nytimes_cli 0.1.8
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/bin/console +14 -0
- data/bin/nytimes_cli +10 -0
- data/bin/setup +8 -0
- data/lib/article.rb +84 -0
- data/lib/nytimes_cli/cli.rb +163 -0
- data/lib/nytimes_cli/navagation.rb +32 -0
- data/lib/nytimes_cli/version.rb +3 -0
- data/lib/nytimes_cli.rb +0 -0
- data/lib/scraper.rb +69 -0
- metadata +177 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 485c4d2f7a55939cdd8e07e1d4dfa0abb180527d
|
4
|
+
data.tar.gz: ee2ad28060dbcb739b3c3578ffbf42066768f9a3
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 66367a084ca445b35f9474dd40d25e395637078836dbf8cd6df71d7b837a9d27cc9d134f99c458d1a84551f363b76fcd036f73dc7753aa9b2ee40a3706ff3b17
|
7
|
+
data.tar.gz: 7e0e385204a68906811263591d24ad0102a37b4783dd0fe0a0b9aa95bbbb72c3fb0303f1f314a39c6aba77ae4f70e8db1251942c931341ae36d93578dd545a7c
|
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "nytimes_cli"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start
|
data/bin/nytimes_cli
ADDED
data/bin/setup
ADDED
data/lib/article.rb
ADDED
@@ -0,0 +1,84 @@
|
|
1
|
+
class Article
|
2
|
+
|
3
|
+
attr_accessor :title, :author, :url, :story
|
4
|
+
|
5
|
+
@@articles = []
|
6
|
+
|
7
|
+
|
8
|
+
def initialize(title = nil, url = nil, author = nil, story = nil)
|
9
|
+
@title = title
|
10
|
+
@author = author
|
11
|
+
@url = url
|
12
|
+
@story = story
|
13
|
+
end
|
14
|
+
|
15
|
+
|
16
|
+
def self.create_articles_from_array(array)
|
17
|
+
|
18
|
+
array.each do |article|
|
19
|
+
title = article[:title]
|
20
|
+
url = article[:url]
|
21
|
+
a = Article.new(title, url)
|
22
|
+
@@articles << a
|
23
|
+
end
|
24
|
+
@@articles
|
25
|
+
end
|
26
|
+
|
27
|
+
def self.all
|
28
|
+
@@articles
|
29
|
+
end
|
30
|
+
|
31
|
+
|
32
|
+
def self.create_article_from_hash(hash)
|
33
|
+
a = Article.new
|
34
|
+
a.title = hash[:title]
|
35
|
+
a.url = hash[:url]
|
36
|
+
a.author = hash[:author]
|
37
|
+
string = hash[:story]
|
38
|
+
a.story = self.word_wrap(hash[:story])
|
39
|
+
a
|
40
|
+
end
|
41
|
+
|
42
|
+
def self.word_wrap(text)
|
43
|
+
|
44
|
+
paragraphs = []
|
45
|
+
|
46
|
+
paragraphs = text.split(/\n/)
|
47
|
+
finshed_text = ""
|
48
|
+
|
49
|
+
paragraphs.each do |p|
|
50
|
+
final_p = self.p_wrap(p, 78)
|
51
|
+
finshed_text << "\n" + final_p
|
52
|
+
end
|
53
|
+
finshed_text
|
54
|
+
end
|
55
|
+
|
56
|
+
|
57
|
+
|
58
|
+
#following method was taken from https://www.safaribooksonline.com/library/view/ruby-cookbook/0596523696/ch01s15.html
|
59
|
+
def self.p_wrap(s, width=78)
|
60
|
+
lines = []
|
61
|
+
line = ""
|
62
|
+
s.split(/\s+/).each do |word|
|
63
|
+
if line.size + word.size >= width
|
64
|
+
lines << line
|
65
|
+
line = word
|
66
|
+
elsif line.empty?
|
67
|
+
line = word
|
68
|
+
else
|
69
|
+
line << " " << word
|
70
|
+
end
|
71
|
+
end
|
72
|
+
lines << line if line
|
73
|
+
return lines.join "\n"
|
74
|
+
end
|
75
|
+
|
76
|
+
|
77
|
+
|
78
|
+
|
79
|
+
|
80
|
+
|
81
|
+
|
82
|
+
|
83
|
+
|
84
|
+
end
|
@@ -0,0 +1,163 @@
|
|
1
|
+
# cli controller
|
2
|
+
|
3
|
+
class NytimesCli::CLI
|
4
|
+
|
5
|
+
attr_accessor :index
|
6
|
+
|
7
|
+
def call
|
8
|
+
puts ""
|
9
|
+
puts ""
|
10
|
+
puts "Welcome to Nytimes CLI"
|
11
|
+
puts "All articles © The New York Times"
|
12
|
+
puts "http://www.nytimes.com"
|
13
|
+
puts ""
|
14
|
+
puts ""
|
15
|
+
front
|
16
|
+
puts ""
|
17
|
+
puts ""
|
18
|
+
puts "There are currently " + num_articles + " articles on the front page of nytimes.com."
