Class: Statement::Scraper
- Inherits:
-
Object
- Object
- Statement::Scraper
- Defined in:
- lib/statement/scraper.rb
Class Method Summary collapse
- .backfill_bilirakis(page = 1) ⇒ Object
- .backfill_boustany(congress) ⇒ Object
- .backfill_from_scrapers ⇒ Object
- .barton ⇒ Object
- .bennet(page = 1) ⇒ Object
- .bennie_thompson ⇒ Object
- .billnelson(page = 0) ⇒ Object
- .boxer ⇒ Object
- .burr(page = 1) ⇒ Object
- .capuano ⇒ Object
- .cassidy(page = 1) ⇒ Object
- .chabot(year = Date.today.year) ⇒ Object
- .clark(year = Date.today.year) ⇒ Object
- .cold_fusion(year = Date.today.year, month = nil, skip_domains = []) ⇒ Object
- .committee_methods ⇒ Object
- .committee_scrapers ⇒ Object
- .conaway(page = 1) ⇒ Object
- .costa ⇒ Object
- .crapo ⇒ Object
- .crenshaw(year = Date.today.year, month = nil) ⇒ Object
- .culberson_chabot_grisham(page = 1) ⇒ Object
- .document_query(page = 1) ⇒ Object
-
.donnelly(year = Date.today.year) ⇒ Object
deprecated.
- .drupal(urls = [], page = 0) ⇒ Object
- .durbin(page = 1) ⇒ Object
- .edwards ⇒ Object
- .ellison(page = 0) ⇒ Object
- .farr(year = 2014) ⇒ Object
- .fischer(year = Date.today.year) ⇒ Object
- .gabbard ⇒ Object
- .grassley(page = 0) ⇒ Object
- .house_energy_minority ⇒ Object
- .house_gop(url) ⇒ Object
- .house_homeland_security_minority ⇒ Object
- .house_judiciary_majority ⇒ Object
- .house_rules_majority ⇒ Object
- .house_ways_means_majority ⇒ Object
- .inhofe(year = Date.today.year) ⇒ Object
- .jenkins ⇒ Object
- .keating ⇒ Object
- .klobuchar(year) ⇒ Object
- .lowey(page = 0) ⇒ Object
- .lujan ⇒ Object
- .mcclintock ⇒ Object
- .mcmorris(page = 1) ⇒ Object
- .member_methods ⇒ Object
- .member_scrapers ⇒ Object
- .olson(year = 2014) ⇒ Object
- .open_html(url) ⇒ Object
- .patrick_meehan(page = 0) ⇒ Object
- .perlmutter ⇒ Object
- .poe(year, month = 0) ⇒ Object
- .rand_paul(page = 1) ⇒ Object
- .schiff(page = 1) ⇒ Object
- .schumer(page = 1) ⇒ Object
- .senate_aging ⇒ Object
-
.senate_approps_majority ⇒ Object
special cases for committees without RSS feeds.
- .senate_approps_minority ⇒ Object
- .senate_banking(year = Date.today.year) ⇒ Object
- .senate_hsag_majority(year = Date.today.year) ⇒ Object
- .senate_hsag_minority(year = Date.today.year) ⇒ Object
- .senate_indian ⇒ Object
- .senate_intel(congress = 113, start_year = 2013, end_year = 2014) ⇒ Object
- .senate_smallbiz_minority ⇒ Object
- .sessions(year = Date.today.year) ⇒ Object
- .shaheen(page = 1) ⇒ Object
- .speier ⇒ Object
-
.swalwell(page = 1) ⇒ Object
special cases for members without RSS feeds.
- .takano(page = 1) ⇒ Object
- .vitter(year = Date.today.year) ⇒ Object
- .welch ⇒ Object
Class Method Details
.backfill_bilirakis(page = 1) ⇒ Object
890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 |
# File 'lib/statement/scraper.rb', line 890 def self.backfill_bilirakis(page=1) results = [] domain = 'bilirakis.house.gov' url = "https://bilirakis.house.gov/press-releases?page=#{page}" doc = open_html(url) return if doc.nil? doc.css("#region-content .views-row").each do |row| title_anchor = row.css("h3 a") title = title_anchor.text release_url = "http://#{domain + title_anchor.attr('href')}" raw_date = row.css(".views-field-created").text results << { :source => url, :url => release_url, :title => title, :date => begin Date.parse(raw_date) rescue nil end, :domain => domain } end results end |
.backfill_boustany(congress) ⇒ Object
910 911 912 913 914 915 916 917 918 919 920 |
# File 'lib/statement/scraper.rb', line 910 def self.backfill_boustany(congress) results = [] domain = 'boustany.house.gov' url = "http://boustany.house.gov/#{congress}th-congress/showallitems/" doc = open_html(url) return if doc.nil? (doc/:ul)[13].search(:li).each do |row| results << {:source => url, :url => 'http://boustany.house.gov' + row.children.search(:a)[0]['href'], :title => row.children.search(:a)[0].text, :date => Date.parse(row.children[5].text), :domain => domain } end results end |
.backfill_from_scrapers ⇒ Object
54 55 56 57 58 59 60 61 62 63 |
# File 'lib/statement/scraper.rb', line 54 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), grassley(page=1), grassley(page=2), grassley(page=3), burr(page=2), burr(page=3), burr(page=4), vitter(year=2012), vitter(year=2011), swalwell(page=2), swalwell(page=3), clark(year=2013), culberson_chabot_grisham(page=2), sessions(year=2013), pryor(page=1), farr(year=2013), farr(year=2012), farr(year=2011), cassidy(page=2), cassidy(page=3), olson(year=2013), schumer(page=2), schumer(page=3), poe(year=2015, month=2), ellison(page=1), ellison(page=2), lowey(page=1), lowey(page=2), lowey(page=3), poe(year=2015, month=1), mcmorris(page=2), mcmorris(page=3), schiff(page=2), schiff(page=3), takano(page=2), takano(page=3)].flatten Utils.remove_generic_urls!(results) end |
.barton ⇒ Object
690 691 692 693 694 695 696 697 698 699 700 |
# File 'lib/statement/scraper.rb', line 690 def self. results = [] domain = 'joebarton.house.gov' url = "http://joebarton.house.gov/press-releasescolumns/" doc = open_html(url) return if doc.nil? (doc/:h3)[0..-3].each do |row| results << { :source => url, :url => "http://joebarton.house.gov/"+row.children[1]['href'], :title => row.children[1].text.strip, :date => Date.parse(row.next.next.text), :domain => domain} end results end |
.bennet(page = 1) ⇒ Object
829 830 831 832 833 834 835 836 837 838 839 |
# File 'lib/statement/scraper.rb', line 829 def self.bennet(page=1) results = [] domain = 'www.bennet.senate.gov' url = "http://www.bennet.senate.gov/?p=releases&pg=#{page}" doc = open_html(url) return if doc.nil? (doc/:h2).each do |row| results << {:source => url, :url => 'http://www.bennet.senate.gov' + row.children.first['href'], :title => row.text.strip, :date => Date.parse(row.previous.previous.text), :domain => domain } end results end |
.bennie_thompson ⇒ Object
