selenium_tor 1.4.0 → 1.5.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 89802b75ed87505f2f9ba8671aeb649b66db4a7fd63a9f44f695acc3b7bcce18
-  data.tar.gz: fcaa6f71fbac4a9ba4a165ab6919c1c7160fb01b0d3d79a8b2c4db55bd65dec0
+  metadata.gz: 9c45649309a0d50821238c2dc502b8e1d5e9f2137a24229cd09c4493aa45ea7d
+  data.tar.gz: 56177ff95c346118c5497bc0cfa44a1de83d3705be663596d7aefe8ab475e72e
 SHA512:
-  metadata.gz: 01fb59e8597bf62a649785f65ea8c616479384e8a18c376954981d7dedc978cb063dca1f8ce280a23dfbe1c05a0ca538e8115b3c6b4c5fd4a1c8cb56ebf173fd
-  data.tar.gz: 91cb32514aef461e29695b1e5e5470e439c8e0c407ec19229adb84b9207e7febc94cde429c235a809ad4db8cca37fb57c6f857d909b5589e408970bbbdadfb0e
+  metadata.gz: 3d8ed9f5b35b852ea189f755d33af91676cbfb3b5750506b9955653220ec5bda98303dfe89dbf2ff850bdbc538d37d26169e5a5b74ff3f10cb3bfeff04b511e9
+  data.tar.gz: 4628ebe827ab1ef4004c7c5c09d1126a2aecb5ce53f52c652221ec76da36890f5ab9bb8df46b44da331a00d6a8a5eb8b94750ef8bdf84df6849d31cc1782f56f

data/CHANGELOG.md

@@ -1,5 +1,21 @@
 ## master (unreleased)
 
+## [1.5.1] - 2024-09-02
+
+Fix load path error in LibxulPatchable module
+
+## [1.5.0] - 2024-08-31
+
+### Bug fixes
+
+* [#15](https://gitlab.com/matzfan/selenium-tor/-/issues/15)
+* [#16](https://gitlab.com/matzfan/selenium-tor/-/issues/16)
+* [#17](https://gitlab.com/matzfan/selenium-tor/-/issues/17)
+
+### New features
+
+* add ability to patch libxul.so to avoid webdriver fingerprint detection
+
 ## [1.4.0] - 2024-08-07
 
 ### Breaking changes

data/README.md

@@ -49,6 +49,19 @@ The location of the TBB is not expected to change during code execution.
 
 Tor Selenium is tested on **Linux only** right now.
 
+### Patching libxul.so
+
+A configuration option to patch the libxul.so packaged with Tor Browser is provided. This has the effect of preventing websites from fingerprinting Selenium-driven Tor Browser via a JS call to `navigator.webdriver`:
+```ruby
+Tor::Driver.libxul_patched? # is Tor Browser's libxul.so patched?
+# => false
+Tor::Driver.patch_libxul # patch libxul.so
+Tor::Driver.libxul_patched?
+# => true
+Tor::Driver.unpatch_libxul # revert the patch and restore the libxul.so packaged with Tor Browser
+```
+The patcher uses the `[bsdiff](https://www.daemonology.net/bsdiff)` package, which must be installed on your system.
+
 ## Usage
 ```ruby
 require 'selenium_tor'
@@ -63,7 +76,7 @@ A separate tor process is used for each driver. Failure to call `Driver#quit` af
 
 In addition to the regular Firefox options, a :tor_opts key may be passed to an instance of `Tor::Options` with a hash of tor options. All valid tor options are recognized - see `man tor`. For convenience, "SocksPort" and "ControlPort" options may be set using snake_case symbols - i.e. :socks_port and :control_port. Additionally, a :tor_opts timeout value may be set with the :timeout key. This overrides the default time allowed for the tor process to bootstrap (10 seconds).
 
-### Multiple driver instances (headless drivers only)
+### Multiple driver instances
 
 Running multiple tor processes requires that each uses different ports for SocksPort (and ControlPort, if used). These must be passed using the `:tor_opts` key. An example using the [Parallel gem](https://rubygems.org/gems/parallel):
 ```ruby
@@ -121,6 +134,7 @@ A number of constants are set during driver initialization based upon values fou
 Tor::TBB_DIR # path to the TBB root directory
 Tor::TBB_BROWSER_DIR # path to the 'Browser' directory in the above
 Tor::TBB_BINARY_PATH # path to the firefox binary
+Tor::TBB_TOR_BINARY_PATH # path to the bundled tor binary
 Tor::TBB_PROFILE_DIR # path to the default profile directory
 Tor::TBB_EXTENSIONS_DIR # path to the 'extensions' directory in the above
 Tor::TBB_VERSION # the version installed, e.g. "13.0.1", note: driver.capabilities.browser_version returns the Firefox version Tor Browser is based on 

data/lib/tor/driver.rb

@@ -4,6 +4,7 @@ require 'open-uri'
 require_relative '../service'
 require_relative '../options'
 require_relative '../firefox_prefs'
+require_relative 'libxul_patchable'
 require_relative 'profile'
 require_relative 'tor_process'
 
