guardianscraper 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/lib/guardianscraper.rb +36 -0
- metadata +45 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 7844bf4e98d141cf05ae449a8cf20dcaf99cadc9
|
4
|
+
data.tar.gz: 462c193afcfec2d3535bd585d4256f35f393982a
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: b5ae4e816de1b2efaea18456bf53d3d1587561d82bc086e31decfb8c0e88d9a9d96e3d8567bd886ae75301cb7e9505910163af3ce692ed64a1b58e0855736992
|
7
|
+
data.tar.gz: 78071d2df2b3fc6a42d36d6ceb064b7279c51b5d02ac16bdc1c5408218f514bbb126c96e31124c38fde9504600c9678a4b66d5ef0714ccc888808293dead1c99
|
@@ -0,0 +1,36 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
require 'open-uri'
|
3
|
+
require 'json'
|
4
|
+
|
5
|
+
# Scraper for the articles about the NSA docs in the Guardian
|
6
|
+
class GuardianScraper
|
7
|
+
def initialize(url)
|
8
|
+
@url = url
|
9
|
+
end
|
10
|
+
|
11
|
+
# Download the article and save the text and other data
|
12
|
+
def getArticle
|
13
|
+
articlehash = Hash.new
|
14
|
+
html = Nokogiri::HTML(open(@url))
|
15
|
+
|
16
|
+
# Gets misc data on article
|
17
|
+
articlehash[:headline] = html.css('h1[itemprop="name headline "]').text
|
18
|
+
articlehash[:description] = html.css('div[itemprop="description"]').text
|
19
|
+
articlehash[:date] = html.css('time[itemprop="datePublished"]').text
|
20
|
+
articlehash[:author] = html.css("a.contributor").text
|
21
|
+
articlehash[:published_by] = "The Guardian"
|
22
|
+
articlehash[:caption] = html.css("div.caption").text
|
23
|
+
|
24
|
+
# Gets list of documents linked to
|
25
|
+
articlehash[:documents] = Array.new
|
26
|
+
html.css('div[itemprop="description"]').css("a").each do |d|
|
27
|
+
articlehash[:documents].push(d["href"])
|
28
|
+
end
|
29
|
+
|
30
|
+
# Gets text of article
|
31
|
+
articlehash[:text] = html.css("div#article-body-blocks").text
|
32
|
+
articlehash[:plaintext] = html.css("div#article-body-blocks").text
|
33
|
+
|
34
|
+
JSON.pretty_generate(articlehash)
|
35
|
+
end
|
36
|
+
end
|
metadata
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: guardianscraper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- M. C. McGrath
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-04-29 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: Scrapes Guardian articles.
|
14
|
+
email: shidash@shidash.com
|
15
|
+
executables: []
|
16
|
+
extensions: []
|
17
|
+
extra_rdoc_files: []
|
18
|
+
files:
|
19
|
+
- lib/guardianscraper.rb
|
20
|
+
homepage: https://github.com/Shidash/GuardianScraper
|
21
|
+
licenses:
|
22
|
+
- GPL
|
23
|
+
metadata: {}
|
24
|
+
post_install_message:
|
25
|
+
rdoc_options: []
|
26
|
+
require_paths:
|
27
|
+
- lib
|
28
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
29
|
+
requirements:
|
30
|
+
- - '>='
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '0'
|
33
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
34
|
+
requirements:
|
35
|
+
- - '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
requirements: []
|
39
|
+
rubyforge_project:
|
40
|
+
rubygems_version: 2.0.14
|
41
|
+
signing_key:
|
42
|
+
specification_version: 4
|
43
|
+
summary: Scrapes Guardian articles
|
44
|
+
test_files: []
|
45
|
+
has_rdoc:
|