866 867 868 869 870 871 872 873 874 875 876 |
# File 'lib/statement/scraper.rb', line 866 def self.bennie_thompson results = [] domain = "benniethompson.house.gov" url = "http://benniethompson.house.gov/index.php?option=com_content&view=category&id=41&Itemid=148" doc = open_html(url) return if doc.nil? doc.xpath('//*[@id="adminForm"]/table/tbody/tr').each do |row| results << {:source => url, :url => 'http://benniethompson.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 |
.billnelson(page = 0) ⇒ Object
407 408 409 410 411 412 413 414 415 416 417 |
# File 'lib/statement/scraper.rb', line 407 def self.billnelson(page=0) results = [] url = "http://www.billnelson.senate.gov/newsroom/press-releases?page=#{page}" doc = open_html(url) return if doc.nil? dates = doc.xpath("//div[@class='date-box']").map{|d| Date.parse(d.children.map{|x| x.text.strip}.join(" "))} (doc/:h3).each_with_index do |row, index| results << { :source => url, :url => "http://www.billnelson.senate.gov" + row.children.first['href'], :title => row.children.first.text.strip, :date => dates[index], :domain => "billnelson.senate.gov" } end results end |
.boxer ⇒ Object
569 570 571 572 573 574 575 576 577 578 579 580 |
# File 'lib/statement/scraper.rb', line 569 def self.boxer results = [] url = "http://www.boxer.senate.gov/press/release" domain = 'www.boxer.senate.gov' doc = open_html(url) return if doc.nil? doc.css("tr")[1..-1].each do |row| next if row.children[1].text == "Sat, January 1st 0000 " results << { :source => url, :url => "http://"+domain + row.children[3].children[1]['href'], :title => row.children[3].children[1].text.strip, :date => Date.parse(row.children[1].text), :domain => domain} end results end |
.burr(page = 1) ⇒ Object
499 500 501 502 503 504 505 506 507 508 509 |
# File 'lib/statement/scraper.rb', line 499 def self.burr(page=1) results = [] url = "http://www.burr.senate.gov/press/releases?PageNum_rs=#{page}&" doc = open_html(url) return if doc.nil? rows = doc.css("#press").first.css('h2') rows.each do |row| results << { :source => url, :url => "http://www.burr.senate.gov" + row.children.first['href'], :title => row.children.last.text.strip, :date => Date.strptime(row.previous.previous.text, "%m.%d.%y"), :domain => "burr.senate.gov" } end results end |
.capuano ⇒ Object
251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 |
# File 'lib/statement/scraper.rb', line 251 def self.capuano results = [] base_url = "http://www.house.gov/capuano/news/" list_url = base_url + 'date.shtml' doc = open_html(list_url) return if doc.nil? doc.xpath("//a").select{|l| !l['href'].nil? and l['href'].include?('/pr')}[1..-5].each do |link| begin year = link['href'].split('/').first date = Date.parse(link.text.split(' ').first+'/'+year) rescue date = nil end results << { :source => list_url, :url => base_url + link['href'], :title => link.text.split(' ',2).last, :date => date, :domain => "www.house.gov/capuano/" } end return results[0..-5] end |
.cassidy(page = 1) ⇒ Object
511 512 513 514 515 516 517 518 519 520 521 |
# File 'lib/statement/scraper.rb', line 511 def self.cassidy(page=1) results = [] url = "http://www.cassidy.senate.gov/newsroom/press-releases?PageNum_rs=#{page}&" doc = open_html(url) return if doc.nil? rows = doc.css("#press").first.css('h2') rows.each do |row| results << { :source => url, :url => "http://www.cassidy.senate.gov" + row.children.first['href'], :title => row.children.last.text.strip, :date => Date.strptime(row.previous.previous.text, "%m.%d.%y"), :domain => "cassidy.senate.gov" } end results end |
.chabot(year = Date.today.year) ⇒ Object
343 344 345 346 347 348 349 350 351 352 353 354 |
# File 'lib/statement/scraper.rb', line 343 def self.chabot(year=Date.today.year) results = [] base_url = "http://chabot.house.gov/news/" url = base_url + "documentquery.aspx?DocumentTypeID=2508&Year=#{year}" doc = open_html(url) return if doc.nil? doc.xpath("//li")[40..48].each do |row| next if not row.text.include?('Posted') results << { :source => url, :url => base_url + row.children[1]['href'], :title => row.children[1].children.text.strip, :date => Date.parse(row.children[3].text.strip), :domain => "chabot.house.gov" } end results end |
.clark(year = Date.today.year) ⇒ Object
635 636 637 638 639 640 641 642 643 644 645 646 |
# File 'lib/statement/scraper.rb', line 635 def self.clark(year=Date.today.year) results = [] domain = 'katherineclark.house.gov' url = "http://katherineclark.house.gov/index.cfm/press-releases?MonthDisplay=0&YearDisplay=#{year}" doc = open_html(url) return if doc.nil? (doc/:tr)[1..-1].each do |row| next if row.children[1].text.strip == 'Date' results << { :source => url, :date => Date.parse(row.children[1].text.strip), :title => row.children[3].children.text, :url => row.children[3].children[0]['href'], :domain => domain} end results end |
.cold_fusion(year = Date.today.year, month = nil, skip_domains = []) ⇒ Object
289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 |
# File 'lib/statement/scraper.rb', line 289 def self.cold_fusion(year=Date.today.year, month=nil, skip_domains=[]) results = [] year = Date.today.year if not year domains = ['www.ronjohnson.senate.gov','www.risch.senate.gov', 'www.lee.senate.gov', 'www.barrasso.senate.gov', 'www.heitkamp.senate.gov'] domains = domains - skip_domains if skip_domains domains.each do |domain| 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://#{domain}/public/index.cfm/press-releases" else 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? if domain == 'www.lee.senate.gov' or domain == 'www.barrasso.senate.gov' or domain == "www.heitkamp.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) results << { :source => url, :url => row.children[3].children.first['href'], :title => title, :date => date, :domain => domain } end end results.flatten end |
.committee_methods ⇒ Object
