statement 0.6 → 0.7

data/lib/statement/version.rb

@@ -1,3 +1,3 @@
 module Statement
-  VERSION = "0.6"
+  VERSION = "0.7"
 end

data/lib/statement.rb

@@ -10,26 +10,53 @@ module Statement
   class Link
     def self.absolute_link(url, link)
       return link if link =~ /^http:\/\//
-
-      (URI.parse(url) + link).to_s
+      ("http://"+URI.parse(url).host + "/"+link).to_s
+    end
+    
+    def self.open_rss(url)
+      begin
+        Nokogiri::XML(open(url))
+      rescue
+        nil
+      end
+    end
+    
+    def self.open_html(url)
+      begin
+        Nokogiri::HTML(open(url).read)
+      rescue
+        nil
+      end
+    end
+    
+    def self.date_from_rss_item(link)
+      if !link.xpath('pubDate').empty?
+        Date.parse(link.xpath('pubDate').text)
+      elsif !link.xpath('pubdate').empty?
+        Date.parse(link.xpath('pubdate').text)
+      else
+        nil
+      end
     end
 
     def self.from_rss(url)
-      doc = Nokogiri::XML(open(url))
+      doc = open_rss(url)
+      return unless doc
       links = doc.xpath('//item')
-      links.map do |link| 
+      links.map do |link|
         abs_link = absolute_link(url, link.xpath('link').text)
-        { :source => url, :url => abs_link, :title => link.xpath('title').text, :date => link.xpath('pubDate').empty? ? nil: Date.parse(link.xpath('pubDate').text), :domain => URI.parse(link.xpath('link').text).host }
+        abs_link = "http://www.burr.senate.gov/public/"+ link.xpath('link').text if url == 'http://www.burr.senate.gov/public/index.cfm?FuseAction=RSS.Feed'
+        { :source => url, :url => abs_link, :title => link.xpath('title').text, :date => date_from_rss_item(link), :domain => URI.parse(url).host }
       end
     end
     
     def self.house_gop(url)
+      doc = open_html(url)
+      return unless doc
       uri = URI.parse(url)
       date = Date.parse(uri.query.split('=').last)
-      doc = Nokogiri::HTML(open(url).read)
       links = doc.xpath("//ul[@id='membernews']").search('a')
       links.map do |link| 
-        # return a hash
         abs_link = absolute_link(url, link["href"])
         { :source => url, :url => abs_link, :title => link.text.strip, :date => date, :domain => URI.parse(link["href"]).host }
       end
@@ -55,7 +82,8 @@ module Statement
       results = []
       base_url = "http://www.house.gov/capuano/news/"
       list_url = base_url + 'date.shtml'
-      doc = Nokogiri::HTML(open(list_url).read)
+      doc = open_html(list_url)
+      return if doc.nil?
       doc.xpath("//a").each do |link|
         if link['href'] and link['href'].include?('/pr')
           begin 
@@ -82,7 +110,8 @@ module Statement
         else
           url = "http://"+domain + "index.cfm/press-releases?YearDisplay=#{year}&MonthDisplay=#{month}&page=1"
         end
-        doc = Nokogiri::HTML(open(url).read)
+        doc = open_html(url)
+        return if doc.nil?
         doc.xpath("//tr")[2..-1].each do |row|
           date_text, title = row.children.map{|c| c.text.strip}.reject{|c| c.empty?}
           next if date_text == 'Date' or date_text.size > 8
@@ -97,7 +126,8 @@ module Statement
       results = []
       base_url = "http://conaway.house.gov/news/"
       page_url = base_url + "documentquery.aspx?DocumentTypeID=1279&Page=#{page}"
-      doc = Nokogiri::HTML(open(page_url).read)
+      doc = open_html(page_url)
+      return if doc.nil?
       doc.xpath("//tr")[1..-1].each do |row|
         results << { :source => page_url, :url => base_url + row.children.children[1]['href'], :title => row.children.children[1].text.strip, :date => Date.parse(row.children.children[4].text), :domain => "conaway.house.gov" }
       end
@@ -107,7 +137,8 @@ module Statement
     def self.susandavis
       results = []
       base_url = "http://www.house.gov/susandavis/"
-      doc = Nokogiri::HTML(open(base_url+'news.shtml').read)
+      doc = open_html(base_url+'news.shtml')
+      return if doc.nil?
       doc.search("ul")[6].children.each do |row|
         next if row.text.strip == ''
         results << { :source => base_url+'news.shtml', :url => base_url + row.children[1]['href'], :title => row.children[1].text.split.join(' '), :date => Date.parse(row.children.first.text), :domain => "house.gov/susandavis" }
@@ -118,7 +149,8 @@ module Statement
     def self.faleomavaega
       results = []
       base_url = "http://www.house.gov/faleomavaega/news-press.shtml"
-      doc = Nokogiri::HTML(open(base_url).read)
+      doc = open_html(base_url)
+      return if doc.nil?
       doc.xpath("//li[@type='disc']").each do |row|
         results << { :source => base_url, :url => "http://www.house.gov/" + row.children[0]['href'], :title => row.children[0].text.gsub(/[u201cu201d]/, '').split('Washington, D.C.').last, :date => Date.parse(row.children[1].text), :domain => "house.gov/faleomavaega" }
       end
@@ -129,7 +161,8 @@ module Statement
       results = []
       ['baldwin', 'donnelly', 'flake', 'hirono','heinrich','murphy','scott','king','heitkamp','cruz','kaine'].each do |senator|
         base_url = "http://www.#{senator}.senate.gov/"
-        doc = Nokogiri::HTML(open(base_url+'press.cfm?maxrows=200&startrow=1&&type=1').read)
+        doc = open_html(base_url+'press.cfm?maxrows=200&startrow=1&&type=1')
+        return if doc.nil?
         doc.xpath("//tr")[3..-1].each do |row|
           next if row.text.strip == ''
           results << { :source => base_url+'press.cfm?maxrows=200&startrow=1&&type=1', :url => base_url + row.children.children[1]['href'], :title => row.children.children[1].text.strip.split.join(' '), :date => Date.parse(row.children.children[0].text), :domain => "#{senator}.senate.gov" }
@@ -143,7 +176,8 @@ module Statement
       base_url = "http://www.klobuchar.senate.gov/"
       [2012,2013].each do |year|
         year_url = base_url + "newsreleases.cfm?year=#{year}"
-        doc = Nokogiri::HTML(open(year_url).read)
+        doc = open_html(year_url)
+        return if doc.nil?
         doc.xpath("//dt").each do |row|
           results << { :source => year_url, :url => base_url + row.next.children[0]['href'], :title => row.next.text.strip.gsub(/[u201cu201d]/, '').split.join(' '), :date => Date.parse(row.text), :domain => "klobuchar.senate.gov" }
         end
@@ -154,7 +188,8 @@ module Statement
     def self.lujan
       results = []
       base_url = 'http://lujan.house.gov/'
-      doc = Nokogiri::HTML(open(base_url+'index.php?option=com_content&view=article&id=981&Itemid=78').read)
+      doc = open_html(base_url+'index.php?option=com_content&view=article&id=981&Itemid=78')
+      return if doc.nil?
       doc.xpath('//ul')[1].children.each do |row|
         next if row.text.strip == ''
         results << { :source => base_url+'index.php?option=com_content&view=article&id=981&Itemid=78', :url => base_url + row.children[0]['href'], :title => row.children[0].text, :date => nil, :domain => "lujan.house.gov" }
@@ -166,7 +201,8 @@ module Statement
       results = []
       base_url = "http://www.billnelson.senate.gov/news/"
       year_url = base_url + "media.cfm?year=#{year}"
-      doc = Nokogiri::HTML(open(year_url).read)
+      doc = open_html(year_url)
+      return if doc.nil?
       doc.xpath('//li').each do |row|
         results << { :source => year_url, :url => base_url + row.children[0]['href'], :title => row.children[0].text.strip, :date => Date.parse(row.children.last.text), :domain => "billnelson.senate.gov" }
       end
@@ -178,7 +214,8 @@ module Statement
       results = []
       base_url = 'http://www.lautenberg.senate.gov/newsroom/'
       url = base_url + "releases.cfm?maxrows=#{rows}&startrow=1&&type=1"
-      doc = Nokogiri::HTML(open(url).read)
+      doc = open_html(url)
+      return if doc.nil?
       doc.xpath("//tr")[4..-2].each do |row|
         results << { :source => url, :url => base_url + row.children[2].children[0]['href'], :title => row.children[2].text.strip, :date => Date.parse(row.children[0].text.strip), :domain => "lautenberg.senate.gov" }
       end
@@ -189,7 +226,8 @@ module Statement
       results = []
       base_url = "http://www.crapo.senate.gov/media/newsreleases/"
       url = base_url + "release_all.cfm"
-      doc = Nokogiri::HTML(open(url).read)
+      doc = open_html(url)
+      return if doc.nil?
       doc.xpath("//tr").each do |row|
         results << { :source => url, :url => base_url + row.children[2].children[0]['href'], :title => row.children[2].text.strip, :date => Date.parse(row.children[0].text.strip.gsub('-','/')), :domain => "crapo.senate.gov" }
       end
@@ -199,7 +237,8 @@ module Statement
     def self.coburn(year=Date.today.year)
       results = []
       url = "http://www.coburn.senate.gov/public/index.cfm?p=PressReleases&ContentType_id=d741b7a7-7863-4223-9904-8cb9378aa03a&Group_id=7a55cb96-4639-4dac-8c0c-99a4a227bd3a&MonthDisplay=0&YearDisplay=#{year}"
-      doc = Nokogiri::HTML(open(url).read)
+      doc = open_html(url)
+      return if doc.nil?
       doc.xpath("//tr")[2..-1].each do |row|
         next if row.text[0..3] == "Date"
         results << { :source => url, :url => row.children[2].children[0]['href'], :title => row.children[2].text.strip, :date => Date.parse(row.children[0].text.strip), :domain => "coburn.senate.gov" }
@@ -211,7 +250,8 @@ module Statement
       results = []
       url = "http://www.boxer.senate.gov/en/press/releases.cfm?start=#{start}"
       domain = 'www.boxer.senate.gov'
-      doc = Nokogiri::HTML(open(url).read)
+      doc = open_html(url)
+      return if doc.nil?
       doc.xpath("//div[@class='left']")[1..-1].each do |row|
         results << { :source => url, :url => domain + row.next.next.children[1].children[0]['href'], :title => row.next.next.children[1].children[0].text, :date => Date.parse(row.text.strip), :domain => domain}
       end
@@ -222,7 +262,8 @@ module Statement
       results = []
       url = "http://www.mccain.senate.gov/public/index.cfm?FuseAction=PressOffice.PressReleases&ContentRecordType_id=75e7e4a0-6088-44b6-8061-089d80513dc4&Region_id=&Issue_id=&MonthDisplay=0&YearDisplay=#{year}"
       domain = 'www.mccain.senate.gov'
-      doc = Nokogiri::HTML(open(url).read)
+      doc = open_html(url)
+      return if doc.nil?
       doc.xpath("//li")[7..-1].each do |row|
         results << { :source => url, :url => domain + row.children[3].children[1].children[4].children[0]['href'], :title => row.children[3].children[1].children[4].text, :date => Date.parse(row.children[3].children[1].children[0].text), :domain => domain}
       end
@@ -235,7 +276,8 @@ module Statement
       urls.each do |url|
         next if year < 2013 and url == "http://www.cowan.senate.gov/"
         domain = url == "http://www.vitter.senate.gov/newsroom/" ? "www.vitter.senate.gov" : "www.cowan.senate.gov"
-        doc = Nokogiri::HTML(open(url+"press?year=#{year}").read)
+        doc = open_html(url+"press?year=#{year}")
+        return if doc.nil?
         doc.xpath("//tr")[1..-1].each do |row|
           next if row.text.strip.size < 30
           results << { :source => url, :url => row.children[2].children[0]['href'].strip, :title => row.children[2].text, :date => Date.parse(row.children[0].text), :domain => domain}
@@ -248,7 +290,8 @@ module Statement
       results = []
       url = "http://www.inhofe.senate.gov/newsroom/press-releases?year=#{year}"
       domain = "www.inhofe.senate.gov"
-      doc = Nokogiri::HTML(open(url).read)
+      doc = open_html(url)
+      return if doc.nil?
       doc.xpath("//tr")[1..-1].each do |row|
         results << { :source => url, :url => row.children[2].children[0]['href'].strip, :title => row.children[2].text, :date => Date.parse(row.children[0].text), :domain => domain}
       end
@@ -259,7 +302,8 @@ module Statement
       results = []
       url = "http://www.levin.senate.gov/newsroom/index.cfm?PageNum_rs=#{page}&section=press"
       domain = "www.levin.senate.gov"
-      doc = Nokogiri::HTML(open(url).read)
+      doc = open_html(url)
+      return if doc.nil?
       doc.xpath('//tr').each do |row|
         results << { :source => url, :url => row.children[2].children[0]['href'].gsub(/\s+/, ""), :title => row.children[2].children[0].text, :date => Date.parse(row.children[0].text), :domain => domain}
       end
@@ -270,7 +314,8 @@ module Statement
       results = []
       url = "http://www.reid.senate.gov/newsroom/press_releases.cfm"
       domain = "www.reid.senate.gov"
-      doc = Nokogiri::HTML(open(url).read)
+      doc = open_html(url)
+      return if doc.nil?
       doc.xpath("//table[@id='CS_PgIndex_21891_21893']//tr")[1..-1].each do |row|
         results << { :source => url, :url => "http://www.reid.senate.gov"+row.children[0].children[0]['href'], :title => row.children[0].children[0].text, :date => Date.parse(row.children[0].children[2].text), :domain => domain}
       end
@@ -281,7 +326,8 @@ module Statement
       results = []
       domains = [{"roe.house.gov" => 1532}, {"thornberry.house.gov" => 1776}, {"wenstrup.house.gov" => 2491}]
       domains.each do |domain|
-        doc = Nokogiri::HTML(open("http://"+domain.keys.first+"/news/documentquery.aspx?DocumentTypeID=#{domain.values.first}&Page=#{page}").read)
+        doc = open_html("http://"+domain.keys.first+"/news/documentquery.aspx?DocumentTypeID=#{domain.values.first}&Page=#{page}")
+        return if doc.nil?
         doc.xpath("//span[@class='middlecopy']").each do |row|
           results << { :source => "http://"+domain.keys.first+"/news/"+"documentquery.aspx?DocumentTypeID=#{domain.values.first}&Page=#{page}", :url => "http://"+domain.keys.first+"/news/" + row.children[6]['href'], :title => row.children[1].text.strip, :date => Date.parse(row.children[4].text.strip), :domain => domain.keys.first }
         end

data/spec/house_gop_releases.html

@@ -159,7 +159,7 @@
            </a>
          </li>
         <li>
-           <a href="other/relative_url_test.html" target="_blank">
+           <a href="republicans/other/relative_url_test.html" target="_blank">
              <img src="/resources/images/contact/members/113/WA/04x60.jpg" border="0" alt="" width="40" style="float: left; margin-right: 10px;" />
              Relative URL test
            </a>

data/spec/richard_burr.xml

@@ -0,0 +1,196 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<rss version="2.0">
+		<channel>
+			<title>Richard Burr, United States Senator of North Carolina</title>
+			<link>http://www.burr.senate.gov/public/</link>
+			<description>A collection of the posts to Richard Burr, United States Senator of North Carolina's website.</description>
+			<!-- 
+			<image>
+				<title>Richard Burr, United States Senator of North Carolina</title>
+				<link>http://www.burr.senate.gov/public/</link>
+				<url>http://www.burr.senate.gov/public/_images/rss_banner.gif</url>
+			</image>
+			 -->
+			<docs>index.cfm?FuseAction=RSS.About</docs>
+			<generator>SiteDirector || www.gslsolutions.com</generator>
+			<language>en-us</language>
+			<lastbuilddate>Tue, 07 May 2013 12:45:39 EST</lastbuilddate>
+			<webmaster>support@gslsolutions.com</webmaster>
+			
+			<item>
+				<title>Senator Burr Congratulates Rep. Mel Watt On His Nomination As FHFA Director</title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=65dbea38-d64c-6208-ef8f-2b000e899b3a</link>
+				<category>Press Release</category>
+				<pubdate>Thu, 02 May 2013 11:27:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senator Burr Congratulates Charlotte Mayor Anthony Foxx On His Nomination As Transportation Secretary</title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=5712e00a-cd2a-0e38-9b57-90e9b9d2bc2e</link>
+				<category>Press Release</category>
+				<pubdate>Mon, 29 Apr 2013 02:32:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Sanders, Burr Propose Legislation for Homeless Veterans  </title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=42cf2199-f221-d2e6-4b48-945212c16f6c</link>
+				<category>Press Release</category>
+				<pubdate>Thu, 25 Apr 2013 04:03:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senator Burr Statement on Constituent Mailing Operations  </title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=3da93329-977f-867f-8b83-28c2ab5f4f50</link>
+				<category>Press Release</category>
+				<pubdate>Wed, 24 Apr 2013 04:05:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Burr, Coburn, Thune Introduce Public Employee Pension Transparency Act</title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=38458726-b8d6-0e8c-b1d4-935b9ffe0b9b</link>
+				<category>Press Release</category>
+				<pubdate>Tue, 23 Apr 2013 02:58:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senator Burr Announces Opposition to Manchin-Toomey Amendment</title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=13190e4a-ecf0-4e63-65f9-dc6878152437</link>
+				<category>Press Release</category>
+				<pubdate>Tue, 16 Apr 2013 09:45:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>The President's Budget</title>
+				<link>index.cfm?FuseAction=PressOffice.Blogs&amp;Type=Blog&amp;ContentRecord_id=f9a8d43b-998f-e827-0106-27170d45b646</link>
+				<category>Blog</category>
+				<pubdate>Thu, 11 Apr 2013 11:00:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senator Burr Votes Against Irresponsible Senate Budget</title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=97794cc5-ae48-edc6-1636-6d6cb2ba2907</link>
+				<category>Press Release</category>
+				<pubdate>Sat, 23 Mar 2013 09:37:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senator Burr Introduces Child Care Protection Act of 2013 </title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=897e43f5-98e9-9fe5-5997-e48fd6da7ad5</link>
+				<category>Press Release</category>
+				<pubdate>Wed, 20 Mar 2013 04:13:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senator Burr Introduces Veterans Second Amendment Protection Act</title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=6a68a29a-d82c-d395-729d-3490338689eb</link>
+				<category>Press Release</category>
+				<pubdate>Thu, 14 Mar 2013 03:36:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Burr Reorganization Bill Would Put Veterans' Health Care First</title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=69722f69-99d4-e00c-2cf6-dfaaab0b829c</link>
+				<category>Press Release</category>
