Class: Statement::Scraper

Inherits:
Object
  • Object
show all
Defined in:
lib/statement/scraper.rb

Class Method Summary collapse

Class Method Details

.backfill_bilirakis ⇒ Object 



800
801
802
803
804
805
806
807
808
809
 
# File 'lib/statement/scraper.rb', line 800

def self.backfill_bilirakis
  results = []
  domain = 'bilirakis.house.gov'
  url = 'http://bilirakis.house.gov/press-releases/'
  doc = open_html(url)
  return if doc.nil?
  doc.css("ul li[@class='article articleright']").each do |row|
    results << {:source => url, :url => 'http://bilirakis.house.gov' + row.children[3].children[1]['href'], :title => row.children[3].text.strip, :date => Date.parse(row.children[5].text), :domain => domain }
  end
end

.backfill_boustany ⇒ Object 



811
812
813
814
815
816
817
818
 
# File 'lib/statement/scraper.rb', line 811

def self.backfill_boustany
  results = []
  domain = 'boustany.house.gov'
  url = 'http://boustany.house.gov/113th-congress/showallitems/'
  doc = open_html(url)
  return if doc.nil?

end

.backfill_from_scrapers ⇒ Object 



53
54
55
56
57
58
59
60
61
 
# File 'lib/statement/scraper.rb', line 53

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),
    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),
    olson(year=2013), schumer(page=2), schumer(page=3), poe(year=2015, month=2),
    poe(year=2015, month=1)].flatten
  Utils.remove_generic_urls!(results)
end

.barton ⇒ Object 



578
579
580
581
582
583
584
585
586
587
588
 
# File 'lib/statement/scraper.rb', line 578

def self.barton
  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 



710
711
712
713
714
715
716
717
718
719
720
 
# File 'lib/statement/scraper.rb', line 710

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 



776
777
778
779
780
781
782
783
784
785
786
 
# File 'lib/statement/scraper.rb', line 776

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 



394
395
396
397
398
399
400
401
402
403
404
 
# File 'lib/statement/scraper.rb', line 394

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 



454
455
456
457
458
459
460
461
462
463
464
465
 
# File 'lib/statement/scraper.rb', line 454

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

.capuano ⇒ Object 



249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
 
# File 'lib/statement/scraper.rb', line 249

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

.chabot(year = Date.today.year) ⇒ Object 



341
342
343
344
345
346
347
348
349
350
351
352
 
# File 'lib/statement/scraper.rb', line 341

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 



523
524
525
526
527
528
529
530
531
532
533
534
 
# File 'lib/statement/scraper.rb', line 523

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 



287
288
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
 
# File 'lib/statement/scraper.rb', line 287

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 



63
64
65
66
67
68
69
 
# File 'lib/statement/scraper.rb', line 63

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 



329
330
331
332
333
334
335
336
337
338
339
 
# File 'lib/statement/scraper.rb', line 329

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 



614
615
616
617
618
619
620
621
622
623
624
 
# File 'lib/statement/scraper.rb', line 614

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 



419
420
421
422
423
424
425
426
427
428
429
 
# File 'lib/statement/scraper.rb', line 419

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 



267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
 
# File 'lib/statement/scraper.rb', line 267

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 



562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
 
# File 'lib/statement/scraper.rb', line 562

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 



666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
 
# File 'lib/statement/scraper.rb', line 666

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" => 2608},
    {"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}
  ]
  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



481
482
483
484
485
486
487
488
489
490
491
492
 
# File 'lib/statement/scraper.rb', line 481

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 



848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
 
# File 'lib/statement/scraper.rb', line 848

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://sarbanes.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"
    ]
  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_burr(page = 1) ⇒ Object 



494
495
496
497
498
499
500
501
502
503
504
505
506
 
# File 'lib/statement/scraper.rb', line 494

def self.durbin_burr(page=1)
  results = []
  domains = ["www.durbin.senate.gov", "www.burr.senate.gov"]
  domains.each do |domain|
    url = "http://#{domain}/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://#{domain}"+row.children[0]['href'], :title => row.children[0].text.strip, :date => Date.parse(row.previous.previous.text.gsub(".","/")), :domain => domain}
    end
  end
  results
end