38 39 40 |
# File 'lib/statement/scraper.rb', line 38 def self.committee_methods [:senate_approps_majority, :senate_approps_minority, :senate_banking, :senate_hsag_majority, :senate_hsag_minority, :senate_indian, :senate_aging, :senate_smallbiz_minority, :senate_intel, :house_energy_minority, :house_homeland_security_minority, :house_judiciary_majority, :house_rules_majority, :house_ways_means_majority] end |
.committee_scrapers ⇒ Object
65 66 67 68 69 70 71 |
# File 'lib/statement/scraper.rb', line 65 def self.committee_scrapers year = Date.today.year results = [senate_approps_majority, senate_approps_minority, senate_banking(year), senate_hsag_majority(year), senate_hsag_minority(year), senate_indian, senate_aging, senate_smallbiz_minority, senate_intel(113, 2013, 2014), house_energy_minority, house_homeland_security_minority, house_judiciary_majority, house_rules_majority, house_ways_means_majority].flatten Utils.remove_generic_urls!(results) end |
.conaway(page = 1) ⇒ Object
331 332 333 334 335 336 337 338 339 340 341 |
# File 'lib/statement/scraper.rb', line 331 def self.conaway(page=1) results = [] base_url = "http://conaway.house.gov/news/" page_url = base_url + "documentquery.aspx?DocumentTypeID=1279&Page=#{page}" doc = open_html(page_url) return if doc.nil? doc.xpath("//li")[41..50].each do |row| results << { :source => page_url, :url => base_url + row.children[1]['href'], :title => row.children[1].children.text.strip, :date => Date.parse(row.children[3].text.strip), :domain => "conaway.house.gov" } end results end |
.costa ⇒ Object
726 727 728 729 730 731 732 733 734 735 736 |
# File 'lib/statement/scraper.rb', line 726 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 |
.crapo ⇒ Object
523 524 525 526 527 528 529 530 531 532 533 |
# File 'lib/statement/scraper.rb', line 523 def self.crapo results = [] base_url = "http://www.crapo.senate.gov/media/newsreleases/" url = base_url + "release_all.cfm" doc = open_html(url) return if doc.nil? doc.xpath("//tr").each do |row| results << { :source => url, :url => base_url + row.children[3].children[0]['href'], :title => row.children[3].text.strip, :date => Date.parse(row.children[1].text.strip.gsub('-','/')), :domain => "crapo.senate.gov" } end results end |
.crenshaw(year = Date.today.year, month = nil) ⇒ Object
269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 |
# File 'lib/statement/scraper.rb', line 269 def self.crenshaw(year=Date.today.year, month=nil) results = [] year = Date.today.year if not year domain = 'crenshaw.house.gov' if month url = "http://crenshaw.house.gov/index.cfm/pressreleases?YearDisplay=#{year}&MonthDisplay=#{month}&page=1" else url = "http://crenshaw.house.gov/index.cfm/pressreleases" end doc = Statement::Scraper.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 > 10 date = Date.parse(date_text) results << { :source => url, :url => row.children[3].children.first['href'], :title => title, :date => date, :domain => domain } end results end |
.culberson_chabot_grisham(page = 1) ⇒ Object
674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 |
# File 'lib/statement/scraper.rb', line 674 def self.culberson_chabot_grisham(page=1) results = [] domains = [{'culberson.house.gov' => 2573}, {'chabot.house.gov' => 2508}, {'lujangrisham.house.gov' => 2447}] 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.css('ul.UnorderedNewsList li').each do |row| link = "http://"+domain.keys.first+"/news/" + row.children[1]['href'] title = row.children[1].text.strip date = Date.parse(row.children[3].text.strip) results << { :source => "http://"+domain.keys.first+"/news/"+"documentquery.aspx?DocumentTypeID=#{domain.values.first}&Page=#{page}", :title => title, :url => link, :date => date, :domain => domain.keys.first } end end results.flatten end |
.document_query(page = 1) ⇒ Object
778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 |
# File 'lib/statement/scraper.rb', line 778 def self.document_query(page=1) results = [] domains = [ {"thornberry.house.gov" => 1776}, {"wenstrup.house.gov" => 2491}, {"clawson.house.gov" => 2641}, {"palazzo.house.gov" => 2519}, {"roe.house.gov" => 1532}, {"perry.house.gov" => 2607}, {"rodneydavis.house.gov" => 2427}, {"kevinbrady.house.gov" => 2657}, {"loudermilk.house.gov" => 27}, {"babin.house.gov" => 27}, {"bridenstine.house.gov" => 2412}, {"allen.house.gov" => 27}, {"davidscott.house.gov" => 377}, {"buddycarter.house.gov" => 27}, {"grothman.house.gov" => 27}, {"beyer.house.gov" => 27}, {"kathleenrice.house.gov" => 27}, {"hanna.house.gov" => 27}, {"trentkelly.house.gov" => 27}, {"lamborn.house.gov" => 27}, {"wittman.house.gov" => 2670}, {"kinzinger.house.gov" => 2665}, {"ellmers.house.gov" => 27}, {"frankel.house.gov" => 27} ] 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("//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 end |
.donnelly(year = Date.today.year) ⇒ Object
deprecated
596 597 598 599 600 601 602 603 604 605 606 607 |
# File 'lib/statement/scraper.rb', line 596 def self.donnelly(year=Date.today.year) results = [] url = "http://www.donnelly.senate.gov/newsroom/" domain = "www.donnelly.senate.gov" 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 => "http://www.donnelly.senate.gov"+row.children[3].children[1]['href'].strip, :title => row.children[3].text.strip, :date => Date.strptime(row.children[1].text, "%m/%d/%y"), :domain => domain} end results end |
.drupal(urls = [], page = 0) ⇒ Object
950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 |
