youtube-captions 0.0.3

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 15c3c25edd3842b8c1e7ca12a867806c80ec2457a02a590deb67a43b3da80e39
+  data.tar.gz: 6e90375916db90e5e398e2c7ebbbe4b92b9ceed87e39fff268b20d5331ef4067
+SHA512:
+  metadata.gz: 9f57ea785e6bc8300557bbba7e82dfa927940f81b511abf4f3ef8ca7aaa2a71f9664e8ce8f04ab67281c90fecd8d7cb174e94b1ada9be7afcf8a16053b978c18
+  data.tar.gz: 78dfd88bf33fd9e403347b7aacfcb800b4a7c225541e3772b1ce1530b9e01db323b2ae9a7084b9b672220112a36fdd641d5057bfce6b4db6e6795375fd367cea

data/lib/youtube-captions.rb

@@ -0,0 +1,44 @@
+require 'cgi'
+require 'httparty'
+
+class YoutubeCaptions
+  include HTTParty
+
+  attr_reader :id, :lang
+  def initialize(id:, lang: nil)
+    @id = id
+    @lang = lang
+  end
+
+  TRANSLATABLE_REGEX = /({"captionTracks":.*"isTranslatable":(true|false)}\])/
+
+  def call
+    youtube_html = self.class.get("https://www.youtube.com/watch?v=#{id}")
+    match_data = youtube_html.match(TRANSLATABLE_REGEX)
+    raise StandardError.new("There are no captions") unless match_data
+
+    caption_tracks = JSON.parse("#{match_data[1]}}")["captionTracks"]
+    if lang.present?
+      subtitle = caption_tracks.find {|json| json["vssId"] == ".#{lang}"} || caption_tracks.find {|json| json["vssId"] == "a.#{lang}"}
+      if !subtitle || (subtitle && !subtitle["baseUrl"])
+        raise ArgumentError.new("Lang no available")
+      end
+    else
+      subtitle = caption_tracks.find {|json| json["vssId"] == ".en"} || caption_tracks.find {|json| json["vssId"] == "a.en"}
+      subtitle = caption_tracks.first unless subtitle
+    end
+
+    transcript_html = self.class.get(subtitle["baseUrl"])
+    transcript_tags = transcript_html.to_s.gsub('<?xml version="1.0" encoding="utf-8" ?><transcript>', '').gsub('</transcript>', '').split('</text>').select {|line| line && line.strip}
+
+    transcript_parts = transcript_tags.map do |transcript_tag|
+      encoded_transcript = transcript_tag.gsub(/<text.+>/, '')
+                                         .gsub("/&amp;/gi", '&')
+                                         .gsub("/<\/?[^>]+(>|$)/g", '')
+                                         .gsub(/&amp;#(\d+);/) { [$1.to_i].pack('U*') }
+      CGI.unescapeHTML(encoded_transcript)
+    end
+
+    transcript_parts.join(" ")
+  end
+end

metadata

@@ -0,0 +1,56 @@
+--- !ruby/object:Gem::Specification
+name: youtube-captions
+version: !ruby/object:Gem::Version
+  version: 0.0.3
+platform: ruby
+authors:
+- Kevin S.
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2023-07-27 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: httparty
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description:
+email:
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/youtube-captions.rb
+homepage:
+licenses: []
+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: []
+rubygems_version: 3.4.6
+signing_key:
+specification_version: 4
+summary: A gem to get captions of a youtube video
+test_files: []