scrapix 0.1.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/.rvmrc +52 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +94 -0
- data/Rakefile +2 -0
- data/bin/scrapix +46 -0
- data/lib/scrapix.rb +5 -0
- data/lib/scrapix/drivers/capybara.rb +20 -0
- data/lib/scrapix/google_images.rb +113 -0
- data/lib/scrapix/vbulletin.rb +72 -0
- data/lib/scrapix/version.rb +3 -0
- data/scrapix.gemspec +28 -0
- metadata +145 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 7229eb9784d2c1e6a49ebc62c56cd2639b8b18aa
|
4
|
+
data.tar.gz: 766a3bda0863e5126ca10188a3d629250097392b
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 31237fb06e6cb6413305d1fae6f3f593072c40225619e3975f883ce805f89e8f1c2a1eddb2aaae045e37fab0427b1d6c7b07c7fe040c072b2ac5c373387c6a2c
|
7
|
+
data.tar.gz: 57cd2684ac04991a4ff5ae28b5a37c48362d6db4338fec0af575cc2b0288cedeb056c170781d10d17605f119f46024e9aa82388c16ea51672dc4cfdea9b27d0d
|
data/.gitignore
ADDED
data/.rvmrc
ADDED
@@ -0,0 +1,52 @@
|
|
1
|
+
#!/usr/bin/env bash
|
2
|
+
|
3
|
+
# This is an RVM Project .rvmrc file, used to automatically load the ruby
|
4
|
+
# development environment upon cd'ing into the directory
|
5
|
+
|
6
|
+
# First we specify our desired <ruby>[@<gemset>], the @gemset name is optional,
|
7
|
+
# Only full ruby name is supported here, for short names use:
|
8
|
+
# echo "rvm use 2.0.0" > .rvmrc
|
9
|
+
environment_id="ruby-2.0.0-p0@scrapix"
|
10
|
+
|
11
|
+
# Uncomment the following lines if you want to verify rvm version per project
|
12
|
+
# rvmrc_rvm_version="1.18.15 (stable)" # 1.10.1 seams as a safe start
|
13
|
+
# eval "$(echo ${rvm_version}.${rvmrc_rvm_version} | awk -F. '{print "[[ "$1*65536+$2*256+$3" -ge "$4*65536+$5*256+$6" ]]"}' )" || {
|
14
|
+
# echo "This .rvmrc file requires at least RVM ${rvmrc_rvm_version}, aborting loading."
|
15
|
+
# return 1
|
16
|
+
# }
|
17
|
+
|
18
|
+
# First we attempt to load the desired environment directly from the environment
|
19
|
+
# file. This is very fast and efficient compared to running through the entire
|
20
|
+
# CLI and selector. If you want feedback on which environment was used then
|
21
|
+
# insert the word 'use' after --create as this triggers verbose mode.
|
22
|
+
if [[ -d "${rvm_path:-$HOME/.rvm}/environments"
|
23
|
+
&& -s "${rvm_path:-$HOME/.rvm}/environments/$environment_id" ]]
|
24
|
+
then
|
25
|
+
\. "${rvm_path:-$HOME/.rvm}/environments/$environment_id"
|
26
|
+
[[ -s "${rvm_path:-$HOME/.rvm}/hooks/after_use" ]] &&
|
27
|
+
\. "${rvm_path:-$HOME/.rvm}/hooks/after_use" || true
|
28
|
+
if [[ $- == *i* ]] # check for interactive shells
|
29
|
+
then echo "Using: $(tput setaf 2)$GEM_HOME$(tput sgr0)" # show the user the ruby and gemset they are using in green
|
30
|
+
else echo "Using: $GEM_HOME" # don't use colors in non-interactive shells
|
31
|
+
fi
|
32
|
+
else
|
33
|
+
# If the environment file has not yet been created, use the RVM CLI to select.
|
34
|
+
rvm --create use "$environment_id" || {
|
35
|
+
echo "Failed to create RVM environment '${environment_id}'."
