scrapers 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/.gitignore +18 -0
- data/.rspec-example +2 -0
- data/.watchr +27 -0
- data/Gemfile +4 -0
- data/Guardfile +6 -0
- data/LICENSE.txt +22 -0
- data/README.md +32 -0
- data/Rakefile +1 -0
- data/lib/scrapers/allrecipes.rb +49 -0
- data/lib/scrapers/discoverynews.rb +28 -0
- data/lib/scrapers/download.rb +37 -0
- data/lib/scrapers/gocomics.rb +43 -0
- data/lib/scrapers/imgur.rb +56 -0
- data/lib/scrapers/nasa_apod.rb +60 -0
- data/lib/scrapers/version.rb +7 -0
- data/lib/scrapers.rb +9 -0
- data/scrapers.gemspec +29 -0
- data/spec/scrapers/allrecipes_spec.rb +29 -0
- data/spec/scrapers/discoverynews_spec.rb +39 -0
- data/spec/scrapers/download_spec.rb +36 -0
- data/spec/scrapers/gocomics_spec.rb +46 -0
- data/spec/scrapers/imgur_spec.rb +31 -0
- data/spec/scrapers/nasa_apod_spec.rb +30 -0
- data/spec/scrapers_spec.rb +9 -0
- data/spec/spec_helper.rb +31 -0
- data/vcr_cassettes/allrecipes_morning-glory-muffins-i.yml +1047 -0
- data/vcr_cassettes/disconews_history-of-space.yml +385 -0
- data/vcr_cassettes/download_cassette.yml +431 -0
- data/vcr_cassettes/exampleatspecscrapersnasaapodspecrb16_cassette.yml +326 -0
- data/vcr_cassettes/exampleatspecscrapersnasaapodspecrb21_cassette.yml +326 -0
- data/vcr_cassettes/exampleatspecscrapersnasaapodspecrb22_cassette.yml +312 -0
- data/vcr_cassettes/gocomics_nonsequitur.yml +336 -0
- data/vcr_cassettes/shouldincludecontentencoded_cassette.yml +326 -0
- data/vcr_cassettes/shouldincludedescription_cassette.yml +326 -0
- data/vcr_cassettes/shouldincludeguid_cassette.yml +326 -0
- data/vcr_cassettes/shouldincludelink_cassette.yml +326 -0
- data/vcr_cassettes/shouldincludepubDate_cassette.yml +326 -0
- data/vcr_cassettes/shouldincludetitle_cassette.yml +326 -0
- metadata +203 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: eef6a353955404ad8beaf88e4db8ab4b0a4f3cec
|
4
|
+
data.tar.gz: 87ec094c87d315640c1ebb274b6f334b6dd73646
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: ece9775696f757216e7c9fd9c2ef2a6ff4a1bd3a9dcbf1fd754caed7c751bdeb1f055a2ea6694b216dfaf61f7a1678cedc777fd0281d660d73e68f34399f2c90
|
7
|
+
data.tar.gz: 370b23a91c38f349a8f02a6fe4ed8770bb58017b43876ad736c449087da7b303aae605f2a314e76b6489bdfc89aaceaa2588f94a6e6e1d7b3e0423c50f2c5f63
|
data/.gitignore
ADDED
data/.rspec-example
ADDED
data/.watchr
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
# -*- ruby -*-
|
2
|
+
def run_spec(file)
|
3
|
+
unless File.exist?(file)
|
4
|
+
puts "#{file} does not exist"
|
5
|
+
return
|
6
|
+
end
|
7
|
+
|
8
|
+
puts "Running #{file}"
|
9
|
+
system "bundle exec rspec #{file}"
|
10
|
+
puts
|
11
|
+
end
|
12
|
+
|
13
|
+
watch("^spec/*_spec.rb$") do |match|
|
14
|
+
run_spec match[0]
|
15
|
+
end
|
16
|
+
|
17
|
+
watch("^spec/.*/*_spec.rb$") do |match|
|
18
|
+
run_spec match[0]
|
19
|
+
end
|
20
|
+
|
21
|
+
watch("^lib/(.*).rb$") do |match|
|
22
|
+
run_spec "spec/#{match[1]}_spec.rb"
|
23
|
+
end
|
24
|
+
|
25
|
+
watch("^lib/(.*/.*).rb$") do |match|
|
26
|
+
run_spec "spec/#{match[1]}_spec.rb"
|
27
|
+
end
|
data/Gemfile
ADDED
data/Guardfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Tamara Temple
|
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 +1,32 @@
|
|
1
|
+
# Scrapers
|
2
|
+
|
3
|
+
A library of web site scrapers utilizing mechanize and other goodies. Helpful in gathering images, moving things, saving things, etc.
