Implement downloads

CHANGELOG.md

@@ -3,6 +3,10 @@
 ### Added
 - `Ferrum::Page#disable_javascript` disables the JavaScript from the HTML source
 - `Ferrum::Page#set_viewport` emulates the viewport
+- `Ferrum::Downloads`
+  - `#files` information about downloaded files
+  - `#wait` wait for file download to be completed
+  - `#set_behavior` where and whether to store file
 
 ### Changed
 

Gemfile

@@ -7,7 +7,7 @@ gem "chunky_png", "~> 1.3"
 gem "image_size", "~> 2.0"
 gem "kramdown", "~> 2.0", require: false
 gem "pdf-reader", "~> 2.2"
-gem "puma", "~> 4.1"
+gem "puma", ">= 5.6.7"
 gem "rake", "~> 13.0"
 gem "redcarpet", require: false, platform: :mri
 gem "rspec", "~> 3.8"

README.md

@@ -35,8 +35,8 @@ based on Ferrum and Mechanize.
 * [Navigation](https://github.com/rubycdp/ferrum#navigation)
 * [Finders](https://github.com/rubycdp/ferrum#finders)
 * [Screenshots](https://github.com/rubycdp/ferrum#screenshots)
-* [Cleaning Up](https://github.com/rubycdp/ferrum#cleaning-up)
 * [Network](https://github.com/rubycdp/ferrum#network)
+* [Downloads](https://github.com/rubycdp/ferrum#downloads)
 * [Proxy](https://github.com/rubycdp/ferrum#proxy)
 * [Mouse](https://github.com/rubycdp/ferrum#mouse)
 * [Keyboard](https://github.com/rubycdp/ferrum#keyboard)
@@ -49,6 +49,7 @@ based on Ferrum and Mechanize.
 * [Animation](https://github.com/rubycdp/ferrum#animation)
 * [Node](https://github.com/rubycdp/ferrum#node)
 * [Tracing](https://github.com/rubycdp/ferrum#tracing)
+* [Clean Up](https://github.com/rubycdp/ferrum#clean-up)
 * [Thread safety](https://github.com/rubycdp/ferrum#thread-safety)
 * [Development](https://github.com/rubycdp/ferrum#development)
 * [Contributing](https://github.com/rubycdp/ferrum#contributing)
@@ -411,25 +412,6 @@ browser.mhtml(path: "google.mhtml") # => 87742
 ```
 
 
-## Cleaning Up
-
-#### reset
-
-Closes browser tabs opened by the `Browser` instance.
-
-```ruby
-# connect to a long-running Chrome process
-browser = Ferrum::Browser.new(url: 'http://localhost:9222')
-
-browser.go_to("https://github.com/")
-
-# clean up, lest the tab stays there hanging forever
-browser.reset
-
-browser.quit
-```
-
-
 ## Network
 
 `browser.network`
@@ -608,6 +590,50 @@ Toggles ignoring cache for each request. If true, cache will not be used.
 browser.network.cache(disable: true)
 ```
 
+
+## Downloads
+
+`browser.downloads`
+
+#### files `Array<Hash>`
+
+Returns all information about downloaded files as a `Hash`.
+
+```ruby
+browser.go_to("http://localhost/attachment.pdf")
+browser.downloads.files # => [{"frameId"=>"E3316DF1B5383D38F8ADF7485005FDE3", "guid"=>"11a68745-98ac-4d54-9b57-9f9016c268b3", "url"=>"http://localhost/attachment.pdf", "suggestedFilename"=>"attachment.pdf", "totalBytes"=>4911, "receivedBytes"=>4911, "state"=>"completed"}]
+```
+
+#### wait(timeout)
+
+Waits until the download is finished.
+
+```ruby
+browser.go_to("http://localhost/attachment.pdf")
+browser.downloads.wait
+```
+
+or
+
+```ruby
+browser.go_to("http://localhost/page")
+browser.downloads.wait { browser.at_css("#download").click }
+```
+
+#### set_behavior(\*\*options)
+
+Sets behavior in case of file to be downloaded.
+
+* options `Hash`
+  * :save_path `String` absolute path of where to store the file
+  * :behavior `Symbol` `deny | allow | allowAndName | default`, `allow` by default
+
+```ruby
+browser.go_to("https://example.com/")
+browser.downloads.set_behavior(save_path: "/tmp", behavior: :allow)
+```
+
+
 ## Proxy
 
 You can set a proxy with a `:proxy` option:
@@ -1210,6 +1236,25 @@ Accepts block, records trace and by default returns trace data from `Tracing.tra
     only one trace config can be active at a time per browser.
 
 
+## Clean Up
+
+#### reset
+
+Closes browser tabs opened by the `Browser` instance.
+
+```ruby
+# connect to a long-running Chrome process
+browser = Ferrum::Browser.new(url: 'http://localhost:9222')
+
+browser.go_to("https://github.com/")
+
+# clean up, lest the tab stays there hanging forever
+browser.reset
+
+browser.quit
+```
+
+
 ## Thread safety ##
 