|
36
|
+
return 1
|
37
|
+
}
|
38
|
+
fi
|
39
|
+
|
40
|
+
# If you use bundler, this might be useful to you:
|
41
|
+
# if [[ -s Gemfile ]] && {
|
42
|
+
# ! builtin command -v bundle >/dev/null ||
|
43
|
+
# builtin command -v bundle | GREP_OPTIONS= \grep $rvm_path/bin/bundle >/dev/null
|
44
|
+
# }
|
45
|
+
# then
|
46
|
+
# printf "%b" "The rubygem 'bundler' is not installed. Installing it now.\n"
|
47
|
+
# gem install bundler
|
48
|
+
# fi
|
49
|
+
# if [[ -s Gemfile ]] && builtin command -v bundle >/dev/null
|
50
|
+
# then
|
51
|
+
# bundle install | GREP_OPTIONS= \grep -vE '^Using|Your bundle is complete'
|
52
|
+
# fi
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Nikhil Gupta
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,94 @@
|
|
1
|
+
# Scrapix
|
2
|
+
|
3
|
+
A gem that is able to scrape images from various sources. The gem provides you with the
|
4
|
+
results of these searches in a neat way, which you can then use to download these images,
|
5
|
+
or simply obtain a list of such images.
|
6
|
+
|
7
|
+
You can, also, use the API to call these scraping methods inside your own applications.
|
8
|
+
|
9
|
+
## Installation
|
10
|
+
|
11
|
+
Add this line to your application's Gemfile:
|
12
|
+
|
13
|
+
gem 'scrapix'
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install scrapix
|
22
|
+
|
23
|
+
## Usage :: Google Images
|
24
|
+
|
25
|
+
This gem is able to scrape images from Google Images search. It uses `Capybara` along with the
|
26
|
+
`Poltergeist` driver (which works on top of `PhantomJS`) for this purpose.
|
27
|
+
|
28
|
+
To use the `Google Images Scraper` inside your ruby applications, simply do:
|
29
|
+
|
30
|
+
scraper = Scrapix::GoogleImages.new # create the scraper
|
31
|
+
|
32
|
+
scraper.query = "programmer" # find images for keyword: "programmer"
|
33
|
+
scraper.total = 30 # search is limited to 30 images (default: 100)
|
34
|
+
scraper.find # return a list of such images
|
35
|
+
|
36
|
+
# search for 'large' images, and put safesearch to off!
|
37
|
+
scraper.options = { safe: false, size: "large" }
|
38
|
+
scraper.find
|
39
|
+
|
40
|
+
# everything:
|
41
|
+
scraper = Scrapix::GoogleImages.new "programmer", safe: false, size: "large"
|
42
|
+
scraper.total = 30 # limits to 30 images - default: 100 images
|
43
|
+
scraper.find
|
44
|
+
|
45
|
+
|
46
|
+
The `size` option can be supplied in following ways:
|
47
|
+
|
48
|
+
- __icon__, __small__, __medium__, or __large__
|
49
|
+
- __<n>__: searches for images with exact dimensions (width: _<m>_, height: _<n>_)
|
50
|
+
- __<m>x<n>__: searches for images with exact dimensions (width: _<m>_, height: _<n>_)
|
51
|
+
- __<n>mp__: searches for images larger than _<n>_ MP. Intelligently, adjusts to
|
52
|
+
the closest available option, if _<n>_ is not in the supported list of sizes
|
53
|
+
for this search.
|
54
|
+
|
55
|
+
You can also use the scraper on CLI:
|
56
|
+
|
57
|
+
scrapix google_images "programmer" --no-safe --total=30 --size=large
|
58
|
+
|
59
|
+
## Usage :: vBulletin Threads
|
60
|
+
|
61
|
+
This gem is able to scrape vBulletin threads for images. It uses `Mechanize` gem for this purpose.