|
19
|
+
puts ""
|
20
|
+
num = get_articles.length
|
21
|
+
index(num)
|
22
|
+
interface_logic
|
23
|
+
|
24
|
+
end
|
25
|
+
|
26
|
+
|
27
|
+
|
28
|
+
|
29
|
+
def get_articles_from_front_page
|
30
|
+
array = Scraper.scrape_front_page
|
31
|
+
articles = Article.create_articles_from_array(array)
|
32
|
+
articles
|
33
|
+
end
|
34
|
+
|
35
|
+
def num_articles
|
36
|
+
get_articles.length.to_s
|
37
|
+
end
|
38
|
+
|
39
|
+
def input_to_index(num)
|
40
|
+
num.to_i - 1
|
41
|
+
end
|
42
|
+
|
43
|
+
def front
|
44
|
+
print_articles(0, 9)
|
45
|
+
end
|
46
|
+
|
47
|
+
|
48
|
+
#TODO
|
49
|
+
def print_articles(first_index, last_index )
|
50
|
+
array = get_articles_from_front_page
|
51
|
+
a = array[first_index..last_index]
|
52
|
+
a.each do |article|
|
53
|
+
all_articles = get_articles
|
54
|
+
i = all_articles.index(article) + 1
|
55
|
+
puts i.to_s + ". " + article.title
|
56
|
+
end
|
57
|
+
puts ""
|
58
|
+
puts ""
|
59
|
+
|
60
|
+
end
|
61
|
+
|
62
|
+
def index(num)
|
63
|
+
@index = Navagation.new(num)
|
64
|
+
end
|
65
|
+
|
66
|
+
def get_articles
|
67
|
+
Article.all
|
68
|
+
end
|
69
|
+
|
70
|
+
def get_article_url(num)
|
71
|
+
i = input_to_index(num)
|
72
|
+
a = get_articles[i]
|
73
|
+
a.url
|
74
|
+
end
|
75
|
+
|
76
|
+
def get_article(url)
|
77
|
+
hash = Scraper.scrape_article(url)
|
78
|
+
article = Article.create_article_from_hash(hash)
|
79
|
+
end
|
80
|
+
|
81
|
+
|
82
|
+
def print_article(num)
|
83
|
+
url = get_article_url(num)
|
84
|
+
a = get_article(url)
|
85
|
+
puts ""
|
86
|
+
puts ""
|
87
|
+
puts a.title
|
88
|
+
puts ""
|
89
|
+
puts a.author
|
90
|
+
puts ""
|
91
|
+
puts a.story
|
92
|
+
puts ""
|
93
|
+
puts ""
|
94
|
+
puts "Link to nytimes.com: " + a.url
|
95
|
+
puts ""
|
96
|
+
puts ""
|
97
|
+
|
98
|
+
end
|
99
|
+
|
100
|
+
def show_manual
|
101
|
+
|
102
|
+
puts "man -> displays manual"
|
103
|
+
puts "front -> shows first ten headlines"
|
104
|
+
puts "more -> shows 10 more headlines"
|
105
|
+
puts "less -> shows previous 10 headlines"
|
106
|
+
puts "exit -> terminates program"
|
107
|
+
puts ""
|
108
|
+
puts ""
|
109
|
+
puts "All articles © The New York Times"
|
110
|
+
puts "http://www.nytimes.com"
|
111
|
+
puts ""
|
112
|
+
puts ""
|
113
|
+
|
114
|
+
end
|
115
|
+
|
116
|
+
def more
|
117
|
+
@index.more
|
118
|
+
print_articles(@index.start_index, @index.end_index)
|
119
|
+
end
|
120
|
+
|
121
|
+
def less
|
122
|
+
@index.less
|
123
|
+
print_articles(@index.start_index, @index.end_index)
|
124
|
+
end
|
125
|
+
|
126
|
+
def interface_logic
|
127
|
+
while true
|
128
|
+
puts "Enter the number you would like to read or 'man' to see a list of commands."
|
129
|
+
answer = gets.chomp
|
130
|
+
if answer.upcase == "EXIT"
|
131
|
+
puts ""
|
132
|
+
puts "Ciao. Auf Wiedersehen. Goodbye."