# File 'lib/statement/scraper.rb', line 950 def self.drupal(urls=[], page=0) if urls.empty? urls = [ "http://sherman.house.gov/media-center/press-releases", "http://mccaul.house.gov/media-center/press-releases", "https://ellison.house.gov/media-center/press-releases", "http://mcnerney.house.gov/media-center/press-releases", "http://sanford.house.gov/media-center/press-releases", "http://butterfield.house.gov/media-center/press-releases", "http://walz.house.gov/media-center/press-releases", "https://pingree.house.gov/media-center/press-releases", "http://wilson.house.gov/media-center/press-releases", "https://bilirakis.house.gov/press-releases", "http://quigley.house.gov/media-center/press-releases", "https://denham.house.gov/media-center/press-releases", "https://sewell.house.gov/media-center/press-releases", "https://buchanan.house.gov/media-center/press-releases", "https://meehan.house.gov/media-center/press-releases", "https://olson.house.gov/media-center/press-releases", "https://louise.house.gov/media-center/press-releases", "https://waters.house.gov/media-center/press-releases", "https://walden.house.gov/media-center/press-releases", "https://brooks.house.gov/media-center/news-releases", "https://swalwell.house.gov/media-center/press-releases" ] end results = [] urls.each do |url| source_url = "#{url}?page=#{page}" domain = URI.parse(source_url).host doc = open_html(source_url) return if doc.nil? doc.css("#region-content .views-row").each do |row| title_anchor = row.css("h3 a") title = title_anchor.text release_url = "http://#{domain + title_anchor.attr('href')}" raw_date = row.css(".views-field-created").text results << { :source => source_url, :url => release_url, :title => title, :date => begin Date.parse(raw_date) rescue nil end, :domain => domain } end # mike quigley's release page doesn't have dates, so we fetch those individually if url == "http://quigley.house.gov/media-center/press-releases" results.select{|r| r[:source] == source_url}.each do |result| doc = open_html(result[:url]) result[:date] = Date.parse(doc.css(".pane-content").children[0].text.strip) end end end results end |
.durbin(page = 1) ⇒ Object
609 610 611 612 613 614 615 616 617 618 |
# File 'lib/statement/scraper.rb', line 609 def self.durbin(page=1) results = [] url = "http://www.durbin.senate.gov/newsroom/press-releases?PageNum_rs=#{page}&" doc = open_html(url) return if doc.nil? doc.xpath("//div[@id='press']//h2").each do |row| results << { :source => url, :url => "http://www.durbin.senate.gov"+row.children[0]['href'], :title => row.children[0].text.strip, :date => Date.parse(row.previous.previous.text.gsub(".","/")), :domain => 'www.durbin.senate.gov'} end results end |
.edwards ⇒ Object
661 662 663 664 665 666 667 668 669 670 671 672 |
# File 'lib/statement/scraper.rb', line 661 def self.edwards results = [] domain = 'donnaedwards.house.gov' url = "http://donnaedwards.house.gov/index.php?option=com_content&view=category&id=10&Itemid=18" doc = open_html(url) return if doc.nil? table = (doc/:table)[4] (table/:tr).each do |row| results << { :source => url, :url => "http://donnaedwards.house.gov/"+row.children.children[1]['href'], :title => row.children.children[1].text.strip, :date => Date.parse(row.children.children[3].text.strip), :domain => domain} end results end |
.ellison(page = 0) ⇒ Object
558 559 560 561 562 563 564 565 566 567 |
# File 'lib/statement/scraper.rb', line 558 def self.ellison(page=0) results = [] 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| results << { :source => url, :url => "http://ellison.house.gov" + row.next.next.children[1].children[0]['href'], :title => row.next.next.text.strip, :date => Date.parse(row.text.strip), :domain => "ellison.house.gov" } end results end |
.farr(year = 2014) ⇒ Object
738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 |
# File 'lib/statement/scraper.rb', line 738 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 |
.fischer(year = Date.today.year) ⇒ Object
535 536 537 538 539 540 541 542 543 544 545 |
# File 'lib/statement/scraper.rb', line 535 def self.fischer(year=Date.today.year) results = [] url = "http://www.fischer.senate.gov/public/index.cfm/press-releases?MonthDisplay=0&YearDisplay=#{year}" 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 => "fischer.senate.gov" } end results end |
.gabbard ⇒ Object
714 715 716 717 718 719 720 721 722 723 724 |
# File 'lib/statement/scraper.rb', line 714 def self. results = [] domain = 'gabbard.house.gov' url = "http://gabbard.house.gov/index.php/news/press-releases" doc = open_html(url) return if doc.nil? doc.css('ul.fc_leading li').each do |row| results << {:source => url, :url => "http://gabbard.house.gov"+row.children[0].children[1]['href'], :title => row.children[0].children[1].text.strip, :date => Date.parse(row.children[2].text), :domain => domain} end results end |
.grassley(page = 0) ⇒ Object
547 548 549 550 551 552 553 554 555 556 |
# File 'lib/statement/scraper.rb', line 547 def self.grassley(page=0) results = [] 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("//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 |
.house_energy_minority ⇒ Object
180 181 182 183 184 185 186 187 188 189 |
# File 'lib/statement/scraper.rb', line 180 def self.house_energy_minority results = [] url = "http://democrats.energycommerce.house.gov/index.php?q=news-releases" doc = open_html(url) return if doc.nil? doc.xpath("//div[@class='views-field-title']").each do |row| results << { :source => url, :url => "http://democrats.energycommerce.house.gov"+row.children[1].children[0]['href'], :title => row.children[1].children[0].text, :date => Date.parse(row.next.next.text.strip), :domain => "http://energycommerce.house.gov/", :party => 'minority' } end results end |
.house_gop(url) ⇒ Object
