zorki 0.1.22 → 0.1.24

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8e6710ae1d1737110bc8385113470b9523414c74ff3ed88e0fe507215ddaa24c
-  data.tar.gz: 27df7892036e33313229ffefef35a6407667fd3d36275bee9ff933a07178a102
+  metadata.gz: fa95bb5ca131ca6b7faed2aab200329579b77012cb079da75a0ad90a60daa5bd
+  data.tar.gz: 82eb0cc29af2cfaeafa8774e027904959f953a50faa03d71dbcbeba9595ac520
 SHA512:
-  metadata.gz: 6147d1586fbb95a28a018139e8bcb71a1f5731a3a15c65767ab43d0f29395db98f0a18f13080aeb2cd9eb82c909db9a65931ca6100beabbc08be01c343729e92
-  data.tar.gz: 4bac8fc6d924404f1671c302c16e5eb895bef4ab9a63c03b5951b4f4c6f9e6314073468ebb5ad4bad3bda0819afcd096a53160950439e044fb55922f80c460cc
+  metadata.gz: 127638ce83ed09be71f194ba3e5dc269374890a1bd89874c8f158896a7664d41724698a258916f63e373b1c6f3dd3b4d315fac49a15e17ff457035ec4d345120
+  data.tar.gz: 105b7e148774a82640ed48bffe46b21d941ce0a18987f59ef0e79a3a058077fbd9dda651811bbc421ff9fcc8323de152b2ac5afbff0e5b9d4e5c65d27f5ac85c

data/lib/zorki/monkeypatch.rb

@@ -41,7 +41,7 @@ module SeleniumMonkeypatch
       data[:sessionId] = @session_id if @session_id
       message = @ws.send_cmd(**data)
       if message.nil? == false && message["error"] && (method != "Fetch.continueRequest")
-        raise Error::WebDriverError, error_message(message["error"])
+        raise Selenium::WebDriver::Error::WebDriverError, error_message(message["error"])
       end
 
       message

data/lib/zorki/scrapers/post_scraper.rb

@@ -23,6 +23,9 @@ module Zorki
       raise ImageRequestZeroSize if count == 5
 
       result
+    ensure
+      page.quit
+      # Make sure it's quit? I'm not sure we really want to do this outside of testing.
     end
 
     def attempt_parse(id)
@@ -44,6 +47,7 @@ module Zorki
         "data,xdt_api__v1__media__shortcode__web_info,items"
       )
 
+
       graphql_object = graphql_object.first if graphql_object.kind_of?(Array)
 
       # For pages that have been marked misinfo the structure is very different than not
@@ -61,6 +65,7 @@ module Zorki
         text = graphql_object["articleBody"]
         username = graphql_object["author"]["identifier"]["value"]
         # 2021-04-01T17:07:10-07:00
+
         date = DateTime.strptime(graphql_object["dateCreated"], "%Y-%m-%dT%H:%M:%S%z")
         interactions = graphql_object["interactionStatistic"]
         number_of_likes = interactions.select do |x|

data/lib/zorki/scrapers/scraper.rb

@@ -72,11 +72,14 @@ module Zorki
 
         continue.call(request) do |response|
           # Check if not a CORS prefetch and finish up if not
-          if !response.body.empty? && response.body
+          if !response.body&.empty? && response.body
             check_passed = true
+
             unless additional_search_parameters.nil?
               body_to_check = Oj.load(response.body)
 
+              debugger if body_to_check.include?("jokoy.komi.io")
+
               search_parameters = additional_search_parameters.split(",")
               search_parameters.each_with_index do |key, index|
                 break if body_to_check.nil?
@@ -119,7 +122,17 @@ module Zorki
           begin
             element_json = JSON.parse(element.text)
 
-            parsed_element_json = element_json["require"].first.last.first["__bbox"]["require"].first.last.last["__bbox"]["result"]["data"]["xdt_api__v1__media__shortcode__web_info"]
+            if element.text.include?("jokoy.komi.io")
+              debugger
+              # if element_json["require"].first.last.first["__bbox"].key?("require")
+
+              #   element_json["require"].first.last.first["__bbox"]["require"].each do |x|
+              #     debugger if x.to_s.include?("Si mulut pelaut")
+              #   end
+              # end
+            end
+
+            parsed_element_json = element_json["require"].last.last.first["__bbox"]["require"].first.last.last["__bbox"]["result"]["data"]["xdt_api__v1__media__shortcode__web_info"]
           rescue StandardError
             next
           end
@@ -137,9 +150,10 @@ module Zorki
       raise ContentUnavailableError.new("Response body nil") if response_body.nil?
       Oj.load(response_body)
     ensure
-      page.quit
+      # 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
+      # NOW wer'e trying this 2024-05-28
     end
 
   private

data/lib/zorki/scrapers/user_scraper.rb

@@ -18,7 +18,7 @@ module Zorki
       # - *Profile image
       login
 
-      graphql_script = get_content_of_subpage_from_url("https://instagram.com/#{username}/", "?username=")
+      graphql_script = get_content_of_subpage_from_url("https://instagram.com/#{username}/", "graphql", "data,user,full_name")
       graphql_script = graphql_script.first if graphql_script.class == Array
 
       if graphql_script.nil?
@@ -62,13 +62,13 @@ module Zorki
         scraped_username = user["username"]
         raise Zorki::Error unless username == scraped_username
 
-        profile_image_url = user["profile_pic_url_hd"]
+        profile_image_url = user["hd_profile_pic_url_info"]["url"]
         {
           name: user["full_name"],
           username: username,
-          number_of_posts: user["edge_owner_to_timeline_media"]["count"],
-          number_of_followers: user["edge_followed_by"]["count"],
-          number_of_following: user["edge_follow"]["count"],
+          number_of_posts: user["media_count"],
+          number_of_followers: user["follower_count"],
+          number_of_following: user["following_count"],
           verified: user["is_verified"],
           profile: user["biography"],
           profile_link: user["external_url"],
@@ -76,6 +76,8 @@ module Zorki
           profile_image_url: profile_image_url
         }
       end
+    rescue Zorki::ContentUnavailableError
+      raise Zorki::UserScrapingError.new("Zorki could not find user #{username}", additional_data: { username: username })
     end
   end
 end

data/lib/zorki/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Zorki
-  VERSION = "0.1.22"
+  VERSION = "0.1.24"
 end

data/lib/zorki.rb

@@ -32,6 +32,17 @@ module Zorki
     end
   end
 
+  class UserScrapingError < Error
+    def initialize(msg = "Zorki encountered an error scraping a user", additional_data: {})
+      super(msg)
+      @additional_data = additional_data
+    end
+
+    def to_honeybadger_context
+      additional_data
+    end
+  end
+
   class RetryableError < Error; end
 
   class ImageRequestTimedOutError < RetryableError

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: zorki
 version: !ruby/object:Gem::Version
-  version: 0.1.22
+  version: 0.1.24
 platform: ruby
 authors:
 - Christopher Guess
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-03-29 00:00:00.000000000 Z
+date: 2024-06-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: capybara