|
133
|
+
puts ""
|
134
|
+
puts ""
|
135
|
+
exit
|
136
|
+
elsif answer.to_i.class == Fixnum && answer.to_i != 0
|
137
|
+
print_article(answer)
|
138
|
+
elsif answer.upcase == "MAN"
|
139
|
+
show_manual
|
140
|
+
elsif answer.upcase == "MORE"
|
141
|
+
more
|
142
|
+
elsif answer.upcase == "LESS"
|
143
|
+
less
|
144
|
+
elsif answer.upcase == "FRONT"
|
145
|
+
print_articles(0, 9)
|
146
|
+
else
|
147
|
+
puts ""
|
148
|
+
puts ""
|
149
|
+
puts "That was not a valid entry. Please try again."
|
150
|
+
puts ""
|
151
|
+
puts ""
|
152
|
+
end
|
153
|
+
|
154
|
+
end
|
155
|
+
|
156
|
+
end
|
157
|
+
|
158
|
+
|
159
|
+
|
160
|
+
|
161
|
+
|
162
|
+
|
163
|
+
end
|
@@ -0,0 +1,32 @@
|
|
1
|
+
class Navagation
|
2
|
+
|
3
|
+
attr_accessor :start_index, :end_index, :articles_length
|
4
|
+
|
5
|
+
def initialize(length)
|
6
|
+
@start_index = 0
|
7
|
+
@end_index = 9
|
8
|
+
@articles_length = length
|
9
|
+
end
|
10
|
+
|
11
|
+
|
12
|
+
def more
|
13
|
+
if @end_index + 10 < @articles_length
|
14
|
+
@start_index += 10
|
15
|
+
@end_index += 10
|
16
|
+
else
|
17
|
+
@start_index = @articles_length - 9
|
18
|
+
@end_index = @articles_length
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
def less
|
23
|
+
if @start_index >= 10
|
24
|
+
@start_index -= 10
|
25
|
+
@end_index = @start_index + 9
|
26
|
+
else
|
27
|
+
@start_index = 0
|
28
|
+
@end_index = 9
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
end
|
data/lib/nytimes_cli.rb
ADDED
File without changes
|
data/lib/scraper.rb
ADDED
@@ -0,0 +1,69 @@
|
|
1
|
+
require 'mechanize'
|
2
|
+
|
3
|
+
class Scraper
|
4
|
+
|
5
|
+
attr_accessor :title, :url, :author, :story
|
6
|
+
|
7
|
+
BASE_URL = "http://www.nytimes.com"
|
8
|
+
|
9
|
+
def self.scrape_front_page
|
10
|
+
|
11
|
+
agent = Mechanize.new
|
12
|
+
index = agent.get(BASE_URL)
|
13
|
+
front_page_articles = []
|
14
|
+
index.css(".story-heading").each do |story|
|
15
|
+
val = story.css("a").text
|
16
|
+
next if val.nil? || val == false || val == ""
|
17
|
+
hash = {
|
18
|
+
|
19
|
+
:title => story.css("a").text.strip,
|
20
|
+
:url => story.css('a').attribute('href').value
|
21
|
+
}
|
22
|
+
|
23
|
+
front_page_articles << hash
|
24
|
+
end
|
25
|
+
|
26
|
+
front_page_articles
|
27
|
+
end
|
28
|
+
|
29
|
+
def self.scrape_article(url)
|
30
|
+
|
31
|
+
agent = Mechanize.new
|
32
|
+
article = agent.get(url)
|
33
|
+
stories = []
|
34
|
+
story_hash = {}
|
35
|
+
|
36
|
+
title = article.search("//*[@id='headline']").text
|
37
|
+
author = article.search('.byline-author').text
|
38
|
+
|
39
|
+
story_hash[:title] = title
|
40
|
+
story_hash[:author] = author
|
41
|
+
story_hash[:url] = url
|
42
|
+
|
43
|
+
article_string = ""
|
44
|
+
|
45
|
+
article.search(".story-body *").each do |paragraph|
|
46
|
+
|
47
|
+
if !article_string.include?(paragraph.children.text)
|
48
|
+
|
49
|
+
if paragraph.name == "p" && paragraph.children.text != "Advertisement"
|
50
|
+
article_string << paragraph.children.text + "\n" + "\n"
|
51
|
+
elsif paragraph.name == "h4" && !paragraph.children.text.nil?
