href_scraper 0.2.0 → 0.3.0

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.
Files changed (3) hide show
  1. checksums.yaml +4 -4
  2. data/lib/href_scraper.rb +4 -1
  3. metadata +2 -2
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 8cceaad0196924b1a15e206e44d0dbe317e475ae3883e33cf1365a16d2aa7a6f
4
- data.tar.gz: 0eb0a090760855586ec91029fe68e22cbfd0b292e9df233b1bf79770870fde7e
3
+ metadata.gz: b88142a7b9d9bd650f975fa17c8ffb5148f16dc5eb7984cb0a128274c0de5d63
4
+ data.tar.gz: 28d27b4ee2e3f2ebe050ee77a710a5c3e1a3253962d77b7303d29154fb82bf9c
5
5
  SHA512:
6
- metadata.gz: fd34dc317c92e5b4fdbbd550798f77ea2b733e54d00bf08ce1fe6480124601d343e1d879a3c67dcecb12fa95574aec4b50b8aa62608ce4740c02405f81060082
7
- data.tar.gz: c0ccddf4643773ccec9a67f9b1e65fcbcd47233e1d8765665591aae246e38a88ffa8d93f58fe0d3efb444e9bdef5fa7342da21091616e43cd33f291808fac68e
6
+ metadata.gz: 1cddf2e03fbe347bc97a6705a8fd25462708ba08a64e61979b5834f1a7aec0fd2f9cb4108c90c7b4af0e6603ec245de824f6e423f2e7824453646c6dc19279ea
7
+ data.tar.gz: e35e83d59be4d4411bb7810baf1e7865ffe95e16cd616524066172dcdcb6c5c4de19e592cfa9ba2e8cb228bd2f5a0b99cd37a7bf27890bb3a3dc6bb1d8088a78
data/lib/href_scraper.rb CHANGED
@@ -3,6 +3,7 @@
3
3
  require 'optparse'
4
4
  require 'open-uri'
5
5
  require 'nokogiri'
6
+ require 'json'
6
7
 
7
8
  module HrefScraper
8
9
  def self.fetch_html(url)
@@ -13,13 +14,15 @@ module HrefScraper
13
14
  OptionParser.new do |opt|
14
15
  opt.on('-u', '--url URL', 'URL to scrape links from') do |url|
15
16
  url !~ /^http/ && abort('Invalid URL passed')
17
+ links = []
16
18
  anchors = fetch_html(url).xpath('//a')
17
19
  hrefs = anchors.map { |tag| tag['href'] }
18
20
  hrefs.each do |link|
19
21
  if link =~ /^http/
20
- puts link
22
+ links.push(link)
21
23
  end
22
24
  end
25
+ puts links.to_json
23
26
  end
24
27
  end.parse!
25
28
  end
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: href_scraper
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.2.0
4
+ version: 0.3.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - Caleb Lemoine
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2018-08-18 00:00:00.000000000 Z
11
+ date: 2018-08-19 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: bundler