+				<pubdate>Thu, 14 Mar 2013 11:01:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Bill to Protect Americans From Bioterrorism and Pandemics Becomes Law</title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=65bd54eb-c17a-0c29-aed9-604dd6ceec8e</link>
+				<category>Press Release</category>
+				<pubdate>Wed, 13 Mar 2013 05:50:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Burr Bill Will Modify Commencement Date on Camp Lejeune Water Contamination </title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=6586dabb-fb95-2952-3c2f-c57b0c77a622</link>
+				<category>Press Release</category>
+				<pubdate>Wed, 13 Mar 2013 04:51:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senators Burr, Hagan Reintroduce Bill that Would Allow Off-Road Vehicle Use on Cape Hatteras National Seashore</title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=46db2d27-0e21-ceac-d353-9121c89d17a6</link>
+				<category>Press Release</category>
+				<pubdate>Thu, 07 Mar 2013 04:54:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senator Burr Introduces Careers for Veterans Act</title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=46d955e3-c359-6136-c4df-10011c441cb1</link>
+				<category>Press Release</category>
+				<pubdate>Thu, 07 Mar 2013 04:52:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Working to address our nation's economic issues</title>
+				<link>index.cfm?FuseAction=PressOffice.Blogs&amp;Type=Blog&amp;ContentRecord_id=46673ba9-c23c-c056-1ea2-1f01f61791e7</link>
+				<category>Blog</category>
+				<pubdate>Thu, 07 Mar 2013 02:49:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senator Burr Introduces "Vietnam Veterans Day" Resolution</title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=223a1adb-daf8-ba63-d999-a5aef5e96ec9</link>
+				<category>Press Release</category>
+				<pubdate>Thu, 28 Feb 2013 02:10:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senator Burr Applauds Unanimous Passage of the Pandemic and All-Hazards Preparedness Reauthorization Act of 2013 (PAHPRA) </title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=2217055e-c37f-4540-e654-e0d1997ed67b</link>
+				<category>Press Release</category>
+				<pubdate>Thu, 28 Feb 2013 01:31:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>1400 Days Since the Senate Last Passed A Budget</title>
+				<link>index.cfm?FuseAction=PressOffice.Blogs&amp;Type=Blog&amp;ContentRecord_id=183105fd-9cb5-0e29-7ef9-8bc6bcb17e1f</link>
+				<category>Blog</category>
+				<pubdate>Tue, 26 Feb 2013 02:35:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>MEDIA ADVISORY: Senator Burr Announces Events for February 19-21, 2013</title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=dfbb3931-c6e8-a0be-9415-319eba9d2190</link>
+				<category>Press Release</category>
+				<pubdate>Fri, 15 Feb 2013 04:20:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senator Burr Introduces Bipartisan Bill to Renew and Improve Landmark Conservation Program</title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=dad2788d-ee57-0a95-15a2-1e232317ca94</link>
+				<category>Press Release</category>
+				<pubdate>Thu, 14 Feb 2013 05:24:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senator Burr: IOM report underscores need for track and trace system </title>
+				<link>index.cfm?FuseAction=PressOffice.Blogs&amp;Type=Blog&amp;ContentRecord_id=d57f4e69-97b5-2d4a-138d-ac5454c8b20e</link>
+				<category>Blog</category>
+				<pubdate>Wed, 13 Feb 2013 04:37:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senator Burr Questions Jack Lew at Finance Committee Hearing</title>
+				<link>index.cfm?FuseAction=PressOffice.Blogs&amp;Type=Blog&amp;ContentRecord_id=d56fcaf1-f725-3d26-469d-657ca4fa92f8</link>
+				<category>Blog</category>
+				<pubdate>Wed, 13 Feb 2013 04:21:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senator Burr Applauds the Passage of the Pandemic and All-Hazards Preparedness Act of 2013 (PAHPA) by the HELP Committee</title>
+				<link>index.cfm?FuseAction=PressOffice.Blogs&amp;Type=Blog&amp;ContentRecord_id=d54beed7-fdcf-7d37-f380-2e80e2b0a598</link>
+				<category>Blog</category>
+				<pubdate>Wed, 13 Feb 2013 03:38:00 EST</pubdate>
+			</item>
+			
+			<item>
+				<title>Senator Burr Statement on the State of the Union Address</title>
+				<link>index.cfm?FuseAction=PressOffice.PressReleases&amp;Type=Press Release&amp;ContentRecord_id=d3ffaeda-a2af-186e-a4e8-bac2286b0d03</link>
+				<category>Press Release</category>
+				<pubdate>Wed, 13 Feb 2013 09:38:00 EST</pubdate>
+			</item>
+			
+		</channel>
+	</rss>

