bandcamp-discover 0.1.6 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9fc34d8854761f38e20c75aa23bb7b4be9ce47fe163720be9f6b0d39f4b9de2f
-  data.tar.gz: 134e62a2644a9411bec1d7049ff741cfde2d70847eddab58efbbd75c7e01f564
+  metadata.gz: a65e9bf97cd9ca459ed51bfebb55d81262de863b6e291187d6b41d004ae2e863
+  data.tar.gz: b8bd036e56d9276480966cdabb0ef49eda334d325559cd41cde9cf54c3b7e0d8
 SHA512:
-  metadata.gz: b198b2a4330308e1d9cb887132ec9d78f083e2de53279088a4677972109e97f97e19cfbc4692f56b2e38098c2d22f8d60eabc726b2d89954bf89d54f9edc726e
-  data.tar.gz: 4feb458ce7370f4b7fae724a451723cc59ca778c1b420ae1712b491f06dcde89de6eef607c1eae832ceeb4a57390a1957431f9a19d3620e903dbac64aef5909f
+  metadata.gz: c2ef36b3ff546e648f9029da0e42cc4d7fbaced58112156788f30255bbf3ff595448030d827e608fb5ff596d79b3734394de734ca983a6397341a45c6015c1a5
+  data.tar.gz: 622f759d307cf57357b278c77f2310f1917281a459e6b15856c98811be1926a9344556cf08f4681b80cddc9632239192217d5c67d3184251da001386a25a1bb8

data/Gemfile.lock

@@ -0,0 +1,110 @@
+PATH
+  remote: .
+  specs:
+    bandcamp-discover (0.1.7)
+      async
+      base64
+      concurrent-ruby
+      gli (~> 2.21.5)
+      logger
+      ostruct
+      playwright-ruby-client
+      sqlite3
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    ast (2.4.2)
+    async (2.15.3)
+      console (~> 1.26)
+      fiber-annotation
+      io-event (~> 1.6, >= 1.6.5)
+    base64 (0.2.0)
+    concurrent-ruby (1.3.5)
+    console (1.27.0)
+      fiber-annotation
+      fiber-local (~> 1.1)
+      json
+    fiber-annotation (0.2.0)
+    fiber-local (1.1.0)
+      fiber-storage
+    fiber-storage (1.0.0)
+    gli (2.21.5)
+    io-event (1.6.5)
+    json (2.7.2)
+    language_server-protocol (3.17.0.3)
+    lint_roller (1.1.0)
+    logger (1.7.0)
+    mime-types (3.7.0)
+      logger
+      mime-types-data (~> 3.2025, >= 3.2025.0507)
+    mime-types-data (3.2025.0729)
+    mini_portile2 (2.8.7)
+    minitest (5.24.1)
+    ostruct (0.6.1)
+    parallel (1.25.1)
+    parser (3.3.4.0)
+      ast (~> 2.4.1)
+      racc
+    playwright-ruby-client (1.54.0)
+      concurrent-ruby (>= 1.1.6)
+      mime-types (>= 3.0)
+    psych (5.1.2)
+      stringio
+    racc (1.8.1)
+    rainbow (3.1.1)
+    rake (13.2.1)
+    rdoc (6.7.0)
+      psych (>= 4.0.0)
+    regexp_parser (2.9.2)
+    rexml (3.3.4)
+      strscan
+    rubocop (1.64.1)
+      json (~> 2.3)
+      language_server-protocol (>= 3.17.0)
+      parallel (~> 1.10)
+      parser (>= 3.3.0.2)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 1.8, < 3.0)
+      rexml (>= 3.2.5, < 4.0)
+      rubocop-ast (>= 1.31.1, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 2.4.0, < 3.0)
+    rubocop-ast (1.31.3)
+      parser (>= 3.3.1.0)
+    rubocop-performance (1.21.1)
+      rubocop (>= 1.48.1, < 2.0)
+      rubocop-ast (>= 1.31.1, < 2.0)
+    ruby-progressbar (1.13.0)
+    sqlite3 (2.5.0)
+      mini_portile2 (~> 2.8.0)
+    sqlite3 (2.5.0-arm64-darwin)
+    standard (1.39.2)
+      language_server-protocol (~> 3.17.0.2)
+      lint_roller (~> 1.0)
+      rubocop (~> 1.64.0)
+      standard-custom (~> 1.0.0)
+      standard-performance (~> 1.4)
+    standard-custom (1.0.2)
+      lint_roller (~> 1.0)
+      rubocop (~> 1.50)
+    standard-performance (1.4.0)
+      lint_roller (~> 1.1)
+      rubocop-performance (~> 1.21.0)
+    stringio (3.1.1)
+    strscan (3.1.0)
+    unicode-display_width (2.5.0)
+
+PLATFORMS
+  arm64-darwin-22
+  ruby
+
+DEPENDENCIES
+  bandcamp-discover!
+  minitest
+  rake
+  rdoc
+  standard
+
+BUNDLED WITH
+   2.5.9

data/lib/bandcamp-discover/analyzer.rb

@@ -0,0 +1,30 @@
+module BandcampDiscover
+  class Analyzer
+    def initialize(description)
+      @description = description
+    end
+
+    def label?
+      if defined?(OpenRouter) && !!OpenRouter.configuration.access_token
+        response = OpenRouter::Client.new.complete(
+          [
+            { role: "system", content: "You are given a description that could or could not be that of a record label. Analyze and answer with true or false only. Be critical: Individuals and bands are not labels, but collectives can be labels." },
+            { role: "user", content: @description }
+          ],
+          model: [
+            "mistralai/mistral-small-3.2-24b-instruct:free"
+          ],
+          extras: {
+            response_format: {
+              type: "json_object"
+            }
+          }
+        )
+
+        JSON.parse(response["choices"][0]["message"]["content"])["answer"]&.downcase == "true"
+      else
+        @description.match? /label|platform|records/i
+      end
+    end
+  end
+end

data/lib/bandcamp-discover/scrapers/label.rb

@@ -1,5 +1,6 @@
 require_relative "./base"
 require_relative "./music"
+require_relative "../analyzer"
 
 module BandcampDiscover
   module Scrapers
@@ -15,7 +16,7 @@ module BandcampDiscover
           name = band_name_location_container.query_selector(".title").inner_text
           location = band_name_location_container.query_selector(".location").inner_text
 
-          if force || bio_text&.inner_html =~ /label|platform|records/i
+          if force || Analyzer.new(bio_text&.inner_html).label?
             return Sync do
               music_tags = Scrapers::Music.new(url: "#{@url}/music", browser: @browser, max_tasks: @max_tasks).scrape
 

data/lib/bandcamp-discover/scrapers/music.rb

@@ -23,7 +23,7 @@ module BandcampDiscover
 
           album_tags = album_links.take(20).map do |album_link|
             semaphore.async do
-              url = "#{@base_url}#{album_link[:href]}"
+              url = album_link[:href].start_with?("https://") ? album_link[:href] : "#{@base_url}#{album_link[:href]}"
               puts "starting to scrape #{url}"
 
               tags = Scrapers::Album.new(url: url, browser: @browser).scrape

data/lib/bandcamp-discover/version.rb

@@ -1,3 +1,3 @@
 module BandcampDiscover
-  VERSION = "0.1.6"
+  VERSION = "0.2.0"
 end

data/lib/bandcamp-discover.rb

@@ -1,7 +1,7 @@
 require 'async'
 require 'bandcamp-discover/version.rb'
+require 'bandcamp-discover/analyzer.rb'
 require 'bandcamp-discover/scrapers/discover.rb'
 
 # Add requires for other files you add to your project here, so
 # you just need to require this one file in your bin file
-

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: bandcamp-discover
 version: !ruby/object:Gem::Version
-  version: 0.1.6
+  version: 0.2.0
 platform: ruby
 authors:
 - Julian RUbisch
 bindir: bin
 cert_chain: []
-date: 2025-03-02 00:00:00.000000000 Z
+date: 2025-08-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -187,12 +187,14 @@ extra_rdoc_files:
 files:
 - ".gitignore"
 - Gemfile
+- Gemfile.lock
 - README.rdoc
 - Rakefile
 - bandcamp-discover.gemspec
 - bandcamp-discover.rdoc
 - bin/bandcamp-discover
 - lib/bandcamp-discover.rb
+- lib/bandcamp-discover/analyzer.rb
 - lib/bandcamp-discover/scrapers/album.rb
 - lib/bandcamp-discover/scrapers/base.rb
 - lib/bandcamp-discover/scrapers/discover.rb