|
4
|
+
|
5
|
+
LICENSE:: MIT
|
6
|
+
WEBSITE:: http://github.com/tamouse/scrapers
|
7
|
+
|
8
|
+
## Installation
|
9
|
+
|
10
|
+
Add this line to your application's Gemfile:
|
11
|
+
|
12
|
+
gem 'scrapers'
|
13
|
+
|
14
|
+
And then execute:
|
15
|
+
|
16
|
+
$ bundle
|
17
|
+
|
18
|
+
Or install it yourself as:
|
19
|
+
|
20
|
+
$ gem install scrapers
|
21
|
+
|
22
|
+
## Usage
|
23
|
+
|
24
|
+
See the various RDoc for explanation of each item.
|
25
|
+
|
26
|
+
## Contributing
|
27
|
+
|
28
|
+
1. Fork it
|
29
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
30
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
31
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
32
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
@@ -0,0 +1,49 @@
|
|
1
|
+
require 'mechanize'
|
2
|
+
|
3
|
+
|
4
|
+
module Scrapers
|
5
|
+
|
6
|
+
module AllRecipes
|
7
|
+
|
8
|
+
def self.scrape(url)
|
9
|
+
|
10
|
+
results = Hash.new
|
11
|
+
|
12
|
+
Scrapers.agent.get(url).tap do |page|
|
13
|
+
results[:url] = page.uri.to_s
|
14
|
+
results[:title] = page.title.strip
|
15
|
+
results[:ingredients] = scrape_ingredients(page)
|
16
|
+
results[:directions] = scrape_directions(page)
|
17
|
+
results[:photo] = scrape_photo(page)
|
18
|
+
end
|
19
|
+
|
20
|
+
results
|
21
|
+
|
22
|
+
end
|
23
|
+
|
24
|
+
def self.scrape_ingredients(page)
|
25
|
+
page.
|
26
|
+
search("ul.ingredient-wrap").
|
27
|
+
search(".//li").
|
28
|
+
map do |i|
|
29
|
+
i.text.gsub(/[[:space:]]+/,' ').sub(/^/,'*')
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
def self.scrape_directions(page)
|
34
|
+
page.
|
35
|
+
search("div.directLeft").first.
|
36
|
+
search("li").
|
37
|
+
map do |i|
|
38
|
+
i.text.gsub(/[[:space:]]+/,' ').sub(/^/,'# ')
|
39
|
+
end
|
40
|
+
end
|
41
|
+
|
42
|
+
def self.scrape_photo(page)
|
43
|
+
photo = page.search("img#imgPhoto").first
|
44
|
+
Hash[photo.attributes.map{|k,v| [k,v.value]}]
|
45
|
+
end
|
46
|
+
|
47
|
+
end
|
48
|
+
|
49
|
+
end
|
@@ -0,0 +1,28 @@
|
|
1
|
+
=begin rdoc
|
2
|
+
|
3
|
+
= DISCOVERYNEWS.RB
|
4
|
+
|
5
|
+
*Author*:: Tamara Temple <tamouse@gmail.com>
|
6
|
+
*Since*:: 2013-06-15
|
7
|
+
*Copyright*:: (c) 2013 Tamara Temple Web Development
|
8
|
+
*License*:: MIT
|
9
|
+
|
10
|
+
Scraper for disco news pictures of the week
|
11
|
+
|
12
|
+
=end
|
13
|
+
|
14
|
+
require 'mechanize'
|
15
|
+
|
16
|
+
module Scrapers
|
17
|
+
|
18
|
+
module DiscoNews
|
19
|
+
|
20
|
+
def self.disco_downloads(url)
|
21
|
+
@url = url.clone
|
22
|
+
@page = Scrapers.agent.get(url)
|
23
|
+
images = @page.images_with(:class => "media-hero").map(&:src)
|
24
|
+
end
|
25
|
+
|
26
|
+
end
|
27
|
+
|
28
|
+
end
|
@@ -0,0 +1,37 @@
|
|
1
|
+
=begin rdoc
|
2
|
+
|
3
|
+
= DOWNLOAD.RB
|
4
|
+
|
5
|
+
*Author*:: Tamara Temple <tamara@tamaratemple.com>
|
6
|
+
*Since*:: 2013-05-27
|
7
|
+
*Copyright*:: (c) 2013 Tamara Temple Web Development
|
8
|
+
*License*:: MIT
|
9
|
+
|
10
|
+
=end
|
11
|
+
|
12
|
+
require 'mechanize'
|
13
|
+
|
14
|
+
module Scrapers
|
15
|
+
|
16
|
+
module Download
|
17
|
+
|
18
|
+
def self.download(url,dir=".")