data/spec/statement_spec.rb

@@ -24,6 +24,15 @@ describe Statement do
     @results = Statement::Link.from_rss(@feed_url)
     @results.first[:date].must_equal nil
   end
+  
+  it "parses invalid RSS" do
+    @feed_url = "http://www.burr.senate.gov/public/index.cfm?FuseAction=RSS.Feed"
+    stub_request(:any, @feed_url).to_return(:body => File.new(File.join(File.dirname(__FILE__), "richard_burr.xml")), :status => 200)
+    
+    @results = Statement::Link.from_rss(@feed_url)
+    @results.first[:url].must_equal "http://www.burr.senate.gov/public/index.cfm?FuseAction=PressOffice.PressReleases&Type=Press Release&ContentRecord_id=65dbea38-d64c-6208-ef8f-2b000e899b3a"
+    @results.first[:date].to_s.must_equal "2013-05-02"
+  end
 
   it "handles relative URLs" do
     @feed_url = "http://www.gop.gov/republicans/news?offset=03/29/13"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: statement
 version: !ruby/object:Gem::Version
-  version: '0.6'
+  version: '0.7'
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-05-02 00:00:00.000000000 Z
+date: 2013-05-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
-  requirement: &2152470040 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -21,10 +21,15 @@ dependencies:
         version: '1.3'
   type: :development
   prerelease: false
-  version_requirements: *2152470040
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &2152469580 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,10 +37,15 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2152469580
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: webmock
-  requirement: &2152469100 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -43,10 +53,15 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2152469100
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: american_date
-  requirement: &2152468680 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -54,10 +69,15 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2152468680
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &2152468220 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -65,7 +85,12 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2152468220
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 description: Crawls congressional websites for press releases.
 email:
 - dwillis@gmail.com
@@ -84,6 +109,7 @@ files:
 - spec/cowan_press.html
 - spec/culberson_rss.xml
 - spec/house_gop_releases.html
+- spec/richard_burr.xml
 - spec/ruiz_rss.xml
 - spec/statement_spec.rb
 - spec/vitter_press.html
@@ -101,15 +127,21 @@ required_ruby_version: !ruby/object:Gem::Requirement
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
+      segments:
+      - 0
+      hash: 3428073218065646458
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
+      segments:
+      - 0
+      hash: 3428073218065646458
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.17
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: Given a url, Statement returns links to press releases and official statements.
@@ -118,6 +150,7 @@ test_files:
 - spec/cowan_press.html
 - spec/culberson_rss.xml
 - spec/house_gop_releases.html
+- spec/richard_burr.xml
 - spec/ruiz_rss.xml
 - spec/statement_spec.rb
 - spec/vitter_press.html