    }
+
+    if(!args.width)        { args.width = 1024; }
+    if(args.url)           { args.url = decodeURIComponent(args.url); }
+    if(args.debug)         { debug = true; }
+    if(args.resourceWait)  { resourceWait = args.resourceWait; }
+    if(args.maxRenderWait) { maxRenderWait = args.maxRenderWait; }
+}
+
+function setupMask() {
+    // if given settings for an area to take create a mask for that
+    if( args.top && args.left && args.width && args.height) {
+        mask = {
+            top:    args.top,
+            left:   args.left,
+            width:  args.width,
+            height: args.height
+        };
+    }
+}
 
-address = phantom.args[0];
-output = phantom.args[1];
-div = phantom.args[2];
+function doRender() {
+    clearTimeout(renderTimeout);
+    clearTimeout(forcedRenderTimeout);
+    page.render(args.output);
+    phantom.exit();
+}
 
-//console.log(address, output, div)
+function delayScreenshotForResources() {
+    forcedRenderTimeout = setTimeout(doRender, maxRenderWait);
+}
 
-function evaluate(page, func) {
-    var args = [].slice.call(arguments, 2);
-    var fn = "function() { return (" + func.toString() + ").apply(this, " + JSON.stringify(args) + ");}";
+function evaluateWithArgs(func) {
+    var args = [].slice.call(arguments, 1);
+    var fn =  "function() { return (" + func.toString() + ").apply(this, " + JSON.stringify(args) + "); }";
     return page.evaluate(fn);
 }
 
- function returnDivDimensions(div){
+function takeScreenshot() {
+   page.open(args.url, function(status) {
+        if(status !== 'success') {
+            console.log('Unable to load: ' + args.url);
+            phantom.exit();
+        } else {
+            page.includeJs(
+                "https://ajax.googleapis.com/ajax/libs/jquery/1.11.0/jquery.min.js",
+                function() {
+
+                    var foundDiv = true;
+                    page.evaluate(function(){ jQuery.noConflict(); });
+
+                    if(args.div) {
+                        var clip = evaluateWithArgs(withinPage_GetDivDimensions, args.div);
+                        foundDiv = clip;
+                        page.clipRect = clip;
+                    } else if(mask) {
+                        page.clipRect = mask;
+                    } else if(args.height) {
+                        // have a height resize the html & body to workaround https://github.com/ariya/phantomjs/issues/10619
+                        evaluateWithArgs(
+                            function(w,h) {
+                                jQuery('body, html').css({
+                                    width: w + 'px',
+                                    height: h + 'px',
+                                    overflow: 'hidden'
+                               });
+                            },
+                            page.viewportSize.width,
+                            page.viewportSize.height
+                        );
+                    }
+
+                    if(foundDiv) {
+                        delayScreenshotForResources();
+                    } else {
+                        phantom.exit();
+                    }
+                }
+            );
+        }
+    });
+}
+
+//
+// Functions evaluated within the page context
+//
+function withinPage_GetDivDimensions(div){
     var $el = jQuery(div);
-    var box = $el.offset()
-    box.height = $el.height();
-    box.width = $el.width();
-    return box;
+
+    if($el.length === 0){
+        console.log(div + ' was not found. exiting');
+        return false;
+    }
+
+    var dims    = $el.offset();
+    dims.height = $el.height();
+    dims.width  = $el.width();
+    return dims;
 }
 
-page.onConsoleMessage = function (msg) { 
-    //console.log("from page:" + msg); 
+//
+// Event handlers
+//
+page.onConsoleMessage = function(msg) {
+    console.log('from page: ' + msg);
 };
 
-page.viewportSize = { width: 1000, height: 550 }
+page.onResourceRequested = function(req) {
+    resourceCount += 1;
+    if(debug) { console.log('> ' + req.id + ' - ' + req.url); }
+    clearTimeout(renderTimeout);
+};
 
-page.open(address, function (status) {
-     if (status !== 'success') {
-            console.log('Unable to load:' + address);
-            phantom.exit();
-        } 
-    //once page loaded, include jQuery from cdn
-    page.includeJs("http://ajax.googleapis.com/ajax/libs/jquery/1.6.1/jquery.min.js", function() {
-        page.evaluate(function(){jQuery.noConflict()})
-
-        if(div) {
-            var clip =  evaluate(page, returnDivDimensions, div);
-            page.clipRect = clip;
+page.onResourceReceived = function(res) {
+    if(!res.stage || res.stage == 'end') {
+        resourceCount -= 1;
+        if(debug) {
+            console.log(res.id + ' ' + res.status + ' - ' + res.url);
+            console.log(resourceCount + ' resources remaining');
+        }
+        if(resourceCount === 0) {
+            // Once all resources are loaded, we wait a small amount of time
+            // (resourceWait) in case these resources load other resources.
+            clearTimeout(forcedRenderTimeout);
+            renderTimeout = setTimeout(doRender, resourceWait);
         }
+    }
+};
 
-        page.render(output);
-        phantom.exit();     
-    });
-});
+//
+// Do the processing
+//
+pickupNamedArguments();
+setupMask();
+
+console.log(JSON.stringify(args));
+
+if( !args.url || !args.output ) {
+    console.log('Usage: raster.js url=URL output=filename width=width[optional] height=height[optional] debug=true/false[optional] (div=div[optional] OR top=top left=left width=width height=height)');
+    phantom.exit();
+}
+
+page.viewportSize = { width: args.width, height: args.height || 1024 };
+
+takeScreenshot();

data/lib/screencap/version.rb

@@ -1,3 +1,3 @@
 module Screencap
-  VERSION = "0.0.3"
+  VERSION = "0.1.1"
 end

data/screencap.gemspec

@@ -2,7 +2,7 @@
 require File.expand_path('../lib/screencap/version', __FILE__)
 
