forki 0.2.6 → 0.2.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 78986561738c2e71c7504b8d4810c790e1cefa212b97358eae17accf4b1c2131
-  data.tar.gz: 9f72cf4a6496e4c40f3d47d566c2ec9fd1096edf8e54257223a6b26d96f0c9b2
+  metadata.gz: b8c9afa0643b490f011539868cf5c6fa72a816e047e259ecb11dab00016d1ee4
+  data.tar.gz: f24cbd85f1e68dc1bbb8222b6e1c8730a0c101d2d0ee2eb0fd1748fbd276850b
 SHA512:
-  metadata.gz: a6fd3e3328b1c1c17d8d4bcab492588d88d7bcfc6feb20f1e85c5b75dfacc24b75c519d388353d733bf2ef0c6899f9c1804f82736d9bdb28971f21299159fed2
-  data.tar.gz: eb1f2608844ba87fc294d38091b6327de25e35f505ac1e873f5a56f797994de57fdf2a1e80d4781821330ff05cee15bc4f0d0fbe2f7a1b72ab7abab6806f7765
+  metadata.gz: '0579059d7a8756652705ceea98d34bac0b0217e0a0898ca891040bcb123306b9b5e9e0ce438566d6d51be9a1eb2bf21b1a12c9a369c8c5d67cb158d57067d8d0'
+  data.tar.gz: d32fc074ee987b6479c5b6076f9b1ae3d69b8fde25beaa895efefed550efb23ce33376be6945f428d0f1fd2524f9914b6d73bd44143b14474cdac77fbb89f10c

data/lib/forki/scrapers/post_scraper.rb

@@ -37,7 +37,9 @@ module Forki
       elsif post_has_image
         extract_image_post_data(graphql_objects)
       else
-        raise UnhandledContentError
+        extract_image_post_data(graphql_objects)
+
+        #raise UnhandledContentError
       end
     end
 
@@ -71,6 +73,9 @@ module Forki
         if !graphql_object.dig("node", "comet_sections", "content", "story", "attachments").nil?
           if graphql_object["node"]["comet_sections"]["content"]["story"]["attachments"].count.positive?
             return true unless graphql_object["node"]["comet_sections"]["content"]["story"]["attachments"].first.dig("styles", "attachment", "all_subattachments", "nodes")&.first&.dig("media", "image", "uri").nil?
+
+            # Another version I guess
+            return true unless graphql_object["node"]["comet_sections"]["content"]["story"]["attachments"].first.dig("styles", "attachment", "media", "large_share_image")&.dig("uri").nil?
           end
         end
 
@@ -318,7 +323,6 @@ module Forki
           feedback_object = graphql_object["node"]["comet_sections"]["feedback"]["story"]["feedback_context"]["feedback_target_with_context"]["ufi_renderer"]["feedback"]["comet_ufi_summary_and_actions_renderer"]["feedback"]
         end
 
-
         if feedback_object.has_key?("cannot_see_top_custom_reactions")
           reaction_counts = extract_reaction_counts(feedback_object["cannot_see_top_custom_reactions"]["top_reactions"])
         else
@@ -326,18 +330,28 @@ module Forki
         end
 
         id = graphql_object["node"]["post_id"]
-        num_comments = feedback_object["share_count"]["count"]
+        num_comments = feedback_object["comments_count_summary_renderer"]["feedback"]["comment_rendering_instance"]["comments"]["total_count"]
         reshare_warning = feedback_object["should_show_reshare_warning"]
 
-        if attachments.first["styles"]["attachment"].key?("all_subattachments")
+        if attachments.count.positive? && attachments.first["styles"]["attachment"]&.key?("all_subattachments")
           image_url = attachments.first["styles"]["attachment"]["all_subattachments"]["nodes"].first["media"]["image"]["uri"]
         else
-          image_url = attachments.first["styles"]["attachment"]["media"]["photo_image"]["uri"]
+          image_url = attachments.first&.dig("styles", "attachment", "media", "photo_image", "uri")
+
+          if image_url.nil?
+            image_url = attachments.first&.dig("styles", "attachment", "media", "large_share_image", "uri")
+          end
         end
 
         text = graphql_object["node"]["comet_sections"]["content"]["story"]["message"]["text"]
         profile_link = graphql_object["node"]["comet_sections"]["content"]["story"]["actors"].first["url"]
-        created_at = graphql_object["node"]["comet_sections"]["content"]["story"]["comet_sections"]["context_layout"]["story"]["comet_sections"]["metadata"].first["story"]["creation_time"]
+
+        unless graphql_object["node"]["comet_sections"].dig("content", "story", "comet_sections", "context_layout", "story", "comet_sections", "metadata").nil?
+          created_at = graphql_object["node"]["comet_sections"].dig("content", "story", "comet_sections", "context_layout", "story", "comet_sections", "metadata")&.first["story"]["creation_time"]
+        else
+          created_at = graphql_object["node"]["comet_sections"]["context_layout"]["story"]["comet_sections"]["metadata"].first["story"]["creation_time"]
+        end
+
         has_video = false
       else
         graphql_object_array.find { |graphql_object| graphql_object.key?("viewer_actor") && graphql_object.key?("display_comments") }
@@ -490,6 +504,7 @@ module Forki
       graphql_strings = find_graphql_data_strings(page.html)
 
       post_data = extract_post_data(graphql_strings)
+
       post_data[:url] = url
       user_url = post_data[:profile_link]
 

data/lib/forki/scrapers/sieves/image_sieves/image_sieve.rb.rb

@@ -4,7 +4,6 @@ class ImageSieve
   end
 
   def self.sieve_for_graphql_objects(graphql_objects)
-
     sieve = sieve_class_for_graphql_objects(graphql_objects)
     return nil if sieve.nil?
 
@@ -19,7 +18,6 @@ private
   end
 end
 
-
-Dir['./lib/forki/scrapers/sieves/image_sieves/*.rb'].each do |file|
+Dir["./lib/forki/scrapers/sieves/image_sieves/*.rb"].each do |file|
   require file unless file.end_with?("image_sieve.rb")
 end

data/lib/forki/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Forki
-  VERSION = "0.2.6"
+  VERSION = "0.2.8"
 end

data/lib/forki.rb

@@ -53,6 +53,8 @@ module Forki
   # Extract the file extension from a media URL
   # E.g. ".png" from https://scontent-atl3-2.xx.fbcdn.net/v/t39.30808-1.png?stp=dst-png_p148x148
   def self.extract_file_extension_from_url(url)
+    return nil if url.nil?
+
     stripped_url = url.split("?").first  # remove URL query params
     extension = stripped_url.split(".").last
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: forki
 version: !ruby/object:Gem::Version
-  version: 0.2.6
+  version: 0.2.8
 platform: ruby
 authors:
 - ''
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-04-04 00:00:00.000000000 Z
+date: 2024-05-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: capybara
@@ -165,7 +165,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.20
+rubygems_version: 3.5.9
 signing_key:
 specification_version: 4
 summary: A gem to scrape Facebook pages for archive purposes.