polyrex-feed-reader 0.3.3 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 773afa001f435cd5649ef38f0192d3c824978741
-  data.tar.gz: 80262467ab430bf114cd75a273fbac0f3ba445a5
+  metadata.gz: d2364e173da28ab14324d98fccf4b354425c0ff0
+  data.tar.gz: 461a2e062a34e5129edfd6af447c5f804f5ea3fa
 SHA512:
-  metadata.gz: b29cf61164afe5004f9834802016ce63abfbd530ced266dc3114f27502193c344b3f806e4689a42b2b14c3a197f1ec8a5e5bb4ca701beccea41c6525d1d831a1
-  data.tar.gz: 8a6d63456eacf1c7c3046183ba658148b17bb83a5c07d7d9beb42449fd64a7960e04f78c1ef058709cccebd46ebf272ae557d229790f413191267a0b00ca7a21
+  metadata.gz: cce648e7b9d68215de24b57f115de5b8df4b380b31117fdff3c391f5ff019e4bf470d9c58ca98eeb1ae3ad1dec3d5e350f2dc9d18e0b6b5b38846caace16ec6c
+  data.tar.gz: 0e9a871c24819b6df8b9d3911161c675ab3b167fa83ba74f95774ca1a3076136ae1114b2b8973233a1fdc44e716fd6d4c3f98ab52defc68518de04bfa831f2a7

data/lib/feeds.xsl

@@ -0,0 +1,48 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
+<xsl:output method="html" indent="yes" />
+
+<xsl:template match='feeds'>
+<xsl:element name="div">
+    <xsl:apply-templates select='summary'/>    
+    <xsl:apply-templates select='records'/>    
+</xsl:element>
+</xsl:template>
+
+<xsl:template match='feeds/summary'>
+  <h1><xsl:value-of select='title'/></h1>  
+</xsl:template>
+
+<xsl:template match='records/column'>
+
+    <xsl:apply-templates select='summary'/>
+    <xsl:apply-templates select='records'/>
+
+</xsl:template>
+
+<xsl:template match='column/summary'>
+  <h2><xsl:value-of select='id'/></h2>
+</xsl:template>
+
+<xsl:template match='records/feed'>
+    <xsl:apply-templates select='summary'/>
+    <ul><xsl:apply-templates select='records'/></ul>
+</xsl:template>
+
+<xsl:template match='feed/summary'>
+    <h3><xsl:value-of select='title'/></h3>
+</xsl:template>
+
+<xsl:template match='records/item'>
+  <li>
+    <xsl:apply-templates select='summary'/>
+    <xsl:apply-templates select='records'/>
+  </li>
+</xsl:template>
+
+<xsl:template match='item/summary'>
+  <h4><xsl:value-of disable-output-escaping="yes" select='title'/></h4>
+  <p><xsl:value-of disable-output-escaping="yes" select='description'/></p>
+</xsl:template>
+
+</xsl:stylesheet>

data/lib/polyrex-feed-reader.rb

@@ -1,196 +1,88 @@
-#!/usr/bin/ruby
+#!/usr/bin/env ruby
 
 # file: polyrex-feed-reader.rb
 
+require 'nokogiri'
+require 'rss_to_dynarex'
 require 'polyrex'
-require 'open-uri'
-require 'rexml/document'
-require 'builder'
-require 'time'
-require 'date'
-require 'chronic'
-require 'pathname'
-
-class Fixnum
-  def seconds() self end
-  def minutes() self * 60 end
-  def hours() self * 60 * 60 end
-  def days() self * 3600 * 24 end
-  def weeks() self * 3600 * 24 * 7 end
-  def months() self * 86400 * 30 end
-  alias second seconds; alias hour hours; alias minute minutes
-  alias day days; alias week weeks; alias month months
-end
-
 
 class PolyrexFeedReader
-  include REXML
-
-  # read the Polyrex file otherwise create the file_path
-  #
-  def initialize(file_path)
-    @file_path = file_path
-    if File.exists? @file_path then
-      @feeds = Polyrex.new @file_path
-    else
-      schema = 'feeds/column[id]/feed[rss_url,title,important,occurrence,recent,url, xhtml, xhtml_mobile, last_modified, last_accessed]/item[title,link,description]'
-      @feeds = Polyrex.new schema
-      @feeds.save @file_path
-    end
-  end
 
