zorki 0.1.20 → 0.1.22

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1e635e294bb6e73e0e57481ba79d23c603bab3ebbd73bbb4939d12f615644098
-  data.tar.gz: 876ce40814980d04a962c8002662bf7462a269fa7b6885d89c419b1a2a64c8e0
+  metadata.gz: 8e6710ae1d1737110bc8385113470b9523414c74ff3ed88e0fe507215ddaa24c
+  data.tar.gz: 27df7892036e33313229ffefef35a6407667fd3d36275bee9ff933a07178a102
 SHA512:
-  metadata.gz: 552de3b78d4bce7c18d6e0df96d3fdb4eb2b1b43e35961a64617e738510be4979453fe496a55e642329f47d2e4fc8ced52ff390263f39c010693eee4e71a9074
-  data.tar.gz: 07be9124885ef2eedf0b7433385e1a29a1c1fd33c58686530d99b7c9767784df6b1b7343c57c97157fed756c196d33125b35e621da9a7bf4737da1855a05c911
+  metadata.gz: 6147d1586fbb95a28a018139e8bcb71a1f5731a3a15c65767ab43d0f29395db98f0a18f13080aeb2cd9eb82c909db9a65931ca6100beabbc08be01c343729e92
+  data.tar.gz: 4bac8fc6d924404f1671c302c16e5eb895bef4ab9a63c03b5951b4f4c6f9e6314073468ebb5ad4bad3bda0819afcd096a53160950439e044fb55922f80c460cc

data/lib/zorki/scrapers/post_scraper.rb

@@ -5,6 +5,27 @@ require "typhoeus"
 module Zorki
   class PostScraper < Scraper
     def parse(id)
+      count = 0
+
+      until count == 2
+        puts "Retrieving ID #{id}"
+
+        begin
+          result = attempt_parse(id)
+          break
+        rescue ImageRequestZeroSize
+          # If the image is zero size, we retry
+          puts "Zero sized image found, retrying #{count}"
+          count += 1
+        end
+      end
+
+      raise ImageRequestZeroSize if count == 5
+
+      result
+    end
+
+    def attempt_parse(id)
       # Stuff we need to get from the DOM (implemented is starred):
       # - User *
       # - Text *

data/lib/zorki/scrapers/scraper.rb

@@ -172,6 +172,7 @@ module Zorki
 
     def login
       puts "Attempting to login..."
+
       # Reset the sessions so that there's nothing laying around
       # page.driver.browser.close
 
@@ -185,7 +186,10 @@ module Zorki
 
       # We don't have to login if we already are
       begin
-        return if find_field("Search", wait: 10).present?
+        if find_field("Search", wait: 10).present?
+          puts "Already logged in"
+          return
+        end
       rescue Capybara::ElementNotFound; end
 
       # Check if we're redirected to a login page, if we aren't we're already logged in
@@ -213,9 +217,10 @@ module Zorki
       # Sometimes Instagram just... doesn't let you log in
       raise "Instagram not accessible" if loop_count == 5
 
+      puts "Login successful"
       # No we don't want to save our login credentials
       begin
-        puts "Checking and clearing Save Info button..."
+        puts "Checking and clearing Save Info button"
 
         find_button("Save Info").click()
       rescue Capybara::ElementNotFound; end

data/lib/zorki/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Zorki
-  VERSION = "0.1.20"
+  VERSION = "0.1.22"
 end

data/lib/zorki.rb

@@ -46,11 +46,32 @@ module Zorki
     end
   end
 
+  class ImageRequestZeroSize < RetryableError; end
+
   define_setting :temp_storage_location, "tmp/zorki"
 
   # Get an image from a URL and save to a temp folder set in the configuration under
   # temp_storage_location
+
+  # We do this because sometimes the images are coming back sized zero
   def self.retrieve_media(url)
+    count = 0
+
+    until count == 5
+      temp_file_name = attempt_retrieve_media(url)
+
+      # If it's more than 1kb return properly
+      return temp_file_name if File.size(temp_file_name) > 100
+
+      # Delete the file since we want to retry
+      File.delete(temp_file_name)
+      count += 1
+    end
+
+    raise(ImageRequestZeroSize)
+  end
+
+  def self.attempt_retrieve_media(url)
     response = Typhoeus.get(url)
 
     # Get the file extension if it's in the file
@@ -69,6 +90,7 @@ module Zorki
     # We do this in case the folder isn't created yet, since it's a temp folder we'll just do so
     self.create_temp_storage_location
     File.binwrite(temp_file_name, response.body)
+
     temp_file_name
   end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: zorki
 version: !ruby/object:Gem::Version
-  version: 0.1.20
+  version: 0.1.22
 platform: ruby
 authors:
 - Christopher Guess
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-03-28 00:00:00.000000000 Z
+date: 2024-03-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: capybara