urlarchiver 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/archiver.rb +74 -0
- metadata +45 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: a1ab52e74bee05d257e62ee0e35a5d0cd92099c4
|
4
|
+
data.tar.gz: ced5a1dd308846cadb08973673addeaddb11c47f
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: ecf480684ce7b304b8d1920b51e3878468f368273ab2150eb9d974e49d6f1697d2d987306d74ff2d8430742bbb0142a4bb717934f02958852184ed292152b447
|
7
|
+
data.tar.gz: 60c648e12b67f1fb9944c5918ec238481de839006187b40ebd0e246706d86846d718ef670931655233c450c6696e393ae0a18dcafe2e79ddd96bef877af2dc47
|
data/lib/archiver.rb
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
require 'pdfkit'
|
3
|
+
require 'open-uri'
|
4
|
+
require 'fileutils'
|
5
|
+
require 'json'
|
6
|
+
|
7
|
+
class Archiver
|
8
|
+
def initialize(type)
|
9
|
+
@type = type
|
10
|
+
end
|
11
|
+
|
12
|
+
# Archive a single url
|
13
|
+
def archiveone(url)
|
14
|
+
begin
|
15
|
+
html = Nokogiri::HTML(open(url))
|
16
|
+
url.gsub!("https", "http")
|
17
|
+
k = PDFKit.new(url, :page_size => "Letter")
|
18
|
+
pdf = k.to_pdf
|
19
|
+
|
20
|
+
# Save files
|
21
|
+
FileUtils::mkdir_p 'public/uploads/archive'
|
22
|
+
filepath = "public/uploads/archive/"+url.gsub("http", "https").gsub("/", "").gsub(".", "").gsub(":", "")+".pdf"
|
23
|
+
File.open(filepath.gsub(".pdf", ".html"), 'w') { |file| file.write(html) }
|
24
|
+
file = k.to_file(filepath)
|
25
|
+
|
26
|
+
# Save output if single url
|
27
|
+
if @type == "single"
|
28
|
+
@output = Hash.new
|
29
|
+
@output[:pdf_path] = filepath
|
30
|
+
@output[:html_path] = filepath.gsub(".pdf", ".html")
|
31
|
+
@output[:text] = html.text
|
32
|
+
end
|
33
|
+
|
34
|
+
# Return file paths
|
35
|
+
out = Hash.new
|
36
|
+
out[:pdf_path] = filepath
|
37
|
+
out[:html_path] = filepath.gsub(".pdf", ".html")
|
38
|
+
return out
|
39
|
+
rescue
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
# Archive multiple fields in a json
|
44
|
+
def multiarchive(json, field)
|
45
|
+
pjson = JSON.parse(json)
|
46
|
+
htmlfield = field+"_htmlpath"
|
47
|
+
pdffield = field+"_pdfpath"
|
48
|
+
@output = Array.new
|
49
|
+
|
50
|
+
pjson.each do |p|
|
51
|
+
pitem = Hash.new
|
52
|
+
paths = archiveone(p[field])
|
53
|
+
|
54
|
+
# Save paths
|
55
|
+
if !(paths == nil)
|
56
|
+
pitem[htmlfield] = paths[:pdf_path]
|
57
|
+
pitem[pdffield] = paths[:html_path]
|
58
|
+
end
|
59
|
+
|
60
|
+
# Save other fields
|
61
|
+
p.each do |key, value|
|
62
|
+
pitem[key] = value
|
63
|
+
end
|
64
|
+
|
65
|
+
@output.push(pitem)
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
# Generate JSON from output
|
70
|
+
def genJSON
|
71
|
+
JSON.pretty_generate(@output)
|
72
|
+
end
|
73
|
+
end
|
74
|
+
|
metadata
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: urlarchiver
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- M. C. McGrath
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-05-26 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: Saves html and pdfs of websites.
|
14
|
+
email: shidash@shidash.com
|
15
|
+
executables: []
|
16
|
+
extensions: []
|
17
|
+
extra_rdoc_files: []
|
18
|
+
files:
|
19
|
+
- lib/archiver.rb
|
20
|
+
homepage: https://github.com/TransparencyToolkit/Archiver
|
21
|
+
licenses:
|
22
|
+
- GPL
|
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: 2.0.14
|
41
|
+
signing_key:
|
42
|
+
specification_version: 4
|
43
|
+
summary: Archives websites.
|
44
|
+
test_files: []
|
45
|
+
has_rdoc:
|