18 19 20 21 22 23 24 25 26 27 28 29 |
# File 'lib/statement/scraper.rb', line 18 def self.house_gop(url) doc = open_html(url) return unless doc uri = URI.parse(url) date = Date.parse(uri.query.split('=').last) links = doc.xpath("//ul[@id='membernews']").search('a') results = links.map do |link| abs_link = Utils.absolute_link(url, link["href"]) { :source => url, :url => abs_link, :title => link.text.strip, :date => date, :domain => URI.parse(link["href"]).host } end Utils.remove_generic_urls!(results) end |
.house_homeland_security_minority ⇒ Object
191 192 193 194 195 196 197 198 199 200 |
# File 'lib/statement/scraper.rb', line 191 def self.house_homeland_security_minority results = [] url = "http://chsdemocrats.house.gov/press/index.asp?subsection=1" doc = open_html(url) return if doc.nil? doc.xpath("//li[@class='article']").each do |row| results << { :source => url, :url => "http://chsdemocrats.house.gov"+row.children[1]['href'], :title => row.children[1].text.strip, :date => Date.parse(row.children[3].text), :domain => "http://chsdemocrats.house.gov/", :party => 'minority' } end results end |
.house_judiciary_majority ⇒ Object
202 203 204 205 206 207 208 209 210 211 212 |
# File 'lib/statement/scraper.rb', line 202 def self.house_judiciary_majority results = [] url = "http://judiciary.house.gov/news/press2013.html" doc = open_html(url) return if doc.nil? doc.xpath("//p")[3..60].each do |row| next if row.text.size < 30 results << { :source => url, :url => row.children[5]['href'], :title => row.children[0].text, :date => Date.parse(row.children[1].text.strip), :domain => "http://judiciary.house.gov/", :party => 'majority' } end results end |
.house_rules_majority ⇒ Object
214 215 216 217 218 219 220 221 222 223 224 |
# File 'lib/statement/scraper.rb', line 214 def self.house_rules_majority results = [] url = "http://www.rules.house.gov/News/Default.aspx" doc = open_html(url) return if doc.nil? doc.xpath("//tr")[1..-2].each do |row| next if row.text.strip.size < 30 results << { :source => url, :url => "http://www.rules.house.gov/News/"+row.children[0].children[1].children[0]['href'], :title => row.children[0].children[1].children[0].text, :date => Date.parse(row.children[2].children[1].text.strip), :domain => "http://www.rules.house.gov/", :party => 'majority' } end results end |
.house_ways_means_majority ⇒ Object
226 227 228 229 230 231 232 233 234 235 236 |
# File 'lib/statement/scraper.rb', line 226 def self.house_ways_means_majority results = [] url = "http://waysandmeans.house.gov/news/documentquery.aspx?DocumentTypeID=1496" doc = open_html(url) return if doc.nil? doc.xpath("//ul[@class='UnorderedNewsList']").children.each do |row| next if row.text.strip.size < 10 results << { :source => url, :url => "http://waysandmeans.house.gov"+row.children[1].children[1]['href'], :title => row.children[1].children[1].text, :date => Date.parse(row.children[3].children[0].text.strip), :domain => "http://waysandmeans.house.gov/", :party => 'majority' } end results end |
.inhofe(year = Date.today.year) ⇒ Object
620 621 622 623 624 625 626 627 628 629 630 631 632 633 |
# File 'lib/statement/scraper.rb', line 620 def self.inhofe(year=Date.today.year) results = [] url = "http://www.inhofe.senate.gov/newsroom/press-releases?year=#{year}" domain = "www.inhofe.senate.gov" doc = open_html(url) return if doc.nil? if doc.xpath("//tr")[1..-1] doc.xpath("//tr")[1..-1].each do |row| next if row.text.strip.size < 30 results << { :source => url, :url => row.children[3].children[0]['href'].strip, :title => row.children[3].text, :date => Date.strptime(row.children[1].text, "%m/%d/%y"), :domain => domain} end end results end |
.jenkins ⇒ Object
854 855 856 857 858 859 860 861 862 863 864 |
# File 'lib/statement/scraper.rb', line 854 def self.jenkins results = [] domain = 'lynnjenkins.house.gov/' url = "http://lynnjenkins.house.gov/index.cfm?sectionid=186" doc = open_html(url) return if doc.nil? doc.xpath("//ul[@class='sectionitems']//li").each do |row| results << {:source => url, :url => 'http://lynnjenkins.house.gov' + row.children[3].children[1]['href'], :title => row.children[3].text.strip, :date => Date.parse(row.children[5].text), :domain => domain } end results end |
.keating ⇒ Object
935 936 937 938 939 940 941 942 943 944 945 946 947 948 |
# File 'lib/statement/scraper.rb', line 935 def self.keating results = [] domain = "keating.house.gov" source_url = "http://#{domain}/index.php?option=com_content&view=category&id=14&Itemid=13" doc = open_html(source_url) return if doc.nil? doc.css("#adminForm tr")[0..-1].each do |row| url = 'http://' + domain + row.children[1].children[1]['href'] title = row.children[1].children[1].text.strip results << { :source => source_url, :url => url, :title => title, :date => Date.parse(row.children[3].text), :domain => domain} end results end |
.klobuchar(year) ⇒ Object
367 368 369 370 371 372 373 374 375 376 377 378 379 380 |
# File 'lib/statement/scraper.rb', line 367 def self.klobuchar(year) results = [] base_url = "http://www.klobuchar.senate.gov/" [year.to_i-1,year.to_i].each do |year| year_url = base_url + "public/news-releases?MonthDisplay=0&YearDisplay=#{year}" doc = open_html(year_url) return if doc.nil? doc.xpath("//tr")[1..-1].each do |row| next if row.children[3].children[0].text.strip == 'Title' results << { :source => year_url, :url => row.children[3].children[0]['href'], :title => row.children[3].children[0].text.strip, :date => Date.strptime(row.children[1].text, "%m/%d/%y"), :domain => "klobuchar.senate.gov" } end end results end |
.lowey(page = 0) ⇒ Object
878 879 880 881 882 883 884 885 886 887 888 |