-  # read the input from raw lines
-  #
-  def parse(lines)
-    @feeds.parse(lines)
-  end
+  def initialize(polyrex)
 
-  # read all feeds
-  #
-  def read()
-    @feeds.records.each do |col|
-      col.records.each do |feed|
-        fetch_feed(feed)
-      end
-      col.records.sort_by!{|x| -Time.parse(x.text('summary/last_modified').to_s).to_i}
+    @polyrex = polyrex
 
-    end
+  end  
 
-    @feeds.save @file_path
+  def fetch_feeds()
 
-    a = @feeds.records.map {|column| column.records.select{|feed| feed.records.length > 0 }}
-    interleaved = a[0].zip(*a[1..-1]).flatten
+    feeds = @polyrex.xpath('//column/records/feed/summary')
 
-    xml = Builder::XmlMarkup.new( :target => buffer='', :indent => 2 )
-    xml.instruct! :xml, :version => "1.0", :encoding => "UTF-8"
+    feeds.each do |feed|
 
-    xml.feeds do
-      xml.summary do
-        xml.recordx_type 'polyrex'
-      end
-      xml.records do
-        interleaved.each do |feed|
-          xml.feed do
-            xml.summary do
-              xml.title feed.title
-              xml.last_modified feed.last_modified
-              xml.recent feed.recent
-              xml.important feed.important
-            end
-            xml.records do
-              feed.records.each do |item|
-                xml.item do            
-                  xml.summary do
-                    xml.title item.title
-                    xml.description item.description
-                  end
-                  xml.records
-                end
-              end # 
-            end # / records
-          end # /feed
-        end
-      end # /records
-    end
+      puts "fetching %s ..." % feed.text('rss_url').inspect
 
-    buffer
-  end
-  
-  # read a single feed
-  #
-  def read_feed(feed_name)
-    feed = @feeds.find_by_feed_title(feed_name)
-    fetch_feed(feed, save_rss: true)
-    @feeds.save @file_path
-
-    File.open(rss_file(feed),'r').read
+      rtd = RSStoDynarex.new feed.text('rss_url')
+      dynarex = rtd.to_dynarex
+      dynarex.save "%s.xml" % feed.text('title')\
+                          .downcase.gsub(/\s/,'').gsub('-','_')
+    end
   end
 
-  private
-  
-  def fetch_feed(feed, opts={})
-    o = {save_rss: false}.merge opts
-    
-    if scheduled? feed.occurrence and recency(feed.last_accessed) != 'hot' then
-
-      buffer = open(feed.rss_url, 'UserAgent' => 'PolyrexFeedReader').read
-      if o[:save_rss] == true then
-                
-        pathname = Pathname.new(rss_file(feed))
-        pathname.dirname.mkdir unless pathname.dirname.exist?
-        File.open(rss_file(feed),'w'){|f| f.write buffer}
-        
-      end
-      rss_doc = Document.new(buffer)
-      rss_items = XPath.match(rss_doc.root, '//item')[0..2]
+  def refresh
+
+    @polyrex.records.each do |column|
 
-      if feed.records.length <= 0 then
-        # create the items
-        k = 3 - feed.records.length
-        k.times {|x| feed.create.item}
+      column.records.each do |feed|
 
-        fetch_items(rss_items, feed)
+        filename = "%s.xml" % feed.title\
+                            .downcase.gsub(/\s/,'').gsub('-','_')
 
-      else
+        d = Dynarex.new filename
 
-        if REXML::Text::unnormalize(feed.item[0].title) != rss_items[0].text('title').to_s then
+        d.to_h[0..2].each.with_index do |x, i|
 
