scrape_creators 0.4.0 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 41069945ebf877cbd439c8bfbb318ba0114d4e9df6275aabacef16867417a7b4
-  data.tar.gz: 24d8743a67a698cfc97f974015a8ff30ab33254b8dd155e96f1d4b0283e9d9c0
+  metadata.gz: c214fa7c8b7b56a2483d3432420003745f73747e8391100312168466f9f03c7b
+  data.tar.gz: 0ec20deecab206e3ba0f54707abbfee7e624485d5f7954311bdb34552b207f40
 SHA512:
-  metadata.gz: fdab6ab8877d97093743a3e52d3daa17bf33ac1c4b3a461b6ea85957e83bff213b9e27adbaa878b36e9af15858f014334aceda898beae6cb9d498d15e56e2d1f
-  data.tar.gz: ddeaf8dc9f781648485b348a3ccaeb660a2dfe47a611e37a6c0cd9283fae66179a91521c11be731faf698b8cf22683cf5a8b8b3862b198d1c148f20641011bda
+  metadata.gz: f15f5722980fca1ccb48a32e1d62927324ae944c81132cc3210f2a35d12209033ef244804c988a9f4b3924c28f78c9ddca63bf66e29dd0e24e9477195ad95aed
+  data.tar.gz: 20aadfbd40d3362a8d6fbbe52223fb1bb4baafdaec99406e9a9bbe477e8ab1fd40b29bf7279fdfc813a88c3126237a5bd598bf7ccf2db5c0adb133e7c79d4c66

data/README.md

@@ -50,6 +50,16 @@ info = scraper.post("https://www.instagram.com/p/DKSMEpKRd6h/", download_media:
 
 ```ruby
 comments = scraper.comments("https://www.instagram.com/p/DKSMEpKRd6h/")
+
+page = scraper.comments_page("https://www.instagram.com/p/DKSMEpKRd6h/")
+page[:comments]
+page[:cursor]
+page[:has_more]
+
+next_page = scraper.comments_page(
+  "https://www.instagram.com/p/DKSMEpKRd6h/",
+  cursor: page[:cursor]
+)
 ```
 
 ## License

data/lib/scrape_creators/client.rb

@@ -73,12 +73,31 @@ module ScrapeCreators
     end
 
     def comments(url_or_code, options = {})
+      comments_page(url_or_code, options)[:comments]
+    end
+
+    def comments_page(url_or_code, options = {})
       source = (options[:source] || 'instagram').to_s
       url = normalize_url(url_or_code)
-      params = { url: url }.merge(options.reject { |k, _| k.to_s == 'source' })
-      comments_url = comments_url_for(source: source)
-      res = get(comments_url, params)
-      res.is_a?(Hash) ? (res["comments"] || []) : []
+      extra = options.reject { |k, _| %w[source cursor continuationToken continuation_token].include?(k.to_s) }
+      params = { url: url }.merge(extra)
+      cursor = options[:cursor] || options['cursor'] || options[:continuationToken] || options['continuationToken'] || options[:continuation_token]
+      if cursor && !cursor.to_s.empty?
+        if source == YOUTUBE
+          params[:continuationToken] = cursor
+        else
+          params[:cursor] = cursor
+        end
+      end
+
+      res = get(comments_url_for(source: source), params)
+      comments = res.is_a?(Hash) ? (res['comments'] || []) : []
+      next_cursor = next_comments_cursor(res, source)
+      {
+        comments: comments,
+        cursor: next_cursor,
+        has_more: comments_has_more?(res, source, next_cursor)
+      }
     end
 
     def get(endpoint, params = {}, options = {})
@@ -121,6 +140,29 @@ module ScrapeCreators
 
     private
 
+    def next_comments_cursor(res, source)
+      return nil unless res.is_a?(Hash)
+
+      cursor = if source == YOUTUBE
+                 res['continuationToken']
+               else
+                 res['cursor']
+               end
+      return nil if cursor.nil? || cursor.to_s.empty?
+
+      cursor
+    end
+
+    def comments_has_more?(res, source, next_cursor)
+      return false unless res.is_a?(Hash)
+
+      if source == TIKTOK
+        res['has_more'].to_i == 1
+      else
+        !next_cursor.nil?
+      end
+    end
+
     def normalize_url(url_or_code)
       str = url_or_code.to_s.strip
       if str.start_with?('http://', 'https://')

data/lib/scrape_creators/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ScrapeCreators
-  VERSION = "0.4.0"
+  VERSION = "0.5.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: scrape_creators
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.5.0
 platform: ruby
 authors:
 - swlkr