 Gem::Specification.new do |gem|
-  gem.authors       = ["Maxwell Salzberg"]
+  gem.authors       = ["Maxwell Salzberg","David Spurr"]
   gem.email         = ["maxwell@joindiaspora.com"]
   gem.description   = %q{a gem to grab screenshots of webpages, or just parts of webpages}
   gem.summary       = %q{uses Phantom.js to grab pages, or parts of pages. Simple API.}
@@ -17,4 +17,7 @@ Gem::Specification.new do |gem|
 
   gem.add_development_dependency 'rspec', '~> 2.10'
   gem.add_development_dependency 'rake'
+  gem.add_development_dependency 'phantomjs.rb'
+  gem.add_development_dependency 'fastimage'
+  gem.add_runtime_dependency 'phantomjs'
 end

data/spec/fetcher_spec.rb

@@ -6,7 +6,28 @@ describe Screencap::Fetcher do
   end
 
   it 'supports a custom filename' do
-    screenshot = Screencap::Fetcher.new('http://yahoo.com').fetch(:output => Screencap::TMP_DIRECTORY + 'kats.png')
+    screenshot = Screencap::Fetcher.new('http://yahoo.com').fetch(:output => TMP_DIRECTORY + 'custom_filename.png')
     File.exists?(screenshot).should == true
   end
+
+  it 'supports a custom width' do
+    screenshot = Screencap::Fetcher.new('http://google.com').fetch(:output => TMP_DIRECTORY + 'custom_width.jpg', :width => 800)
+    FastImage.size(screenshot)[0].should == 800
+  end
+
+  it 'supports a custom height' do
+    # note using stackoverflow.com as google.com implements x-frame-options header meaning that it won't load in the object element
+    screenshot = Screencap::Fetcher.new('http://stackoverflow.com').fetch(:output => TMP_DIRECTORY + 'custom_height.jpg', :height => 600)
+    FastImage.size(screenshot)[1].should == 600
+  end
+
+  it 'captures a given element' do
+    screenshot = Screencap::Fetcher.new('http://placehold.it').fetch(:output => TMP_DIRECTORY + 'given_element.jpg', :div => 'img.image')
+    FastImage.size(screenshot)[0].should == 140
+  end
+
+  it 'should work when given a query string with ampersand in it' do
+    screenshot = Screencap::Fetcher.new('http://google.com?1=2&3=4').fetch(:output => TMP_DIRECTORY + 'ampersand.jpg', :width => 800)
+    FastImage.size(screenshot)[0].should == 800
+  end
 end

data/spec/screencap_spec.rb

@@ -2,6 +2,13 @@ require 'spec_helper'
 
 describe Screencap do
   it 'works' do
-    Screencap::Fetcher.new('http://google.com').fetch
+    screenshot = Screencap::Fetcher.new('http://google.com').fetch(output: TMP_DIRECTORY + 'google.png')
+    FastImage.size(screenshot)[0].should == 1024
+  end
+
+  it 'throws error when phantom could not load page' do
+    expect {
+      Screencap::Fetcher.new('http://doesnotexistatallipromise.com/').fetch(output: TMP_DIRECTORY + 'foo.png')
+    }.to raise_error Screencap::Error, "Could not load URL http://doesnotexistatallipromise.com/"
   end
 end

data/spec/spec_helper.rb

@@ -1,5 +1,8 @@
 $:.unshift File.dirname(__FILE__) + '/../lib'
 require 'screencap'
+require 'fastimage'
+
+TMP_DIRECTORY = Screencap::SCREENCAP_ROOT.join('..', 'tmp')
 
 RSpec.configure do |config|
   config.treat_symbols_as_metadata_keys_with_true_values = true
@@ -7,6 +10,9 @@ RSpec.configure do |config|
   config.filter_run :focus
 
   config.before(:all) do
-    system("rm #{Screencap::TMP_DIRECTORY}/*.png")
+    unless ENV['KEEP_OUTPUT']
+      system("rm #{TMP_DIRECTORY}/*.png")
+      system("rm #{TMP_DIRECTORY}/*.jpg")
+    end
   end
 end

metadata

@@ -1,38 +1,86 @@
 --- !ruby/object:Gem::Specification
 name: screencap
 version: !ruby/object:Gem::Version
-  version: 0.0.3
-  prerelease: 
+  version: 0.1.1
 platform: ruby
 authors:
 - Maxwell Salzberg
+- David Spurr
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-06-06 00:00:00.000000000 Z
+date: 2014-04-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &70117782109160 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '2.10'
   type: :development
   prerelease: false
-  version_requirements: *70117782109160
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.10'
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &70117782124980 !ruby/object:Gem::Requirement
-    none: false
+  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: phantomjs.rb
+  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: fastimage
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70117782124980
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: phantomjs
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: a gem to grab screenshots of webpages, or just parts of webpages
 email:
 - maxwell@joindiaspora.com
@@ -40,9 +88,9 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
-- .rspec
-- .travis.yml
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
 - Gemfile
 - Guardfile
 - LICENSE
@@ -59,27 +107,26 @@ files:
 - spec/spec_helper.rb
 homepage: http://github.com/maxwell/screencap
 licenses: []
+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: 1.8.17
+rubygems_version: 2.0.2
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: uses Phantom.js to grab pages, or parts of pages. Simple API.
 test_files:
 - spec/fetcher_spec.rb