|
19
|
+
Scrapers.agent.pluggable_parser.default = Mechanize::Download
|
20
|
+
@dir = validate_directory(dir)
|
21
|
+
dl = Scrapers.agent.get(url)
|
22
|
+
Dir.chdir(@dir) do |dir|
|
23
|
+
dl.save()
|
24
|
+
end
|
25
|
+
File.join(@dir,dl.filename)
|
26
|
+
end
|
27
|
+
|
28
|
+
def self.validate_directory(d)
|
29
|
+
STDERR.puts caller(0,1).first +
|
30
|
+
"d: #{d.inspect}. directory? #{File.directory?(d)}. writable? #{File.writable?(d)}"
|
31
|
+
raise "#{d} is not a writable directory!" unless File.directory?(d) and File.writable?(d)
|
32
|
+
d
|
33
|
+
end
|
34
|
+
|
35
|
+
end
|
36
|
+
|
37
|
+
end
|
@@ -0,0 +1,43 @@
|
|
1
|
+
require 'open-uri'
|
2
|
+
require 'nokogiri'
|
3
|
+
|
4
|
+
|
5
|
+
module Scrapers
|
6
|
+
|
7
|
+
module GoComics
|
8
|
+
|
9
|
+
GOCOMIC_URL = "http://www.gocomics.com/"
|
10
|
+
|
11
|
+
def self.scrape(comic)
|
12
|
+
|
13
|
+
results = Hash.new
|
14
|
+
|
15
|
+
url = URI.parse GOCOMIC_URL
|
16
|
+
url.path = "/#{comic}"
|
17
|
+
|
18
|
+
page = Nokogiri::HTML(open(url.to_s))
|
19
|
+
results[:url] = url.to_s
|
20
|
+
results[:title] = scrape_title(page)
|
21
|
+
results[:pubdate] = scrape_pubdate(page)
|
22
|
+
results[:img_src] = scrape_image_source(page)
|
23
|
+
results
|
24
|
+
end
|
25
|
+
|
26
|
+
def self.scrape_title(page)
|
27
|
+
page.at_css("title").content.strip.gsub(/[[:space:]]/,' ').squeeze(" ")
|
28
|
+
end
|
29
|
+
|
30
|
+
def self.scrape_pubdate(page)
|
31
|
+
Date.parse(page.at_css("ul.feature-nav > li").content).to_s
|
32
|
+
end
|
33
|
+
|
34
|
+
def self.scrape_image_source(page)
|
35
|
+
page.
|
36
|
+
at_css("p.feature_item").
|
37
|
+
at_css("img").
|
38
|
+
attr("src")
|
39
|
+
end
|
40
|
+
|
41
|
+
end
|
42
|
+
|
43
|
+
end
|
@@ -0,0 +1,56 @@
|
|
1
|
+
=begin rdoc
|
2
|
+
|
3
|
+
= IMGUR.RB
|
4
|
+
|
5
|
+
*Author*:: Tamara Temple <tamara@tamaratemple.com>
|
6
|
+
*Since*:: 2013-05-27
|
7
|
+
*Copyright*:: (c) 2013 Tamara Temple Web Development
|
8
|
+
*License*:: MIT
|
9
|
+
|
10
|
+
=end
|
11
|
+
|
12
|
+
module Scrapers
|
13
|
+
|
14
|
+
IMGUR_TEMPLATE="http://imgur.com/path"
|
15
|
+
|
16
|
+
class Imgur
|
17
|
+
|
18
|
+
attr_accessor :agent, :url, :download, :page
|
19
|
+
|
20
|
+
def initialize
|
21
|
+
@agent = Mechanize.new
|
22
|
+
@url = URI.parse(IMGUR_TEMPLATE)
|
23
|
+
@download = URI.parse(IMGUR_TEMPLATE)
|
24
|
+
end
|
25
|
+
|
26
|
+
def download_link(code)
|
27
|
+
make_url(code)
|
28
|
+
retrieve_page()
|
29
|
+
find_download()
|
30
|
+
@download.to_s
|
31
|
+
end
|
32
|
+
|
33
|
+
def make_url(imgur_code)
|
34
|
+
@url.path = "/#{imgur_code}"
|
35
|
+
end
|
36
|
+
|
37
|
+
def retrieve_page()
|
38
|
+
@page = @agent.get(@url.to_s)
|
39
|
+
end
|
40
|
+
|
41
|
+
def find_download(link_text=/Download/)
|
42
|
+
link = @page.link_with(:text => link_text)
|
43
|
+
raise "#{link_text} not found on #{@page.uri.to_s}" if link.nil?
