statement 1.9.5 → 1.9.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: b730bb6562fc15cdf2764e73d8fae0c1dab016b1
-  data.tar.gz: 52a062703b6b78e858977719182a627f360a2fa0
+  metadata.gz: 9210caafe5f39c592c2d5865620e11eb6f14fbff
+  data.tar.gz: 5a9f789a96688513a517d739144a9136a93ea63d
 SHA512:
-  metadata.gz: 0fb86e56ea56bfb5bddd3600b6f013b264d30a0fb2271298c0b9699eb5459ae0307b06f05830ea8a0035d958493a58f170484959d5dfa2680e3bec1bb90a7bc7
-  data.tar.gz: 34d4d50a1d1d2dbc70c457000d1be4986217d339f8d5beaffe15a8b67fe5872b76ac1270d26c3ebc689b0a2fff0ce0e4233b41efab87b25d4d0c3c0c75984aa1
+  metadata.gz: 886ce38c989a07e6bf1b5e8785e50dba38d90038e4e7c9077aae49b98111be2aa4f7a9e6ccfdc25c691bc97329710be4a434e3f1082cf276b9dfae5ab436c5c3
+  data.tar.gz: 6d6e2f124d32faf588c4b2a78ed63a27866b916a78720e4f975a9213f6e65e9e122ff1e9dc89cde0fb64741b6019ea5a77ff0c996c2a465bab50f5a0a1309bc6

data/lib/statement/scraper.rb

@@ -32,7 +32,7 @@ module Statement
       [:crenshaw, :capuano, :cold_fusion, :conaway, :chabot, :freshman_senators, :klobuchar, :billnelson, :crapo, :boxer,
       :vitter, :inhofe, :palazzo, :roe, :document_query, :swalwell, :fischer, :clark, :edwards, :culberson_chabot_grisham, :barton,
       :sherman_mccaul, :welch, :sessions, :gabbard, :ellison, :costa, :farr, :mcclintock, :mcnerney, :olson, :schumer, :lamborn, :walden,
-      :bennie_thompson, :speier, :poe]
+      :bennie_thompson, :speier, :poe, :grassley]
     end
 
     def self.committee_methods
@@ -42,7 +42,7 @@ module Statement
     def self.member_scrapers
       year = Date.today.year
       results = [crenshaw, capuano, cold_fusion(year, nil), conaway, chabot, klobuchar(year), palazzo(page=1), roe(page=1), billnelson(year=year),
-        document_query(page=1), document_query(page=2), swalwell(page=1), crapo, coburn, boxer(start=1),
+        document_query(page=1), document_query(page=2), swalwell(page=1), crapo, boxer(start=1), grassley(page=0),
         vitter(year=year), inhofe(year=year), fischer, clark(year=year), edwards, culberson_chabot_grisham(page=1), barton, sherman_mccaul, welch,
         sessions(year=year), gabbard, ellison(page=0), costa, farr, olson, mcnerney, schumer, lamborn(limit=10), walden, bennie_thompson, speier,
         poe(year=year, month=0)].flatten
@@ -52,7 +52,7 @@ module Statement
 
     def self.backfill_from_scrapers
       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),
+        document_query(page=4), boxer(start=11), boxer(start=21), grassley(page=1), grassley(page=2), grassley(page=3),
         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),
         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),
         mcnerney(page=2), mcnerney(page=3), mcnerney(page=4), mcnerney(page=5), mcnerney(page=6), olson(year=2013), schumer(page=2), schumer(page=3), poe(year=2015, month=2),
@@ -287,24 +287,35 @@ module Statement
     def self.cold_fusion(year=Date.today.year, month=nil)
       results = []
       year = Date.today.year if not year
-      domains = ['www.ronjohnson.senate.gov/public/','www.risch.senate.gov/public/']
+      domains = ['www.ronjohnson.senate.gov','www.risch.senate.gov', 'www.lee.senate.gov']
       domains.each do |domain|
-        if domain == 'www.risch.senate.gov/public/'
+        if domain == 'www.risch.senate.gov'
           if not month
             url = "http://www.risch.senate.gov/public/index.cfm/pressreleases"
           else
             url = "http://www.risch.senate.gov/public/index.cfm/pressreleases?YearDisplay=#{year}&MonthDisplay=#{month}&page=1"
           end
+        elsif domain == 'www.barrasso.senate.gov'
+          if not month
+            url = "http://#{domain}/public/index.cfm/news-releases"
+          else
+            url = "http://#{domain}/public/index.cfm/news-releases?YearDisplay=#{year}&MonthDisplay=#{month}&page=1"
+          end
         else
           if not month
-            url = "http://www.ronjohnson.senate.gov/public/index.cfm/press-releases"
+            url = "http://#{domain}/public/index.cfm/press-releases"
           else
-            url = "http://www.ronjohnson.senate.gov/public/index.cfm/press-releases?YearDisplay=#{year}&MonthDisplay=#{month}&page=1"
+            url = "http://#{domain}/public/index.cfm/press-releases?YearDisplay=#{year}&MonthDisplay=#{month}&page=1"
           end
         end
         doc = Statement::Scraper.open_html(url)
         return if doc.nil?
-        doc.xpath("//tr")[2..-1].each do |row|
+        if domain == 'www.lee.senate.gov' or domain == 'www.barrasso.senate.gov'
+          rows = doc.xpath("//tr")[1..-1]
+        else
+          rows = doc.xpath("//tr")[2..-1]
+        end
+        rows.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 > 10
           date = Date.parse(date_text)
@@ -428,14 +439,13 @@ module Statement
       results
     end
 
-    def self.coburn(year=Date.today.year)
+    def self.grassley(page=0)
       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}"
+      url = "http://www.grassley.senate.gov/news/news-releases?title=&tid=All&date[value]&page=#{page}"
       doc = open_html(url)
       return if doc.nil?
-      doc.xpath("//tr")[2..-1].each do |row|
-        next if row.text.strip[0..3] == "Date"
-        results << { :source => url, :url => row.children[3].children[0]['href'], :title => row.children[3].text.strip, :date => Date.strptime(row.children[1].text.strip, "%m/%d/%y"), :domain => "coburn.senate.gov" }
+      doc.xpath("//div[@class='views-field views-field-field-release-date']").each do |row|
+        results << { :source => url, :url => "http://www.grassley.senate.gov" + row.next.next.children[1].children[0]['href'], :title => row.next.next.text.strip, :date => Date.parse(row.text.strip), :domain => "grassley.senate.gov" }
       end
       results
     end

data/lib/statement/version.rb

@@ -1,3 +1,3 @@
 module Statement
-  VERSION = "1.9.5"
+  VERSION = "1.9.6"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: statement
 version: !ruby/object:Gem::Version
-  version: 1.9.5
+  version: 1.9.6
 platform: ruby
 authors:
 - Derek Willis
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-03-27 00:00:00.000000000 Z
+date: 2015-04-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -211,3 +211,4 @@ test_files:
 - spec/ruiz_rss.xml
 - spec/statement_spec.rb
 - spec/vitter_press.html
+has_rdoc: