DZone Snippets: atom code

Supporting authenticated web feeds in rss2imbot

jrobertson (James Robertson) — Fri, 26 Sep 2008 13:30:44 GMT



  def fetch_title(url)

    buffer = open(url, "UserAgent" => "Ruby-RSS2IMbot").read

    get_title(buffer)

  end



  def fetch_secure_title(url, username, password)

    client = HTTPClient.new

    client.set_auth(url, username, password)

    buffer = client.get(url)

    get_title(buffer.content)

  end

here is the modification to function 'action_msg'



    case action

      when 'add'

        remainder = $3

        rss_feed = remainder[/^(https?sec:\/\/.[^\s]+)/,1]

        unless rss_feed.nil?

          after_url = $'



          # check if there are authentation details to be included

          username = after_url[/-u\s+(\w+)\s+-p\s+(\w+)/,1]

          puts 'username : ' + username

          if username.nil?

            title = fetch_title(rss_feed)

          else

            password = $2

            puts 'password : ' + password

            title = fetch_secure_title(rss_feed, username, password) 

          end



          add_feed(title,rss_feed, username, password)

        else

           messenger.deliver(buddy,  "That web feed isn't valid'")

        end



  def fetch_feed(url5)



    buffer7 = open(url5, "UserAgent" => "Ruby-RSS2IMbot").read

    get_item(buffer7)

  end



  def fetch_secure_feed(url5, username, password)



    client = HTTPClient.new

    client.set_auth(url5, username, password)

    buffer7 = client.get(url5)

     

    get_item(buffer7.content)

  end







  # displays only the latest unread new message from each feed

  def check_feed(messenger)

    result = false

    puts 'check feed'

    buddy = @user



    url = URL_BASE + "select/rss2imbot.db/t#{@table}/column=*"

    buffer = open(url, "UserAgent" => "Ruby-RSS2IMbot").read



    doc = ''

    doc = Document.new(buffer)

    rows = ''

    rows = doc.root.elements['rows']

    puts 'rows : ' + rows.to_s

    unless rows.nil?

      puts 'rows exist'

      result = rows.elements.each('row'){}.map do |node|

        puts 'looking at a row'



        # check for a new item

        # if it's different alert the user and update the database, then go to next link,

        rss_title = node.elements["col[@name='title']"].text.to_s

        old_item_link = ''

        old_item_link = node.elements["col[@name='item_link']"].text.to_s + ''

        id = node.elements["col[@name='t1key']"].text.to_s

        rss_link = node.elements["col[@name='link']"].text.to_s

        username = node.elements["col[@name='username']"].text.to_s + ''

        password = node.elements["col[@name='password']"].text.to_s + ''



        if username.empty? then

          #get the latest item from the rss feed

          new_item_title, new_item_link = fetch_feed(rss_link)

        else

          new_item_title, new_item_link = fetch_secure_feed(rss_link, username, password)

        end

        #puts 'after get_item_title'

        unless new_item_title.empty?

          #puts 'comparing new_item_link ; *' + new_item_link + '*' 

          #puts 'with old_item_link ; *' + old_item_link + '*' 



          if new_item_link != old_item_link then

            #update record

            result = update_feed(id, new_item_link)

            messenger.deliver(@user,  '"' + new_item_title + '" ' + new_item_link)

          end

        end



      end

    end

  end

References:
- XMPP simple feed reader [dzone.com]
- Retrieve your Gmail messages as an XML feed [dzone.com]

XMPP simple feed reader

jrobertson (James Robertson) — Tue, 16 Sep 2008 00:29:46 GMT

This Ruby script is based on the code from Build your own Twitter 'track' feature [dzone.com] but now the latest entry can be tracked for any RSS or Atom feed.

