statement 1.8.7 → 1.8.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5d24d337a4b4bf8bc8f8789940543cec80eee884
-  data.tar.gz: b718f210fc6e0c7a0d30b81304fc64d40029bf28
+  metadata.gz: 88ef7c73e2da9cf4f89002e9d60a228508c4fb9d
+  data.tar.gz: 0423e9d85fd4ab80a247fe4a836e10fdaf31a2ab
 SHA512:
-  metadata.gz: 474fc04b2a15b38ddbecd92ce6af3438a1be3fb0baa1ae56456315fbc10ae4358646f2f19bf37219ef25b630308219fdf85e04152728a2fb320af484be5a1171
-  data.tar.gz: 093756d65a5eba4b75bf21fb05784eb6bea4898fd72106cdbd50e9d94449c158f469dce3b9a4db3ab6fd8977792173eea9072ce0b3eb7aa8d252e3313f4d91e9
+  metadata.gz: 0753f5edd8d58526b457cde2bda819e814e3d805f547e302f920e061f4204837786c088f0083a8afa7b6fcd625502d55f978c1b0b98feb9ff0ed19c451943f36
+  data.tar.gz: 2e3ab0f04fdeaa2d4c5d4b9c12ca004620dbab6ee7bb483688faf99d171c861ce5f31acf5da1c62246e0ce33564adc9b45a9eccf5708fb66c0512404991301e8

data/lib/statement/scraper.rb

@@ -29,7 +29,7 @@ module Statement
     end
     
     def self.member_methods
-      [:capuano, :cold_fusion, :conaway, :chabot, :susandavis, :freshman_senators, :klobuchar, :billnelson, :lautenberg, :crapo, :coburn, :boxer, :vitter, :donnelly, :inhofe, :palazzo, :roe, :document_query, :swalwell, :fischer, :clark, :edwards, :culberson_chabot_grisham, :barton, :wolf_sherman_mccaul, :welch, :sessions, :gabbard]
+      [:capuano, :cold_fusion, :conaway, :chabot, :susandavis, :freshman_senators, :klobuchar, :billnelson, :lautenberg, :crapo, :coburn, :boxer, :vitter, :donnelly, :inhofe, :palazzo, :roe, :document_query, :swalwell, :fischer, :clark, :edwards, :culberson_chabot_grisham, :barton, :wolf_sherman_mccaul, :welch, :sessions, :gabbard, :ellison, :costa, :farr]
     end
     
     def self.committee_methods
@@ -41,7 +41,7 @@ module Statement
       results = [capuano, cold_fusion(year, 0), conaway, chabot, susandavis, klobuchar(year), palazzo(page=1), roe(page=1), billnelson(year=year), 
         document_query(page=1), document_query(page=2), swalwell(page=1), donnelly(year=year), crapo, coburn, boxer(start=1),
         vitter(year=year), inhofe(year=year), fischer, clark(year=year), edwards, culberson_chabot_grisham(page=1), barton, wolf_sherman_mccaul, welch,
-        sessions(year=year), gabbard, pryor].flatten
+        sessions(year=year), gabbard, pryor, ellison(page=0), costa, farr].flatten
       results = results.compact
       Utils.remove_generic_urls!(results)
     end
@@ -50,7 +50,7 @@ module Statement
       results = [cold_fusion(2012, 0), cold_fusion(2011, 0), cold_fusion(2010, 0), billnelson(year=2012), document_query(page=3), 
         document_query(page=4), coburn(year=2012), coburn(year=2011), coburn(year=2010), boxer(start=11), boxer(start=21), 
         boxer(start=31), boxer(start=41), vitter(year=2012), vitter(year=2011), swalwell(page=2), swalwell(page=3), clark(year=2013), culberson_chabot_grisham(page=2),
-        wolf_sherman_mccaul(page=1), sessions(year=2013), pryor(page=1)].flatten
+        wolf_sherman_mccaul(page=1), sessions(year=2013), pryor(page=1), ellison(page=1), ellison(page=2), ellison(page=3), farr(year=2013), farr(year=2012), farr(year=2011)].flatten
       Utils.remove_generic_urls!(results)
     end
     
@@ -602,14 +602,55 @@ module Statement
       results
     end
 
+    def self.ellison(page=0)
+      results = []
+      domain = 'ellison.house.gov'
+      url = "http://ellison.house.gov/media-center/press-releases?page=#{page}"
+      doc = open_html(url)
+      return if doc.nil?
+      doc.xpath("//div[@class='views-field views-field-created datebar']").each do |row|
+        next if row.nil?
+        results << { :source => url, :url => "http://ellison.house.gov" + row.next.next.children[1].children[0]['href'], :title => row.next.next.children[1].children[0].text.strip, :date => Date.parse(row.text.strip), :domain => domain}
+      end
+      results
+    end
+
+    def self.costa
+      results = []
+      domain = 'costa.house.gov'
+      url = "http://costa.house.gov/index.php/newsroom30/press-releases12"
+      doc = open_html(url)
+      return if doc.nil?
+      doc.xpath("//div[@class='nspArt']").each do |row|
+        results << { :source => url, :url => "http://costa.house.gov" + row.children[0].children[1].children[0]['href'], :title => row.children[0].children[1].children[0].text.strip, :date => Date.parse(row.children[0].children[0].text), :domain => domain}
+      end
+      results
+    end
+
+    def self.farr(year=2014)
+      results = []
+      domain = 'www.farr.house.gov'
+      if year == 2014
+        url = "http://www.farr.house.gov/index.php/newsroom/press-releases"
+      else
+        url = "http://www.farr.house.gov/index.php/newsroom/press-releases-archive/#{year.to_s}-press-releases"
+      end
+      doc = open_html(url)
+      return if doc.nil?
+      doc.xpath("//tr[@class='cat-list-row0']").each do |row|
+        results << { :source => url, :url => "http://farr.house.gov" + row.children[1].children[1]['href'], :title => row.children[1].children[1].text.strip, :date => Date.parse(row.children[3].text.strip), :domain => domain}
+      end
+      results
+    end
+
     def self.document_query(page=1)
       results = []
-      domains = [{"thornberry.house.gov" => 1776}, {"wenstrup.house.gov" => 2491}]
+      domains = [{"thornberry.house.gov" => 1776}, {"wenstrup.house.gov" => 2491}, {"clawson.house.gov" => 2641}]
       domains.each do |domain|
         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 }
+        doc.xpath("//div[@class='middlecopy']//li").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[1]['href'], :title => row.children[1].text.strip, :date => Date.parse(row.children[3].text.strip), :domain => domain.keys.first }
         end
       end
       results.flatten

data/lib/statement/version.rb

@@ -1,3 +1,3 @@
 module Statement
-  VERSION = "1.8.7"
+  VERSION = "1.8.8"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: statement
 version: !ruby/object:Gem::Version
-  version: 1.8.7
+  version: 1.8.8
 platform: ruby
 authors:
 - Derek Willis
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-09-10 00:00:00.000000000 Z
+date: 2014-10-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler