nytimes_top_stories 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +13 -0
- data/.rspec +2 -0
- data/.travis.yml +5 -0
- data/Gemfile +9 -0
- data/LICENSE.txt +21 -0
- data/README.md +37 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/nytimes-top-stories +4 -0
- data/bin/setup +8 -0
- data/config/environment.rb +5 -0
- data/fixtures/nytindex.htm +10119 -0
- data/lib/nytimes_top_stories/cli.rb +37 -0
- data/lib/nytimes_top_stories/scraper.rb +35 -0
- data/lib/nytimes_top_stories/story.rb +41 -0
- data/lib/nytimes_top_stories/version.rb +3 -0
- data/lib/nytimes_top_stories.rb +1 -0
- data/nytimes_top_stories.gemspec +38 -0
- data/spec.md +15 -0
- metadata +139 -0
@@ -0,0 +1,37 @@
|
|
1
|
+
class NytimesTopStories::CLI
|
2
|
+
def call
|
3
|
+
puts NytimesTopStories::Scraper.get_date
|
4
|
+
puts "Headlines live from NYT:"
|
5
|
+
self.display_stories
|
6
|
+
self.menu
|
7
|
+
self.goodbye
|
8
|
+
end
|
9
|
+
|
10
|
+
def display_stories
|
11
|
+
NytimesTopStories::Story.new_from_array
|
12
|
+
NytimesTopStories::Story.all.each.with_index(1) {|story, i| puts "#{i}: #{story.headline}"}
|
13
|
+
end
|
14
|
+
|
15
|
+
def menu
|
16
|
+
choice = nil
|
17
|
+
until choice == "exit"
|
18
|
+
puts "Enter story number for more information, or type 'list'/'exit'"
|
19
|
+
choice = gets.strip.downcase
|
20
|
+
if choice.to_i > 0 && !NytimesTopStories::Story.all[choice.to_i-1].nil?
|
21
|
+
story = NytimesTopStories::Story.all[choice.to_i-1]
|
22
|
+
story.puts_story
|
23
|
+
elsif choice == "list"
|
24
|
+
self.call
|
25
|
+
elsif choice == "exit"
|
26
|
+
break
|
27
|
+
else
|
28
|
+
puts "Input invalid. Type 'list' or 'exit'."
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
def goodbye
|
34
|
+
puts "The truth is more important now than ever."
|
35
|
+
exit(0)
|
36
|
+
end
|
37
|
+
end
|
@@ -0,0 +1,35 @@
|
|
1
|
+
require 'open-uri'
|
2
|
+
|
3
|
+
class NytimesTopStories::Scraper
|
4
|
+
|
5
|
+
def self.open_site(site = "http://nytimes.com")
|
6
|
+
html = open(site)
|
7
|
+
doc = Nokogiri::HTML(html)
|
8
|
+
end
|
9
|
+
|
10
|
+
def self.get_top_stories(site = "http://nytimes.com")
|
11
|
+
doc = self.open_site(site)
|
12
|
+
top_stories_array = []
|
13
|
+
stories = doc.css("#top-news .collection .theme-summary")
|
14
|
+
stories.each do |story|
|
15
|
+
story_hash = {}
|
16
|
+
story_hash[:headline] = story.css(".story-heading a").text
|
17
|
+
story_hash[:byline] = story.css(".byline").text.strip
|
18
|
+
if !story.css("ul").empty?
|
19
|
+
story_hash[:summary] = story.css("ul").text.strip
|
20
|
+
else
|
21
|
+
story_hash[:summary] = story.css("p.summary").text.strip
|
22
|
+
end
|
23
|
+
if !story.at_css(".story-heading a").nil?
|
24
|
+
story_hash[:url] = story.css(".story-heading a").attr("href").value
|
25
|
+
end
|
26
|
+
top_stories_array << story_hash
|
27
|
+
end
|
28
|
+
top_stories_array
|
29
|
+
end
|
30
|
+
|
31
|
+
def self.get_date(site = "http://nytimes.com")
|
32
|
+
doc = self.open_site(site)
|
33
|
+
doc.css(".masthead-menu .date").text
|
34
|
+
end
|
35
|
+
end
|
@@ -0,0 +1,41 @@
|
|
1
|
+
class NytimesTopStories::Story
|
2
|
+
attr_accessor :headline, :byline, :summary, :url
|
3
|
+
@@all = []
|
4
|
+
def initialize(story_hash)
|
5
|
+
@headline = story_hash[:headline].gsub(/â/,"'")
|
6
|
+
@byline = story_hash[:byline]
|
7
|
+
@summary = story_hash[:summary].gsub(/â/,"'")
|
8
|
+
@url = story_hash[:url]
|
9
|
+
@@all << self
|
10
|
+
end
|
11
|
+
|
12
|
+
def self.new_from_array(array = NytimesTopStories::Scraper.get_top_stories)
|
13
|
+
self.clear_all
|
14
|
+
array.each do |scraped_story|
|
15
|
+
story = NytimesTopStories::Story.new(scraped_story) unless scraped_story[:headline].empty? || scraped_story[:byline].empty? || scraped_story[:summary].empty? || scraped_story[:url].empty?
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
def puts_story
|
20
|
+
puts @headline
|
21
|
+
puts @byline
|
22
|
+
puts @summary
|
23
|
+
puts "Press enter to open, enter any other input to escape."
|
24
|
+
choice = gets.strip
|
25
|
+
if choice == ""
|
26
|
+
self.open_story
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
def open_story
|
31
|
+
system("open #{@url}")
|
32
|
+
end
|
33
|
+
|
34
|
+
def self.all
|
35
|
+
@@all
|
36
|
+
end
|
37
|
+
|
38
|
+
def self.clear_all
|
39
|
+
@@all.clear
|
40
|
+
end
|
41
|
+
end
|
@@ -0,0 +1 @@
|
|
1
|
+
require_relative "../config/environment.rb"
|
@@ -0,0 +1,38 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "./lib/nytimes_top_stories/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "nytimes_top_stories"
|
8
|
+
spec.version = NytimesTopStories::VERSION
|
9
|
+
spec.authors = ["Luisa Scavo"]
|
10
|
+
spec.email = ["luisascavo@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{Pulls headlines from the NYT website and offers more information on request}
|
13
|
+
spec.homepage = "https://github.com/weezwo/nytimes-top-stories"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
# Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
|
17
|
+
# to allow pushing to a single host or delete this section to allow pushing to any host.
|
18
|
+
# if spec.respond_to?(:metadata)
|
19
|
+
# spec.metadata["allowed_push_host"] = "'http://mygemserver.com'"
|
20
|
+
# else
|
21
|
+
# raise "RubyGems 2.0 or newer is required to protect against " \
|
22
|
+
# "public gem pushes."
|
23
|
+
# end
|
24
|
+
|
25
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
26
|
+
f.match(%r{^(test|spec|features)/})
|
27
|
+
end
|
28
|
+
spec.bindir = "exe"
|
29
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
30
|
+
spec.require_paths = ["lib"]
|
31
|
+
|
32
|
+
spec.add_development_dependency "bundler", "~> 1.15"
|
33
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
34
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
35
|
+
|
36
|
+
spec.add_dependency 'nokogiri', '~> 1.6', '>= 1.6.8'
|
37
|
+
spec.add_dependency'require_all', '~> 1.4'
|
38
|
+
end
|
data/spec.md
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
# Specifications for the CLI Assessment
|
2
|
+
|
3
|
+
Specs:
|
4
|
+
- [x] Have a CLI for interfacing with the application
|
5
|
+
Upon execution, the program presents the user with a list of articles scraped
|
6
|
+
from the NY Times homepage. The user can interact with the program through the
|
7
|
+
command line.
