websitary 0.3 → 0.4

data/History.txt

@@ -1,3 +1,14 @@
+= 0.4
+
+* Sources may have a :timeout option.
+* exclude: Argument can be a string or a regexp.
+* htmldiff: :ignore option to exclude certain nodes from the diff.
+* Left-mouse clicks make items collapse/expand.
+* iconv: Support for converting encodings (require the per-url iconv 
+  option to be set).
+* exclude mailto urls.
+
+
 = 0.3
 
 * Renamed the global option :downloadhtml to :download_html.

data/README.txt

@@ -189,9 +189,13 @@ This is the same a <tt>option :global, OPTION => VALUE</tt>.
 
 Known global options:
 
-<tt>:filename_size => N</tt>::
-  The max filename size. If a filename becomes longer, md5 encoding will 
-  be used for local copies in the cache.
+<tt>:canonic_filename => BLOCK(FILENAME)</tt>::
+  Rewrite filenames as they are stored in the mtimes register. This may 
+  useful if you want to use the same repository on several computers 
+  with in different locations etc.
+
+<tt>:encoding => OUTPUT_DOCUMENT_ENCODING</tt>::
+  The default is 'ISO-8859-1'.
 
 <tt>:downloadhtml => SHORTCUT</tt>::
   The default shortcut for downloading plain HTML.
@@ -201,10 +205,12 @@ Known global options:
   copies in the output. This may useful if you want to use the same 
   repository on several computers with in different locations etc.
 
-<tt>:canonic_filename => BLOCK(FILENAME)</tt>::
-  Rewrite filenames as they are stored in the mtimes register. This may 
-  useful if you want to use the same repository on several computers 
-  with in different locations etc.
+<tt>:filename_size => N</tt>::
+  The max filename size. If a filename becomes longer, md5 encoding will 
+  be used for local copies in the cache.
+
+<tt>:toggle_body => BOOLEAN</tt>::
+  If true, make a news body collabsable on mouse-clicks (sort of).
 
 
 ==== output_format FORMAT, output_format [FORMAT1, FORMAT2, ...]
@@ -270,6 +276,14 @@ Options
   wraps the output in +pre+ tags. :webdiff, :body_html, :website_below, 
   :website, and :openuri will simply add a newline character.
 
+<tt>:iconv => ENCODING</tt>::
+  If set, use iconv to convert the page body into the summary's document 
+  encoding (see the 'global' section). Websitary currently isn't able to 
+  automatically determine and convert encodings.
+
+<tt>:timeout => SECONDS</tt>::
+  When using openuri, download the page with a timeout.
+
 <tt>:hours => HOURS, :days => DAYS</tt>::
   Don't download the file unless it's older than that
 
@@ -733,5 +747,3 @@ along with this program; if not, write to the Free Software
 Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  
 USA
 
-
-% vi: ft=rd:tw=72:ts=4

data/Rakefile

@@ -21,7 +21,11 @@ require 'rtagstask'
 RTagsTask.new
 
 task :ctags do
-    `ctags --extra=+q --fields=+i -R bin lib`
+    `ctags --extra=+q --fields=+i+S -R bin lib`
+end
+
+task :files do
+    `find bin lib -name "*.rb" > files.lst`
 end
 
 # vim: syntax=Ruby

data/bin/websitary

@@ -1,6 +1,6 @@
-#! /usr/bin/ruby.exe
+#! /usr/bin/env ruby
 # websitary.rb -- The website news, rss feed, podcast catching monitor
-# @Last Change: 2007-09-09.
+# @Last Change: 2007-12-26.
 # Author::      Thomas Link (micathom at gmail com)
 # License::     GPL (see http://www.gnu.org/licenses/gpl.txt)
 # Created::     2007-06-09.

data/lib/websitary.rb

@@ -1,5 +1,5 @@
 # websitary.rb
-# @Last Change: 2007-10-26.
+# @Last Change: 2008-01-13.
 # Author::      Thomas Link (micathom AT gmail com)
 # License::     GPL (see http://www.gnu.org/licenses/gpl.txt)
 # Created::     2007-09-08.
@@ -14,6 +14,7 @@ require 'pathname'
 require 'rbconfig'
 require 'uri'
 require 'open-uri'
+require 'timeout'
 require 'yaml'
 require 'rss'
 
@@ -32,8 +33,8 @@ end
 
 module Websitary
     APPNAME     = 'websitary'
-    VERSION     = '0.3'
-    REVISION    = '2437'
+    VERSION     = '0.4'
+    REVISION    = '2464'
 end
 
 require 'websitary/applog'
@@ -71,92 +72,7 @@ class Websitary::App
         unless File.exists?(css)
             $logger.info "Copying default css file: #{css}"
             @configuration.write_file(css, 'w') do |io|
-                io.puts <<CSS
-body {
-color: black;
-background-color: #f0f0f0;
-}
-a.external {
-}
-a.old {
-}
-a.latest {
-}
-a.toc {
-}
-ol.toc {
-float: left;
-width: 200px;
-position: fixed;
-padding: 0;
-margin: 0;
-}
-li.toc {
-list-style: none;
-border: 1px solid #e0e0e0;
-background-color: #fafafa;
-    padding: 0.1em;
-font-size: 80%;
-font-family: Verdana, Myriad Web, Syntax, sans-serif;
-}
-li.toc:hover {
-background-color: #ffff8d;
-}
-div.contents {
-margin-left: 210px;
-min-width: 16em;
-}
-div.webpage {
-margin: 5px 0 5px 0;
-padding: 5px;
-border: 1px solid #e0e0e0;
-background-color: white;
-}
-div.count {
-text-align: right;
-}
-.enclosure {
-padding: 4px;
-margin: 4px 0 4px 0;
-background: #f9f9f9;
-}
-h1.diff {
-    font-family: Verdana, Myriad Web, Syntax, sans-serif;
-}
-h2.rss {
-    border-top: 10px solid #f0f0f0;
-    padding-top: 10px;
-}
-div.diff {
-    padding-left: 2em;
-}
-pre.diff {
-    padding-left: 2em;
-}
-div.annotation {
-    font-size: 80%;
-}
-hr.separator {
-    width: 100%;
-    visibility: hidden;
-}
-.error {
-    color: yellow;
-    background-color: red;
-}
-.highlight-yellow {
-    background-color: #ffc730;
-}
-.highlight-red {
-    background-color: red;
-}
-.highlight-blue {
-    background-color: blue;
-}
-.highlight-aqua {
-    background-color: aqua;
-}
-CSS
+                io.puts @configuration.get_option(:page, :css)
             end
         end
     end
@@ -318,7 +234,7 @@ CSS
             difftext.delete('')
             unless difftext.empty?
                 joindiffs = @configuration.get(url, :joindiffs, lambda {|t| t.join("\n")})
-                difftext  = @configuration.call_cmd(joindiffs, [difftext]) if joindiffs
+                difftext  = @configuration.call_cmd(joindiffs, [difftext], :url => url) if joindiffs
                 accumulate(url, difftext, opts)
             end
             aggrfiles.each do |file|
@@ -437,7 +353,7 @@ CSS
 
         $logger.warn "Download: #{@configuration.get(url, :title, url).inspect}"
         @configuration.done << url
-        text = @configuration.call_cmd(@configuration.get(url, :download), [url])
+        text = @configuration.call_cmd(@configuration.get(url, :download), [url], :url => url)
         # $logger.debug text #DBG#
         unless text
             $logger.warn "no contents: #{@configuration.get(url, :title, url)}"
@@ -477,7 +393,7 @@ CSS
         pprc = @configuration.get(url, :downloadprocess)
         if pprc
             $logger.debug "download process: #{pprc}"
-            text = @configuration.call_cmd(pprc, [text])
+            text = @configuration.call_cmd(pprc, [text], :url => url)
             # $logger.debug text #DBG#
         end
 
@@ -500,13 +416,13 @@ CSS
     def diff(url, opts, new, old)
         if File.exists?(old)
             $logger.debug "diff: #{old} <-> #{new}"
-            difftext = @configuration.call_cmd(@configuration.get(url, :diff), [old, new])
+            difftext = @configuration.call_cmd(@configuration.get(url, :diff), [old, new], :url => url)
             # $logger.debug "diff: #{difftext}" #DBG#
 
             if difftext =~ /\S/
                 if (pprc = @configuration.get(url, :diffprocess))
                     $logger.debug "diff process: #{pprc}"
-                    difftext = @configuration.call_cmd(pprc, [difftext])
+                    difftext = @configuration.call_cmd(pprc, [difftext], :url => url)
                 end
                 # $logger.debug "difftext: #{difftext}" #DBG#
                 if difftext =~ /\S/
@@ -514,7 +430,7 @@ CSS
                     return difftext
                 end
             end
-            
+
             $logger.debug "Unchanged: #{@configuration.get(url, :title, url).inspect}"
 
         elsif File.exist?(new) and

data/lib/websitary/configuration.rb

@@ -1,5 +1,5 @@
 # configuration.rb
-# @Last Change: 2007-10-21.
+# @Last Change: 2008-01-09.
 # Author::      Thomas Link (micathom AT gmail com)
 # License::     GPL (see http://www.gnu.org/licenses/gpl.txt)
 # Created::     2007-09-08.
@@ -129,7 +129,7 @@ class Websitary::Configuration
             end
 
             opts.on('-x', '--exclude=N', Regexp, 'Exclude URLs matching this pattern') do |value|
-                exclude(value)
+                exclude(Regexp.new(value))
             end
 
             opts.separator ''
@@ -337,9 +337,14 @@ class Websitary::Configuration
 
 
     def to_do(url)
-        unless @exclude.any? {|p| url =~ p}
-            @todo << url
-        end
+        @todo << url unless is_excluded?(url)
+    end
+
+
+    def is_excluded?(url)
+        rv = @exclude.any? {|p| url =~ p}
+        $logger.debug "is_excluded: #{url}: #{rv}"
+        rv
     end
 
 
@@ -434,9 +439,19 @@ class Websitary::Configuration
 
 
     # Configuration command:
-    # Add URL-exclusion patterns (REGEXPs).
+    # Add URL-exclusion patterns (REGEXPs or STRINGs).
     def exclude(*urls)
-        @exclude += urls
+        @exclude += urls.map do |url|
+            case url
+            when Regexp
+                url
+            when String
+                Regexp.new(Regexp.escape(url))
+            else
+                $logger.fatal "Must be regexp or string: #{url.inspect}"
+                exit 5
+            end
+        end
     end
 
 
@@ -461,10 +476,26 @@ class Websitary::Configuration
     end
 
 
+    def format_text(url, text)
+        enc = get(url, :iconv)
+        if enc
+            denc = get_optionvalue(:global, :encoding)
+            begin
+                require 'iconv'
+                text = Iconv.conv(denc, enc, text)
+            rescue Exception => e
+                $logger.error "IConv failed #{enc} => #{denc}: #{e}"
+            end
+        end
+        return text
+    end
+
+
     # Format a diff according to URL's source options.
     def format(url, difftext)
-        fmt = get(url, :format)
-        eval_arg(fmt, [difftext], difftext)
+        fmt  = get(url, :format)
+        text = format_text(url, difftext)
+        eval_arg(fmt, [text], text)
     end
 
 
@@ -493,8 +524,22 @@ class Websitary::Configuration
 
     # Apply the argument to cmd (a format String or a Proc). If a 
     # String, execute the command.
-    def call_cmd(cmd, args, default=nil)
-        eval_arg(cmd, args, default) {|cmd| `#{cmd}`}
+    def call_cmd(cmd, cmdargs, args={})
+        default = args[:default]
+        url     = args[:url]
+        timeout = url ? get(url, :timeout) : nil
+        if timeout
+            begin
+                Timeout::timeout(timeout) do |timeout_length|
+                    eval_arg(cmd, cmdargs, default) {|cmd| `#{cmd}`}
+                end
+            rescue Timeout::Error
+                $logger.error "Timeout #{timeout}: #{url}"
+                return default
+            end
+        else
+            eval_arg(cmd, cmdargs, default) {|cmd| `#{cmd}`}
+        end
     end
 
