curlyq 0.0.12 → 0.0.13

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: af564949987eb7b96f7dfc730fea6ac79fb4a903c3eaff7a412af446c4a0e699
-  data.tar.gz: 58fb83c8132da551813adad468a6eb546a0d758df2b7c756b794a2a019963084
+  metadata.gz: db3d3f02ab489eefdf85122b219d01a14d43322040009566548ba76ebed07767
+  data.tar.gz: 1979f168d55f7f11fab7625a3916154b97ec9a1736e9a204a561399de5a3406c
 SHA512:
-  metadata.gz: 70e9485a7729acbd45a501278ceaae575bf358205c05da49de5c36f08ab8fd263824c8f8bd302c32b058986db3783b7abc6d9f0e58bb11f18879cdfde5210eac
-  data.tar.gz: 8d2e664b9e786c0a9d13fb8177c703be84c0a784835dba14354189978c34501334cc1dbdd68cc0112ad363c73554c170e9eb5fea64b60ee229bc4105b08d3fc6
+  metadata.gz: b47fd47823f2b74493affc0180eb96cb4146c34d89d670edb4350703009dccd341ce278f1221e9c7eafd8f2d8a117caa2ba6991a931e5927396091347d4970b6
+  data.tar.gz: 3143684aabac9d380583de9bfcb51045e78efacefc75051a7281dc2760a2efc24e70101f6c688ef396b7ba7f336d128f6641372a52c2e95be33082c8d9724712

data/CHANGELOG.md

@@ -1,7 +1,20 @@
+### 0.0.13
+
+2024-10-25 10:23
+
+#### FIXED
+
+- Fix tests, handle empty results better
+
 ### 0.0.12
 
 2024-04-04 13:06
 
+#### NEW
+
+- Add --script option to screenshot command
+- Add `execute` command for executing JavaScript on a page
+
 ### 0.0.11
 
 2024-01-21 15:29

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    curlyq (0.0.12)
+    curlyq (0.0.13)
       gli (~> 2.21.0)
       nokogiri (~> 1.16.0)
       selenium-webdriver (~> 4.16.0)

data/README.md

@@ -13,7 +13,7 @@ _If you find this useful, feel free to [buy me some coffee][donate]._
 [jq]: https://github.com/jqlang/jq "Command-line JSON processor"
 [yq]: https://github.com/mikefarah/yq "yq is a portable command-line YAML, JSON, XML, CSV, TOML and properties processor"
 
-The current version of `curlyq` is 0.0.12.
+The current version of `curlyq` is 0.0.13.
 
 CurlyQ is a utility that provides a simple interface for curl, with additional features for things like extracting images and links, finding elements by CSS selector or XPath, getting detailed header info, and more. It's designed to be part of a scripting pipeline, outputting everything as structured data (JSON or YAML). It also has rudimentary support for making calls to JSON endpoints easier, but it's expected that you'll use something like [jq] to parse the output.
 
@@ -46,7 +46,7 @@ SYNOPSIS
     curlyq [global options] command [command options] [arguments...]
 
 VERSION
-    0.0.12
+    0.0.13
 
 GLOBAL OPTIONS
     --help          - Show this message

data/bin/curlyq

@@ -148,6 +148,12 @@ command %i[html curl] do |c|
     end
     output.delete_if(&:nil?)
     output.delete_if(&:empty?)
+
+    if output.nil? || output.empty?
+      print_out([], global_options[:yaml], raw: options[:raw], pretty: global_options[:pretty])
+      Process.exit 1
+    end
+
     output.map! { |o| o[options[:raw].to_sym] } if options[:raw]
 
     output = output.clean_output
@@ -486,6 +492,11 @@ command :images do |c|
       end
     end
 
+    if output.nil? || output.empty?
+      print_out([], global_options[:yaml], raw: options[:raw], pretty: global_options[:pretty])
+      Process.exit 1
+    end
+
     print_out(output, global_options[:yaml], pretty: global_options[:pretty])
   end
 end

data/lib/curly/array.rb

@@ -180,6 +180,8 @@ class ::Array
     while output.is_a?(Array) && output.count == 1
       output = output[0]
     end
+    return [] unless output
+
     output.ensure_array
   end
 