|
44
|
+
@download.path = link.href
|
45
|
+
end
|
46
|
+
|
47
|
+
end
|
48
|
+
|
49
|
+
module_function
|
50
|
+
|
51
|
+
def imgur(url)
|
52
|
+
code = File.basename(url).sub(/\.[^.]+$/,'')
|
53
|
+
"http://imgur.com/download/#{code}/"
|
54
|
+
end
|
55
|
+
|
56
|
+
end
|
@@ -0,0 +1,60 @@
|
|
1
|
+
=begin rdoc
|
2
|
+
|
3
|
+
nasa_apod.rb -- oneline desc
|
4
|
+
|
5
|
+
Time-stamp: <2013-08-23 22:47:58 tamara>
|
6
|
+
Copyright (C) 2013 Tamara Temple Web Development
|
7
|
+
Author: Tamara Temple <tamouse@gmail.com>
|
8
|
+
License: MIT
|
9
|
+
|
10
|
+
== Discussion
|
11
|
+
|
12
|
+
NASA's Astronomy Picture of the Day is a great source for nice astro
|
13
|
+
photos and various other information. But it isn't something I
|
14
|
+
remember to go see every day, so I'd like it to drop in my in-box or
|
15
|
+
an evernote notebook. But the feed does not include the image, for
|
16
|
+
some ungodly reason, so I'm adding a scraper to grab the nice info off
|
17
|
+
the page including the photo.
|
18
|
+
|
19
|
+
=end
|
20
|
+
|
21
|
+
|
22
|
+
module Scrapers
|
23
|
+
|
24
|
+
module NasaApod
|
25
|
+
|
26
|
+
module_function
|
27
|
+
|
28
|
+
def scrape(url)
|
29
|
+
apod = Hash.new
|
30
|
+
unless url.nil?
|
31
|
+
|
32
|
+
Mechanize.start do |m|
|
33
|
+
|
34
|
+
m.get url
|
35
|
+
|
36
|
+
# APOD has a funky entry page, but we want the actual page
|
37
|
+
prev = m.current_page.link_with(:text => '<').href
|
38
|
+
m.get prev
|
39
|
+
canonical = m.current_page.link_with(:text => '>' ).href
|
40
|
+
m.get canonical
|
41
|
+
|
42
|
+
m.current_page.tap do |page|
|
43
|
+
apod[:title] = page.title.strip
|
44
|
+
apod[:link] = page.uri.to_s
|
45
|
+
apod[:description] = (page/("body")).text
|
46
|
+
apod[:pubDate] = page.response['date'].to_s
|
47
|
+
apod[:guid] = page.uri.to_s
|
48
|
+
apod[:content_encoded] = (page/("body")).to_html
|
49
|
+
end
|
50
|
+
|
51
|
+
end
|
52
|
+
|
53
|
+
end
|
54
|
+
|
55
|
+
apod
|
56
|
+
end
|
57
|
+
|
58
|
+
end
|
59
|
+
|
60
|
+
end
|
@@ -0,0 +1,7 @@
|
|
1
|
+
module Scrapers
|
2
|
+
VERSION = "0.2.0"
|
3
|
+
DESCRIPTION = "A library of web site scrapers utilizing mechanize and other goodies. Helpful in gathering images, moving things, saving things, etc."