 
@@ -630,15 +675,17 @@ class Websitary::Configuration
                 ext  = %{ (#{old}, #{lst})}
                 urlr = url
             end
-            note = difftext_annotation(url)
+            note    = difftext_annotation(url)
+            onclick = get_optionvalue(:global, :toggle_body) ? 'onclick="ToggleBody(this)"' : ''
             <<HTML
-<div id="#{bid}" class="webpage">
+<div id="#{bid}" class="webpage" #{onclick}>
 <div class="count">
 #{idx}
 </div>
 <h1 class="diff">
-<a class="external" href="#{urlr}">#{ti}</a>#{ext}
+<a class="external" href="#{urlr}">#{format_text(url, ti)}</a>#{ext}
 </h1>
+<div id="#{bid}_body">
 <div class="annotation">
 #{note && CGI::escapeHTML(note)}
 </div>
@@ -646,6 +693,7 @@ class Websitary::Configuration
 #{format(url, text)}
 </div>
 </div>
+</div>
 HTML
         end.join(('<hr class="separator"/>') + "\n")
 
@@ -795,7 +843,8 @@ HTML
     # already included.
     def push_hrefs(url, hpricot, &condition)
         begin
-            return if robots?(hpricot, 'nofollow')
+            $logger.debug "push_refs: #{url}"
+            return if robots?(hpricot, 'nofollow') or is_excluded?(url)
             depth = get(url, :depth)
             return if depth and depth <= 0
             uri0  = URI.parse(url)
@@ -804,8 +853,8 @@ HTML
             (hpricot / 'a').each do |a|
                 next if a['rel'] == 'nofollow'
                 href = a['href']
-                next if href.nil? or href == url or href =~ /^\s*javascript:/
-                    uri  = URI.parse(href)
+                next if href.nil? or href == url or href =~ /^\s*javascript:/ or href =~ /^\s*mailto:/ or is_excluded?(href)
+                uri  = URI.parse(href)
                 pn   = guess_dir(uri.path)
                 href = rewrite_href(href, url, uri0, pn0, true)
                 curl = canonic_url(href)
@@ -838,17 +887,33 @@ HTML
         uri = URI.parse(url)
         urd = guess_dir(uri.path)
         (doc / 'a').each do |a|
-            href = rewrite_href(a['href'], url, uri, urd, true)
-            a['href'] = href if href
+            href = a['href']
+            if is_excluded?(href)
+                comment_element(doc, a)
+            else
+                href = rewrite_href(href, url, uri, urd, true)
+                a['href'] = href if href
+            end
         end
         (doc / 'img').each do |a|
-            href = rewrite_href(a['src'], url, uri, urd, false)
-            a['src'] = href if href
+            href = a['src']
+            if is_excluded?(href)
+                comment_element(doc, a)
+            else
+                href = rewrite_href(href, url, uri, urd, false)
+                a['src'] = href if href
+            end
         end
         doc
     end
 
 
+    def comment_element(doc, elt)
+        doc.insert_before(elt, '<!-- WEBSITARY: ')
+        doc.insert_after(elt, '-->')
+    end
+
+
     # Try to make href an absolute url.
     def rewrite_href(href, url, uri=nil, urd=nil, local=false)
         begin
@@ -961,7 +1026,7 @@ HTML
 
 
     def canonic_filename(filename)
-        call_cmd(get_optionvalue(:global, :canonic_filename), [filename], filename)        
+        call_cmd(get_optionvalue(:global, :canonic_filename), [filename], :default => filename)
     end
 
 
@@ -970,6 +1035,8 @@ HTML
         @options = {
             :global => {
                 :download_html => :openuri,
+                :encoding => 'ISO-8859-1',
+                :toggle_body => false,
             },
         }
 
@@ -996,9 +1063,13 @@ HTML
             :raw => :new,
 
             :htmldiff => lambda {|old, new|
-                oldhtml  = File.read(old)
-                newhtml  = File.read(new)
-                difftext = Websitary::Htmldiff.new(:oldtext => oldhtml, :newtext => newhtml).diff
+                url  = url_from_filename(new)
+                args = {
+                    :oldhtml => File.read(old),
+                    :newhtml => File.read(new),
+                    :ignore  => get(url, :ignore),
+                }
+                difftext = Websitary::Htmldiff.new(args).diff
                 difftext
             },
 
@@ -1130,7 +1201,8 @@ HTML
                                     rss_diff = Websitary::Htmldiff.new(:highlight => 'highlight', :oldtext => olditem.description, :newtext => item.description).process
                                     rnew << format_rss_item(item, rss_diff)
                                 else
-                                    if item.enclosure and (curl = item.enclosure.url)
+                                    enc = item.respond_to?(:enclosure) && item.enclosure
+                                    if enc and (curl = enc.url)
                                         url   = url_from_filename(new)
                                         dir   = get(url, :rss_enclosure)
                                         curl  = rewrite_href(curl, url, nil, nil, true)
@@ -1229,15 +1301,31 @@ HTML
             }
 
