LinkDetailsExtractor adjustments (#31357)

3 months ago · 0518613dd7
parent 68c7782940
commit 0518613dd7
3 changed files with 21 additions and 9 deletions
--- a/app/lib/link_details_extractor.rb
+++ b/app/lib/link_details_extractor.rb
@ -157,7 +157,7 @@ class LinkDetailsExtractor
  end

  def title
-    html_entities.decode(structured_data&.headline || opengraph_tag('og:title') || document.xpath('//title').map(&:content).first)&.strip
+    html_entities.decode(structured_data&.headline || opengraph_tag('og:title') || head.at_xpath('title')&.content)&.strip
  end

  def description
@ -205,11 +205,11 @@ class LinkDetailsExtractor
  end

  def language
-    valid_locale_or_nil(structured_data&.language || opengraph_tag('og:locale') || document.xpath('//html').pick('lang'))
+    valid_locale_or_nil(structured_data&.language || opengraph_tag('og:locale') || document.root.attr('lang'))
  end

  def icon
-    valid_url_or_nil(structured_data&.publisher_icon || link_tag('apple-touch-icon') || link_tag('shortcut icon'))
+    valid_url_or_nil(structured_data&.publisher_icon || link_tag('apple-touch-icon') || link_tag('icon'))
  end

  private
@ -237,18 +237,20 @@ class LinkDetailsExtractor
  end

  def link_tag(name)
-    document.xpath("//link[nokogiri:link_rel_include(@rel, '#{name}')]", NokogiriHandler).pick('href')
+    head.at_xpath("//link[nokogiri:link_rel_include(@rel, '#{name}')]", NokogiriHandler)&.attr('href')
  end

  def opengraph_tag(name)
-    document.xpath("//meta[@property=\"#{name}\" or @name=\"#{name}\"]").pick('content')
+    head.at_xpath("//meta[nokogiri:casecmp(@property, '#{name}') or nokogiri:casecmp(@name, '#{name}')]", NokogiriHandler)&.attr('content')
  end

  def meta_tag(name)
-    document.xpath("//meta[@name=\"#{name}\"]").pick('content')
+    head.at_xpath("//meta[nokogiri:casecmp(@name, '#{name}')]", NokogiriHandler)&.attr('content')
  end

  def structured_data
+    return @structured_data if defined?(@structured_data)
+
    # Some publications have more than one JSON-LD definition on the page,
    # and some of those definitions aren't valid JSON either, so we have
    # to loop through here until we find something that is the right type
@ -273,6 +275,10 @@ class LinkDetailsExtractor
    @document ||= detect_encoding_and_parse_document
  end

+  def head
+    @head ||= document.at_xpath('/html/head')
+  end
+
  def detect_encoding_and_parse_document
    html = nil
    encoding = nil
--- a/app/lib/nokogiri_handler.rb
+++ b/app/lib/nokogiri_handler.rb
@ -8,5 +8,9 @@ class NokogiriHandler
    def link_rel_include(token_list, token)
      token_list.to_s.downcase.split(WHITE_SPACE).include?(token.downcase)
    end
+
+    def casecmp(str1, str2)
+      str1.to_s.casecmp?(str2.to_s)
+    end
  end
 end
--- a/spec/lib/link_details_extractor_spec.rb
+++ b/spec/lib/link_details_extractor_spec.rb
@ -49,7 +49,8 @@ RSpec.describe LinkDetailsExtractor do
      <html lang="en">
      <head>
        <title>Man bites dog</title>
-        <meta name="description" content="A dog&#39;s tale">
+        <meta name="descripTION" content="A dog&#39;s tale">
+        <link rel="pretty IcoN" href="/favicon.ico">
      </head>
      </html>
    HTML
@ -59,7 +60,8 @@ RSpec.describe LinkDetailsExtractor do
        .to have_attributes(
          title: eq('Man bites dog'),
          description: eq("A dog's tale"),
-          language: eq('en')
+          language: eq('en'),
+          icon: eq('https://example.com/favicon.ico')
        )
    end
  end
@ -256,7 +258,7 @@ RSpec.describe LinkDetailsExtractor do
      <head>
        <meta property="og:url" content="https://example.com/dog.html">
        <meta property="og:title" content="Man bites dog">
-        <meta property="og:description" content="A dog's tale">
+        <meta property="OG:description" content="A dog's tale">
        <meta property="article:published_time" content="2022-01-31T19:53:00+00:00">
        <meta property="og:author" content="Charlie Brown">
        <meta property="og:locale" content="en">