pet_rescue-scraper 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +14 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +31 -0
- data/Rakefile +6 -0
- data/lib/pet_rescue/listing_page.rb +18 -0
- data/lib/pet_rescue/listing_page_parser.rb +106 -0
- data/lib/pet_rescue/pet.rb +26 -0
- data/lib/pet_rescue/scraper/version.rb +5 -0
- data/lib/pet_rescue/scraper.rb +33 -0
- data/lib/pet_rescue/search_results_page.rb +46 -0
- data/pet_rescue-scraper.gemspec +30 -0
- data/spec/fixtures/dog_search_first_page.html +1492 -0
- data/spec/fixtures/dog_search_last_page.html +742 -0
- data/spec/fixtures/mau.html +354 -0
- data/spec/fixtures/muttley.html +402 -0
- data/spec/fixtures/vcr_cassettes/dogs.yml +3743 -0
- data/spec/fixtures/wyatt.html +375 -0
- data/spec/pet_rescue/listing_page_parser_spec.rb +140 -0
- data/spec/pet_rescue/listing_page_spec.rb +20 -0
- data/spec/pet_rescue/scraper_spec.rb +15 -0
- data/spec/pet_rescue/search_results_page_spec.rb +32 -0
- data/spec/spec_helper.rb +19 -0
- data/spec/support/vcr.rb +7 -0
- metadata +192 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: e0869a2e7eca1d31e68d6b428c5c470a94c73958
|
4
|
+
data.tar.gz: 7ac8ef13bcdde87b2cd716ab7bf8e3e9835e5429
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 0be3f54185d3d0d4fb90aef48ac500be43ea1bf94705350c1998ddb49751e620f1a0470671b09c3bb80fcc85cbf22407009b69daec8c7dd648ae7545ebf6efe5
|
7
|
+
data.tar.gz: d059b42dd88c4d0aab3d00313af90d08eed1346088f218246fb29119f50febbe96411da22216b69dde0cd8c389543264fd9abc73e7b77057c2804c87bec2def7
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Alex Smith
|
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 +1,31 @@
|
|
1
|
+
# PetRescue::Scraper
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'pet_rescue-scraper'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install pet_rescue-scraper
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
TODO: Write usage instructions here
|
24
|
+
|
25
|
+
## Contributing
|
26
|
+
|
27
|
+
1. Fork it ( https://github.com/[my-github-username]/pet_rescue-scraper/fork )
|
28
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
29
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
30
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
31
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,18 @@
|
|
1
|
+
require 'open-uri'
|
2
|
+
|
3
|
+
module PetRescue
|
4
|
+
# A listing page on petrescue.com.au
|
5
|
+
class ListingPage
|
6
|
+
attr_reader :id
|
7
|
+
|
8
|
+
def initialize(id, parser)
|
9
|
+
@id = id
|
10
|
+
@url = "http://www.petrescue.com.au/listings/#{@id}"
|
11
|
+
@parser = parser
|
12
|
+
end
|
13
|
+
|
14
|
+
def pet
|
15
|
+
@parser.parse(open(@url))
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
@@ -0,0 +1,106 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
require 'pet_rescue/pet'
|
3
|
+
|
4
|
+
module PetRescue
|
5
|
+
# Parses an HTML listing page from petrescue.com.au
|
6
|
+
class ListingPageParser
|
7
|
+
def parse(document)
|
8
|
+
@document = Nokogiri::HTML(document)
|
9
|
+
|
10
|
+
Pet.new(name: pet_name,
|
11
|
+
size: pet_size,
|
12
|
+
gender: pet_gender,
|
13
|
+
breed: pet_breed,
|
14
|
+
age: pet_age,
|
15
|
+
location: pet_location,
|
16
|
+
vaccinated: pet_vaccinated?,
|
17
|
+
desexed: pet_desexed?,
|
18
|
+
biography: pet_biography,
|
19
|
+
rescue_group: pet_rescue_group,
|
20
|
+
small_photo_url: pet_small_photo_url,
|
21
|
+
large_photo_url: pet_large_photo_url,
|
22
|
+
adoption_fee: pet_adoption_fee,
|
23
|
+
adoption_process: pet_adoption_process,
|
24
|
+
contact_name: pet_contact_name,
|
25
|
+
contact_number: pet_contact_number)
|
26
|
+
end
|
27
|
+
|
28
|
+
def pet_name
|
29
|
+
@document.at_css("#main h1").text.strip
|
30
|
+
end
|
31
|
+
|
32
|
+
def pet_size
|
33
|
+
species.split(" ")[0]
|
34
|
+
end
|
35
|
+
|
36
|
+
def pet_gender
|
37
|
+
species.split(" ")[1]
|
38
|
+
end
|
39
|
+
|
40
|
+
def pet_breed
|
41
|
+
species.split(" ").drop(2).join(" ")
|
42
|
+
end
|
43
|
+
|
44
|
+
def pet_age
|
45
|
+
@document.at_css("dd.age").text.strip
|
46
|
+
end
|
47
|
+
|
48
|
+
def pet_location
|
49
|
+
@document.at_css(".located_in").text.strip.gsub("Located in ", "").strip
|
50
|
+
end
|
51
|
+
|
52
|
+
def pet_vaccinated?