#!/usr/bin/ruby



#file: xmppserver_db1.rb



require 'rubygems'  

require 'open-uri'

require 'xmpp4r-simple'

require 'rexml/document'

include REXML



URL_BASE = 'http://yourwebsite.com/sqlite3/'

messenger = Jabber::Simple.new('jeeves3@jamesrobertson.eu', "passwordsecret")

$file = ''



class String

  def escape()

    URI.escape(self).gsub(/\?/,'%3F')

  end

end



def get_title(url)



  title = ''

  buffer = open(url, "UserAgent" => "Ruby-RSS2IMbot").read



  doc = Document.new(buffer)

  # get the title

  node_title = doc.root.elements['channel/title|title']

  puts 'title : ' + node_title.to_s

  unless node_title.nil?

    title = node_title.text.to_s

  end

  title

end



# displays only the latest unread new message from each feed

def check_feed(messenger)

  result = false

  puts 'check feed'

  buddy = 'james@jamesrobertson.eu'



  url = URL_BASE + "select/rss2imbot.db/t1/column=*"

  buffer = open(url, "UserAgent" => "Ruby-RSS2IMbot").read

  doc = Document.new(buffer)

  rows = doc.root.elements['rows']

  puts 'rows : ' + rows.to_s

  unless rows.nil?

    result = rows.elements.each('row'){}.map do |node|

      # check for a new item

      # if it's different alert the user and update the database, then go to next link,

      rss_title = node.elements["col[@name='title']"].text.to_s

      old_item_title = node.elements["col[@name='item_title']"].text.to_s

      id = node.elements["col[@name='t1key']"].text.to_s

      rss_link = node.elements["col[@name='link']"].text.to_s



      #get the latest item from the rss feed

      new_item_title, link = get_item_title(rss_link)



      if new_item_title != old_item_title then



        #update record

        result = update_feed(id, new_item_title)

        messenger.deliver(buddy,  '"' + new_item_title + '" ' + link)

      end



    end

  end

end





def update_feed(id, item_title)

  result = false



  url = URL_BASE + "update/rss2imbot.db/t1/set-column=item_title:#{item_title.escape}&t1key=#{id}"

  buffer = open(url, "UserAgent" => "Ruby-RSS2IMbot").read

  doc = Document.new(buffer)

  node_result = doc.root.attribute('method')

  result = true unless node_result.nil?

  result

end



def get_item_title(url)



  title = ''

  buffer = open(url, "UserAgent" => "Ruby-RSS2IMbot").read



  doc = Document.new(buffer)

  # get the title

  node_title = doc.root.elements['channel/item/title|entry/title']

  unless node_title.nil?

    title = node_title.text.to_s

    node_link = doc.root.elements['channel/item/link|entry/link']

    unless node_link.nil?

      unless node_link.text.to_s.empty? then

        link = node_link.text.to_s # it's an rss feed

      else

        link = node_link.attribute('href').to_s # it's an atom feed

      end

    end

  end

  return title, link

end



def action_msg(messenger, buddy, message)



  action = message[/^(\w+)(\s+)?(.*)?/,1]



  case action

    when 'add'

      rss_feed = $3

      if rss_feed.match(/^http:\/\/.*$/) then

        title = get_title(rss_feed)

        add_feed(title,rss_feed)

      else

         messenger.deliver(buddy,  "That web feed isn't valid'")

      end



    when 'list'

      url = URL_BASE + "select/rss2imbot.db/t1/column=*"

      buffer = open(url,"UserAgent" => "Ruby-IMBot").read

      doc = Document.new(buffer)

      rows = doc.root.elements['rows']

      unless rows.nil?

        result = rows.elements.each('row'){}.map do |node|

          node.attribute('id').to_s + '. ' + node.elements["col[@name='title']"].text.to_s

        end

        messenger.deliver(buddy,  result.inspect)

      end



    when 'remove'

      id = $3



      url = URL_BASE + 'select/rss2imbot.db/t1/column=title&t1key=1'

      buffer = open(url,"UserAgent" => "Ruby-IMBot").read

      doc = Document.new(buffer)

      node_col = doc.root.elements['rows/row/col']

      unless node_col.nil? 