|
52
|
+
article_string << paragraph.children.text + "\n" + "\n"
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
end
|
57
|
+
story_hash[:story] = article_string
|
58
|
+
|
59
|
+
story_hash
|
60
|
+
|
61
|
+
|
62
|
+
end
|
63
|
+
|
64
|
+
|
65
|
+
|
66
|
+
|
67
|
+
|
68
|
+
end
|
69
|
+
|
metadata
ADDED
@@ -0,0 +1,177 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: nytimes_cli
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.8
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- interestinall
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-06-08 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: '1.12'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.12'
|
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: require_all
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.3'
|
62
|
+
- - ">="
|
63
|
+
- !ruby/object:Gem::Version
|
64
|
+
version: 1.3.3
|
65
|
+
type: :development
|
66
|
+
prerelease: false
|
67
|
+
version_requirements: !ruby/object:Gem::Requirement
|
68
|
+
requirements:
|
69
|
+
- - "~>"
|
70
|
+
- !ruby/object:Gem::Version
|
71
|
+
version: '1.3'
|
72
|
+
- - ">="
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: 1.3.3
|
75
|
+
- !ruby/object:Gem::Dependency
|
76
|
+
name: mechanize
|
77
|
+
requirement: !ruby/object:Gem::Requirement
|
78
|
+
requirements:
|
79
|
+
- - "~>"
|
80
|
+
- !ruby/object:Gem::Version
|
81
|
+
version: '2.7'
|
82
|
+
- - ">="
|
83
|
+
- !ruby/object:Gem::Version
|
84
|
+
version: 2.7.4
|
85
|
+
type: :development
|
86
|
+
prerelease: false
|
87
|
+
version_requirements: !ruby/object:Gem::Requirement
|
88
|
+
requirements:
|
89
|
+
- - "~>"
|
90
|
+
- !ruby/object:Gem::Version
|
91
|
+
version: '2.7'
|
92
|
+
- - ">="
|
93
|
+
- !ruby/object:Gem::Version
|
94
|
+
version: 2.7.4
|
95
|
+
- !ruby/object:Gem::Dependency
|
96
|
+
name: require_all
|
97
|
+
requirement: !ruby/object:Gem::Requirement
|
98
|
+
requirements:
|
99
|
+
- - "~>"
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: '1.3'
|
102
|
+
- - ">="
|
103
|
+
- !ruby/object:Gem::Version
|
104
|
+
version: 1.3.3
|
105
|
+
type: :runtime
|
106
|
+
prerelease: false
|
107
|
+
version_requirements: !ruby/object:Gem::Requirement
|
108
|
+
requirements:
|
109
|
+
- - "~>"
|
110
|
+
- !ruby/object:Gem::Version
|
111
|
+
version: '1.3'
|
112
|
+
- - ">="
|
113
|
+
- !ruby/object:Gem::Version
|
114
|
+
version: 1.3.3
|
115
|
+
- !ruby/object:Gem::Dependency
|
116
|
+
name: mechanize
|
117
|
+
requirement: !ruby/object:Gem::Requirement
|
118
|
+
requirements:
|
119
|
+
- - "~>"
|
120
|
+
- !ruby/object:Gem::Version
|
121
|
+
version: '2.7'
|
122
|
+
- - ">="
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: 2.7.4
|
125
|
+
type: :runtime
|
126
|
+
prerelease: false
|
127
|
+
version_requirements: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - "~>"
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '2.7'
|
132
|
+
- - ">="
|
133
|
+
- !ruby/object:Gem::Version
|
134
|
+
version: 2.7.4
|
135
|
+
description: Allows users to browse nytimes.com and read articles from the command
|
136
|
+
line.
|
137
|
+
email:
|
138
|
+
- justin.lefurjah@gmail.com
|
139
|
+
executables:
|
140
|
+
- nytimes_cli
|
141
|
+
extensions: []
|
142
|
+
extra_rdoc_files: []
|
143
|
+
files:
|
144
|
+
- bin/console
|
145
|
+
- bin/nytimes_cli
|
146
|
+
- bin/setup
|
147
|
+
- lib/article.rb
|
148
|
+
- lib/nytimes_cli.rb
|
149
|
+
- lib/nytimes_cli/cli.rb
|
150
|
+
- lib/nytimes_cli/navagation.rb
|
151
|
+
- lib/nytimes_cli/version.rb
|
152
|
+
- lib/scraper.rb
|
153
|
+
homepage: https://github.com/interestinall/nytimes_cli
|
154
|
+
licenses:
|
155
|
+
- MIT
|
156
|
+
metadata: {}
|
157
|
+
post_install_message:
|
158
|
+
rdoc_options: []
|
159
|
+
require_paths:
|
160
|
+
- lib
|
161
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
162
|
+
requirements:
|
163
|
+
- - ">="
|
164
|
+
- !ruby/object:Gem::Version
|
165
|
+
version: '0'
|
166
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
167
|
+
requirements:
|
168
|
+
- - ">="
|
169
|
+
- !ruby/object:Gem::Version
|
170
|
+
version: '0'
|
171
|
+
requirements: []
|
172
|
+
rubyforge_project:
|
173
|
+
rubygems_version: 2.6.4
|
174
|
+
signing_key:
|
175
|
+
specification_version: 4
|
176
|
+
summary: Command line interface for nytimes.com
|
177
|
+
test_files: []
|