|
53
|
+
@document.at_css("dd.vaccinated").text.strip == "Yes"
|
54
|
+
end
|
55
|
+
|
56
|
+
def pet_desexed?
|
57
|
+
@document.at_css("dd.desexed").text.strip == "Yes"
|
58
|
+
end
|
59
|
+
|
60
|
+
def pet_biography
|
61
|
+
@document.at_css(".personality").text.strip
|
62
|
+
end
|
63
|
+
|
64
|
+
def pet_adoption_fee
|
65
|
+
@document.at_css("dd.adoption_fee").text.strip.gsub("$", "").to_i
|
66
|
+
end
|
67
|
+
|
68
|
+
def pet_adoption_process
|
69
|
+
node = @document.at_css(".adoption_process")
|
70
|
+
node && node.text.strip
|
71
|
+
end
|
72
|
+
|
73
|
+
def pet_rescue_group
|
74
|
+
@document.at_css("dd.fostered_by").text.strip
|
75
|
+
end
|
76
|
+
|
77
|
+
def pet_contact_name
|
78
|
+
node = @document.at_css("dd.contact_name")
|
79
|
+
node && node.text.strip
|
80
|
+
end
|
81
|
+
|
82
|
+
def pet_contact_number
|
83
|
+
node = @document.at_css("dt.contact_number")
|
84
|
+
node &&= node.next_element.children.first
|
85
|
+
node && node.text.strip
|
86
|
+
end
|
87
|
+
|
88
|
+
def pet_small_photo_url
|
89
|
+
photo_node && photo_node.at_css("img").attributes["src"].value
|
90
|
+
end
|
91
|
+
|
92
|
+
def pet_large_photo_url
|
93
|
+
photo_node && photo_node.at_css("a").attributes["href"].value
|
94
|
+
end
|
95
|
+
|
96
|
+
private
|
97
|
+
|
98
|
+
def photo_node
|
99
|
+
@document.at_css("#featured_photo")
|
100
|
+
end
|
101
|
+
|
102
|
+
def species
|
103
|
+
@document.at_css(".species").text.strip
|
104
|
+
end
|
105
|
+
end
|
106
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
require 'virtus'
|
2
|
+
|
3
|
+
module PetRescue
|
4
|
+
# Model for a pet on petrescue.com.au
|
5
|
+
class Pet
|
6
|
+
include Virtus.model
|
7
|
+
|
8
|
+
attribute :id, String
|
9
|
+
attribute :name, String
|
10
|
+
attribute :size, String
|
11
|
+
attribute :gender, String
|
12
|
+
attribute :breed, String
|
13
|
+
attribute :age, String
|
14
|
+
attribute :location, String
|
15
|
+
attribute :vaccinated, Boolean
|
16
|
+
attribute :desexed, Boolean
|
17
|
+
attribute :biography, String
|
18
|
+
attribute :adoption_fee, Integer
|
19
|
+
attribute :adoption_process, String
|
20
|
+
attribute :rescue_group, String
|
21
|
+
attribute :contact_name , String
|
22
|
+
attribute :contact_number, String
|
23
|
+
attribute :small_photo_url, String
|
24
|
+
attribute :large_photo_url, String
|
25
|
+
end
|
26
|
+
end
|
@@ -0,0 +1,33 @@
|
|
1
|
+
require 'pet_rescue/scraper/version'
|
2
|
+
require 'pet_rescue/search_results_page'
|
3
|
+
|
4
|
+
module PetRescue
|
5
|
+
module Scraper
|
6
|
+
# A collection of dog listings on petrescue.com.au
|
7
|
+
class DogListings
|
8
|
+
include Enumerable
|
9
|
+
|
10
|
+
def initialize(per_page: 48)
|
11
|
+
@per_page = per_page
|
12
|
+
end
|
13
|
+
|
14
|
+
def each(&block)
|
15
|
+
search_page = SearchResultsPage.from_url(first_page_url)
|
16
|
+
|
17
|
+
loop do
|
18
|
+
search_page.listing_pages.each(&block)
|
19
|
+
|
20
|
+
break unless search_page.has_next_page?