  

        title = node_col.text.to_s

        messenger.deliver(buddy,   'remove \'' + title + '\' (y/n)') 

        elapsed = 0

        start_time = Time.now

        answered = false

        response = ''



        while (elapsed < 30 and not answered == true)

          messenger.received_messages do |msg|  

            puts msg.body

            if msg.body.match(/^(y|n)$/) then

              response = msg.body

              answered = true            

            end

          end

          elapsed = Time.now - start_time        

        end

        messenger.deliver(buddy, 'you took too long to answer, I\'m *not* removing any feed now!') if elapsed >= 30

        if response == 'y' then

          messenger.deliver(buddy,   ' will now remove ' + title)  

          url = URL_BASE + "delete/rss2imbot.db/t1/t1key=#{id}"

          result_buffer = open(url,"UserAgent" => "Ruby-IMBot").read

          doc_result = Document.new(result_buffer)

          node_result = doc_result.root.attribute('method')

          messenger.deliver(buddy,   '\'' + title + '\' has been removed.') unless node_result.nil?

        end

      end



    when 'help'

      messenger.deliver(buddy,   "Help: 'add' a feed, 'list' all feeds, or 'remove' a feed.") 

  else

    puts 'sorry I don\'t know how to process that. Type \'help\' for a list of commands.'

  end

end



def add_feed(title, link)

  result = false



  puts "insert/rss2imbot.db/t1/title=#{title.escape}&link=#{link.escape}"

  url = URL_BASE + "insert/rss2imbot.db/t1/title=#{title.escape}&link=#{link.escape}"

  buffer = open(url, "UserAgent" => "Ruby-RSS2IMbot").read

  doc = Document.new(buffer)

  node_result = doc.root.attribute('method')

  result = true unless node_result.nil?

  result

end





while true



  # check the feeds every 1 minute.

  check_feed(messenger) if Time.now.strftime("%S").to_i <= 3

  messenger.received_messages do |msg|  



    message = URI.unescape(msg.body).gsub(/</,'<').gsub(/>/,'>').gsub(/'/,'\'').gsub(/"/,'"').gsub(/&/,'&')

    buddy = msg.from



    messenger.deliver(buddy,  "you said ... " + message)    

    action_msg(messenger,buddy, message)



  end  

  sleep 2

end

test:
[01:20:38] jeeves3 is now Available (Available)
[01:20:41] James: list
[01:20:42] jeeves3: you said ... list
[01:20:43] jeeves3: ["1. ruby - Twitter Search"]
[01:21:04] jeeves3: "babysitting Ruby while the missus gets some accupuncture.. now covered in vomit too - thanks Ruby!" http://twitter.com/gregdwyer/statuses/922733451
[01:21:39] James: add http://snippets.dzone.com/rss
[01:21:41] jeeves3: you said ... add http://snippets.dzone.com/rss
[01:22:16] jeeves3: "Test" http://feeds.dzone.com/~r/dzone/snippets/~3/393549326/6080
[01:22:20] James: list
[01:22:20] jeeves3: you said ... list
[01:22:21] jeeves3: ["1. ruby - Twitter Search", "2. DZone Snippets: Store, sort and share source code, with tag goodness"]
[01:22:49] James: remove 1
[01:22:49] jeeves3: you said ... remove 1
[01:22:51] jeeves3: remove 'ruby - Twitter Search' (y/n)
[01:22:53] James: y
[01:22:53] jeeves3: will now remove ruby - Twitter Search
[01:22:54] jeeves3: 'ruby - Twitter Search' has been removed.
[01:22:57] James: list
[01:22:58] jeeves3: you said ... list
[01:23:00] jeeves3: ["1. DZone Snippets: Store, sort and share source code, with tag goodness"]

Retrieve your Gmail messages as an XML feed

jrobertson (James Robertson) — Sun, 03 Feb 2008 16:29:06 GMT

This Ruby example shows how to retrieve your most recent email as an atom XML feed from the Google Apps website.



require 'rubygems'

require 'httpclient'



url = "https://mail.google.com/a/yourwebsite.com/feed/atom"

client = HTTPClient.new

client.debug_dev = STDOUT if $DEBUG

client.set_auth(url, 'yourname@yourwebsite.com', 'yourpassword')

resp = client.get(url)

Note: You might require to gem install httpclient.

