ask-web-fetch 0.5.6 → 0.5.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a4c0b6735b967e38e8b837e7128bb501875ea1ce239f2df1549518396740ba8e
-  data.tar.gz: 0c6b95aba29f4914d062b35b3e21a43d1616a95ab01111a8d81d73326bd7f985
+  metadata.gz: d3e0494d6f9fd54b7b80b667b97d57f17d1b0e871d44c26fada9ad91669a391d
+  data.tar.gz: e06918a4ca162ee2111715530f67ab68c8feae529c27c180cebb0cf462f13867
 SHA512:
-  metadata.gz: 6f7f82bc5b93d368395989049757d86675e89d7645f7b351f3d24edff50a8303ee86cdc04dec9240a9e71ef2f6f7dedd0d6641da93ddc3b9d5494b116fa5ccd0
-  data.tar.gz: c160aac9363740829eaceeb53b18e91b009dcdc278b194d7774ba692b3b6d14d3404cb5b4f38e0d50fb73a62390fad7b2e0bbc1ca60a47d8dce8de8c1e745072
+  metadata.gz: 4a045bb9226bb302cd60bda942acfa05a00e1f3d1aced99edc3bbd77a061c7650580b40447c385a4777b7156fa81aa0fcc57267caa4385b478e4d005c015f41f
+  data.tar.gz: ffab19b64968c909c67dd631902b447738248c7e6a0d3da5db8851cc2ff615ec627bc8a89407b40dbeabbebb591d2cd6726c21747de34962cc9ff77c98ce16e8

data/lib/ask/web_fetch/backend.rb

@@ -59,6 +59,18 @@ module Ask
       # Wikipedia embeds an hcaptcha edit-config flag on every page).
       CHALLENGE_RE = /just a moment|checking your browser|cf-chl/i
 
+      # Registrar parking-page markers: the page is an ad for a parked
+      # (for-sale) domain, not the site's content. A content company must
+      # never store these as if they were the site. Observed live on the
+      # CC list, three shapes: (a) GoDaddy's parking-lander JS app
+      # (ap:"parking" flag, parking-lander asset, LANDER_SYSTEM="PW")
+      # served at /lander, (b) Namecheap's parking app (utm_campaign=
+      # nc_market + parkingpage links), and (c) static registrar pages
+      # ("is parked free, courtesy of GoDaddy.com", "is registered at
+      # Namecheap"). Deliberately specific — generic terms like "domain"
+      # or "for sale" appear on real pages.
+      PARKED_DOMAIN_MARKERS = /ap:"parking"|parking-lander|LANDER_SYSTEM="PW"|utm_campaign=nc_market|utm_source=parkingpage|is parked free, courtesy of GoDaddy|is available on GoDaddy Auctions|is registered at Namecheap/i
+
       def self.backend_name
         name.split('::').last
       end
@@ -118,6 +130,10 @@ module Ask
         body.to_s.match?(CHALLENGE_RE)
       end
 
+      def parked_domain?(body)
+        body.to_s.match?(PARKED_DOMAIN_MARKERS)
+      end
+
       def usable_content?(content)
         content.to_s.strip.length >= MIN_CONTENT_LENGTH
       end

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

@@ -27,7 +27,11 @@ module Ask
 
         # Creates a page as a fresh tab in the attached browser.
         def create_page
-          Page.new(client, timeout: @timeout)
+          # Capture the frontmost app once per browser instance, not per
+          # page: a batch of fetches steals focus once and restores to the
+          # same app, and consecutive fetches don't fight each other.
+          @frontmost_app ||= FocusRestorer.capture_frontmost
+          Page.new(client, timeout: @timeout, restore_focus_to: @frontmost_app)
         end
 
         private
@@ -43,9 +47,10 @@ module Ask
         # enough CDP for the Browser backend: navigate, read title/URL/HTML,
         # and report the main-document HTTP status.
         class Page
-          def initialize(client, timeout:)
+          def initialize(client, timeout:, restore_focus_to: nil)
             @client = client
             @timeout = timeout
+            @restore_focus_to = restore_focus_to
             @target_id = @client.command('Target.createTarget', url: 'about:blank')['targetId']
             @session = @client.session(
               @client.command('Target.attachToTarget', targetId: @target_id, flatten: true)['sessionId']
@@ -91,6 +96,12 @@ module Ask
             @client.command('Target.closeTarget', targetId: @target_id)
           rescue Ferrum::Error
             nil
+          ensure
+            # The attached dev Chrome window steals focus when a tab is
+            # created; give it back once the tab is gone — but only to an
+            # app that ISN'T Chrome, so a fetch while the user is already
+            # looking at Chrome doesn't ping-pong.
+            FocusRestorer.restore_frontmost(@restore_focus_to)
           end
 
           def evaluate(expression)
@@ -189,6 +200,48 @@ module Ask
           end
         end
       end
+
+      # macOS dev convenience: the attached Chrome window steals focus when
+      # a tab is created, and a developer working in another app wants it
+      # back once the tab is closed. Captures the frontmost app before the
+      # page is created and re-activates it after close. Deliberately
+      # cheap and quiet: one osascript each way, rescued to nil everywhere
+      # else (prod is headless Linux — this module is a no-op there, and
+      # even on macOS a failure must never fail a fetch).
+      module FocusRestorer
+        # The command runner, injectable for tests (minitest 6 ships no
+        # mock support, so tests swap this instead of stubbing).
+        class << self
+          attr_writer :runner
+
+          def runner
+            @runner ||= method(:system)
+          end
+        end
+
+        def self.capture_frontmost
+          return nil unless RUBY_PLATFORM.include?('darwin')
+
+          out = `osascript -e 'tell application "System Events" to get name of first application process whose frontmost is true' 2>/dev/null`.strip
+          out.empty? ? nil : out
+        rescue StandardError
+          nil
+        end
+
+        def self.restore_frontmost(app)
+          return if app.nil? || app.empty?
+
+          # Never ping-pong: if the user is already looking at Chrome (or
+          # headless/CI has no frontmost app at all), there's nothing to
+          # give back.
+          return if app == 'Google Chrome'
+
+          runner.call("osascript -e 'tell application \"#{app}\" to activate' 2>/dev/null")
+          nil
+        rescue StandardError
+          nil
+        end
+      end
     end
   end
 end

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

@@ -199,6 +199,10 @@ module Ask
 
             return fetch_attempt(page, url, warmed: true)
           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)
 
           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

@@ -45,6 +45,18 @@ module Ask
 
           page = to_markdown(body, url)
           page[:redirected] = redirect
+          # Parked-domain pages are not content: the domain owner parked it
+          # with a registrar and the page is an ad for buying the domain
+          # (GoDaddy/Namecheap/Sedo parking). A content company must never
+          # store these as if they were the site. Checked BEFORE the
+          # content-minimum — a parking page can render as "content" above
+          # the minimum (puncta.ai: 395c of Namecheap auction ads), and
+          # must still be rejected. Detectable from the server HTML —
+          # 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"
+          end
           raise EmptyContentError, "no readable content at #{url}" unless usable_content?(page[:content])
           # The completeness signal: a JS-app shell whose server HTML
           # renders little is a TRUNCATED page, not a complete one — the

data/lib/ask/web_fetch/version.rb

@@ -2,6 +2,6 @@
 
 module Ask
   module WebFetch
-    VERSION = '0.5.6'
+    VERSION = '0.5.8'
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ask-web-fetch
 version: !ruby/object:Gem::Version
-  version: 0.5.6
+  version: 0.5.8
 platform: ruby
 authors:
 - Kaka Ruto