|
4
|
+
SUMMARY = "Web site scrapers"
|
5
|
+
LICENSE = "MIT"
|
6
|
+
WEBSITE = "http://github.com/tamouse/scrapers"
|
7
|
+
end
|
data/lib/scrapers.rb
ADDED
data/scrapers.gemspec
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'scrapers/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "scrapers"
|
8
|
+
spec.version = Scrapers::VERSION
|
9
|
+
spec.authors = ["Tamara Temple"]
|
10
|
+
spec.email = ["tamouse@gmail.com"]
|
11
|
+
spec.description = Scrapers::DESCRIPTION
|
12
|
+
spec.summary = Scrapers::SUMMARY
|
13
|
+
spec.homepage = Scrapers::WEBSITE
|
14
|
+
spec.license = Scrapers::LICENSE
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
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_development_dependency "bundler"
|
22
|
+
spec.add_development_dependency "rake"
|
23
|
+
spec.add_development_dependency "rspec"
|
24
|
+
spec.add_dependency "mechanize"
|
25
|
+
spec.add_development_dependency "guard"
|
26
|
+
spec.add_development_dependency "guard-rspec"
|
27
|
+
spec.add_development_dependency "webmock"
|
28
|
+
spec.add_development_dependency "vcr"
|
29
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
module Scrapers
|
4
|
+
|
5
|
+
describe AllRecipes do
|
6
|
+
it{should respond_to :scrape}
|
7
|
+
context "scraping" do
|
8
|
+
before(:all) do
|
9
|
+
@url = "http://allrecipes.com/recipe/morning-glory-muffins-i/detail.aspx"
|
10
|
+
@recipe = VCR.use_cassette('allrecipes.morning-glory-muffins-i') do
|
11
|
+
Scrapers::AllRecipes.scrape(@url)
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
it "retrieves a recipe" do
|
16
|
+
@recipe.should_not be_nil
|
17
|
+
end
|
18
|
+
it "should be a Hash" do
|
19
|
+
@recipe.should be_a(Hash)
|
20
|
+
end
|
21
|
+
%w{title url ingredients directions photo}.map(&:to_sym).each do |key|
|
22
|
+
it "should have key #{key}" do
|
23
|
+
@recipe.should have_key(key)
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
@@ -0,0 +1,39 @@
|
|
1
|
+
=begin rdoc
|
2
|
+
|
3
|
+
= DISCOVERYNEWS_SPEC.RB
|
4
|
+
|
5
|
+
*Author*:: Tamara Temple <tamouse@gmail.com>
|
6
|
+
*Since*:: 2013-06-15
|
7
|
+
*Copyright*:: (c) 2013 Tamara Temple Web Development
|
8
|
+
*License*:: MIT
|
9
|
+
|
10
|
+
=end
|
11
|
+
|
12
|
+
require 'spec_helper'
|
13
|
+
|
14
|
+
|
15
|
+
module Scrapers
|
16
|
+
|
17
|
+
describe DiscoNews do
|
18
|
+
it {should respond_to(:disco_downloads)}
|
19
|
+
|
20
|
+
context "scraping" do
|
21
|
+
let(:url) {"http://news.discovery.com/space/history-of-space/stunning-space-photos-week-june-9-14-pictures-130614.htm"}
|
22
|
+
let(:images) do
|
23
|
+
VCR.use_cassette('disconews.history-of-space') do
|
24
|
+
Scrapers::DiscoNews.disco_downloads(url)
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
it "retrieves an array of images" do
|
29
|
+
images.should be_a(Array)
|
30
|
+
images.each do |i|
|
31
|
+
i.should =~ /^http:\/\/.*(jpe?g|png|gif)/
|
32
|
+
end
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
end
|
37
|
+
|
38
|
+
end
|
39
|
+
|
@@ -0,0 +1,36 @@
|
|
1
|
+
=begin rdoc
|
2
|
+
|
3
|
+
= DOWNLOAD_SPEC.RB
|
4
|
+
|
5
|
+
*Author*:: Tamara Temple <tamara@tamaratemple.com>
|
6
|
+
*Since*:: 2013-05-27
|
7
|
+
*Copyright*:: (c) 2013 Tamara Temple Web Development
|
8
|
+
*License*:: MIT
|
9
|
+
|
10
|
+
=end
|
11
|
+
|
12
|
+
require 'spec_helper'
|
13
|
+
require 'tmpdir'
|
14
|
+
|
15
|
+
module Scrapers
|
16
|
+
|
17
|
+
describe Download do
|
18
|
+
it {Scrapers::Download.should respond_to :download}
|
19
|
+
|
20
|
+
context "download" do
|
21
|
+
before(:all) do
|
22
|
+