|
21
|
+
|
22
|
+
search_page = search_page.next_page
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
private
|
27
|
+
|
28
|
+
def first_page_url
|
29
|
+
"http://www.petrescue.com.au/listings/dogs?per_page=#{@per_page}&page=1"
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end
|
@@ -0,0 +1,46 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
require 'open-uri'
|
3
|
+
require 'pet_rescue/listing_page'
|
4
|
+
require 'pet_rescue/listing_page_parser'
|
5
|
+
|
6
|
+
module PetRescue
|
7
|
+
# A page of search results on petrescue.com.au
|
8
|
+
class SearchResultsPage
|
9
|
+
def self.from_url(url)
|
10
|
+
SearchResultsPage.new(open(url))
|
11
|
+
end
|
12
|
+
|
13
|
+
def initialize(document)
|
14
|
+
@document = Nokogiri::HTML(document)
|
15
|
+
end
|
16
|
+
|
17
|
+
def listing_pages
|
18
|
+
listing_ids.map do |id|
|
19
|
+
parser = PetRescue::ListingPageParser.new
|
20
|
+
ListingPage.new(id, parser)
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
def has_next_page?
|
25
|
+
!!next_page_href
|
26
|
+
end
|
27
|
+
|
28
|
+
def next_page
|
29
|
+
url = "http://www.petrescue.com.au#{next_page_href}"
|
30
|
+
SearchResultsPage.from_url(url)
|
31
|
+
end
|
32
|
+
|
33
|
+
private
|
34
|
+
|
35
|
+
def next_page_href
|
36
|
+
node = @document.at_css(".next a")
|
37
|
+
node && node[:href]
|
38
|
+
end
|
39
|
+
|
40
|
+
def listing_ids
|
41
|
+
@document
|
42
|
+
.css(".listing .name a")
|
43
|
+
.map { |node| Integer(node[:href].to_s.gsub("/listings/", "")) }
|
44
|
+
end
|
45
|
+
end
|
46
|
+
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'pet_rescue/scraper/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "pet_rescue-scraper"
|
8
|
+
spec.version = PetRescue::Scraper::VERSION
|
9
|
+
spec.authors = ["Alex Smith"]
|
10
|
+
spec.email = ["alex@thatalexguy.com"]
|
11
|
+
spec.summary = %q{Scraper for petrescue.com.au}
|
12
|
+
spec.description = %q{Allows scraping of pet listings from petrescue.com.au}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
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 "nokogiri", "~> 1.6.3.1"
|
22
|
+
spec.add_dependency "virtus", "~> 1.0.3"
|
23
|
+
|
24
|
+
spec.add_development_dependency "bundler", "~> 1.7"
|
25
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
26
|
+
spec.add_development_dependency "rspec", "~> 3.1.0"
|
27
|
+
spec.add_development_dependency "vcr", "~> 2.9.3"
|
28
|
+
spec.add_development_dependency "webmock", "~> 1.19.0"
|
29
|
+
spec.add_development_dependency "simplecov", "~> 0.9.1"
|
30
|
+
end
|