surgescrape 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.rake_tasks~ +6 -0
- data/COPYING +21 -0
- data/README.md +40 -0
- data/Rakefile +2 -0
- data/bin/setup +6 -0
- data/bin/sscrape +52 -0
- data/lib/surgescrape/version.rb +3 -0
- data/lib/surgescrape.rb +94 -0
- data/pkg/surgescrape-0.1.0.gem +0 -0
- data/surgescrape.gemspec +25 -0
- metadata +83 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: b3d1e58be8a7ae49097955652334f148e92f0949
|
4
|
+
data.tar.gz: 9087e21894944b34a4a92b0ad89cf6a5cd3472b9
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: a07cba90208e7c06d5c638a216ca0137ae5ea425a5063ad1c92a04f10f0508ce8858bdfff54df4657e86a5698c8d4c53556e46ad7fb47e2b44eda5b2ea525773
|
7
|
+
data.tar.gz: 62a55f03e9ec0b6fc68d56fe99a768eb2c626170e62e24bb0efda801da63d1ca13ed5ee5b4781621ab8afe37afae2100e280552cd3aca93e07a5f0d0c9d14812
|
data/.rake_tasks~
ADDED
data/COPYING
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
MIT License
|
2
|
+
|
3
|
+
Copyright (c) 2016 Daniel E
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in all
|
13
|
+
copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
21
|
+
SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,40 @@
|
|
1
|
+
# SurgeScrape - Scrape your surge.sh website's files
|
2
|
+
|
3
|
+
## Installation
|
4
|
+
|
5
|
+
+ `[sudo] gem install surgescrape` Download & install via RubyGems
|
6
|
+
|
7
|
+
## Usage
|
8
|
+
|
9
|
+
`sscrape website.surge.sh` A simple really, just specify a domain
|
10
|
+
and watch all the files download. Run each time you need to update your
|
11
|
+
directory, the tool won't download untouched files.
|
12
|
+
|
13
|
+
## What it lookes like
|
14
|
+
|
15
|
+
```
|
16
|
+
Installing new gem...
|
17
|
+
surgescrape (0.1.0) installed.
|
18
|
+
daniel@pancake:~/surgescrape$ sscrape
|
19
|
+
Usage : `sscrape website.surge.sh`
|
20
|
+
daniel@pancake:~/Desktop/surge$ sscrape surge.sh
|
21
|
+
Scraping the files from https://surge.sh...
|
22
|
+
The website has different versions of your files and/or new files, your version of these will be overwritten :
|
23
|
+
/css/index.css
|
24
|
+
/help/about-the-surge-cdn.html
|
25
|
+
[...]
|
26
|
+
/stickers/thanks.html
|
27
|
+
/tour.html
|
28
|
+
|
29
|
+
Downloading 107 file(s)...
|
30
|
+
Downloaded /css/index.css
|
31
|
+
Downloaded /help/about-the-surge-cdn.html
|
32
|
+
[...]
|
33
|
+
Downloaded /stickers/thanks.html
|
34
|
+
Downloaded /tour.html
|
35
|
+
Finished!
|
36
|
+
daniel@pancake:~/Desktop/surge$ sudo serve 80
|
37
|
+
Serving on http://pancake:80
|
38
|
+
```
|
39
|
+
|
40
|
+
## MIT License
|
data/Rakefile
ADDED
data/bin/setup
ADDED
data/bin/sscrape
ADDED
@@ -0,0 +1,52 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# SurgeScrape - Scrape your surge.sh website's files
|
3
|
+
# Daniel Ethridge
|
4
|
+
|
5
|
+
require "surgescrape"
|
6
|
+
include SurgeScrape
|
7
|
+
|
8
|
+
usage = "Usage : `sscrape website.surge.sh`"
|
9
|
+
version = "SurgeScrape version : 0.1.0" #{SurgeScrape::VERSION}"
|
10
|
+
|
11
|
+
help = "\n#{usage}
|
12
|
+
|
13
|
+
#{version}
|
14
|
+
|
15
|
+
A simple utility, just specify a domain
|
16
|
+
and watch all the files download. Run each time
|
17
|
+
you need to update your directory, the tool won't
|
18
|
+
download untouched files.
|
19
|
+
|
20
|
+
--------------------------------------------------
|
21
|
+
|
22
|
+
If you find a bug, want extra features, or have a suggestion,
|
23
|
+
make a branch on github : https://github.com/wlib/surgescrape\n\n"
|
24
|
+
|
25
|
+
# If there are no arguments, print usage
|
26
|
+
if ARGV.length == 0
|
27
|
+
puts usage
|
28
|
+
exit
|
29
|
+
end
|
30
|
+
|
31
|
+
# Argument "parser", though only takes one argument...
|
32
|
+
arg = ARGV[0].downcase
|
33
|
+
case (arg)
|
34
|
+
when "help", "--help", "h", "-h", "?"
|
35
|
+
puts help
|
36
|
+
exit
|
37
|
+
when "version", "--version", "v", "-v"
|
38
|
+
puts version
|
39
|
+
exit
|
40
|
+
else
|
41
|
+
if arg.match( /^https:\/\/.+/i )
|
42
|
+
scrape(arg)
|
43
|
+
exit
|
44
|
+
elsif arg.match( /^http:\/\/.+/i )
|
45
|
+
puts "https:// only"
|
46
|
+
exit
|
47
|
+
else
|
48
|
+
scrape("https://#{arg}")
|
49
|
+
exit
|
50
|
+
end
|
51
|
+
exit
|
52
|
+
end
|
data/lib/surgescrape.rb
ADDED
@@ -0,0 +1,94 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# "Scrape" the website based on its `/auto.appcache` file
|
3
|
+
# Daniel Ethridge
|
4
|
+
|
5
|
+
require 'net/http'
|
6
|
+
require 'digest'
|
7
|
+
require 'fileutils'
|
8
|
+
|
9
|
+
module SurgeScrape
|
10
|
+
def rm_dot(path)
|
11
|
+
return path[1..-1]
|
12
|
+
end
|
13
|
+
|
14
|
+
def get(site, file)
|
15
|
+
uri = URI.parse("#{site}/#{file}")
|
16
|
+
http = Net::HTTP.new(uri.host, uri.port)
|
17
|
+
http.use_ssl = true
|
18
|
+
request = Net::HTTP::Get.new(uri.request_uri, {"Accept-Encoding" => "gzip"})
|
19
|
+
response = http.request(request)
|
20
|
+
return response.body
|
21
|
+
end
|
22
|
+
|
23
|
+
def get_cache_list(site)
|
24
|
+
cache_manifest = get(site, "auto.appcache")
|
25
|
+
cache = cache_manifest
|
26
|
+
files = cache.scan( /^\/.+\..+$/ )
|
27
|
+
hashes = cache.scan( /[a-f0-9]{32}/i )
|
28
|
+
out = {}
|
29
|
+
for i in 0...hashes.length
|
30
|
+
out[files[i].chomp] = hashes[i].chomp
|
31
|
+
end
|
32
|
+
if out.empty?
|
33
|
+
puts "Website does not have a `/auto.appcache` file, try a *.surge.sh URL"
|
34
|
+
exit
|
35
|
+
end
|
36
|
+
return out
|
37
|
+
end
|
38
|
+
|
39
|
+
def get_local_list()
|
40
|
+
files = Dir.glob("./**/*", File::FNM_DOTMATCH).select{ |e| File.file?(e) }
|
41
|
+
hashes = []
|
42
|
+
files.each { |f| hashes << Digest::MD5.file(f).hexdigest }
|
43
|
+
out = {}
|
44
|
+
for i in 0...hashes.length
|
45
|
+
out[files[i].chomp] = hashes[i].chomp
|
46
|
+
end
|
47
|
+
return out
|
48
|
+
end
|
49
|
+
|
50
|
+
def compare_lists(cache, local)
|
51
|
+
local.keys.each { |k| local[rm_dot(k)] = local.delete k }
|
52
|
+
diffs = ( cache.to_a - local.to_a ).to_h.keys
|
53
|
+
extra = ( local.to_a - cache.to_a ).to_h.keys - diffs
|
54
|
+
if ! extra.empty?
|
55
|
+
puts "This directory has file(s) that are not recorded on the website, \
|
56
|
+
they will not be overwritten : \n#{extra.join("\n")} \n\n"
|
57
|
+
end
|
58
|
+
if ! diffs.empty?
|
59
|
+
puts "The website has different versions of your files and/or new files, \
|
60
|
+
your version of these will be overwritten : \n#{diffs.join("\n")} \n\n"
|
61
|
+
return diffs
|
62
|
+
else
|
63
|
+
return nil
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
def get_files(site, files)
|
68
|
+
puts "Downloading #{files.length} file(s)..."
|
69
|
+
files.each do |file|
|
70
|
+
retrieved = get(site, file)
|
71
|
+
if retrieved.nil?
|
72
|
+
puts "#{file} could not be downloaded"
|
73
|
+
next
|
74
|
+
end
|
75
|
+
FileUtils.mkdir_p("./#{File.dirname(file)}") unless Dir.exists?("./#{File.dirname(file)}")
|
76
|
+
local = File.open("./#{file}", "w")
|
77
|
+
local.write retrieved
|
78
|
+
puts "Downloaded #{file}"
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
def scrape(site)
|
83
|
+
puts "Scraping the files from #{site}..."
|
84
|
+
cache = get_cache_list(site)
|
85
|
+
local = get_local_list()
|
86
|
+
files = compare_lists(cache, local)
|
87
|
+
if files.nil?
|
88
|
+
puts "Nothing to download"
|
89
|
+
exit
|
90
|
+
end
|
91
|
+
get_files(site, files)
|
92
|
+
puts "Finished!"
|
93
|
+
end
|
94
|
+
end
|
Binary file
|
data/surgescrape.gemspec
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "surgescrape/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |gem|
|
7
|
+
gem.name = "surgescrape"
|
8
|
+
gem.version = SurgeScrape::VERSION
|
9
|
+
gem.authors = ["Daniel Ethridge"]
|
10
|
+
gem.email = ["danielethridge@icloud.com"]
|
11
|
+
gem.license = "MIT"
|
12
|
+
|
13
|
+
gem.summary = %q{Scrape your surge.sh website's files}
|
14
|
+
gem.homepage = "https://github.com/wlib/surgescrape"
|
15
|
+
|
16
|
+
gem.files = `git ls-files -z`.split("\x0").reject do |f|
|
17
|
+
f.match(%r{^(test|spec|features)/})
|
18
|
+
end
|
19
|
+
gem.bindir = "bin"
|
20
|
+
gem.executables = ["sscrape"]
|
21
|
+
gem.require_paths = ["lib"]
|
22
|
+
|
23
|
+
gem.add_development_dependency "bundler", "~> 1.13"
|
24
|
+
gem.add_development_dependency "rake", "~> 10.0"
|
25
|
+
end
|
metadata
ADDED
@@ -0,0 +1,83 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: surgescrape
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Daniel Ethridge
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-12-21 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: '1.13'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.13'
|
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
|
+
description:
|
42
|
+
email:
|
43
|
+
- danielethridge@icloud.com
|
44
|
+
executables:
|
45
|
+
- sscrape
|
46
|
+
extensions: []
|
47
|
+
extra_rdoc_files: []
|
48
|
+
files:
|
49
|
+
- ".rake_tasks~"
|
50
|
+
- COPYING
|
51
|
+
- README.md
|
52
|
+
- Rakefile
|
53
|
+
- bin/setup
|
54
|
+
- bin/sscrape
|
55
|
+
- lib/surgescrape.rb
|
56
|
+
- lib/surgescrape/version.rb
|
57
|
+
- pkg/surgescrape-0.1.0.gem
|
58
|
+
- surgescrape.gemspec
|
59
|
+
homepage: https://github.com/wlib/surgescrape
|
60
|
+
licenses:
|
61
|
+
- MIT
|
62
|
+
metadata: {}
|
63
|
+
post_install_message:
|
64
|
+
rdoc_options: []
|
65
|
+
require_paths:
|
66
|
+
- lib
|
67
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
68
|
+
requirements:
|
69
|
+
- - ">="
|
70
|
+
- !ruby/object:Gem::Version
|
71
|
+
version: '0'
|
72
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
73
|
+
requirements:
|
74
|
+
- - ">="
|
75
|
+
- !ruby/object:Gem::Version
|
76
|
+
version: '0'
|
77
|
+
requirements: []
|
78
|
+
rubyforge_project:
|
79
|
+
rubygems_version: 2.5.1
|
80
|
+
signing_key:
|
81
|
+
specification_version: 4
|
82
|
+
summary: Scrape your surge.sh website's files
|
83
|
+
test_files: []
|