-          fetch_items(rss_items, feed)
-        else
-          feed.recent = recency(feed.last_modified)
+          h = {title: x[:title]}
+
+          if i == 0 then
+
+            raw_desc = CGI.unescapeHTML(x[:description]).gsub(/<\/?[^>]*>/, "")
+            desc = raw_desc.length > 300 ? raw_desc[0..296] + ' ...' : raw_desc
+            h[:description] = desc
+          end
+
+          feed.create.item h
         end
-      end
-      feed.last_accessed = Time.now   
-    end    
-  end
 
-  def recency(time)  
-    case (Time.now - Time.parse(time))
-      when 1.second..5.minutes then 'hot'
-      when 5.minutes..4.hours then 'warm'
-      when 4.hours..1.week then 'cold'
-      when 1.week..1.month then 'coldx1week'
-      when 1.month..6.months then 'coldx1month'
-      else 'coldx6months'
+      end
     end
   end
 
-  def fetch_items(rss_items, feed)
-    important = feed.important.downcase == 'important' 
-    feed.last_modified = Time.now      
-    feed.recent = 'hot'
+  alias update_doc refresh
 
-    rss_items.each_with_index do |rss_item,i|
-      feed.item[i].title = rss_item.text('title')        
-    end
-    feed.item[0].description = rss_items[0].text('description') if important
-  end
+  def save_html(filepath='feeds.html')
 
-  def scheduled?(s='')
-    a = s.split(/,/).map &:strip
-    return true if a.empty?
-
-    d = Time.now.wday
-    pattern = "%s|%s" % [Date::DAYNAMES[d],Date::ABBR_DAYNAMES[d]]
-    a.map!{|x| x.sub(/#{pattern}/i,'today')}
-
-    dates = a.map do |s|
-      if s.split(/\s/).length > 1 then
-        d = Chronic.parse(s, guess: false)
-        [d.first, d.last]
-      else
-        d = Chronic.parse(s)
-        d1 = d2 =  Time.parse("%s-%s-%s" % [d.year, d.month, d.day])
-        [d1, d2 + 24.hours]
-      end
-    end
+    lib = File.dirname(__FILE__)
+    xsl_buffer = File.read(lib + '/feeds.xsl')
+    #xsl_buffer = File.read('feeds.xsl')
 
-    dates.detect{|x| Time.now.between? *x} ? true : false
+    xslt  = Nokogiri::XSLT(xsl_buffer)
+    html = xslt.transform(Nokogiri::XML(@polyrex.to_xml)).to_s
+    File.write filepath, html
   end
-  
-  def rss_file(feed)
-    "%s/%s/%s.rss" % [File.dirname(@file_path), feed.parent.id, feed.title]    
+
+  def save_xml(filepath='feeds.xml')
+    @polyrex.save filepath, pretty: true
   end
 
 end
 
+if __FILE__ == $0 then
+
+  pfr = PolyrexFeedReader.new(px)
+  pfr.fetch_feeds
+  pfr.update_doc
+  pfr.save_xml 'feeds.xml'
+  pfr.save_html 'feeds.html'
+
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: polyrex-feed-reader
 version: !ruby/object:Gem::Version
-  version: 0.3.3
+  version: 0.5.0
 platform: ruby
 authors:
 - James Robertson
@@ -29,48 +29,48 @@ cert_chain:
   LxhpHfLSRfOWDFimU0YGVs8dISSHOneULhblAYTTb7tvv2Zr8wG/bdlLhWuwoz23
   L5EDjzznPMmVNG60mdktue6PKdOEFp7N
   -----END CERTIFICATE-----
-date: 2013-07-27 00:00:00.000000000 Z
+date: 2013-12-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: polyrex
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: builder
+  name: rss_to_dynarex
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: chronic
+  name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 description: 
@@ -80,6 +80,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - lib/polyrex-feed-reader.rb
+- lib/feeds.xsl
 homepage: https://github.com/jrobertson/polyrex-feed-reader
 licenses:
 - MIT
@@ -90,12 +91,12 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
@@ -103,5 +104,6 @@ rubyforge_project:
 rubygems_version: 2.0.0.rc.2
 signing_key: 
 specification_version: 4
-summary: polyrex-feed-reader
+summary: Fetches RSS feeds from a Polyrex file and displays each feed summary on an
+  HTML page
 test_files: []