RSS/Atom Autodiscovery

nathancarnes (Nathan Carnes) — Thu, 12 Apr 2007 04:33:43 GMT

// description of your code here

Blogmarks to Html conversion

ms_michel (Michel) — Fri, 20 Jan 2006 01:18:44 GMT

This file is intended to transform a Blogmarks atom feed (http://api.blogmarks.net/user/ms_michel) into html code fragment to be included in a complete page.







  

  

    

    

    

  

  

    

  

  

    

  

  

    

      

        

          bm_blogmarks bm_odd

        

        

          bm_blogmarks bm_even

        

      

      

      

      

      

        

        

          

             -

The generated html is inspired by the one used on Hot Links (http://dev.upian.com/hotlinks/). It can be styled with the following css:



.bm_blogmarks {

	margin: 10px auto;

	padding: 1%;

	background-color: #f5f5f5;

	border: 1px solid #d9d9d9;

	width: 97%;

	overflow:auto;

}

.bm_even {

    background-color: #fcfcfc;

}

.bm_blogmarks h4 {

	margin-top: 0;

}

.bm_blogmarks p.bm_tags {

	margin-bottom: 0;

	display: block;

	clear: left;

}

.bm_blogmarks img {

	margin: 0 0px 5px 10px;

	float: right;

	border: 0;

	clear: none;

	width: 144px;

	height: 107px;

}

.bm_even img {

	margin: 0 10px 5px 0px;

	float: left;

}

Atom to Html conversion

ms_michel (Michel) — Mon, 16 Jan 2006 19:59:16 GMT

This file is intended to transform an Atom feed into html code fragment to be included in a complete page.





  xmlns:atom="http://purl.org/atom/ns#"

  xmlns:xsl="http://www.w3.org/1999/XSL/Transform"

  xmlns:dc="http://purl.org/dc/elements/1.1/">

Atom rxml template

sco (Scott Raymond) — Sat, 06 Aug 2005 02:53:28 GMT

This rxml template (modified from the one in blinksale.com) generates valid Atom 1.0 feeds. If you have a partial to create HTML for each item, they can be included in the feed's "content" elements.



xml.instruct!



xml.feed "xmlns" => "http://www.w3.org/2005/Atom" do



  xml.title   "Feed Name"

  xml.link    "rel" => "self", "href" => url_for(:only_path => false, :controller => 'feeds', :action => 'atom')

  xml.link    "rel" => "alternate", "href" => url_for(:only_path => false, :controller => 'posts')

  xml.id      url_for(:only_path => false, :controller => 'posts')

  xml.updated @posts.first.updated_at.strftime "%Y-%m-%dT%H:%M:%SZ" if @posts.any?

  xml.author  { xml.name "Author Name" }



  @posts.each do |post|

    xml.entry do

      xml.title   post.title

      xml.link    "rel" => "alternate", "href" => url_for(:only_path => false, :controller => 'posts', :action => 'show', :id => post.id)

      xml.id      url_for(:only_path => false, :controller => 'posts', :action => 'show', :id => post.id)

      xml.updated post.updated_at.strftime "%Y-%m-%dT%H:%M:%SZ"

      xml.author  { xml.name post.author.name }

      xml.summary "Post summary"

      xml.content "type" => "html" do

        xml.text! render(:partial => "posts/post", :post => post)

      end

    end

  end



end

Atom / RSS feed of your GMail account

peter (Peter Cooperx) — Sat, 07 May 2005 22:45:40 GMT

https://USERNAME:PASSWORD@gmail.google.com/gmail/feed/atom