statement 0.9.3 → 0.9.4
Sign up to get free protection for your applications and to get access to all the features.
- data/README.md +16 -2
- data/lib/statement/scraper.rb +7 -8
- data/lib/statement/version.rb +1 -1
- metadata +16 -16
data/README.md
CHANGED
@@ -42,8 +42,22 @@ puts results.first
|
|
42
42
|
The sites that require HTML scraping are detailed in individual methods, and can be called individually or in bulk:
|
43
43
|
|
44
44
|
```
|
45
|
-
|
46
|
-
|
45
|
+
results = Statement::Scraper.billnelson
|
46
|
+
members = Statement::Scraper.member_scrapers
|
47
|
+
```
|
48
|
+
|
49
|
+
Using the `koala` gem, Statement can fetch Facebook status feeds, given a Facebook ID. You'll need to either set environment variables `APP_ID` and `APP_SECRET` or create a `config.yml` file containing `app_id` and `app_secret` keys and values.
|
50
|
+
|
51
|
+
```
|
52
|
+
f = Statement::Facebook.new
|
53
|
+
results = f.feed('RepFincherTN08')
|
54
|
+
```
|
55
|
+
|
56
|
+
It also can process IDs in batches, with a `slice` argument to indicate how many ids are passed in each batch:
|
57
|
+
|
58
|
+
```
|
59
|
+
f = Statement::Facebook.new
|
60
|
+
results = f.batch(array, 10)
|
47
61
|
```
|
48
62
|
|
49
63
|
## Tests
|
data/lib/statement/scraper.rb
CHANGED
@@ -233,15 +233,14 @@ module Statement
|
|
233
233
|
list_url = base_url + 'date.shtml'
|
234
234
|
doc = open_html(list_url)
|
235
235
|
return if doc.nil?
|
236
|
-
doc.xpath("//a").each do |link|
|
237
|
-
|
238
|
-
|
239
|
-
|
240
|
-
|
241
|
-
|
242
|
-
end
|
243
|
-
results << { :source => list_url, :url => base_url + link['href'], :title => link.text.split(' ',2).last, :date => date, :domain => "www.house.gov/capuano/" }
|
236
|
+
doc.xpath("//a").select{|l| !l['href'].nil? and l['href'].include?('/pr')}[1..-5].each do |link|
|
237
|
+
begin
|
238
|
+
year = link['href'].split('/').first
|
239
|
+
date = Date.parse(link.text.split(' ').first+'/'+year)
|
240
|
+
rescue
|
241
|
+
date = nil
|
244
242
|
end
|
243
|
+
results << { :source => list_url, :url => base_url + link['href'], :title => link.text.split(' ',2).last, :date => date, :domain => "www.house.gov/capuano/" }
|
245
244
|
end
|
246
245
|
return results[0..-5]
|
247
246
|
end
|
data/lib/statement/version.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: statement
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.9.
|
4
|
+
version: 0.9.4
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,11 +9,11 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2013-05-
|
12
|
+
date: 2013-05-24 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: bundler
|
16
|
-
requirement: &
|
16
|
+
requirement: &2156038320 !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - ~>
|
@@ -21,10 +21,10 @@ dependencies:
|
|
21
21
|
version: '1.3'
|
22
22
|
type: :development
|
23
23
|
prerelease: false
|
24
|
-
version_requirements: *
|
24
|
+
version_requirements: *2156038320
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: rake
|
27
|
-
requirement: &
|
27
|
+
requirement: &2156037740 !ruby/object:Gem::Requirement
|
28
28
|
none: false
|
29
29
|
requirements:
|
30
30
|
- - ! '>='
|
@@ -32,10 +32,10 @@ dependencies:
|
|
32
32
|
version: '0'
|
33
33
|
type: :development
|
34
34
|
prerelease: false
|
35
|
-
version_requirements: *
|
35
|
+
version_requirements: *2156037740
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: webmock
|
38
|
-
requirement: &
|
38
|
+
requirement: &2156037140 !ruby/object:Gem::Requirement
|
39
39
|
none: false
|
40
40
|
requirements:
|
41
41
|
- - ! '>='
|
@@ -43,10 +43,10 @@ dependencies:
|
|
43
43
|
version: '0'
|
44
44
|
type: :development
|
45
45
|
prerelease: false
|
46
|
-
version_requirements: *
|
46
|
+
version_requirements: *2156037140
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: american_date
|
49
|
-
requirement: &
|
49
|
+
requirement: &2156036600 !ruby/object:Gem::Requirement
|
50
50
|
none: false
|
51
51
|
requirements:
|
52
52
|
- - ! '>='
|
@@ -54,10 +54,10 @@ dependencies:
|
|
54
54
|
version: '0'
|
55
55
|
type: :runtime
|
56
56
|
prerelease: false
|
57
|
-
version_requirements: *
|
57
|
+
version_requirements: *2156036600
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: nokogiri
|
60
|
-
requirement: &
|
60
|
+
requirement: &2156035940 !ruby/object:Gem::Requirement
|
61
61
|
none: false
|
62
62
|
requirements:
|
63
63
|
- - ! '>='
|
@@ -65,10 +65,10 @@ dependencies:
|
|
65
65
|
version: '0'
|
66
66
|
type: :runtime
|
67
67
|
prerelease: false
|
68
|
-
version_requirements: *
|
68
|
+
version_requirements: *2156035940
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: koala
|
71
|
-
requirement: &
|
71
|
+
requirement: &2156035320 !ruby/object:Gem::Requirement
|
72
72
|
none: false
|
73
73
|
requirements:
|
74
74
|
- - ! '>='
|
@@ -76,10 +76,10 @@ dependencies:
|
|
76
76
|
version: '0'
|
77
77
|
type: :runtime
|
78
78
|
prerelease: false
|
79
|
-
version_requirements: *
|
79
|
+
version_requirements: *2156035320
|
80
80
|
- !ruby/object:Gem::Dependency
|
81
81
|
name: oj
|
82
|
-
requirement: &
|
82
|
+
requirement: &2156034620 !ruby/object:Gem::Requirement
|
83
83
|
none: false
|
84
84
|
requirements:
|
85
85
|
- - ! '>='
|
@@ -87,7 +87,7 @@ dependencies:
|
|
87
87
|
version: '0'
|
88
88
|
type: :runtime
|
89
89
|
prerelease: false
|
90
|
-
version_requirements: *
|
90
|
+
version_requirements: *2156034620
|
91
91
|
description: Crawls congressional websites for press releases.
|
92
92
|
email:
|
93
93
|
- dwillis@gmail.com
|