@@ -15,6 +16,8 @@ module Selenium
 
       # tor driver
       class Driver < DelegateClass(DriverDelegate)
+        extend LibxulPatchable
+
         TORRC_PATH_PREF = 'extensions.torlauncher.torrc_path'
         TORRC = 'torrc'
         BROWSER_SECURITY_LEVEL_PREF = 'browser.security_level.security_slider'
@@ -73,6 +76,7 @@ module Selenium
           @tor_process = tor_process(opts)
           @tor_process.start_tor(timeout: timeout)
         rescue Tor::TorProcess::TorProcessError => e
+          instance_variable_get(:@instance)&.quit # avoids hanging firefox.real process
           raise Error::WebDriverError, e
         end
 

data/lib/tor/libxul_checksums.yml

@@ -0,0 +1,13 @@
+---
+13.5.2:
+  unpatched_libxul: b2f8b3fd25466bd3ffa12fb34b422767b28e09577d5714d6d0c97f695dac15dc
+  patched_libxul: 7f761479c2d0307b97023455cfd7811b5749690302f54508b247720105dd0a3b
+  patch_checksum: 695f7534586c757781bd33a6dbc627cfe62d010edce20e5754fa5efff7aa80d0
+14.0a2:
+  unpatched_libxul: e0eda8db975fe315e9be32b3bf95ee62767c60ee34deac97a7163f8ab0480dc9
+  patched_libxul: ed05f9c383f4ecbce69d978aefc0625c44874193707ebe11166e714b3e2b4f64
+  patch_checksum: 0cf817f97bdbe51fba5ad61d566934c9ebdda8fce5540bc803aeca23e0ac3e8b
+14.0a3:
+  unpatched_libxul: f448fc180b547d622b969fe170028408f75493cf95be5e4c1180594daec2226b
+  patched_libxul: 337a4ef0e723069695294b37a4843126529c44e2bc4f90b1533b547100355db3
+  patch_checksum: 08dd8cab30c4416adf7ab6411e1346dce4a8b6f42e4c410adcd5bc63a71506e5

data/lib/tor/libxul_patchable.rb

@@ -0,0 +1,98 @@
+# frozen_string_literal: true
+
+require 'digest'
+require 'json'
+require 'open-uri'
+require_relative 'options' # module needs access to consts therein defined
+
+module Selenium
+  module WebDriver
+    module Tor
+      # methods to patch/unpatch libxul.so
+      module LibxulPatchable
+        class LibxulPatchableError < StandardError; end
+
+        # PATCH_REPO = 'https://gitlab.com/matzfan/keymaster/-/releases' # TODO
+        LIBXUL_CHECKSUMS = YAML.load_file(File.join(__dir__, 'libxul_checksums.yml'))[Tor::TBB_VERSION]
+        PATCH_REPO = 'https://gitlab.com/matzfan/keymaster/-/raw/main/patches/tor-browser'
+        ISSUES_URL = 'https://gitlab.com/matzfan/keymaster/-/issues'
+
+        def libxul_patched?
+          libxul_checksum = checksum_for Tor::TBB_LIBXUL
+          return true if patched_libxul_checksum_for_version == libxul_checksum
+          return false if unpatched_libxul_checksum_for_version == libxul_checksum
+
+          raise LibxulPatchableError, 'Unrecognized libxul.so'
+        end
+
+        def patch_libxul
+          return if libxul_patched?
+
+          patchfile = fetch_patchfile
+          valid? patchfile
+          FileUtils.mv Tor::TBB_LIBXUL, libxul_original # rename libxul.so
+          execute_patch patchfile
+          FileUtils.cp libxul_patched, Tor::TBB_LIBXUL
+        rescue OpenURI::HTTPError
+          raise LibxulPatchableError, "No patch for #{Tor::TBB_VERSION}, please raise an issue at #{ISSUES_URL}"
+        end
+
+        def unpatch_libxul
+          return unless libxul_patched?
+
+          FileUtils.mv libxul_original, Tor::TBB_LIBXUL
+        end
+
+        private
+
+        def libxul_original
+          "#{Tor::TBB_LIBXUL}.ORIGINAL"
+        end
+
+        def libxul_patched
+          "#{Tor::TBB_LIBXUL}.PATCHED"
+        end
+
+        def valid?(patchfile)
+          msg = "Invalid patch for #{Tor::TBB_VERSION}, please raise an issue at #{ISSUES_URL}"
+          raise LibxulPatchableError, msg unless patch_checksum_for_version == checksum_for(patchfile)
+        end
+
+        def execute_patch(patchfile)
+          raise LibxulPatchableError, 'bspatch not found, please install bsdiff' if `which bspatch`.empty?
+
+          `bspatch #{libxul_original} #{libxul_patched} #{patchfile}`
+        end
+
+        def unpatched_libxul_checksum_for_version
+          LIBXUL_CHECKSUMS['unpatched_libxul']
+        end
+
+        def patched_libxul_checksum_for_version
+          LIBXUL_CHECKSUMS['patched_libxul']
+        end
+
+        def patch_checksum_for_version
+          LIBXUL_CHECKSUMS['patch_checksum']
+        end
+
+        def checksum_for(file)
+          Digest::SHA256.file(file).hexdigest
+        end
+
+        def fetch_patchfile
+          tmp = Tempfile.new.tap(&:binmode)
+          URI.parse(patch_url).open('rb') do |f|
+            tmp.write(f.read)
+            tmp.tap(&:flush)
+          end
+          tmp.path
+        end
+
+        def patch_url
+          File.join PATCH_REPO, "#{Tor::TBB_VERSION}.patch"
+        end
+      end
+    end
+  end
+end

