First Attempt to add PowerShell Docs

publicarray · publicarray · commit 9014b0d523b9 · 2026-01-17T13:40:06.000+11:00
diff --git a/docs/file-scrapers.md b/docs/file-scrapers.md
@@ -321,3 +321,56 @@ mv three.js-r${VERSION}/docs/* docs/threejs~${VERSION}/
 rm -rf three.js-r${VERSION}/
 rm threejs.tar.gz
 ```
+
+## PowerShell
+
+```sh
+curl -o PowerShell-Docs-main.zip 'https://github.com/MicrosoftDocs/PowerShell-Docs/archive/refs/heads/main.zip'
+unzip PowerShell-Docs-main.zip
+cd PowerShell-Docs-main
+
+## Has missing documentation, claims it can't find files from toc.yml (get-help.md etc.)
+# pacman -S dotnet-host aspnet-runtime
+# yay -S dotnet-runtime-8.0-bin # for DocFxTocGenerator
+# dotnet --list-runtimes
+# dotnet tool update -g docfx
+# dotnet tool install DocFxTocGenerator -g
+# cd PowerShell-Docs-main/reference
+# DocFxTocGenerator -d reference -sr --indexing NoDefault
+# docfx reference/docfx.json -o ../docs/powershell
+
+
+# strip all front matter in all Markdown files
+find reference -name "*.md" -type f -exec sed -i '/^---$/,/^---$/d' {} +
+## create a simpified template
+# cat > reference/template.html << 'EOF'
+# <!doctype html>
+# <html>
+#     <head>
+#         <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+#         <meta charset="utf-8" />
+#     </head>
+
+#     <body>
+#         <nav id="menu">
+#             <!--NAV-->
+#         </nav>
+#         <div id="layout">
+#             <article id="main" class="content">
+#                 <!--CONTENT-->
+#             </article>
+#         </div>
+#     </body>
+# </html>
+# EOF
+
+npx markdown-folder-to-html reference
+cp -r _reference ../docs/powershell
+cd ..
+
+# process whent on indefinatly
+bundle exec thor docs:generate powershell --debug 
+
+rm -rdf PowerShell-Docs-main/
+rm PowerShell-Docs-main.zip
+```
diff --git a/lib/docs/filters/powershell/clean_html.rb b/lib/docs/filters/powershell/clean_html.rb
@@ -0,0 +1,24 @@
+module Docs
+  class Powershell
+    class CleanHtmlFilter < Filter
+      def call
+        # web
+        css('header').remove
+        css('#ms--content-header').remove
+        css('#article-header').remove
+        css('.left-container').remove
+        css('.layout-body-aside').remove
+        css('#site-user-feedback-footer').remove
+        css('footer').remove
+        # docfx
+        css('.sideaffix').remove
+        # markdown-folder-to-html
+        css('#menuLink').remove
+        css('#menu').remove
+        css('script').remove
+        css('style').remove
+        doc
+      end
+    end
+  end
+end
diff --git a/lib/docs/filters/powershell/entries.rb b/lib/docs/filters/powershell/entries.rb
@@ -0,0 +1,26 @@
+module Docs
+  class Powershell
+    class EntriesFilter < Docs::EntriesFilter
+      def get_name
+        at_css('h1')&.content || "PowerShell"
+      end
+
+      def get_type
+        case slug
+          when /^docs-conceptual/
+            'Scripting'
+          when /^5\.1/
+            '5.1'
+          when /^7\.4/
+            '7.4'
+          when /^7\.5/
+            '7.5'
+          when /^7\.6/
+            '7.6'
+          else
+            'Module'
+        end
+      end
+    end
+  end
+end
diff --git a/lib/docs/scrapers/powershell.rb b/lib/docs/scrapers/powershell.rb
@@ -0,0 +1,32 @@
+module Docs
+  class Powershell < FileScraper
+  # class Powershell < UrlScraper
+    self.name = 'PowerShell'
+    self.type = 'simple'
+    self.release = '7.5'
+    self.base_url = 'https://learn.microsoft.com/en-us/powershell'
+    # self.root_path = 'scripting/overview.html'
+    self.root_path = 'docs-conceptual/overview.html'
+    self.initial_paths = [
+      # 'scripting/toc.html',
+      'module/index.html',
+      # 'module/Microsoft.WSMan.Management/About/about_WS-Management_Cmdlets.html',
+      # 'module/PSWorkflow/About/about_ActivityCommonParameters.html',
+      # 'module/Microsoft.PowerShell.Core/About/About.html',
+      # 'module/PSReadLine/About/about_PSReadLine.html',
+      # 'module/Microsoft.PowerShell.Security/About/about_Certificate_Provider.html',
+      # 'module/PSScheduledJob/About/about_Scheduled_Jobs.html'
+    ]
+    self.links = {
+      home: 'https://learn.microsoft.com/powershell',
+      code: 'https://github.com/MicrosoftDocs/PowerShell-Docs'
+    }
+    html_filters.push 'powershell/clean_html', 'powershell/entries'
+
+    # options[:rate_limit] = 100 # micososft docs online are ratelimited
+    options[:skip_patterns] = [/\/\//] # otherwise infinately adding the same pages
+    options[:attribution] = <<-HTML
+      The MIT License (MIT) Copyright (c) Microsoft Corporation
+    HTML
+  end
+end