         @options[:page] = {
-            :format => lambda do |ti, li, bd|
+            :format => lambda {|ti, li, bd|
                 template = <<OUT
 <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
 <html>
 <head>
 <title>%s</title>
+<meta http-equiv="Content-Type" content="text/html; charset=#{get_optionvalue(:global, :encoding)}">
 <link rel="stylesheet" href="websitary.css" type="text/css">
 <link rel="alternate" href="websitary.rss" type="application/rss+xml" title="%s">
 </head>
+<script type="text/javascript">
+function ToggleBody(Item) {
+    var Body = document.getElementById(Item.id + "_body");
+    if (Body.style.visibility == "collapse") {
+        Body.style.visibility = "visible";
+        Body.style.height = "";
+        Item.style.background = "";
+    } else {
+        Body.style.visibility = "collapse";
+        Body.style.height = "1px";
+        Item.style.background = "#e0f0f0";
+    }
+    return '';
+}
+</script>
 <body>
 <ol class="toc">
 %s
@@ -1249,7 +1337,96 @@ HTML
 </html>
 OUT
                 template % [ti, ti, li, bd]
-            end
+            },
+            :css => <<CSS,
+body {
+    color: black;
+    background-color: #f0f0f0;
+}
+a.external {
+}
+a.old {
+}
+a.latest {
+}
+a.toc {
+}
+ol.toc {
+    float: left;
+    width: 200px;
+    position: fixed;
+    padding: 0;
+    margin: 0;
+}
+li.toc {
+    list-style: none;
+    border: 1px solid #e0e0e0;
+    background-color: #fafafa;
+    padding: 0.1em;
+    font-size: 80%;
+    font-family: Verdana, Myriad Web, Syntax, sans-serif;
+}
+li.toc:hover {
+    background-color: #ffff8d;
+}
+div.contents {
+    margin-left: 210px;
+    min-width: 16em;
+}
+div.webpage {
+    margin: 5px 0 5px 0;
+    padding: 5px;
+    border: 1px solid #e0e0e0;
+    background-color: white;
+}
+div.count {
+    text-align: right;
+}
+.enclosure {
+    padding: 4px;
+    margin: 4px 0 4px 0;
+    background: #f9f9f9;
+}
+h1.diff {
+    font-family: Verdana, Myriad Web, Syntax, sans-serif;
+}
+h2.rss {
+    border-top: 10px solid #f0f0f0;
+    padding-top: 10px;
+}
+div.diff {
+    padding-left: 2em;
+}
+pre.diff {
+    padding-left: 2em;
+}
+div.annotation {
+    font-size: 80%;
+}
+hr.separator {
+    width: 100%;
+    visibility: hidden;
+}
+.error {
+    color: yellow;
+    background-color: red;
+}
+.highlight {
+    background-color: #fac751;
+}
+.highlight-yellow {
+    background-color: #ffc730;
+}
+.highlight-red {
+    background-color: red;
+}
+.highlight-blue {
+    background-color: blue;
+}
+.highlight-aqua {
+    background-color: aqua;
+}
+CSS
         }
     end
 
@@ -1293,7 +1470,7 @@ OUT
 
 
     def get_website(download, url)
-        html = call_cmd(get_optionvalue(:download, download), [url])
+        html = call_cmd(get_optionvalue(:download, download), [url], :url => url)
         if html
             doc = Hpricot(html)
             if doc
@@ -1310,7 +1487,7 @@ OUT
 
     def get_website_below(download, url)
         dwnl = get_optionvalue(:download, download)
-        html = call_cmd(dwnl, [url])
+        html = call_cmd(dwnl, [url], :url => url)
         if html
             doc = Hpricot(html)
             if doc
@@ -1373,7 +1550,7 @@ OUT
     def read_url(url, type='html')
         downloader = get(url, "download_#{type}".intern)
         if downloader
-            call_cmd(downloader, [url])
+            call_cmd(downloader, [url], :url => url)
         else
             read_url_openuri(url)
         end
@@ -1421,10 +1598,12 @@ OUT
 
