href_scraper 0.2.0
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.
- checksums.yaml +7 -0
- data/bin/href_scraper +2 -0
- data/lib/href_scraper.rb +25 -0
- metadata +81 -0
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA256:
|
|
3
|
+
metadata.gz: 8cceaad0196924b1a15e206e44d0dbe317e475ae3883e33cf1365a16d2aa7a6f
|
|
4
|
+
data.tar.gz: 0eb0a090760855586ec91029fe68e22cbfd0b292e9df233b1bf79770870fde7e
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: fd34dc317c92e5b4fdbbd550798f77ea2b733e54d00bf08ce1fe6480124601d343e1d879a3c67dcecb12fa95574aec4b50b8aa62608ce4740c02405f81060082
|
|
7
|
+
data.tar.gz: c0ccddf4643773ccec9a67f9b1e65fcbcd47233e1d8765665591aae246e38a88ffa8d93f58fe0d3efb444e9bdef5fa7342da21091616e43cd33f291808fac68e
|
data/bin/href_scraper
ADDED
data/lib/href_scraper.rb
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
1
|
+
#!/usr/bin/env ruby
|
|
2
|
+
|
|
3
|
+
require 'optparse'
|
|
4
|
+
require 'open-uri'
|
|
5
|
+
require 'nokogiri'
|
|
6
|
+
|
|
7
|
+
module HrefScraper
|
|
8
|
+
def self.fetch_html(url)
|
|
9
|
+
html = open(url)
|
|
10
|
+
Nokogiri::HTML(html)
|
|
11
|
+
end
|
|
12
|
+
|
|
13
|
+
OptionParser.new do |opt|
|
|
14
|
+
opt.on('-u', '--url URL', 'URL to scrape links from') do |url|
|
|
15
|
+
url !~ /^http/ && abort('Invalid URL passed')
|
|
16
|
+
anchors = fetch_html(url).xpath('//a')
|
|
17
|
+
hrefs = anchors.map { |tag| tag['href'] }
|
|
18
|
+
hrefs.each do |link|
|
|
19
|
+
if link =~ /^http/
|
|
20
|
+
puts link
|
|
21
|
+
end
|
|
22
|
+
end
|
|
23
|
+
end
|
|
24
|
+
end.parse!
|
|
25
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: href_scraper
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.2.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Caleb Lemoine
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2018-08-18 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: '1.16'
|
|
20
|
+
type: :development
|
|
21
|
+
prerelease: false
|
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
23
|
+
requirements:
|
|
24
|
+
- - "~>"
|
|
25
|
+
- !ruby/object:Gem::Version
|
|
26
|
+
version: '1.16'
|
|
27
|
+
- !ruby/object:Gem::Dependency
|
|
28
|
+
name: nokogiri
|
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
|
30
|
+
requirements:
|
|
31
|
+
- - "~>"
|
|
32
|
+
- !ruby/object:Gem::Version
|
|
33
|
+
version: 1.8.4
|
|
34
|
+
- - ">="
|
|
35
|
+
- !ruby/object:Gem::Version
|
|
36
|
+
version: 1.8.4
|
|
37
|
+
type: :runtime
|
|
38
|
+
prerelease: false
|
|
39
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
40
|
+
requirements:
|
|
41
|
+
- - "~>"
|
|
42
|
+
- !ruby/object:Gem::Version
|
|
43
|
+
version: 1.8.4
|
|
44
|
+
- - ">="
|
|
45
|
+
- !ruby/object:Gem::Version
|
|
46
|
+
version: 1.8.4
|
|
47
|
+
description: Scrape hrefs from a single webpage
|
|
48
|
+
email:
|
|
49
|
+
- caleblemoine@gmail.com
|
|
50
|
+
executables:
|
|
51
|
+
- href_scraper
|
|
52
|
+
extensions: []
|
|
53
|
+
extra_rdoc_files: []
|
|
54
|
+
files:
|
|
55
|
+
- bin/href_scraper
|
|
56
|
+
- lib/href_scraper.rb
|
|
57
|
+
homepage: https://github.com/circa10a/href-scraper.git
|
|
58
|
+
licenses:
|
|
59
|
+
- MIT
|
|
60
|
+
metadata: {}
|
|
61
|
+
post_install_message:
|
|
62
|
+
rdoc_options: []
|
|
63
|
+
require_paths:
|
|
64
|
+
- lib
|
|
65
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
66
|
+
requirements:
|
|
67
|
+
- - ">="
|
|
68
|
+
- !ruby/object:Gem::Version
|
|
69
|
+
version: '0'
|
|
70
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
71
|
+
requirements:
|
|
72
|
+
- - ">="
|
|
73
|
+
- !ruby/object:Gem::Version
|
|
74
|
+
version: '0'
|
|
75
|
+
requirements: []
|
|
76
|
+
rubyforge_project:
|
|
77
|
+
rubygems_version: 2.7.6
|
|
78
|
+
signing_key:
|
|
79
|
+
specification_version: 4
|
|
80
|
+
summary: CLI to scrape hrefs
|
|
81
|
+
test_files: []
|