 Ferrum is fully thread-safe. You can create one browser or a few as you wish and

lib/ferrum/browser.rb

@@ -20,7 +20,7 @@ class Browser
     delegate %i[go_to goto go back forward refresh reload stop wait_for_reload
                 at_css at_xpath css xpath current_url current_title url title
                 body doctype content=
-                headers cookies network
+                headers cookies network downloads
                 mouse keyboard
                 screenshot pdf mhtml viewport_size device_pixel_ratio
                 frames frame_by main_frame

lib/ferrum/downloads.rb

@@ -0,0 +1,60 @@
+# frozen_string_literal: true
+
+module Ferrum
+  class Downloads
+    VALID_BEHAVIOR = %i[deny allow allowAndName default].freeze
+
+    def initialize(page)
+      @page = page
+      @event = Event.new.tap(&:set)
+      @files = {}
+    end
+
+    def files
+      @files.values
+    end
+
+    def wait(timeout = 5)
+      @event.reset
+      yield if block_given?
+      @event.wait(timeout)
+      @event.set
+    end
+
+    def set_behavior(save_path:, behavior: :allow)
+      raise ArgumentError unless VALID_BEHAVIOR.include?(behavior.to_sym)
+      raise Error, "supply absolute path for `:save_path` option" unless Pathname.new(save_path.to_s).absolute?
+
+      @page.command("Browser.setDownloadBehavior",
+                    browserContextId: @page.context.id,
+                    downloadPath: save_path,
+                    behavior: behavior,
+                    eventsEnabled: true)
+    end
+
+    def subscribe
+      subscribe_download_will_begin
+      subscribe_download_progress
+    end
+
+    def subscribe_download_will_begin
+      @page.on("Browser.downloadWillBegin") do |params|
+        @event.reset
+        @files[params["guid"]] = params
+      end
+    end
+
+    def subscribe_download_progress
+      @page.on("Browser.downloadProgress") do |params|
+        @files[params["guid"]].merge!(params)
+
+        case params["state"]
+        when "completed", "canceled"
+          @event.set
+        else
+          @event.reset
+        end
+      end
+    end
+  end
+end

lib/ferrum/event.rb

@@ -0,0 +1,17 @@
+# frozen_string_literal: true
+
+module Ferrum
+  class Event < Concurrent::Event
+    def iteration
+      synchronize { @iteration }
+    end
+
+    def reset
+      synchronize do
+        @iteration += 1
+        @set = false if @set
+        @iteration
+      end
+    end
+  end
+end

lib/ferrum/page.rb

@@ -1,12 +1,14 @@
 # frozen_string_literal: true
 
 require "forwardable"
+require "ferrum/event"
 require "ferrum/mouse"
 require "ferrum/keyboard"
 require "ferrum/headers"
 require "ferrum/cookies"
 require "ferrum/dialog"
 require "ferrum/network"
+require "ferrum/downloads"
 require "ferrum/page/frames"
 require "ferrum/page/screenshot"
 require "ferrum/page/animation"
@@ -18,20 +20,6 @@ module Ferrum
   class Page
     GOTO_WAIT = ENV.fetch("FERRUM_GOTO_WAIT", 0.1).to_f
 
-    class Event < Concurrent::Event
-      def iteration
-        synchronize { @iteration }
-      end
-
-      def reset
-        synchronize do
-          @iteration += 1
-          @set = false if @set
-          @iteration
-        end
-      end
-    end
-
     extend Forwardable
     delegate %i[at_css at_xpath css xpath
                 current_url current_title url title body doctype content=
@@ -71,6 +59,11 @@ def reset
     # @return [Cookies]
     attr_reader :cookies
 
+    # Downloads object.
+    #
+    # @return [Downloads]
+    attr_reader :downloads
+
     def initialize(target_id, browser, proxy: nil)
       @frames = Concurrent::Map.new
       @main_frame = Frame.new(nil, self)
@@ -91,6 +84,7 @@ def initialize(target_id, browser, proxy: nil)
       @cookies = Cookies.new(self)
       @network = Network.new(self)
       @tracing = Tracing.new(self)
+      @downloads = Downloads.new(self)
 
       subscribe
       prepare_page
@@ -114,8 +108,10 @@ def go_to(url = nil)
       options = { url: combine_url!(url) }
       options.merge!(referrer: referrer) if referrer
       response = command("Page.navigate", wait: GOTO_WAIT, **options)
-      error_text = response["errorText"]
-      raise StatusError.new(options[:url], "Request to #{options[:url]} failed (#{error_text})") if error_text
+      error_text = response["errorText"] # https://cs.chromium.org/chromium/src/net/base/net_error_list.h
+      if error_text && error_text != "net::ERR_ABORTED" # Request aborted due to user action or download
+        raise StatusError.new(options[:url], "Request to #{options[:url]} failed (#{error_text})")
+      end
 
       response["frameId"]
     rescue TimeoutError
@@ -259,9 +255,9 @@ def forward
       history_navigate(delta: 1)
     end
 
-    def wait_for_reload(sec = 1)
+    def wait_for_reload(timeout = 1)
       @event.reset if @event.set?
-      @event.wait(sec)
+      @event.wait(timeout)
       @event.set
     end
 
@@ -356,6 +352,7 @@ def document_node_id
     def subscribe
       frames_subscribe
       network.subscribe
+      downloads.subscribe
 
       if @browser.options.logger
         on("Runtime.consoleAPICalled") do |params|
@@ -398,16 +395,7 @@ def prepare_page
         end
       end
 
-      if @browser.options.save_path
-        unless Pathname.new(@browser.options.save_path).absolute?
-          raise Error, "supply absolute path for `:save_path` option"
-        end
-
-        @browser.command("Browser.setDownloadBehavior",
-                         browserContextId: context.id,
-                         downloadPath: @browser.options.save_path,
-                         behavior: "allow", eventsEnabled: true)
-      end
+      downloads.set_behavior(save_path: @browser.options.save_path) if @browser.options.save_path
 
       @browser.extensions.each do |extension|
         command("Page.addScriptToEvaluateOnNewDocument", source: extension)

spec/browser_spec.rb

@@ -246,6 +246,7 @@
           skip "https://bugs.chromium.org/p/chromium/issues/detail?id=1444729" if browser.headless_new?
 
           browser.go_to("/#{filename}")
+          browser.downloads.wait
 
           expect(File.exist?("#{save_path}/#{filename}")).to be true
         ensure