# File 'lib/statement/scraper.rb', line 878 def self.lowey(page=0) results = [] domain = "lowey.house.gov" url = "https://lowey.house.gov/media-center/press-releases?page=#{page}" doc = open_html(url) return if doc.nil? doc.css(".view-content .views-row").first(10).each do |row| results << {:source => url, :url => 'http://lowey.house.gov' + row.css('h3').first.children.first['href'], :title => row.css('h3').first.children.first.text.strip, :date => Date.parse(row.css(".views-field .field-content")[1].text), :domain => domain } end results end |
.lujan ⇒ Object
395 396 397 398 399 400 401 402 403 404 405 |
# File 'lib/statement/scraper.rb', line 395 def self.lujan results = [] base_url = 'http://lujan.house.gov/' 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" } end results end |
.mcclintock ⇒ Object
754 755 756 757 758 759 760 761 762 763 764 |
# File 'lib/statement/scraper.rb', line 754 def self.mcclintock results = [] domain = 'mcclintock.house.gov' url = "http://mcclintock.house.gov/press-all.shtml" doc = open_html(url) return if doc.nil? doc.css("ul li").first(152).each do |row| results << { :source => url, :url => row.children[0].children[1]['href'], :title => row.children[0].children[1].text.strip, :date => Date.parse(row.children[0].children[0].text), :domain => domain} end results end |
.mcmorris(page = 1) ⇒ Object
356 357 358 359 360 361 362 363 364 365 |
# File 'lib/statement/scraper.rb', line 356 def self.mcmorris(page=1) results = [] url = "http://mcmorris.house.gov/issues/page/#{page}/?tax=types&term=news_releases" doc = open_html(url) return if doc.nil? doc.css(".feed-result").each do |row| results << { :source => url, :url => row.children[3].children[3].children.first['href'], :title => row.children[3].children[3].children.first.text.strip, :date => Date.parse(row.children[3].children[1].text), :domain => "mcmorris.house.gov" } end results end |
.member_methods ⇒ Object
31 32 33 34 35 36 |
# File 'lib/statement/scraper.rb', line 31 def self.member_methods [:crenshaw, :capuano, :cold_fusion, :conaway, :chabot, :klobuchar, :billnelson, :crapo, :boxer, :burr, :ellison, :vitter, :inhofe, :document_query, :swalwell, :fischer, :clark, :edwards, :culberson_chabot_grisham, :barton, :schiff, :welch, :sessions, :gabbard, :costa, :farr, :mcclintock, :olson, :schumer, :cassidy, :lowey, :mcmorris, :takano, :bennie_thompson, :speier, :poe, :grassley, :bennet, :shaheen, :keating, :drupal, :jenkins, :durbin, :rand_paul] end |
.member_scrapers ⇒ Object
42 43 44 45 46 47 48 49 50 51 52 |
# File 'lib/statement/scraper.rb', line 42 def self.member_scrapers year = Date.today.year results = [crenshaw, capuano, cold_fusion(year, nil), conaway, chabot, klobuchar(year), billnelson(page=0), ellison, document_query(page=1), document_query(page=2), swalwell(page=1), crapo, boxer, grassley(page=0), burr, cassidy, vitter(year=year), inhofe(year=year), fischer, clark(year=year), edwards, culberson_chabot_grisham(page=1), , welch, sessions(year=year), , costa, farr, olson, schumer, bennie_thompson, speier, lowey, mcmorris, schiff, takano, poe(year=year, month=0), bennet(page=1), shaheen(page=1), perlmutter, keating, drupal, jenkins, durbin(page=1), rand_paul(page = 1)].flatten results = results.compact Utils.remove_generic_urls!(results) end |
.olson(year = 2014) ⇒ Object
766 767 768 769 770 771 772 773 774 775 776 |
# File 'lib/statement/scraper.rb', line 766 def self.olson(year=2014) results = [] domain = 'olson.house.gov' url = "http://olson.house.gov/#{year}-press-releases/" doc = open_html(url) return if doc.nil? (doc/:h3).each do |row| results << {:source => url, :url => 'http://olson.house.gov' + row.children[1]['href'], :title => row.children[1].text.strip, :date => Date.parse(row.next.next.text), :domain => domain } end results end |
.open_html(url) ⇒ Object
10 11 12 13 14 15 16 |
# File 'lib/statement/scraper.rb', line 10 def self.open_html(url) begin Nokogiri::HTML(open(url).read) rescue nil end end |
.patrick_meehan(page = 0) ⇒ Object
439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 |
# File 'lib/statement/scraper.rb', line 439 def self.patrick_meehan(page = 0) # This is a Drupal page and it uses the View plugin, but unlike the other # Drupal pages, it does not make use of .views-field-created, and instead, the # only Month-Year is given (03 Feb). page_url = "https://meehan.house.gov/media-center/press-releases?page=#{page}" doc = open_html(page_url) return if doc.nil? results = doc.search('.view-congress-press-releases .views-row').inject([]) do |arr, article| title = article.search('.views-field-title a')[0] article_url = URI.join(page_url, title['href']) raise "Date still needs to be parsed; thanks a lot Drupal" article_datestr = title.previous_element.text arr << { :source => page_url, :url => article_url.to_s, :domain => article_url.host, :title => title.text, :date => Date.strptime(article_datestr, 'SOMETHING') } end results end |
.perlmutter ⇒ Object
922 923 924 925 926 927 928 929 930 931 932 933 |
# File 'lib/statement/scraper.rb', line 922 def self.perlmutter results = [] domain = "perlmutter.house.gov" url = "http://#{domain}/index.php/media-center/press-releases-86821" doc = open_html(url) return if doc.nil? doc.css("#adminForm tr")[0..-1].each do |row| results << { :source => url, :url => "http://" + domain + row.children[1].children[1]['href'], :title => row.children[1].children[1].text.strip, :date => Date.parse(row.children[3].text), :domain => domain} end results end |
.poe(year, month = 0) ⇒ Object
382 383 384 385 386 387 388 389 390 391 392 393 |
