X-Git-Url: https://git.netwichtig.de/gitweb/?a=blobdiff_plain;f=data%2Frbot%2Fplugins%2Fdict.rb;h=c9bfabafadef5fb75491d6590f492d7ec8caa48a;hb=052217de30c59206d7025b582d4604557a747470;hp=5176591ae7d84d4f04837146c247dffd7b708c99;hpb=539c526cf8ec0b4b07d84541cd3ce27d08ac946b;p=user%2Fhenk%2Fcode%2Fruby%2Frbot.git

diff --git a/data/rbot/plugins/dict.rb b/data/rbot/plugins/dict.rb
index 5176591a..c9bfabaf 100644
--- a/data/rbot/plugins/dict.rb
+++ b/data/rbot/plugins/dict.rb
@@ -31,14 +31,37 @@ class DictPlugin < Plugin
     :default => 0,
     :desc => "When set to n > 0, the bot will return the first paragraph from the first n dictionary hits")
 
+  def demauro_filter(s)
+    # check if it's a page we can handle
+    loc = Utils.check_location(s, @dmurlrx)
+    # the location might be not good, but we might still be able to handle the
+    # page
+    if !loc and s[:text] !~ /<!-- Il dizionario della lingua italiana Paravia: /
+      debug "not our business"
+      return
+    end
+    # we want to grab the content from the WAP page, since it's in a much
+    # cleaner HTML, so first try to get the word ID
+    if s[:text] !~ %r{<li><a href="(\d+)" title="vai al lemma precedente" accesskey="p">lemma precedente</a></li>}
+      return
+    end
+    id = $1.to_i + 1
+    title = s[:text].ircify_html_title
+    content = @bot.filter(:htmlinfo, URI.parse(@dmwaplemma % id))[:content]
+    return {:title => title, :content => content.sub(/^\S+\s+-\s+/,'')}
+  end
+
   def initialize
     super
-    @dmurl = "http://www.demauroparavia.it/"
+    @dmurl = "http://old.demauroparavia.it/"
+    @dmurlrx = %r{http://(?:www|old\.)?demauroparavia\.it/(\d+)}
     @dmwapurl = "http://wap.demauroparavia.it/index.php?lemma=%s"
     @dmwaplemma = "http://wap.demauroparavia.it/lemma.php?ID=%s"
     @oxurl = "http://www.askoxford.com/concise_oed/%s"
     @chambersurl = "http://www.chambersharrap.co.uk/chambers/features/chref/chref.py/main?query=%s&title=21st"
     @littreurl = "http://francois.gannaz.free.fr/Littre/xmlittre.php?requete=%s"
+
+    @bot.register_filter(:demauro, :htmlinfo) { |s| demauro_filter(s) }
   end
 
 
@@ -89,7 +112,8 @@ class DictPlugin < Plugin
     text += entries[0...hits].map { |ar|
       n += 1
       urls << @dmwaplemma % ar[2]
-      "#{n}. #{Bold}#{ar[0]}#{Bold} - #{ar[1].gsub(/<\/?em>/,'')}: #{@dmurl}#{ar[2]}"
+      key = ar[1].ircify_html
+      "#{n}. #{Bold}#{ar[0]}#{Bold} - #{key}: #{@dmurl}#{ar[2]}"
     }.join(" | ")
     m.reply text
 
@@ -117,9 +141,9 @@ class DictPlugin < Plugin
         url << "?view=uk"
       end
       h = @bot.httputil.get(url, :max_redir => 5)
-      if h and h.match(%r!<h2>#{word}(?:<sup>1</sup>)?</h2>!)
+      if h and h.match(/<h2>#{word}<\/h2>(.*)Perform/m)
         m.reply("#{word} : #{url}") unless justcheck
-        defn = $'
+        defn = $1
         m.reply("#{Bold}%s#{Bold}: %s" % [word, defn.ircify_html(:nbsp => :space)], :overlong => :truncate)
         return true
       end