zorki 0.1.7 → 0.1.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 469ec1ebba03ba1d24f78b28bbd6f1b939b94db49b1e61e6e47647e129ed64c1
-  data.tar.gz: 96655c2182ac16467e581be7965f5588d59f4ea0c181085d5a5c1f7575882b02
+  metadata.gz: 1eadd7ea03af064623b2e0a3deebc32bfa424ac60aab4713b61e3db94c10ee66
+  data.tar.gz: c4cd5d7bb8148eb23fb7d5b80f08f9118a9b39f717ca395a38b1abca34a7ce70
 SHA512:
-  metadata.gz: ec36d4c67c01d9a1198d3916b28f5b4fbc87f4f084ee732a15d268027d6ad164540ea87686ecd0548145d0a85cb3d0028f74e6ddd1d228d291cae78609b655f4
-  data.tar.gz: cf1662ba6bef2b0d3cf5eeb2d879efb5f69efa265268ccf4b6b6156b1b6f440a29a4cbaf2c7dd3f76a4b25a3c1f89d1b9fd384c953cea345169ed0061afbfd54
+  metadata.gz: dcfc9a4129cf62063c34461cfb1ee119ee702a64ed892b10909ddacb4cae544e7875eed7a53355db60c67f590292be951cd515d516b75456aae281a29ea3cbc5
+  data.tar.gz: feb1ca4d372217487c02311241ae9c4379eacc82336cc91e48c7f80ba68bef3538a14b0f17fb77e254d68203c77d4dcba9559b832c6dd9eda4879426a0e19c83

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    zorki (0.1.6)
+    zorki (0.1.8)
       apparition
       capybara
       oj
@@ -59,6 +59,9 @@ GEM
     connection_pool (2.4.1)
     crass (1.0.6)
     curb (1.0.5)
+    debug (1.8.0)
+      irb (>= 1.5.0)
+      reline (>= 0.3.1)
     dotenv (2.7.6)
     drb (2.1.1)
       ruby2_keywords
@@ -162,9 +165,9 @@ GEM
     ruby-progressbar (1.13.0)
     ruby2_keywords (0.0.5)
     rubyzip (2.3.2)
-    selenium-devtools (0.119.0)
+    selenium-devtools (0.120.0)
       selenium-webdriver (~> 4.2)
-    selenium-webdriver (4.15.0)
+    selenium-webdriver (4.16.0)
       rexml (~> 3.2, >= 3.2.5)
       rubyzip (>= 1.2.2, < 3.0)
       websocket (~> 1.0)
@@ -189,6 +192,7 @@ PLATFORMS
 
 DEPENDENCIES
   curb (~> 1.0, >= 1.0.5)
+  debug
   dotenv (~> 2.7.6)
   minitest (~> 5.0)
   rack (= 3.0.8)

data/lib/zorki/scrapers/post_scraper.rb

@@ -97,7 +97,6 @@ module Zorki
 
       # This has to run last since it switches pages
       user = User.lookup([username]).first
-      page.quit
 
       {
         images: images,

data/lib/zorki/scrapers/scraper.rb

@@ -114,27 +114,32 @@ module Zorki
         #   e.attributes.has_key?("type") && e.attributes["type"].value == "application/ld+json"
         # end
 
-        elements = doc.search("script").map do |element|
-            element_json = nil
+        elements = doc.search("script").filter_map do |element|
+          parsed_element_json = nil
           begin
-            element_json = JSON.parse(element)
+            element_json = JSON.parse(element.text)
 
-            element_json = element_json["require"].first.last.first["__bbox"]["require"].first.last.last["__bbox"]["result"]["data"]["xdt_api__v1__media__shortcode__web_info"]
-          rescue StandardError => e
+            parsed_element_json = element_json["require"].first.last.first["__bbox"]["require"].first.last.last["__bbox"]["result"]["data"]["xdt_api__v1__media__shortcode__web_info"]
+          rescue StandardError
             next
           end
 
-          element_json
-        end.compact
+          parsed_element_json
+        end
 
         if elements&.empty?
-          raise ContentUnavailableError
+          raise ContentUnavailableError.new("Cannot find anything", additional_data: { page_source: page.driver.browser.page_source, elements: elements })
         end
+
         return elements
       end
 
-      raise ContentUnavailableError if response_body.nil?
+      raise ContentUnavailableError.new("Response body nil") if response_body.nil?
       Oj.load(response_body)
+    ensure
+      page.quit
+      # TRY THIS TO MAKE SURE CHROME GETS CLOSED?
+      # We may also want to not do this and make sure the same browser is reused instead for cookie purposes
     end
 
   private
@@ -167,7 +172,7 @@ module Zorki
 
     def login
       # Reset the sessions so that there's nothing laying around
-      page.quit
+      # page.driver.browser.close
 
       # Check if we're on a Instagram page already, if not visit it.
       unless page.driver.browser.current_url.include? "instagram.com"
@@ -242,6 +247,15 @@ module Zorki
       # Multiply everything and insure we get an integer back
       (number * multiplier).to_i
     end
+
+    # def reset_window
+    #   old_handle = page.driver.browser.window_handle
+    #   page.driver.browser.switch_to.new_window(:window)
+    #   new_handle = page.driver.browser.window_handle
+    #   page.driver.browser.switch_to.window(old_handle)
+    #   page.driver.browser.close
+    #   page.driver.browser.switch_to.window(new_handle)
+    # end
   end
 end
 

data/lib/zorki/scrapers/user_scraper.rb

@@ -21,6 +21,10 @@ module Zorki
       graphql_script = get_content_of_subpage_from_url("https://instagram.com/#{username}/", "?username=")
       graphql_script = graphql_script.first if graphql_script.class == Array
 
+      if graphql_script.nil?
+        graphql_script = get_content_of_subpage_from_url("https://instagram.com/#{username}/", "web_profile_info")
+      end
+
       if graphql_script.has_key?("author") && !graphql_script["author"].nil?
         user = graphql_script["author"]
 

data/lib/zorki/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Zorki
-  VERSION = "0.1.7"
+  VERSION = "0.1.9"
 end

data/lib/zorki.rb

@@ -20,8 +20,15 @@ module Zorki
   end
 
   class ContentUnavailableError < Error
-    def initialize(msg = "Zorki could not find content requested")
-      super
+    attr_reader :additional_data
+
+    def initialize(msg = "Zorki could not find content requested", additional_data: {})
+      super(msg)
+      @additional_data = additional_data
+    end
+
+    def to_honeybadger_context
+      additional_data
     end
   end
 

data/zorki.gemspec

@@ -29,8 +29,6 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
-  # Uncomment to register a new dependency of your gem
-  # spec.add_dependency "example-gem", "~> 1.0"
   spec.add_dependency "capybara" # For scraping and running browsers
   spec.add_dependency "apparition" # A Chrome driver for Capybara
   spec.add_dependency "typhoeus" # For making API requests
@@ -38,6 +36,8 @@ Gem::Specification.new do |spec|
   spec.add_dependency "selenium-webdriver" # Webdriver selenium
   spec.add_dependency "selenium-devtools" # Allow us to intercept requests
 
+  spec.add_development_dependency "debug"
+
   # For more information and examples about making a new gem, checkout our
   # guide at: https://bundler.io/guides/creating_gem.html
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: zorki
 version: !ruby/object:Gem::Version
-  version: 0.1.7
+  version: 0.1.9
 platform: ruby
 authors:
 - Christopher Guess
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-12-05 00:00:00.000000000 Z
+date: 2024-03-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: capybara
@@ -94,6 +94,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: debug
+  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'
 description:
 email:
 - cguess@gmail.com