.edwards ⇒ Object 



549
550
551
552
553
554
555
556
557
558
559
560
 
# File 'lib/statement/scraper.rb', line 549

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

.farr(year = 2014) ⇒ Object 



626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
 
# File 'lib/statement/scraper.rb', line 626

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 



431
432
433
434
435
436
437
438
439
440
441
 
# File 'lib/statement/scraper.rb', line 431

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 



602
603
604
605
606
607
608
609
610
611
612
 
# File 'lib/statement/scraper.rb', line 602

def self.gabbard
  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 



443
444
445
446
447
448
449
450
451
452
 
# File 'lib/statement/scraper.rb', line 443

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 



178
179
180
181
182
183
184
185
186
187
 
# File 'lib/statement/scraper.rb', line 178

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 



189
190
191
192
193
194
195
196
197
198
 
# File 'lib/statement/scraper.rb', line 189

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 



200
201
202
203
204
205
206
207
208
209
210
 
# File 'lib/statement/scraper.rb', line 200

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 



212
213
214
215
216
217
218
219
220
221
222
 
# File 'lib/statement/scraper.rb', line 212

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 



224
225
226
227
228
229
230
231
232
233
234
 
# File 'lib/statement/scraper.rb', line 224

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 



508
509
510
511
512
513
514
515
516
517
518
519
520
521
 
# File 'lib/statement/scraper.rb', line 508

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 



752
753
754
755
756
757
758
759
760
761
762
 
# File 'lib/statement/scraper.rb', line 752

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 



833
834
835
836
837
838
839
840
841
842
843
844
845
846
 
# File 'lib/statement/scraper.rb', line 833

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 



354
355
356
357
358
359
360
361
362
363
364
365
366
367
 
# File 'lib/statement/scraper.rb', line 354

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

.lamborn(limit = nil) ⇒ Object 



735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
 
# File 'lib/statement/scraper.rb', line 735

def self.lamborn(limit=nil)
  results = []
  domain = 'lamborn.house.gov'
  url = "http://lamborn.house.gov/2015-press-releases/"
  doc = open_html(url)
  return if doc.nil?
  links = (doc/:h3).map{|h| { "http://lamborn.house.gov"+h.children[1]['href'] => h.text.strip} }
  links = links.first(limit) if limit
  links.each do |link|
    page = open_html(link.keys.first)
    print_path = page.search("a").detect{|a| a['onclick'] && a['onclick'].include?('popup')}['onclick'].split("'")[1]
    print_page = open_html("http://lamborn.house.gov"+print_path)
    results << {:source => url, :url => link.keys.first, :title => link.values.first, :date => Date.parse(print_page.xpath('//*[@class="PopupNewsDetailsDate"]').text), :domain => domain }
  end
  results
end

.lautenberg(rows = 1000) ⇒ Object

fetches the latest 1000 releases, can be altered



407
408
409
410
411
412
413
414
415
416
417
 
# File 'lib/statement/scraper.rb', line 407

def self.lautenberg(rows=1000)
  results = []
  base_url = 'http://www.lautenberg.senate.gov/newsroom/'
  url = base_url + "releases.cfm?maxrows=#{rows}&startrow=1&&type=1"
  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.strptime(row.children[0].text.strip, "%m/%d/%y"), :domain => "lautenberg.senate.gov" }
  end
  results
end

.lujan ⇒ Object 



382
383
384
385
386
387
388
389
390
391
392
 
# File 'lib/statement/scraper.rb', line 382

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 



642
643
644
645
646
647
648
649
650
651
652
 
# File 'lib/statement/scraper.rb', line 642

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

.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, :freshman_senators, :klobuchar, :billnelson, :crapo, :boxer,
  :vitter, :inhofe, :document_query, :swalwell, :fischer, :clark, :edwards, :culberson_chabot_grisham, :barton,
  :welch, :sessions, :gabbard, :costa, :farr, :mcclintock, :olson, :schumer, :lamborn, :walden,
  :bennie_thompson, :speier, :poe, :grassley, :bennet, :shaheen, :keating, :drupal, :jenkins, :durbin_burr]
end