|
62
|
+
|
63
|
+
To use the `vBulletin Thread Scraper` inside your ruby applications, simply do:
|
64
|
+
|
65
|
+
scraper = Scrapix::VBulletin.new # create the scraper
|
66
|
+
|
67
|
+
# find images for the following thread
|
68
|
+
scraper.url = "http://www.wetacollectors.com/forum/showthread.php?t=40085"
|
69
|
+
scraper.find # return a list of such images
|
70
|
+
|
71
|
+
# start searching from page 2 of this thread till we find 10 images
|
72
|
+
scraper.options = { start: 2, total: 10 }
|
73
|
+
scraper.find
|
74
|
+
|
75
|
+
# everything:
|
76
|
+
url = "http://www.wetacollectors.com/forum/showthread.php?t=40085"
|
77
|
+
scraper = Scrapix::VBulletin.new url, start: 2, end: 3, total: 10
|
78
|
+
scraper.find
|
79
|
+
|
80
|
+
You can also use the scraper on CLI:
|
81
|
+
|
82
|
+
scrapix vbulletin "http://www.wetacollectors.com/forum/showthread.php?t=40085" --total=10 --start=2
|
83
|
+
|
84
|
+
## Contributing
|
85
|
+
|
86
|
+
1. Fork it
|
87
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
88
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
89
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
90
|
+
5. Create new Pull Request
|
91
|
+
|
92
|
+
## TODO
|
93
|
+
|
94
|
+
1. Check if `mechanize` can be used instead of `capybara + poltergeist` combination for scraping Google Images.
|
data/Rakefile
ADDED
data/bin/scrapix
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# encoding: utf-8
|
3
|
+
|
4
|
+
require 'thor'
|
5
|
+
require 'scrapix'
|
6
|
+
|
7
|
+
module Scrapix
|
8
|
+
class CLI < Thor
|
9
|
+
desc "google_images [KEYWORD]", "scrape images from Google Images"
|
10
|
+
method_option :safe, type: :boolean, default: true, description: "use safe search?"
|
11
|
+
method_option :size, default: "any", description: "size of the images to search for"
|
12
|
+
method_option :ref, type: :boolean, default: false, description: "provide a list of reference urls, instead"
|
13
|
+
method_option :verbose, type: :boolean, default: false, description: "provide all info", alias: "-v"
|
14
|
+
method_option :total, default: 100, description: "number of images to search", aliases: "-n"
|
15
|
+
def google_images(keyword)
|
16
|
+
scraper = Scrapix::GoogleImages.new keyword, options
|
17
|
+
scraper.total = options["total"].to_i
|
18
|
+
images = scraper.find
|
19
|
+
if images.empty?
|
20
|
+
puts "No images were found! :("
|
21
|
+
else
|
22
|
+
puts "URL, WIDTH, HEIGHT, REFERENCE_URL" if options["verbose"]
|
23
|
+
images.each do |image|
|
24
|
+
if options["verbose"]
|
25
|
+
puts "#{image[:url]},#{image[:width]},#{image[:height]},#{image[:reference_url]}"
|
26
|
+
else
|
27
|
+
puts options["ref"] ? image[:reference_url] : image[:url]
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
desc "vbulletin [THREAD_URL]", "scrape images from a vBulletin Thread"
|
34
|
+
method_option :total, default: 100000, description: "number of images to search", aliases: "-n"
|
35
|
+
method_option :start, default: 1, description: "starting page number"
|
36
|
+
method_option :end, default: 10000, description: "ending page number"
|
37
|
+
method_option :verbose, type: :boolean, default: false, description: "be verbose", alias: "-v"
|
38
|
+
def vbulletin(thread_url)
|
39
|
+
scraper = Scrapix::VBulletin.new thread_url, options.merge({"cli" => true})
|
40
|
+
images = scraper.find
|
41
|
+
puts "No images were found! :(" if images.empty?
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
Scrapix::CLI.start
|
data/lib/scrapix.rb
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
# capybara for scraping
|
2
|
+
require 'capybara'
|
3
|
+
require 'capybara/dsl'
|
4
|
+
require 'capybara/poltergeist'
|
5
|
+
|
6
|
+
Capybara.register_driver :poltergeist_debug do |app|
|
7
|
+
Capybara::Poltergeist::Driver.new app, {
|
8
|
+
timeout: 600,
|
9
|
+
inspector: true,
|
10
|
+
# js_errors: false,
|
11
|
+
phantomjs_options: ["--web-security=no"]
|
12
|
+
}
|
13
|
+
end
|
14
|
+
|
15
|
+
# use javascript driver
|
16
|
+
Capybara.current_driver = :poltergeist_debug
|
17
|
+
|
18
|
+
Scrapix::UserAgent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_2) " +
|
19
|
+
"AppleWebKit/537.31 (KHTML, like Gecko) Chrome/26.0.1410.65 Safari/537.31"
|
20
|
+
|
@@ -0,0 +1,113 @@
|
|
1
|
+
module Scrapix
|
2
|
+
# download images from a Google Image Search
|
3
|
+
class GoogleImages
|
4
|
+
include Capybara::DSL
|
5
|
+
|
6
|
+
# options can be:
|
7
|
+
# size: named size, e.g. icon, small, medium, large, 13mp, 1280x800, etc.
|
8
|
+
# safe: true or false
|
9
|
+
#
|
10
|
+
def initialize(query = nil, options = {})
|
11
|
+
self.options = options
|
12
|
+
self.query = query
|
13
|
+
self.total = 100
|
14
|
+
end
|
15
|
+
|
16
|
+
def search_url(page_no = 1)
|
17
|
+
"http://google.com/search?tbm=isch&q=#{@query}#{@params}&start=#{(page_no - 1)*20}"
|
18
|
+
end
|
19
|
+
|
20
|
+
def query=(q)
|
21
|
+
@query = URI.escape(q) if q
|
22
|
+
end
|
23
|
+
|
24
|
+
def total=(n)
|
25
|
+
@num = n.to_i
|
26
|
+
end
|
27
|
+
|
28
|
+
def options=(opts)
|
29
|
+
# convert symbolic keys to string keys
|
30
|
+
options = {}
|
31
|
+
opts.each { |k,v| options[k.to_s] = v }
|
32
|
+
|
33
|
+
# merge the options with defaults!
|
34
|
+
@options ||= { "safe" => true, "size" => "any" }
|
35
|
+
@options.merge!(options)
|
36
|
+
sanitize_size
|
37
|
+
|
38
|
+
# parametrize for url purposes
|
39
|
+
@params = create_params
|
40
|
+
end
|
41
|
+
|
42
|
+
# params: page_no => starting page number for google results
|
43
|
+
def find(page_no = 1)
|
44
|
+
images = {}
|
45
|
+
return images unless @query
|
46
|
+
|
47
|
+
while images.count < @num
|
48
|
+
visit search_url(page_no)
|
49
|
+
links = Capybara.page.all("a")
|
50
|
+
links = links.select{|x| x["href"] =~ /^\/imgres/} if links.any?
|
51
|
+
return images unless links.any?
|
52
|
+
page_counter = 0
|
53
|
+
links.each do |link|
|
54
|
+
attribs = CGI.parse(URI.parse(link["href"]).query) rescue nil
|
55
|
+
next if attribs.nil?
|
56
|
+
hash = Digest::MD5.hexdigest(attribs["imgurl"][0])
|
57
|
+
unless images.has_key?(hash)
|
58
|
+
images[hash] = {
|
59
|
+
width: attribs["w"][0],
|
60
|
+
height: attribs["h"][0],
|
61
|
+
url: attribs["imgurl"][0],
|
62
|
+
reference_url: attribs["imgrefurl"][0]
|
63
|
+
}
|
64
|
+
page_counter += 1
|
65
|
+
end
|
66
|
+
end
|
67
|
+
page_no += 1
|
68
|
+
break if page_counter == 0
|
69
|
+
end
|
70
|
+
images.take(@num).map{|x| x[1]}
|
71
|
+
end
|
72
|
+
|
73
|
+
private
|
74
|
+
|
75
|
+
def validate_mp_size(mp)
|
76
|
+
mp = mp.to_i
|
77
|
+
lower_bound = 0; upper_bound = 9999;
|
78
|
+
valid_mp_sizes = [ 2, 4, 6, 8, 10, 12, 15, 20, 40, 70 ]
|
79
|
+
valid_mp_sizes.each do |s|
|
80
|
+
return s if s == mp
|
81
|
+
lower_bound = s if s < mp
|
82
|
+
upper_bound = s if s > mp && s < upper_bound