 
     def format_rss_item(item, body, enclosure='')
-        hd = [item.title]
-        hd << " (#{item.author})" if item.author
+        ti = rss_field(item, :title)
+        au = rss_field(item, :author)
+        hd = [ti]
+        hd << " (#{au})" if au
         return <<EOT
-<h2 class="rss"><a class="rss" href="#{item.link}">#{hd.join} -- #{item.pubDate}</a></h2>
+<h2 class="rss"><a class="rss" href="#{rss_field(item, :link)}">#{hd.join} -- #{rss_field(item, :pubDate)}</a></h2>
 <div class="rss">
 #{body}
 #{enclosure}
@@ -1432,6 +1611,16 @@ OUT
 EOT
     end
 
+
+    def rss_field(item, field, default=nil)
+        if item.respond_to?(field)
+            return item.send(field)
+        else
+            return default
+        end
+    end
+
+
     # Guess whether text is plain text or html.
     def is_html?(text)
         text =~ /<(div|a|span|body|html|script|p|table|td|tr|th|li|dt|br|hr|em|b)\b/
@@ -1524,7 +1713,7 @@ EOT
     def file_url(filename)
         # filename = File.join(File.basename(File.dirname(filename)), File.basename(filename))
         # "file://#{encode(filename, ':/')}"
-        filename = call_cmd(get_optionvalue(:global, :file_url), [filename], filename)
+        filename = call_cmd(get_optionvalue(:global, :file_url), [filename], :default => filename)
         encode(filename, ':/')
     end
 

data/lib/websitary/htmldiff.rb

@@ -1,6 +1,6 @@
 #!/usr/bin/env ruby
 # htmldiff.rb
-# @Last Change: 2007-10-08.
+# @Last Change: 2007-11-10.
 # Author::      Thomas Link (micathom at gmail com)
 # License::     GPL (see http://www.gnu.org/licenses/gpl.txt)
 # Created::     2007-08-17.
@@ -17,7 +17,7 @@ module Websitary
     # wrong results (especially wrong-negative) in certain occasions.
     class Htmldiff
         VERSION  = '0.1'
-        REVISION = '164'
+        REVISION = '180'
        
         # args:: A hash
         # Fields:
@@ -30,6 +30,10 @@ module Websitary
             @high = args[:highlight] || args[:highlightcolor]
             @old  = explode(args[:olddoc] || Hpricot(args[:oldtext] || File.read(args[:oldfile])))
             @new  =         args[:newdoc] || Hpricot(args[:newtext] || File.read(args[:newfile]))
+            @ignore  = args[:ignore]
+            if @ignore and !@ignore.kind_of?(Enumerable)
+                die "Ignore must be of kind Enumerable: #{ignore.inspect}"
+            end
             @changed = false
         end
 
@@ -46,11 +50,11 @@ module Websitary
         # node, the whole node has changed. If only some sub-nodes have 
         # changed, collect those.
         def process(node=@new)
-            acc    = []
+            acc = []
             node.each_child do |child|
                 ch = child.to_html.strip
                 next if ch.nil? or ch.empty?
-                if @old.include?(ch)
+                if @old.include?(ch) or ignore(child, ch)
                     if @high
                         acc << child
                     end
@@ -67,6 +71,20 @@ module Websitary
         end
 
 
+        def ignore(node, node_as_string)
+            return @ignore && @ignore.any? do |i|
+                case i
+                when Regexp
+                    node_as_string =~ i
+                when Proc
+                    l.call(node)
+                else
+                    die "Unknown type for ignore expression: #{i.inspect}"
+                end
+            end
+        end
+
+
         # Collect all nodes and subnodes in a hpricot document.
         def explode(node)
             if node.respond_to?(:each_child)