.member_scrapers ⇒ Object 



42
43
44
45
46
47
48
49
50
51
 
# 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),
    document_query(page=1), document_query(page=2), swalwell(page=1), crapo, boxer, grassley(page=0),
    vitter(year=year), inhofe(year=year), fischer, clark(year=year), edwards, culberson_chabot_grisham(page=1), barton, welch,
    sessions(year=year), gabbard, costa, farr, olson, schumer, lamborn(limit=10), walden, bennie_thompson, speier,
    poe(year=year, month=0), bennet(page=1), shaheen(page=1), perlmutter, keating, drupal, jenkins, durbin_burr(page=1)].flatten
  results = results.compact
  Utils.remove_generic_urls!(results)
end

.olson(year = 2014) ⇒ Object 



654
655
656
657
658
659
660
661
662
663
664
 
# File 'lib/statement/scraper.rb', line 654

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

.perlmutter ⇒ Object 



820
821
822
823
824
825
826
827
828
829
830
831
 
# File 'lib/statement/scraper.rb', line 820

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 



369
370
371
372
373
374
375
376
377
378
379
380
 
# File 'lib/statement/scraper.rb', line 369

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

.schumer(page = 1) ⇒ Object 



697
698
699
700
701
702
703
704
705
706
707
708
 
# File 'lib/statement/scraper.rb', line 697

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 



145
146
147
148
149
150
151
152
153
154
 
# File 'lib/statement/scraper.rb', line 145

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



73
74
75
76
77
78
79
80
81
82
83
84
 
# File 'lib/statement/scraper.rb', line 73

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 



86
87
88
89
90
91
92
93
94
95
96
97
 
# File 'lib/statement/scraper.rb', line 86

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 



99
100
101
102
103
104
105
106
107
108
 
# File 'lib/statement/scraper.rb', line 99

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 



110
111
112
113
114
115
116
117
118
119
120
 
# File 'lib/statement/scraper.rb', line 110

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 



122
123
124
125
126
127
128
129
130
131
132
 
# File 'lib/statement/scraper.rb', line 122

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 



134
135
136
137
138
139
140
141
142
143
 
# File 'lib/statement/scraper.rb', line 134

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 



167
168
169
170
171
172
173
174
175
176
 
# File 'lib/statement/scraper.rb', line 167

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 



156
157
158
159
160
161
162
163
164
165
 
# File 'lib/statement/scraper.rb', line 156

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 



536
537
538
539
540
541
542
543
544
545
546
547
 
# File 'lib/statement/scraper.rb', line 536

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 



722
723
724
725
726
727
728
729
730
731
732
733
 
# File 'lib/statement/scraper.rb', line 722

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 



788
789
790
791
792
793
794
795
796
797
798
 
# File 'lib/statement/scraper.rb', line 788

def self.speier
  results = []
  domain = "speier.house.gov"
  url = "http://speier.house.gov/index.php?option=com_content&view=category&id=20&Itemid=14"
  doc = open_html(url)
  return if doc.nil?
  doc.xpath('//*[@id="adminForm"]/table/tbody/tr').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 => domain }
  end
  results
end

.swalwell(page = 1) ⇒ Object

special cases for members without RSS feeds



238
239
240
241
242
243
244
245
246
247
 
# File 'lib/statement/scraper.rb', line 238

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

.vitter(year = Date.today.year) ⇒ Object 



467
468
469
470
471
472
473
474
475
476
477
478
 
# File 'lib/statement/scraper.rb', line 467

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

.walden ⇒ Object 



764
765
766
767
768
769
770
771
772
773
774
 
# File 'lib/statement/scraper.rb', line 764

def self.walden
  results = []
  domain = 'walden.house.gov'
  url = "http://walden.house.gov/s2015/"
  doc = open_html(url)
  return if doc.nil?
  doc.xpath('//*[@id="centerbox"]/div[1]/ul/li').each do |row|
    results << {:source => url, :url => 'http://walden.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

.welch ⇒ Object 



590
591
592
593
594
595
596
597
598
599
600
 
# File 'lib/statement/scraper.rb', line 590

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