gramscraper 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: bb199df60b20ff966719255379c5ad733e0d0620
+  data.tar.gz: a8e8eb0124fab7bf5546a88daec57a9c50878a42
+SHA512:
+  metadata.gz: 19b98973b231b04e86480f54c6dd7ae1b43b301d548331231cec5ca93cabba3792b8f8a6a24d00a80a8e78331b4f29e8801cabe8318a1d32dcc704de79ae2fa7
+  data.tar.gz: afd47a211e4292d5bc1239553682a2ce6d50c51a896b637e4f45af3b13f9acb70fee4acef35d7e4598eb6cbd19e229c45b9962db7436f4595f8278ec6ebcc4ab

data/lib/gramscraper.rb

@@ -0,0 +1,56 @@
+require 'httparty'
+
+class Gramscraper
+    
+    def self.scrape(username)
+        # Base URL for instagram media
+        base_url = "https://www.instagram.com/#{username}/media"
+
+        # Initialise the url (without max_id token)
+        url = base_url
+
+        # Initialise instagram array
+        instagram = Array.new
+
+        while true    
+            # Use HTTParty to retrieve the JSON response
+            page = HTTParty.get(url).parsed_response
+
+            # Reset last_id
+            last_id = ""
+            
+            page["items"].each do |page_item|
+
+                # Post ID
+                last_id = page_item["id"]
+
+                # Image Caption
+                caption = page_item["caption"]["text"] unless page_item["caption"].nil?
+
+                # Get images in every resolution available
+                thumbnail = page_item["images"]["thumbnail"]["url"] unless page_item["images"].nil?
+                low_resolution = page_item["images"]["low_resolution"]["url"] unless page_item["images"].nil?
+                standard_resolution = page_item["images"]["standard_resolution"]["url"] unless page_item["images"].nil?
+
+                # Copy data to hash
+                instagram_item = {
+                    :last_id => last_id, :caption => caption, :thumbnail => thumbnail, :low_resolution => low_resolution, :standard_resolution => standard_resolution,
+                }
+
+                # Add instagram item hash to array
+                instagram << instagram_item
+            end
+
+            # If there are more photos to scraper, capture the last_id and use it as token to ?max_id=
+            if page["more_available"]==true
+                next_page_token = "/?max_id=#{last_id}"     # e.g. /?max_id=1537732482693479519_54429723
+                url = base_url + next_page_token
+            
+            # Else there are no more photos so end the loop
+            else
+                break
+            end
+        end
+        instagram
+    end
+end

metadata

@@ -0,0 +1,45 @@
+--- !ruby/object:Gem::Specification
+name: gramscraper
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Glenn Dimaliwat
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2017-10-11 00:00:00.000000000 Z
+dependencies: []
+description: A simple instagram scraping gem which retrieves all your photos (thumbnails,
+  low res, standard res) in instagram with image caption
+email: glenn.dimaliwat@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/gramscraper.rb
+homepage: http://rubygems.org/gems/gramscraper
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.11
+signing_key: 
+specification_version: 4
+summary: Instagram Photo Scraper
+test_files: []