data/lib/curly/curl/html.rb

@@ -289,6 +289,7 @@ module Curl
             end
           when /img/
             next unless %i[all img].include?(type)
+
             width = img[:attrs]['width']
             height = img[:attrs]['height']
             alt = img[:attrs]['alt']
@@ -301,7 +302,7 @@ module Curl
               height: height || 'unknown',
               alt: alt,
               title: title,
-              attrs: img[:attrs],
+              attrs: img[:attrs]
             }
           end
         end
@@ -333,7 +334,9 @@ module Curl
     ##
     def h(level = '\d')
       res = []
-      headlines = @body.to_enum(:scan, %r{<h(?<level>#{level})(?<tag> .*?)?>(?<text>.*?)</h#{level}>}i).map { Regexp.last_match }
+      headlines = @body.to_enum(:scan, %r{<h(?<level>#{level})(?<tag> .*?)?>(?<text>.*?)</h#{level}>}i).map do
+        Regexp.last_match
+      end
       headlines.each do |m|
         headline = { level: m['level'] }
         if m['tag'].nil?
@@ -436,7 +439,13 @@ module Curl
           attrs = tag['attrs'].strip.to_enum(:scan, /(?ix)
                                              (?<key>[@a-z0-9-]+)(?:=(?<quot>["'])
                                              (?<value>[^"']+)\k<quot>|[ >])?/i).map { Regexp.last_match }
-          attributes = attrs.each_with_object({}) { |a, hsh| hsh[a['key']] = a['key'] =~ /^(class|rel)$/ ? a['value'].split(/ /) : a['value'] }
+          attributes = attrs.each_with_object({}) do |a, hsh|
+            if a['value'].nil?
+              hsh[a['key']] = nil
+            else
+              hsh[a['key']] = a['key'] =~ /^(class|rel)$/ ? a['value'].split(/ /) : a['value']
+            end
+          end
         end
         {
           tag: tag['tag'],
@@ -640,7 +649,7 @@ module Curl
         driver.quit
       end
 
-      $stderr.puts "Executed JS on #{@url}"
+      warn "Executed JS on #{@url}"
 
       res
     end
@@ -680,9 +689,7 @@ module Curl
           wait.until { driver.find_element(id: id) }
         end
 
-        if script
-          res = driver.execute_script(script)
-        end
+        res = driver.execute_script(script) if script
 
         sleep wait_seconds.to_i
 
@@ -698,7 +705,7 @@ module Curl
         driver.quit
       end
 
-      $stderr.puts "Screenshot saved to #{destination}"
+      warn "Screenshot saved to #{destination}"
     end
 
     ##
@@ -837,13 +844,11 @@ module Curl
     ## @return     [Boolean] true if hostnames match
     ##
     def same_origin?(href)
-      begin
-        uri = URI(href)
-        origin = URI(@url)
-        uri.host == origin.host
-      rescue StandardError
-        false
-      end
+      uri = URI(href)
+      origin = URI(@url)
+      uri.host == origin.host
+    rescue StandardError
+      false
     end
   end
 end

data/lib/curly/version.rb

@@ -1,5 +1,5 @@
 # Top level module for CurlyQ
 module Curly
   # Current version number
-  VERSION = '0.0.12'
+  VERSION = '0.0.13'
 end

data/src/_README.md

@@ -13,7 +13,7 @@ _If you find this useful, feel free to [buy me some coffee][donate]._
 [jq]: https://github.com/jqlang/jq "Command-line JSON processor"
 [yq]: https://github.com/mikefarah/yq "yq is a portable command-line YAML, JSON, XML, CSV, TOML and properties processor"
 
-The current version of `curlyq` is <!--VER-->0.0.9<!--END VER-->.
+The current version of `curlyq` is <!--VER-->0.0.12<!--END VER-->.
 
 CurlyQ is a utility that provides a simple interface for curl, with additional features for things like extracting images and links, finding elements by CSS selector or XPath, getting detailed header info, and more. It's designed to be part of a scripting pipeline, outputting everything as structured data (JSON or YAML). It also has rudimentary support for making calls to JSON endpoints easier, but it's expected that you'll use something like [jq] to parse the output.
 

data/test/curlyq_html_test.rb

@@ -11,7 +11,7 @@ class CurlyQHtmlTest < Test::Unit::TestCase
   include CurlyQHelpers
 
   def test_html_search_query
-    result = curlyq('html', '-s', '#main article .aligncenter', '-q', 'images[1]', 'https://brettterpstra.com')
+    result = curlyq('html', '-s', '#main article .aligncenter', '-q', 'images[0]', 'https://brettterpstra.com/2024/10/19/web-excursions-for-october-19-2024/')
     json = JSON.parse(result)
 
     assert_match(/aligncenter/, json[0]['class'], 'Should have found an image with class "aligncenter"')

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: curlyq
 version: !ruby/object:Gem::Version
-  version: 0.0.12
+  version: 0.0.13
 platform: ruby
 authors:
 - Brett Terpstra
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-04-04 00:00:00.000000000 Z
+date: 2024-10-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake