zorki 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 384abb984483d4f38da44e77b7cd359e7d3aadea7c96765bc5b2837c3e79e99d
-  data.tar.gz: 48bf93b460b4c947cc9bf47f97dc469de124686cb763eccfa8ef7ef00e11f2b6
+  metadata.gz: e866c6873fc604f1720faeaf9425ff0557a6ef9947e9a9e4f657cc255a8d4665
+  data.tar.gz: e97fa8e84dd02edc9dd47beb9d66fe2b3cab4704297f16005dc09adf68eeb2e4
 SHA512:
-  metadata.gz: e70b44d624a51df5a7ca6d9b6078cf3b44c8da1c07291aee60e4d554e2bc5705cfab3cea112ccbc79f6354d1092dca90330b7697f4e19606034857de361a08e3
-  data.tar.gz: b819d82e750f72cb55ab34b2a7b8332c70828220857501c22315480e644c2b88d5732f3b4074d7d240015a70dadace213b4a1e388145a6d50d544ef36b20b655
+  metadata.gz: f5d6f36fede35c5d54289f6f7a41098e5374f74e8bbbf18ebd66486e4c049fdd064e063a7787000ed5997a9460496d9c5310795585a9098b1bfcbf891c7277e6
+  data.tar.gz: 8a79812eb8d312fef165868bbaad85cc4a7cd0f67ed04fb3e7cb0246e417ec5eefb89a54d3eec7ff78b3a3b38a9df89ae8c82423ea7fbb4ab04d160c86b397f5

data/Gemfile

@@ -15,3 +15,5 @@ gem "rubocop-rails", "~> 2.19.1", require: false # Rails specific styles
 gem "rubocop-rails_config"
 
 gem "dotenv", "~> 2.7.6"
+
+gem "curb", "~> 1.0", ">= 1.0.5"

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    zorki (0.1.0)
+    zorki (0.1.1)
       apparition
       capybara
       oj
@@ -48,6 +48,7 @@ GEM
       xpath (~> 3.2)
     concurrent-ruby (1.2.2)
     crass (1.0.6)
+    curb (1.0.5)
     dotenv (2.7.6)
     erubi (1.12.0)
     ethon (0.16.0)
@@ -150,6 +151,7 @@ PLATFORMS
   arm64-darwin-22
 
 DEPENDENCIES
+  curb (~> 1.0, >= 1.0.5)
   dotenv (~> 2.7.6)
   minitest (~> 5.0)
   rake (~> 13.0)

data/lib/zorki/scrapers/post_scraper.rb

@@ -45,15 +45,17 @@ module Zorki
         end.first["userInteractionCount"]
 
         unless graphql_object["video"].empty?
-          video = graphql_object["video"].first["contentUrl"]
-          video_preview_image = graphql_object["video"].first["thumbnailUrl"]
+          video_url = graphql_object["video"].first["contentUrl"]
+          video = Zorki.retrieve_media(video_url)
+
+          video_preview_image_url = graphql_object["video"].first["thumbnailUrl"]
+          video_preview_image = Zorki.retrieve_media(video_preview_image_url)
         end
       else
         # We need to see if this is a single image post or a slideshow. We do that
         # by looking for a single image, if it's not there, we assume the alternative.
         graphql_object = graphql_object["data"]["xdt_api__v1__media__shortcode__web_info"]
 
-
         unless graphql_object["items"][0].has_key?("video_versions") && !graphql_object["items"][0]["video_versions"].nil?
           # Check if there is a slideshow or not
           unless graphql_object["items"][0].has_key?("carousel_media") && !graphql_object["items"][0]["carousel_media"].nil?

data/lib/zorki/scrapers/scraper.rb

@@ -7,6 +7,7 @@ require "selenium-webdriver"
 require "logger"
 require "debug"
 require "securerandom"
+require "selenium/webdriver/remote/http/curb"
 
 # 2022-06-07 14:15:23 WARN Selenium [DEPRECATION] [:browser_options] :options as a parameter for driver initialization is deprecated. Use :capabilities with an Array of value capabilities/options if necessary instead.
 
@@ -16,13 +17,14 @@ options.add_argument("--no-sandbox")
 options.add_argument("--disable-dev-shm-usage")
 options.add_argument("–-disable-blink-features=AutomationControlled")
 options.add_argument("--disable-extensions")
+options.add_argument("--enable-features=NetworkService,NetworkServiceInProcess")
 options.add_argument("user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 13_3_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36")
 options.add_preference "password_manager_enabled", false
 options.add_argument("--user-data-dir=/tmp/tarun_zorki_#{SecureRandom.uuid}")
 
 Capybara.register_driver :selenium_zorki do |app|
-  client = Selenium::WebDriver::Remote::Http::Default.new
-  client.read_timeout = 60  # Don't wait 60 seconds to return Net::ReadTimeoutError. We'll retry through Hypatia after 10 seconds
+  client = Selenium::WebDriver::Remote::Http::Curb.new
+  # client.read_timeout = 60  # Don't wait 60 seconds to return Net::ReadTimeoutError. We'll retry through Hypatia after 10 seconds
   Capybara::Selenium::Driver.new(app, browser: :chrome, options: options, http_client: client)
 end
 
@@ -94,7 +96,7 @@ module Zorki
       end
 
       # Now that the intercept is set up, we visit the page we want
-      visit(url)
+      page.driver.browser.navigate.to(url)
       # We wait until the correct intercept is processed or we've waited 60 seconds
       start_time = Time.now
       # puts "Waiting.... #{url}"
@@ -134,14 +136,16 @@ module Zorki
       options.add_argument("--disable-dev-shm-usage")
       options.add_argument("–-disable-blink-features=AutomationControlled")
       options.add_argument("--disable-extensions")
+      options.add_argument("--enable-features=NetworkService,NetworkServiceInProcess")
+
       options.add_argument("user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 13_3_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36")
       options.add_preference "password_manager_enabled", false
       options.add_argument("--user-data-dir=/tmp/tarun_zorki_#{SecureRandom.uuid}")
       # options.add_argument("--user-data-dir=/tmp/tarun")
 
       Capybara.register_driver :selenium do |app|
-        client = Selenium::WebDriver::Remote::Http::Default.new
-        client.read_timeout = 60  # Don't wait 60 seconds to return Net::ReadTimeoutError. We'll retry through Hypatia after 10 seconds
+        client = Selenium::WebDriver::Remote::Http::Curb.new
+        # client.read_timeout = 60  # Don't wait 60 seconds to return Net::ReadTimeoutError. We'll retry through Hypatia after 10 seconds
         Capybara::Selenium::Driver.new(app, browser: :chrome, options: options, http_client: client)
       end
 
@@ -153,7 +157,12 @@ module Zorki
       page.quit
 
       # Check if we're on a Instagram page already, if not visit it.
-      visit ("https://instagram.com") unless page.driver.browser.current_url.include? "instagram.com"
+      unless page.driver.browser.current_url.include? "instagram.com"
+        # There seems to be a bug in the Linux ARM64 version of chromedriver where this will properly
+        # navigate but then timeout, crashing it all up. So instead we check and raise the error when
+        # that then fails again.
+        page.driver.browser.navigate.to("https://instagram.com")
+      end
 
       # We don't have to login if we already are
       begin

data/lib/zorki/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Zorki
-  VERSION = "0.1.1"
+  VERSION = "0.1.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: zorki
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - Christopher Guess
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-05-23 00:00:00.000000000 Z
+date: 2023-05-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: capybara