rchive 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/rchive.rb +59 -0
- metadata +44 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 8bb94cb1c24f1b0f5fba6f75977879287f5526be
|
4
|
+
data.tar.gz: 36f99d0ffd210a1f2365c184002757a2a942d72e
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: a49cb4fcc48dee6b5834680f5a926719de801e6042bf4e1b5d781bed353f09f5b6a7f1c0f74cc85e5e7acd39a9060b2524d49ef0290147f08057df3cd54661fc
|
7
|
+
data.tar.gz: 5a16c3dc3010d9e8f1d678840d853977740273d868f82a61bf29070afe774ba2fa7853f84b2d278795b11462191a286d24fb077cab419e0d1c52f6ce09707e1a
|
data/lib/rchive.rb
ADDED
@@ -0,0 +1,59 @@
|
|
1
|
+
require 'httparty'
|
2
|
+
require 'open-uri'
|
3
|
+
require 'nokogiri'
|
4
|
+
require 'pry'
|
5
|
+
|
6
|
+
class Rchive
|
7
|
+
|
8
|
+
attr_accessor :images, :csss, :doc, :url
|
9
|
+
|
10
|
+
def initialize( url )
|
11
|
+
base_url = URI.parse( url )
|
12
|
+
@base_url = base_url.scheme + '://' + base_url.host
|
13
|
+
@url = url
|
14
|
+
@doc = doc
|
15
|
+
end
|
16
|
+
|
17
|
+
def doc
|
18
|
+
Nokogiri::HTML(open( @url ))
|
19
|
+
end
|
20
|
+
|
21
|
+
def csss
|
22
|
+
styles = ''
|
23
|
+
@doc.css('[rel="stylesheet"]').map do |l|
|
24
|
+
l.remove
|
25
|
+
if l['href'].index('http') == 0
|
26
|
+
styles += open( URI.encode(l['href'])).read
|
27
|
+
else
|
28
|
+
styles += open( @base_url + l['href']).read
|
29
|
+
end
|
30
|
+
end
|
31
|
+
style = Nokogiri::XML::Node.new "style", @doc
|
32
|
+
style['type'] = 'text/css'
|
33
|
+
style.content = styles
|
34
|
+
@doc.at_css('head') << style
|
35
|
+
end
|
36
|
+
|
37
|
+
def images
|
38
|
+
@doc.css('img').map do |img|
|
39
|
+
if img['src'].index('http') == 0
|
40
|
+
src = img['src']
|
41
|
+
elsif img['src'].index('/') == 0
|
42
|
+
src = @base_url + img['src']
|
43
|
+
else
|
44
|
+
src = @base_url + '/' + img['src']
|
45
|
+
end
|
46
|
+
binding.pry
|
47
|
+
image = open( src )
|
48
|
+
content_type = image.content_type
|
49
|
+
img.attributes['src'].value = 'data:'+ content_type +';base64,' + Base64.encode64(image.read)
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
def save
|
54
|
+
self.csss
|
55
|
+
self.images
|
56
|
+
File.open( 'tmp.html' , 'w') { |f| f.write(@doc.to_html) }
|
57
|
+
end
|
58
|
+
|
59
|
+
end
|
metadata
ADDED
@@ -0,0 +1,44 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: rchive
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Jesse Shawl
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-11-09 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: It's like wget, for archiving web sites.
|
14
|
+
email: jesse@jshawl.com
|
15
|
+
executables: []
|
16
|
+
extensions: []
|
17
|
+
extra_rdoc_files: []
|
18
|
+
files:
|
19
|
+
- lib/rchive.rb
|
20
|
+
homepage: http://rubygems.org/gems/rchive
|
21
|
+
licenses:
|
22
|
+
- MIT
|
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: 2.2.2
|
41
|
+
signing_key:
|
42
|
+
specification_version: 4
|
43
|
+
summary: rchive
|
44
|
+
test_files: []
|