ask-web-fetch 0.5.8 → 0.5.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d3e0494d6f9fd54b7b80b667b97d57f17d1b0e871d44c26fada9ad91669a391d
-  data.tar.gz: e06918a4ca162ee2111715530f67ab68c8feae529c27c180cebb0cf462f13867
+  metadata.gz: d8f3dc79c573c21dc567f86edd621ad84da98437ef512faea0e13b36219670d2
+  data.tar.gz: 694519194d63c9f4066f943ed2fe472f029ea10afd6e423a41440ff7d8a04964
 SHA512:
-  metadata.gz: 4a045bb9226bb302cd60bda942acfa05a00e1f3d1aced99edc3bbd77a061c7650580b40447c385a4777b7156fa81aa0fcc57267caa4385b478e4d005c015f41f
-  data.tar.gz: ffab19b64968c909c67dd631902b447738248c7e6a0d3da5db8851cc2ff615ec627bc8a89407b40dbeabbebb591d2cd6726c21747de34962cc9ff77c98ce16e8
+  metadata.gz: 270301527344d9b49c982e1d7c27dd83117f23c56de3e321f67e15aae7696998d423bd7cec72852a188412ee54b4183736917a5ec6c7030eab888b621af611f1
+  data.tar.gz: 66933232dbb0f106362e2a9552f19fc152022c5f9ed9b7ca4bda6fe1d2b3935ce3a3b7288bc2d0130aa8d9bddd6a4e5861ff5ed675e11b763b0e0d171e5749ef

data/lib/ask/web_fetch/backend.rb

@@ -16,6 +16,13 @@ module Ask
     # A backend that fetched the page but found nothing usable in it.
     class EmptyContentError < Error; end
 
+    # A backend that fetched a REGISTRAR PARKING PAGE — an ad for a
+    # parked (for-sale) domain, not the site's content. Deterministic and
+    # terminal: retrying will never turn a parking ad into content, so
+    # the pipeline must classify (not retry) it. A subclass of
+    # EmptyContentError so existing empty-content handling still applies.
+    class ParkedDomainError < EmptyContentError; end
+
     # Network-level failure — timeout, connection refused/reset, bad
     # socket. Transient: the same URL may succeed on retry.
     class TimeoutError < Error; end

data/lib/ask/web_fetch/backends/browser.rb

@@ -201,8 +201,9 @@ module Ask
           end
           # Browser renders the parked page a JS redirect lands on (the
           # server shell hands /lander to JS) — Local never sees it. The
-          # shared parked-domain detector catches it here.
-          raise EmptyContentError, "parked domain at #{url} — registrar parking page, not site content" if parked_domain?(body)
+          # shared parked-domain detector catches it here; the distinct
+          # ParkedDomainError lets the pipeline classify (never retry) it.
+          raise ParkedDomainError, "parked domain at #{url} — registrar parking page, not site content" if parked_domain?(body)
 
           result = Markdown.generate(body, base_url: url, filter: self.class.content_filter)
           result[:outlinks] = outlink_urls(body, url)

data/lib/ask/web_fetch/backends/local.rb

@@ -55,7 +55,7 @@ module Ask
           # parked pages are fully server-rendered, so both Local and
           # Browser see the same ad.
           if parked_domain?(body)
-            raise EmptyContentError, "parked domain at #{url} — registrar parking page, not site content"
+            raise ParkedDomainError, "parked domain at #{url} — registrar parking page, not site content"
           end
           raise EmptyContentError, "no readable content at #{url}" unless usable_content?(page[:content])
           # The completeness signal: a JS-app shell whose server HTML

data/lib/ask/web_fetch/version.rb

@@ -2,6 +2,6 @@
 
 module Ask
   module WebFetch
-    VERSION = '0.5.8'
+    VERSION = '0.5.9'
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ask-web-fetch
 version: !ruby/object:Gem::Version
-  version: 0.5.8
+  version: 0.5.9
 platform: ruby
 authors:
 - Kaka Ruto