data/lib/tor/options.rb

@@ -15,8 +15,10 @@ module Selenium
 
         Tor::TBB_DIR = ENV.fetch('TOR_BROWSER_ROOT_DIR', nil) || DEFAULT_TBB_DIR
         Tor::TBB_BROWSER_DIR = File.join Tor::TBB_DIR, 'Browser'
+        Tor::TBB_LIBXUL = File.join Tor::TBB_BROWSER_DIR, 'libxul.so'
         Tor::TBB_BINARY_PATH = File.join Tor::TBB_BROWSER_DIR, 'firefox'
         Tor::TBB_TOR_BINARY_PATH = File.join Tor::TBB_BROWSER_DIR, *%w[TorBrowser Tor tor]
+        Tor::TBB_TOR_DATA_DIR = File.join Tor::TBB_BROWSER_DIR, *%w[TorBrowser Data Tor]
         Tor::TBB_PROFILE_DIR = File.join Tor::TBB_BROWSER_DIR, *%w[TorBrowser Data Browser profile.default]
         Tor::TBB_EXTENSIONS_DIR = File.join Tor::TBB_PROFILE_DIR, 'extensions'
         Tor::TBB_VERSION = JSON.parse(File.read(File.join(Tor::TBB_BROWSER_DIR, 'tbb_version.json')))['version']

data/lib/tor/torrc.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require_relative 'options' # for Tor::TBB_TOR_BINARY_PATH
+require_relative 'options'
 
 module Selenium
   module WebDriver
@@ -36,7 +36,13 @@ module Selenium
         private
 
         def write_default_config
-          write_to_config DEFAULT_PORTS.merge('DataDirectory' => @data_dir)
+          write_to_config DEFAULT_PORTS.merge(default_config)
+        end
+
+        def default_config
+          { 'DataDirectory' => @data_dir,
+            'GeoIPFile' => File.join(TBB_TOR_DATA_DIR, 'geoip'),
+            'GeoIPv6File' => File.join(TBB_TOR_DATA_DIR, 'geoip6') }
         end
 
         def validate_torrc_options(hash)

data/lib/tor/version.rb

@@ -3,7 +3,7 @@
 module Selenium
   module WebDriver
     module Tor
-      VERSION = '1.4.0'
+      VERSION = '1.5.1'
     end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: selenium_tor
 version: !ruby/object:Gem::Version
-  version: 1.4.0
+  version: 1.5.1
 platform: ruby
 authors:
 - MatzFan
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-08-07 00:00:00.000000000 Z
+date: 2024-09-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: selenium-webdriver
@@ -47,6 +47,8 @@ files:
 - lib/selenium_tor.rb
 - lib/service.rb
 - lib/tor/driver.rb
+- lib/tor/libxul_checksums.yml
+- lib/tor/libxul_patchable.rb
 - lib/tor/options.rb
 - lib/tor/profile.rb
 - lib/tor/system_tor.rb
@@ -56,6 +58,7 @@ files:
 - lib/tor/version.rb
 - selenium_tor.gemspec
 - sig/tor.rbs
+- tmp/.placeholder
 homepage: https://gitlab.com/matzfan/selenium-tor
 licenses:
 - MIT