# File 'lib/statement/scraper.rb', line 382 def self.poe(year, month=0) results = [] base_url = "http://poe.house.gov" month_url = base_url + "/press-releases?MonthDisplay=#{month}&YearDisplay=#{year}" doc = open_html(month_url) return if doc.nil? doc.xpath("//tr")[1..-1].each do |row| next if row.children[3].children[0].text.strip == 'Title' results << { :source => month_url, :url => base_url + row.children[3].children[0]['href'], :title => row.children[3].children[0].text.strip, :date => Date.strptime(row.children[1].text, "%m/%d/%y"), :domain => "poe.house.gov" } end results end |
.rand_paul(page = 1) ⇒ Object
419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 |
# File 'lib/statement/scraper.rb', line 419 def self.rand_paul(page = 1) # each page contains a max of 20 results page_url = "http://www.paul.senate.gov/news/press?PageNum_rs=#{page}" doc = open_html(page_url) return if doc.nil? results = doc.search('#press .title').inject([]) do |arr, title| article_url = URI.join(page_url, title.search('a')[0]['href']) article_datestr = title.previous_element.text # e.g. "05.11.15" arr << { :source => page_url, :url => article_url.to_s, :domain => article_url.host, :title => title.text, :date => Date.strptime(article_datestr, '%m.%d.%y') } end results end |
.schiff(page = 1) ⇒ Object
463 464 465 466 467 468 469 470 471 472 473 |
# File 'lib/statement/scraper.rb', line 463 def self.schiff(page=1) results = [] url = "http://schiff.house.gov/news/press-releases?PageNum_rs=#{page}&" doc = open_html(url) return if doc.nil? rows = doc.css("#press").first.css('h2') rows.each do |row| results << { :source => url, :url => "http://schiff.house.gov" + row.children.first['href'], :title => row.children.last.text.strip, :date => Date.strptime(row.previous.previous.text, "%m.%d.%y"), :domain => "schiff.house.gov" } end results end |
.schumer(page = 1) ⇒ Object
816 817 818 819 820 821 822 823 824 825 826 827 |
# File 'lib/statement/scraper.rb', line 816 def self.schumer(page=1) results = [] domain = 'www.schumer.senate.gov' url = "http://www.schumer.senate.gov/newsroom/press-releases/table?PageNum_rs=#{page}" doc = open_html(url) return if doc.nil? rows = (doc/:table/:tr).select{|r| !r.children[3].nil?} rows.each do |row| results << {:source => url, :url => row.children[3].children[1]['href'].strip, :title => row.children[3].text.strip, :date => Date.parse(row.children[1].text.strip), :domain => domain } end results end |
.senate_aging ⇒ Object
147 148 149 150 151 152 153 154 155 156 |
# File 'lib/statement/scraper.rb', line 147 def self.senate_aging results = [] url = "http://www.aging.senate.gov/pressroom.cfm?maxrows=100&startrow=1&&type=1" doc = open_html(url) return if doc.nil? doc.xpath("//tr")[6..104].each do |row| results << { :source => url, :url => "http://www.aging.senate.gov/"+row.children[2].children[0]['href'], :title => row.children[2].text.strip, :date => Date.parse(row.children[0].text), :domain => "http://www.aging.senate.gov/" } end results end |
.senate_approps_majority ⇒ Object
special cases for committees without RSS feeds
75 76 77 78 79 80 81 82 83 84 85 86 |
# File 'lib/statement/scraper.rb', line 75 def self.senate_approps_majority results = [] url = "http://www.appropriations.senate.gov/news.cfm" doc = open_html(url) return if doc.nil? doc.xpath("//div[@class='newsDateUnderlined']").each do |date| date.next.next.children.reject{|c| c.text.strip.empty?}.each do |row| results << { :source => url, :url => url + row.children[0]['href'], :title => row.text, :date => Date.parse(date.text), :domain => "http://www.appropriations.senate.gov/", :party => 'majority' } end end results end |
.senate_approps_minority ⇒ Object
88 89 90 91 92 93 94 95 96 97 98 99 |
# File 'lib/statement/scraper.rb', line 88 def self.senate_approps_minority results = [] url = "http://www.appropriations.senate.gov/republican.cfm" doc = open_html(url) return if doc.nil? doc.xpath("//div[@class='newsDateUnderlined']").each do |date| date.next.next.children.reject{|c| c.text.strip.empty?}.each do |row| results << { :source => url, :url => url + row.children[0]['href'], :title => row.text, :date => Date.parse(date.text), :domain => "http://www.appropriations.senate.gov/", :party => 'minority' } end end results end |
.senate_banking(year = Date.today.year) ⇒ Object
101 102 103 104 105 106 107 108 109 110 |
# File 'lib/statement/scraper.rb', line 101 def self.senate_banking(year=Date.today.year) results = [] url = "http://www.banking.senate.gov/public/index.cfm?FuseAction=Newsroom.PressReleases&ContentRecordType_id=b94acc28-404a-4fc6-b143-a9e15bf92da4&Region_id=&Issue_id=&MonthDisplay=0&YearDisplay=#{year}" doc = open_html(url) return if doc.nil? doc.xpath("//tr").each do |row| results << { :source => url, :url => "http://www.banking.senate.gov/public/" + row.children[2].children[1]['href'], :title => row.children[2].text.strip, :date => Date.parse(row.children[0].text.strip+", #{year}"), :domain => "http://www.banking.senate.gov/", :party => 'majority' } end results end |
.senate_hsag_majority(year = Date.today.year) ⇒ Object
112 113 114 115 116 117 118 119 120 121 122 |
# File 'lib/statement/scraper.rb', line 112 def self.senate_hsag_majority(year=Date.today.year) results = [] url = "http://www.hsgac.senate.gov/media/majority-media?year=#{year}" doc = open_html(url) return if doc.nil? doc.xpath("//tr").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].children[0].text, :date => Date.parse(row.children[0].text), :domain => "http://www.hsgac.senate.gov/", :party => 'majority' } end results end |
.senate_hsag_minority(year = Date.today.year) ⇒ Object
124 125 126 127 128 129 130 131 132 133 134 |
# File 'lib/statement/scraper.rb', line 124 def self.senate_hsag_minority(year=Date.today.year) results = [] url = "http://www.hsgac.senate.gov/media/minority-media?year=#{year}" doc = open_html(url) return if doc.nil? doc.xpath("//tr").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].children[0].text, :date => Date.parse(row.children[0].text), :domain => "http://www.hsgac.senate.gov/", :party => 'minority' } end results end |
.senate_indian ⇒ Object
