jekyll-stats 0.3.0 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3465b65818c34b7a72b5b76d9bb242a37487837e5639927ae65c7d9a00b9ac62
-  data.tar.gz: 9e408de4fcfb55f1581a2b1905018852095cd4ae5c9a4a2f7592e252e24e42b0
+  metadata.gz: 5c9845c1c909307a6ee955d23c51412d24c1a12789d7144a817f8ac619bdaa91
+  data.tar.gz: ec4fdcf95f6b96fca65dac435e0edd307fff6c5ac7ea416e44bb473a0ee29d85
 SHA512:
-  metadata.gz: bd03f85ad69f529b003a211a7004acdf0a30851f0a2084abab6f3f142a511a620d7c3d4f755f4dcab6abc2286c55bb5f25c7bec610ccf565e0f012e975ba21d7
-  data.tar.gz: d42e6b8897070b6529b1cc32f7e6e52c11563e2890bcfdd5c03f4a2237216cb2afb80c62d2ec94489fe6433ffb3706e954d308e31c72a1b4f67fa7a486716ab1
+  metadata.gz: b88c1fb528e0fa65d53c7d22a3580a875b40b18d74f418128457c8faaa8b3bce8fa323e675ae5c64f06d19933cdb85731d3d8218016559c4f35a2b0d79ef4066
+  data.tar.gz: 279c44108897e9686dba753f11aadb8947bdc1fb95ae466ff8bbc5f306364689168ea476ab2cd1500982c4e92e03c62a9d814f6ba91f2599b4d52dea6dd6a494

data/CHANGELOG.md

@@ -1,5 +1,10 @@
 ## [Unreleased]
 
+## [0.4.0] - 2026-08-30
+
+- Add `external_links` to stats: total, unique, and per-domain counts of outbound links
+- Each domain entry includes `posts` (distinct source posts) so single-post link lists are visible
+
 ## [0.3.0] - 2026-08-30
 
 - Add `internal_links` to stats: posts ranked by inbound links from other posts

data/README.md

@@ -84,6 +84,14 @@ The `--save` flag writes `_data/stats.json` with this structure:
   "internal_links": [
     { "url": "/2024/01/foo", "title": "Foo", "inbound_count": 7, "inbound_from": ["/2024/03/bar", "/2024/06/baz"] }
   ],
+  "external_links": {
+    "total": 4637,
+    "unique": 3723,
+    "domains": [
+      { "host": "github.com", "count": 1380, "posts": 172 },
+      { "host": "en.wikipedia.org", "count": 94, "posts": 61 }
+    ]
+  },
   "drafts_count": 3
 }
 ```
@@ -102,6 +110,10 @@ jekyll-stats:
 
 Excluded posts still appear as targets; they just don't contribute outbound links.
 
+### External links
+
+`external_links` counts outbound `http(s)` links to hosts other than your site's `url:`. `total` is raw link occurrences, `unique` is distinct URLs, and each `domains` entry has `count` (distinct URLs at that host) and `posts` (distinct source posts). A high `count` with a low `posts` means one or two posts account for most links to that host. The same `link_source_exclude_tags` config applies.
+
 ## Building a Stats Page
 
 After running `jekyll stats --save`, create a stats page using Liquid:

data/lib/jekyll-stats/formatter.rb

@@ -39,6 +39,11 @@ module JekyllStats
         lines << most_linked_posts
       end
 
+      if stats[:external_links][:domains].any?
+        lines << ""
+        lines << top_external_domains
+      end
+
       if stats[:drafts_count].positive?
         lines << ""
         lines << "Drafts: #{stats[:drafts_count]}"
@@ -113,6 +118,15 @@ module JekyllStats
       lines.join("\n")
     end
 
+    def top_external_domains
+      ext = stats[:external_links]
+      lines = ["External Links: #{format_number(ext[:total])} (#{format_number(ext[:unique])} unique, #{ext[:domains].size} hosts)"]
+      ext[:domains].first(5).each do |d|
+        lines << "  #{d[:count].to_s.rjust(4)}  #{d[:host]} (#{d[:posts]} posts)"
+      end
+      lines.join("\n")
+    end
+
     def format_number(n)
       n.to_s.reverse.gsub(/(\d{3})(?=\d)/, '\\1,').reverse
     end

data/lib/jekyll-stats/stats_calculator.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require "uri"
+
 module JekyllStats
   class StatsCalculator
     WORDS_PER_MINUTE = 200
@@ -41,6 +43,7 @@ module JekyllStats
         tags: tag_counts(posts),
         categories: category_counts(posts),
         internal_links: internal_links(posts),
+        external_links: external_links(posts),
         drafts_count: drafts_count
       }
     end
@@ -180,6 +183,38 @@ module JekyllStats
       }.sort_by { |r| [-r[:inbound_count], r[:url]] }
     end
 
+    def external_links(posts)
+      exclude = Array(site.config.dig("jekyll-stats", "link_source_exclude_tags")).map { |t| normalize_tag(t) }
+      site_host = (URI.parse(site.config["url"].to_s).host rescue nil)
+
+      urls = []
+      posts.each do |post|
+        post_tags = (post.data["tags"] || []).map { |t| normalize_tag(t) }
+        next if exclude.any? && (exclude & post_tags).any?
+
+        post.content.to_s.scan(%r{(?:\]\(|<a\s[^>]*href=["'])(https?://[^"'\s)]+)}i).flatten.each do |href|
+          host = URI.parse(href).host rescue nil
+          next if host.nil?
+          next if site_host && host == site_host
+
+          urls << [href, host, post]
+        end
+      end
+
+      unique = urls.uniq { |u, _, _| u }
+      domains = urls.group_by { |_, h, _| h }
+                    .map { |host, us|
+                      {
+                        host: host,
+                        count: us.map { |u, _, _| u }.uniq.size,
+                        posts: us.map { |_, _, p| p }.uniq.size
+                      }
+                    }
+                    .sort_by { |d| [-d[:count], d[:host]] }
+
+      { total: urls.size, unique: unique.size, domains: domains }
+    end
+
     def normalize_url(url)
       url.sub(/[#?].*\z/, "").sub(%r{/index\.html\z}, "").chomp(".html").chomp("/")
     end
@@ -209,6 +244,7 @@ module JekyllStats
         tags: [],
         categories: [],
         internal_links: [],
+        external_links: { total: 0, unique: 0, domains: [] },
         drafts_count: 0
       }
     end

data/lib/jekyll-stats/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module JekyllStats
-  VERSION = "0.3.0"
+  VERSION = "0.4.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: jekyll-stats
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.4.0
 platform: ruby
 authors:
 - Andrew Nesbitt