metadata

@@ -1,33 +1,45 @@
 --- !ruby/object:Gem::Specification 
-rubygems_version: 0.9.4
-specification_version: 1
 name: websitary
 version: !ruby/object:Gem::Version 
-  version: "0.3"
-date: 2007-10-26 00:00:00 +02:00
-summary: A unified website news, rss feed, podcast monitor
-require_paths: 
-- lib
-email: micathom at gmail com
-homepage: http://rubyforge.org/projects/websitiary/
-rubyforge_project: websitiary
-description: "== DESCRIPTION: websitary (formerly known as websitiary with an extra \"i\") monitors  webpages, rss feeds, podcasts etc. It reuses other programs (w3m, diff  etc.) to do most of the actual work. By default, it works on an ASCII  basis, i.e. with the output of text-based webbrowsers like w3m (or lynx,  links etc.) as the output can easily be post-processed. It can also work  with HTML and highlight new items. This script was originally planned as  a ruby-based websec replacement.  By default, this script will use w3m to dump HTML pages and then run  diff over the current page and the previous backup. Some pages are  better viewed with lynx or links. Downloaded documents (HTML or ASCII)  can be post-processed (e.g., filtered through some ruby block that  extracts elements via hpricot and the like). Please see the  configuration options below to find out how to change this globally or  for a single source.  This user manual is also available as PDF[http://websitiary.rubyforge.org/websitary.pdf].  == FEATURES/PROBLEMS: * Handle webpages, rss feeds (optionally save attachments in podcasts  etc.) * Compare webpages with previous backups * Display differences between the current version and the backup * Provide hooks to post-process the downloaded documents and the diff * Display a one-page report summarizing all news * Automatically open the report in your favourite web-browser * Experimental: Download webpages on defined intervalls and generate  incremental diffs."
-autorequire: 
-default_executable: 
-bindir: bin
-has_rdoc: true
-required_ruby_version: !ruby/object:Gem::Version::Requirement 
-  requirements: 
-  - - ">"
-    - !ruby/object:Gem::Version 
-      version: 0.0.0
-  version: 
+  version: "0.4"
 platform: ruby
-signing_key: 
-cert_chain: 
-post_install_message: 
 authors: 
 - Thomas Link
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2008-01-13 00:00:00 +01:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: hpricot
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: hoe
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 1.4.0
+    version: 
+description: "== DESCRIPTION: websitary (formerly known as websitiary with an extra \"i\") monitors  webpages, rss feeds, podcasts etc. It reuses other programs (w3m, diff  etc.) to do most of the actual work. By default, it works on an ASCII  basis, i.e. with the output of text-based webbrowsers like w3m (or lynx,  links etc.) as the output can easily be post-processed. It can also work  with HTML and highlight new items. This script was originally planned as  a ruby-based websec replacement.  By default, this script will use w3m to dump HTML pages and then run  diff over the current page and the previous backup. Some pages are  better viewed with lynx or links. Downloaded documents (HTML or ASCII)  can be post-processed (e.g., filtered through some ruby block that  extracts elements via hpricot and the like). Please see the  configuration options below to find out how to change this globally or  for a single source.  This user manual is also available as PDF[http://websitiary.rubyforge.org/websitary.pdf].  == FEATURES/PROBLEMS: * Handle webpages, rss feeds (optionally save attachments in podcasts  etc.) * Compare webpages with previous backups * Display differences between the current version and the backup * Provide hooks to post-process the downloaded documents and the diff * Display a one-page report summarizing all news * Automatically open the report in your favourite web-browser * Experimental: Download webpages on defined intervalls and generate  incremental diffs."
+email: micathom at gmail com
+executables: 
+- websitary
+extensions: []
+
+extra_rdoc_files: 
+- History.txt
+- Manifest.txt
+- README.txt
 files: 
 - History.txt
 - Manifest.txt
@@ -40,37 +52,32 @@ files:
 - lib/websitary/configuration.rb
 - lib/websitary/filemtimes.rb
 - lib/websitary/htmldiff.rb
-test_files: []
-
+has_rdoc: true
+homepage: http://rubyforge.org/projects/websitiary/
+post_install_message: 
 rdoc_options: 
 - --main
 - README.txt
-extra_rdoc_files: 
-- History.txt
-- Manifest.txt
-- README.txt
-executables: 
-- websitary
-extensions: []
-
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
 requirements: []
 
-dependencies: 
-- !ruby/object:Gem::Dependency 
-  name: hpricot
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Version::Requirement 
-    requirements: 
-    - - ">"
-      - !ruby/object:Gem::Version 
-        version: 0.0.0
-    version: 
-- !ruby/object:Gem::Dependency 
-  name: hoe
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Version::Requirement 
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        version: 1.3.0
-    version: 
+rubyforge_project: websitiary
+rubygems_version: 1.0.1
+signing_key: 
+specification_version: 2
+summary: A unified website news, rss feed, podcast monitor
+test_files: []
+