@url="http://imgur.com/download/v70StgA/%2Asnrrrrrrrrrrrf%21%2A"
|
23
|
+
VCR.use_cassette("download.cassette") do
|
24
|
+
@file = Scrapers::Download.download(@url,'tmp')
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
it "saves the file" do
|
29
|
+
@file.should =~ /.*snrrrrrrrrrrrf.*Imgur\.jpg/
|
30
|
+
File.exist?(@file).should be_true
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
end
|
35
|
+
|
36
|
+
end
|
@@ -0,0 +1,46 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
module Scrapers
|
4
|
+
|
5
|
+
describe GoComics do
|
6
|
+
it{should respond_to :scrape}
|
7
|
+
context "scraping" do
|
8
|
+
before(:all) do
|
9
|
+
@comic_strip = 'nonsequitur'
|
10
|
+
@comic = VCR.use_cassette('gocomics.nonsequitur') do
|
11
|
+
Scrapers::GoComics.scrape(@comic_strip)
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
it "retrieves a comic" do
|
16
|
+
@comic.should_not be_nil
|
17
|
+
end
|
18
|
+
it "should be a Hash" do
|
19
|
+
@comic.should be_a(Hash)
|
20
|
+
end
|
21
|
+
%w{title url pubdate img_src}.map(&:to_sym).each do |key|
|
22
|
+
it "should have key #{key}" do
|
23
|
+
@comic.should have_key(key)
|
24
|
+
end
|
25
|
+
end
|
26
|
+
context "title" do
|
27
|
+
it{@comic[:title].should_not be_empty}
|
28
|
+
it{@comic[:title].should match /Non Sequitur Comic Strip on GoComics.com/}
|
29
|
+
end
|
30
|
+
context "url" do
|
31
|
+
it{@comic[:url].should_not be_empty}
|
32
|
+
it{@comic[:url].should match /www\.gocomics\.com\/nonsequitur/}
|
33
|
+
end
|
34
|
+
context "pubdate" do
|
35
|
+
it{@comic[:pubdate].should_not be_empty}
|
36
|
+
it{Date.parse(@comic[:pubdate]).should be_a(Date)}
|
37
|
+
end
|
38
|
+
context "img_src" do
|
39
|
+
it{@comic[:img_src].should_not be_empty}
|
40
|
+
it{URI.parse(@comic[:img_src]).should be_a(URI::HTTP)}
|
41
|
+
end
|
42
|
+
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
46
|
+
|
@@ -0,0 +1,31 @@
|
|
1
|
+
=begin rdoc
|
2
|
+
|
3
|
+
= IMGUR_SPEC.RB
|
4
|
+
|
5
|
+
*Author*:: Tamara Temple <tamara@tamaratemple.com>
|
6
|
+
*Since*:: 2013-05-27
|
7
|
+
*Copyright*:: (c) 2013 Tamara Temple Web Development
|
8
|
+
*License*:: MIT
|
9
|
+
|
10
|
+
=end
|
11
|
+
|
12
|
+
require 'spec_helper'
|
13
|
+
|
14
|
+
module Scrapers
|
15
|
+
|
16
|
+
describe "Scrapers" do
|
17
|
+
it {Scrapers.should respond_to(:imgur)}
|
18
|
+
end
|
19
|
+
|
20
|
+
describe "Fetch the download link" do
|
21
|
+
let(:url) {"http://imgur.com/v70StgA"}
|
22
|
+
|
23
|
+
it "should return the download link from a given url" do
|
24
|
+
Scrapers.imgur(url).should =~ %r{http://imgur.com/download/v70StgA/}
|
25
|
+
end
|
26
|
+
|
27
|
+
end
|
28
|
+
|
29
|
+
|
30
|
+
|
31
|
+
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
|
2
|
+
require 'spec_helper'
|
3
|
+
|
4
|
+
|
5
|
+
module Scrapers
|
6
|
+
|
7
|
+
describe NasaApod do
|
8
|
+
it {Scrapers::NasaApod.should respond_to :scrape}
|
9
|
+
|
10
|
+
context "scrape" do
|
11
|
+
let(:url){"http://apod.nasa.gov/apod/astropix.html"}
|
12
|
+
let(:apod_hash){
|
13
|
+
VCR.use_cassette("#{example.description.gsub(/[^-[:alnum:]]/,'')}.cassette", :record => :new_episodes) do
|
14
|
+
Scrapers::NasaApod.scrape(url)
|
15
|
+
end}
|
16
|
+
it {apod_hash.should be_a(Hash)}
|
17
|
+
%w{title link description pubDate guid content_encoded}.map(&:to_sym).each do |attr|
|
18
|
+
it "should include #{attr}" do
|
19
|
+
apod_hash.keys.should include attr
|
20
|
+
end
|
21
|
+
it {apod_hash[attr].should_not be_nil}
|
22
|
+
it {apod_hash[attr].should be_a(String)}
|
23
|
+
|
24
|
+
end
|
25
|
+
|
26
|
+
end
|
27
|
+
|
28
|
+
end
|
29
|
+
|
30
|
+
end
|