statement 1.8.13 → 1.9
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/statement/scraper.rb +6 -20
- data/lib/statement/utils.rb +2 -2
- data/lib/statement/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 3316c0e258c2ed004e32b0c367c10672519f169c
|
4
|
+
data.tar.gz: cd831fcea5e979ac3c27046e9e2617967616f824
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 0ae5af468325c272f9befab60d333e9f9d197588f66e9d50e3f0beb2c3795b67505069f0b73e99972dacc010c5ce7bd6a9e27fc2368863e6f3e816b190ace838
|
7
|
+
data.tar.gz: d34919c91fbc18d45a44d39fbe21120339568ddbd037a97adc91ddd8c8f4a60c48d30d881271f476bf0fe8003713f5af2165c65f934036e666924687f48c32df
|
data/lib/statement/scraper.rb
CHANGED
@@ -29,7 +29,7 @@ module Statement
|
|
29
29
|
end
|
30
30
|
|
31
31
|
def self.member_methods
|
32
|
-
[:crenshaw, :capuano, :cold_fusion, :conaway, :chabot, :susandavis, :freshman_senators, :klobuchar, :billnelson, :
|
32
|
+
[:crenshaw, :capuano, :cold_fusion, :conaway, :chabot, :susandavis, :freshman_senators, :klobuchar, :billnelson, :crapo, :boxer, :vitter, :inhofe, :palazzo, :roe, :document_query, :swalwell, :fischer, :clark, :edwards, :culberson_chabot_grisham, :barton, :sherman_mccaul, :welch, :sessions, :gabbard, :ellison, :costa, :farr, :mcclintock, :mcnerney, :olson]
|
33
33
|
end
|
34
34
|
|
35
35
|
def self.committee_methods
|
@@ -40,8 +40,8 @@ module Statement
|
|
40
40
|
year = Date.today.year
|
41
41
|
results = [crenshaw, capuano, cold_fusion(year, nil), conaway, chabot, susandavis, klobuchar(year), palazzo(page=1), roe(page=1), billnelson(year=year),
|
42
42
|
document_query(page=1), document_query(page=2), swalwell(page=1), crapo, coburn, boxer(start=1),
|
43
|
-
vitter(year=year), inhofe(year=2014), fischer, clark(year=year), edwards, culberson_chabot_grisham(page=1), barton,
|
44
|
-
sessions(year=year), gabbard,
|
43
|
+
vitter(year=year), inhofe(year=2014), fischer, clark(year=year), edwards, culberson_chabot_grisham(page=1), barton, sherman_mccaul, welch,
|
44
|
+
sessions(year=year), gabbard, ellison(page=0), costa, farr, mcclintock, olson, mcnerney].flatten
|
45
45
|
results = results.compact
|
46
46
|
Utils.remove_generic_urls!(results)
|
47
47
|
end
|
@@ -50,7 +50,7 @@ module Statement
|
|
50
50
|
results = [cold_fusion(2012, 0), cold_fusion(2011, 0), cold_fusion(2010, 0), billnelson(year=2012), document_query(page=3),
|
51
51
|
document_query(page=4), coburn(year=2012), coburn(year=2011), coburn(year=2010), boxer(start=11), boxer(start=21),
|
52
52
|
boxer(start=31), boxer(start=41), vitter(year=2012), vitter(year=2011), swalwell(page=2), swalwell(page=3), clark(year=2013), culberson_chabot_grisham(page=2),
|
53
|
-
|
53
|
+
sherman_mccaul(page=1), sessions(year=2013), pryor(page=1), ellison(page=1), ellison(page=2), ellison(page=3), farr(year=2013), farr(year=2012), farr(year=2011),
|
54
54
|
mcnerney(page=2), mcnerney(page=3), mcnerney(page=4), mcnerney(page=5), mcnerney(page=6), olson(year=2013)].flatten
|
55
55
|
Utils.remove_generic_urls!(results)
|
56
56
|
end
|
@@ -579,9 +579,9 @@ module Statement
|
|
579
579
|
results
|
580
580
|
end
|
581
581
|
|
582
|
-
def self.
|
582
|
+
def self.sherman_mccaul(page=0)
|
583
583
|
results = []
|
584
|
-
domains = ['
|
584
|
+
domains = ['sherman.house.gov', 'mccaul.house.gov']
|
585
585
|
domains.each do |domain|
|
586
586
|
url = "http://#{domain}/media-center/press-releases?page=#{page}"
|
587
587
|
doc = open_html(url)
|
@@ -595,20 +595,6 @@ module Statement
|
|
595
595
|
results.flatten
|
596
596
|
end
|
597
597
|
|
598
|
-
def self.pryor(page=0)
|
599
|
-
results = []
|
600
|
-
domain = 'www.pryor.senate.gov'
|
601
|
-
url = "http://www.pryor.senate.gov/newsroom/press-releases?page=#{page}"
|
602
|
-
doc = open_html(url)
|
603
|
-
return if doc.nil?
|
604
|
-
dates = doc.xpath('//span[@class="field-content"]').map {|s| s.text if s.text.strip.include?("201")}.compact!
|
605
|
-
doc.xpath('//div[@class="views-field views-field-title"]').each_with_index do |row, i|
|
606
|
-
date = Date.parse(dates[i])
|
607
|
-
results << {:source => url, :url => "http://www.pryor.senate.gov"+row.children[1].children[0]['href'], :title => row.children[1].children[0].text.strip, :date => date, :domain => domain}
|
608
|
-
end
|
609
|
-
results
|
610
|
-
end
|
611
|
-
|
612
598
|
def self.welch
|
613
599
|
results = []
|
614
600
|
domain = 'welch.house.gov'
|
data/lib/statement/utils.rb
CHANGED
@@ -2,11 +2,11 @@ require 'uri'
|
|
2
2
|
|
3
3
|
module Utils
|
4
4
|
def self.absolute_link(url, link)
|
5
|
-
return link if link =~ /^http
|
5
|
+
return link if link =~ /^http/
|
6
6
|
("http://"+URI.parse(url).host + "/"+link).to_s
|
7
7
|
end
|
8
8
|
|
9
9
|
def self.remove_generic_urls!(results)
|
10
10
|
results.reject{|r| URI.parse(URI.escape(r[:url])).path == '/news/' or URI.parse(URI.escape(r[:url])).path == '/news'}
|
11
11
|
end
|
12
|
-
end
|
12
|
+
end
|
data/lib/statement/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: statement
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: '1.9'
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Derek Willis
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-
|
11
|
+
date: 2015-02-18 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|