|
8
|
+
- [x] Pull data from an external source
|
9
|
+
I use Nokogiri to scrape the NY Times website for content with id #top-news,
|
10
|
+
and classes .collection and .theme-summary. This content is then combed for
|
11
|
+
attributes matching headline, byline, and a short summary.
|
12
|
+
- [x] Implement both list and detail views
|
13
|
+
Upon execution, the program presents the user with a list of articles.
|
14
|
+
Each is numbered, and if that number is entered, the details for that article
|
15
|
+
are displayed.
|
metadata
ADDED
@@ -0,0 +1,139 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: nytimes_top_stories
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Luisa Scavo
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-06-12 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.15'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.15'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: nokogiri
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.6'
|
62
|
+
- - ">="
|
63
|
+
- !ruby/object:Gem::Version
|
64
|
+
version: 1.6.8
|
65
|
+
type: :runtime
|
66
|
+
prerelease: false
|
67
|
+
version_requirements: !ruby/object:Gem::Requirement
|
68
|
+
requirements:
|
69
|
+
- - "~>"
|
70
|
+
- !ruby/object:Gem::Version
|
71
|
+
version: '1.6'
|
72
|
+
- - ">="
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: 1.6.8
|
75
|
+
- !ruby/object:Gem::Dependency
|
76
|
+
name: require_all
|
77
|
+
requirement: !ruby/object:Gem::Requirement
|
78
|
+
requirements:
|
79
|
+
- - "~>"
|
80
|
+
- !ruby/object:Gem::Version
|
81
|
+
version: '1.4'
|
82
|
+
type: :runtime
|
83
|
+
prerelease: false
|
84
|
+
version_requirements: !ruby/object:Gem::Requirement
|
85
|
+
requirements:
|
86
|
+
- - "~>"
|
87
|
+
- !ruby/object:Gem::Version
|
88
|
+
version: '1.4'
|
89
|
+
description:
|
90
|
+
email:
|
91
|
+
- luisascavo@gmail.com
|
92
|
+
executables: []
|
93
|
+
extensions: []
|
94
|
+
extra_rdoc_files: []
|
95
|
+
files:
|
96
|
+
- ".gitignore"
|
97
|
+
- ".rspec"
|
98
|
+
- ".travis.yml"
|
99
|
+
- Gemfile
|
100
|
+
- LICENSE.txt
|
101
|
+
- README.md
|
102
|
+
- Rakefile
|
103
|
+
- bin/console
|
104
|
+
- bin/nytimes-top-stories
|
105
|
+
- bin/setup
|
106
|
+
- config/environment.rb
|
107
|
+
- fixtures/nytindex.htm
|
108
|
+
- lib/nytimes_top_stories.rb
|
109
|
+
- lib/nytimes_top_stories/cli.rb
|
110
|
+
- lib/nytimes_top_stories/scraper.rb
|
111
|
+
- lib/nytimes_top_stories/story.rb
|
112
|
+
- lib/nytimes_top_stories/version.rb
|
113
|
+
- nytimes_top_stories.gemspec
|
114
|
+
- spec.md
|
115
|
+
homepage: https://github.com/weezwo/nytimes-top-stories
|
116
|
+
licenses:
|
117
|
+
- MIT
|
118
|
+
metadata: {}
|
119
|
+
post_install_message:
|
120
|
+
rdoc_options: []
|
121
|
+
require_paths:
|
122
|
+
- lib
|
123
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
124
|
+
requirements:
|
125
|
+
- - ">="
|
126
|
+
- !ruby/object:Gem::Version
|
127
|
+
version: '0'
|
128
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
129
|
+
requirements:
|
130
|
+
- - ">="
|
131
|
+
- !ruby/object:Gem::Version
|
132
|
+
version: '0'
|
133
|
+
requirements: []
|
134
|
+
rubyforge_project:
|
135
|
+
rubygems_version: 2.6.12
|
136
|
+
signing_key:
|
137
|
+
specification_version: 4
|
138
|
+
summary: Pulls headlines from the NYT website and offers more information on request
|
139
|
+
test_files: []
|