|
83
|
+
end
|
84
|
+
mp - lower_bound > upper_bound - mp ? upper_bound : lower_bound
|
85
|
+
end
|
86
|
+
|
87
|
+
# if width or height is specified, use them as 'exact' size
|
88
|
+
# otherwise, use a MP size for finding images larger than that size
|
89
|
+
# otherwise, use a given named size
|
90
|
+
def sanitize_size
|
91
|
+
@options["size"] = case
|
92
|
+
when m = @options["size"].match(/^(\d*)x(\d*)$/)
|
93
|
+
then "isz:ex,iszw:#{m[1]},iszh:#{m[2]}"
|
94
|
+
when m = @options["size"].match(/^(\d*)$/)
|
95
|
+
then "isz:ex,iszw:#{m[1]},iszh:#{m[1]}"
|
96
|
+
when m = @options["size"].match(/^(\d*)mp$/)
|
97
|
+
then "isz:lt,islt:#{validate_mp_size(m[1])}mp"
|
98
|
+
when @options["size"] == "large" then "isz:l"
|
99
|
+
when @options["size"] == "medium" then "isz:m"
|
100
|
+
when @options["size"] == "small" then "isz:s"
|
101
|
+
when @options["size"] == "icon" then "isz:i"
|
102
|
+
else nil
|
103
|
+
end
|
104
|
+
end
|
105
|
+
|
106
|
+
def create_params
|
107
|
+
string = ""
|
108
|
+
string += "&tbs=#{@options["size"]}" if @options["size"]
|
109
|
+
string += "&safe=off" unless @options["safe"]
|
110
|
+
string
|
111
|
+
end
|
112
|
+
end
|
113
|
+
end
|
@@ -0,0 +1,72 @@
|
|
1
|
+
module Scrapix
|
2
|
+
# download images from a vBulletin thread
|
3
|
+
class VBulletin
|
4
|
+
|
5
|
+
attr_reader :title, :max_pages, :options, :page_no, :images, :url
|
6
|
+
|
7
|
+
def initialize(url = nil, options = {})
|
8
|
+
@images = {}
|
9
|
+
@agent = Mechanize.new
|
10
|
+
@agent.user_agent_alias = 'Mac Safari'
|
11
|
+
self.options = options
|
12
|
+
self.url = url
|
13
|
+
end
|
14
|
+
|
15
|
+
# find images for this thread, specified by starting page_no
|
16
|
+
def find
|
17
|
+
reset; return @images unless @url
|
18
|
+
@page_no = @options["start"]
|
19
|
+
until @images.count > @options["total"] || thread_has_ended?
|
20
|
+
page = @agent.get "#{@url}&page=#{@page_no}"
|
21
|
+
puts "[VERBOSE] Searching: #{@url}&page=#{@page_no}" if @options["verbose"] && options["cli"]
|
22
|
+
sources = page.image_urls.map{|x| x.to_s}
|
23
|
+
sources = filter_images sources # hook for sub-classes
|
24
|
+
@page_no += 1
|
25
|
+
continue if sources.empty?
|
26
|
+
sources.each do |source|
|
27
|
+
hash = Digest::MD5.hexdigest(source)
|
28
|
+
unless @images.has_key?(hash)
|
29
|
+
@images[hash] = {url: source}
|
30
|
+
puts source if options["cli"]
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end
|
34
|
+
@images = @images.map{|x, y| y}
|
35
|
+
end
|
36
|
+
|
37
|
+
def thread_has_ended?
|
38
|
+
@page_no > @options["end"] || @page_no > @max_pages
|
39
|
+
end
|
40
|
+
|
41
|
+
def filter_images(sources)
|
42
|
+
# useful for filtering the image by sub-classes
|
43
|
+
return sources
|
44
|
+
end
|
45
|
+
|
46
|
+
def url=(url)
|
47
|
+
@url = url
|
48
|
+
return unless @url
|
49
|
+
page = @agent.get @url
|
50
|
+
@title = page.title.strip
|
51
|
+
puts @title + "\n" + ("=" * @title.length) if self.options["cli"]
|
52
|
+
begin
|
53
|
+
text = page.search(".pagenav .vbmenu_control").first.inner_text
|
54
|
+
@max_pages = text.match(/Page \d* of (\d*)/)[1].to_i
|
55
|
+
rescue
|
56
|
+
@max_pages = 1
|
57
|
+
end
|
58
|
+
end
|
59
|
+
|
60
|
+
def reset
|
61
|
+
@images = {}
|
62
|
+
@page_no = @options["start"]
|
63
|
+
end
|
64
|
+
|
65
|
+
def options=(options = {})
|
66
|
+
@options = { "start" => 1, "end" => 10000, "total" => 100000, "verbose" => false, "cli" => false }
|
67
|
+
options.each { |k,v| @options[k.to_s] = v }
|
68
|
+
["start", "end", "total"].each {|k| @options[k] = @options[k].to_i}
|
69
|
+
@options
|
70
|
+
end
|
71
|
+
end
|
72
|
+
end
|
data/scrapix.gemspec
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'scrapix/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "scrapix"
|
8
|
+
spec.version = Scrapix::VERSION
|
9
|
+
spec.authors = ["Nikhil Gupta"]
|
10
|
+
spec.email = ["me@nikhgupta.com"]
|
11
|
+
spec.description = %q{Scrapes images from various sources e.g. Google Images, vBulletin threads, etc.}
|
12
|
+
spec.summary = %q{A gem that is able to scrape images from various sources. The gem provides you with the results of these searches in a neat way, which you can then use to download these images.}
|
13
|
+
spec.homepage = "http://github.com/nikhgupta/scrapix"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_dependency "thor"
|
22
|
+
spec.add_dependency "capybara"
|
23
|
+
spec.add_dependency "mechanize"
|
24
|
+
spec.add_dependency "poltergeist"
|
25
|
+
|
26
|
+
spec.add_development_dependency "rake"
|
27
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
28
|
+
end
|
metadata
ADDED
@@ -0,0 +1,145 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: scrapix
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.3
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Nikhil Gupta
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-05-03 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: thor
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - '>='
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - '>='
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: capybara
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: mechanize
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: poltergeist
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - '>='
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: rake
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '>='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - '>='
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: bundler
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ~>
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '1.3'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ~>
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '1.3'
|
97
|
+
description: Scrapes images from various sources e.g. Google Images, vBulletin threads,
|
98
|
+
etc.
|
99
|
+
email:
|
100
|
+
- me@nikhgupta.com
|
101
|
+
executables:
|
102
|
+
- scrapix
|
103
|
+
extensions: []
|
104
|
+
extra_rdoc_files: []
|
105
|
+
files:
|
106
|
+
- .gitignore
|
107
|
+
- .rvmrc
|
108
|
+
- Gemfile
|
109
|
+
- LICENSE.txt
|
110
|
+
- README.md
|
111
|
+
- Rakefile
|
112
|
+
- bin/scrapix
|
113
|
+
- lib/scrapix.rb
|
114
|
+
- lib/scrapix/drivers/capybara.rb
|
115
|
+
- lib/scrapix/google_images.rb
|
116
|
+
- lib/scrapix/vbulletin.rb
|
117
|
+
- lib/scrapix/version.rb
|
118
|
+
- scrapix.gemspec
|
119
|
+
homepage: http://github.com/nikhgupta/scrapix
|
120
|
+
licenses:
|
121
|
+
- MIT
|
122
|
+
metadata: {}
|
123
|
+
post_install_message:
|
124
|
+
rdoc_options: []
|
125
|
+
require_paths:
|
126
|
+
- lib
|
127
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - '>='
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '0'
|
132
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
133
|
+
requirements:
|
134
|
+
- - '>='
|
135
|
+
- !ruby/object:Gem::Version
|
136
|
+
version: '0'
|
137
|
+
requirements: []
|
138
|
+
rubyforge_project:
|
139
|
+
rubygems_version: 2.0.0
|
140
|
+
signing_key:
|
141
|
+
specification_version: 4
|
142
|
+
summary: A gem that is able to scrape images from various sources. The gem provides
|
143
|
+
you with the results of these searches in a neat way, which you can then use to
|
144
|
+
download these images.
|
145
|
+
test_files: []
|