136 137 138 139 140 141 142 143 144 145 |
# File 'lib/statement/scraper.rb', line 136 def self.senate_indian results = [] url = "http://www.indian.senate.gov/news/index.cfm" doc = open_html(url) return if doc.nil? doc.xpath("//h3").each do |row| results << { :source => url, :url => "http://www.indian.senate.gov"+row.children[0]['href'], :title => row.children[0].text, :date => Date.parse(row.previous.previous.text), :domain => "http://www.indian.senate.gov/", :party => 'majority' } end results end |
.senate_intel(congress = 113, start_year = 2013, end_year = 2014) ⇒ Object
169 170 171 172 173 174 175 176 177 178 |
# File 'lib/statement/scraper.rb', line 169 def self.senate_intel(congress=113, start_year=2013, end_year=2014) results = [] url = "http://www.intelligence.senate.gov/press/releases.cfm?congress=#{congress}&y1=#{start_year}&y2=#{end_year}" doc = open_html(url) return if doc.nil? doc.xpath("//tr[@valign='top']")[7..-1].each do |row| results << { :source => url, :url => "http://www.intelligence.senate.gov/press/"+row.children[2].children[0]['href'], :title => row.children[2].children[0].text.strip, :date => Date.parse(row.children[0].text), :domain => "http://www.intelligence.senate.gov/" } end results end |
.senate_smallbiz_minority ⇒ Object
158 159 160 161 162 163 164 165 166 167 |
# File 'lib/statement/scraper.rb', line 158 def self.senate_smallbiz_minority results = [] url = "http://www.sbc.senate.gov/public/index.cfm?p=RepublicanPressRoom" doc = open_html(url) return if doc.nil? doc.xpath("//ul[@class='recordList']").each do |row| results << { :source => url, :url => row.children[0].children[2].children[0]['href'], :title => row.children[0].children[2].children[0].text, :date => Date.parse(row.children[0].children[0].text), :domain => "http://www.sbc.senate.gov/", :party => 'minority' } end results end |
.sessions(year = Date.today.year) ⇒ Object
648 649 650 651 652 653 654 655 656 657 658 659 |
# File 'lib/statement/scraper.rb', line 648 def self.sessions(year=Date.today.year) results = [] domain = 'sessions.senate.gov' url = "http://www.sessions.senate.gov/public/index.cfm/news-releases?YearDisplay=#{year}" doc = open_html(url) return if doc.nil? (doc/:tr)[1..-1].each do |row| next if row.children[1].text.strip == 'Date' results << { :source => url, :date => Date.parse(row.children[1].text), :title => row.children[3].children.text, :url => row.children[3].children[0]['href'], :domain => domain} end results end |
.shaheen(page = 1) ⇒ Object
841 842 843 844 845 846 847 848 849 850 851 852 |
# File 'lib/statement/scraper.rb', line 841 def self.shaheen(page=1) results = [] domain = 'www.shaheen.senate.gov' url = "http://www.shaheen.senate.gov/news/press/index.cfm?PageNum_rs=#{page}" doc = open_html(url) return if doc.nil? (doc/:ul)[3].children.each do |row| next if row.text.strip == '' results << {:source => url, :url => row.children[2].children[0]['href'], :title => row.children[2].text.strip, :date => Date.parse(row.children.first.text), :domain => domain } end results end |
.speier ⇒ Object
487 488 489 490 491 492 493 494 495 496 497 |
# File 'lib/statement/scraper.rb', line 487 def self.speier results = [] url = "http://speier.house.gov/index.php?option=com_content&view=category&id=20&Itemid=14" doc = open_html(url) return if doc.nil? rows = doc.css("table.category tr") rows.each do |row| results << { :source => url, :url => "http://speier.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 => "speier.house.gov" } end results end |
.swalwell(page = 1) ⇒ Object
special cases for members without RSS feeds
240 241 242 243 244 245 246 247 248 249 |
# File 'lib/statement/scraper.rb', line 240 def self.swalwell(page=1) results = [] url = "http://swalwell.house.gov/category/press-releases/page/#{page}/" doc = open_html(url) return if doc.nil? doc.xpath("//h3")[0..4].each do |row| results << { :source => url, :url => row.children[0]['href'], :title => row.children[0].text, :date => nil, :domain => 'swalwell.house.gov'} end results end |
.takano(page = 1) ⇒ Object
475 476 477 478 479 480 481 482 483 484 485 |
# File 'lib/statement/scraper.rb', line 475 def self.takano(page=1) results = [] url = "http://takano.house.gov/newsroom/press-releases?PageNum_rs=#{page}" doc = open_html(url) return if doc.nil? rows = doc.css("#press").first.css('h2') rows.each do |row| results << { :source => url, :url => "http://takano.house.gov" + row.children.first['href'], :title => row.children.last.text.strip, :date => Date.strptime(row.previous.previous.text, "%m.%d.%y"), :domain => "takano.house.gov" } end results end |
.vitter(year = Date.today.year) ⇒ Object
582 583 584 585 586 587 588 589 590 591 592 593 |
# File 'lib/statement/scraper.rb', line 582 def self.vitter(year=Date.today.year) results = [] url = "http://www.vitter.senate.gov/newsroom/" domain = "www.vitter.senate.gov" 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[3].children[0]['href'].strip, :title => row.children[3].text, :date => Date.strptime(row.children[1].text, "%m/%d/%y"), :domain => domain} end results end |
.welch ⇒ Object
702 703 704 705 706 707 708 709 710 711 712 |
# File 'lib/statement/scraper.rb', line 702 def self.welch results = [] domain = 'welch.house.gov' url = "http://www.welch.house.gov/press-releases/" doc = open_html(url) return if doc.nil? (doc/:h3).each do |row| results << { :source => url, :url => "http://www.welch.house.gov/"+row.children[1]['href'], :title => row.children[1].text.strip, :date => Date.parse(row.next.next.text), :domain => domain} end results end |