ensnare_bnb 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/.gitignore +14 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +50 -0
- data/Rakefile +2 -0
- data/ensnare_bnb.gemspec +25 -0
- data/lib/ensnare_bnb.rb +70 -0
- data/lib/ensnare_bnb/version.rb +3 -0
- metadata +108 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: a7c0c802c6a7214b4fdf229a8df7407df737da68
|
4
|
+
data.tar.gz: 2d3d37830b72d88344e9e715e9929d089318cfa8
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 561524da36102926629c5dbd22bb866e79cf359953b62dd00ad01c7196ffc239116d7900bf30f954cf6509c544dc961f15078d1f6a7cf46d76a26e871f8dd241
|
7
|
+
data.tar.gz: 5e4b120db19853d0e5f90ba55cb568f28b7f96280044b8fe3010cc21089a89df9d8ae1815fc89085f1eebc2b649de390de0bcbdf2f5e2f88c2fb7075c1f2e937
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Rob Cole
|
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 +1,50 @@
|
|
1
|
+
# EnsnareBnb
|
2
|
+
|
3
|
+
EnsnareBnb is a simple scraper designed to get listings from AirBNB in JSON
|
4
|
+
format.
|
5
|
+
|
6
|
+
## Installation
|
7
|
+
|
8
|
+
Add this line to your application's Gemfile:
|
9
|
+
|
10
|
+
```ruby
|
11
|
+
gem 'ensnare_bnb'
|
12
|
+
```
|
13
|
+
|
14
|
+
And then execute:
|
15
|
+
|
16
|
+
$ bundle
|
17
|
+
|
18
|
+
Or install it yourself as:
|
19
|
+
|
20
|
+
$ gem install ensnare_bnb
|
21
|
+
|
22
|
+
## Usage
|
23
|
+
|
24
|
+
|
25
|
+
|
26
|
+
### United States
|
27
|
+
|
28
|
+
To find a city in the US, only city and country are required. To prevent inaccurate results for common city names (for example, Dover or St. Louis), provide the state name as well.
|
29
|
+
|
30
|
+
```
|
31
|
+
EnsareBnb.find_locations(
|
32
|
+
city: 'Seattle',
|
33
|
+
state: 'WA',
|
34
|
+
country: 'United States')
|
35
|
+
```
|
36
|
+
=> Returns JSON results of all AirBNB listings found in Seattle, WA.
|
37
|
+
|
38
|
+
#### Optional Fields
|
39
|
+
:start\_date, :end\_date
|
40
|
+
:guests, :price\_min, :price\_max, :max_pages
|
41
|
+
|
42
|
+
--
|
43
|
+
|
44
|
+
### Contributing
|
45
|
+
|
46
|
+
1. Fork it ( https://github.com/[my-github-username]/ensnare_bnb/fork )
|
47
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
48
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
49
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
50
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
data/ensnare_bnb.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 'ensnare_bnb/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "ensnare_bnb"
|
8
|
+
spec.version = EnsnareBnb::VERSION
|
9
|
+
spec.authors = ["Rob Cole"]
|
10
|
+
spec.email = ["robcole@gmail.com"]
|
11
|
+
spec.summary = %q{Scrape AirBNB data and convert to JSON format.}
|
12
|
+
spec.description = %q{Scrape AirBNB data and convert to JSON format.}
|
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"
|
22
|
+
spec.add_dependency "activesupport"
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.7"
|
24
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
25
|
+
end
|
data/lib/ensnare_bnb.rb
ADDED
@@ -0,0 +1,70 @@
|
|
1
|
+
require_relative 'ensnare_bnb/version'
|
2
|
+
require 'nokogiri'
|
3
|
+
require 'json'
|
4
|
+
require 'open-uri'
|
5
|
+
require 'active_support'
|
6
|
+
require 'active_support/core_ext/hash'
|
7
|
+
|
8
|
+
module EnsnareBnb
|
9
|
+
|
10
|
+
class << self
|
11
|
+
|
12
|
+
def max_page_number(url)
|
13
|
+
# pagination-buttons-container
|
14
|
+
selector = "body > div.map-search > div.sidebar > " +
|
15
|
+
"div.search-results.panel-body > div.results-footer > " +
|
16
|
+
"div.pagination-buttons-container > div.pagination > ul > " +
|
17
|
+
"li:nth-child(5)"
|
18
|
+
Nokogiri::HTML(open(url)).css(selector).text.to_i
|
19
|
+
end
|
20
|
+
|
21
|
+
def find_airbnb_hosts(**opts)
|
22
|
+
# city, state, country
|
23
|
+
# New-York--NY--United-States
|
24
|
+
city = opts.fetch(:city)
|
25
|
+
state = opts.fetch(:state, nil)
|
26
|
+
country = opts.fetch(:country, nil)
|
27
|
+
|
28
|
+
city_query = [city, state, country].compact.map do |str|
|
29
|
+
str.gsub('-', '~').gsub(' ', '-')
|
30
|
+
end.join('--')
|
31
|
+
|
32
|
+
search_params = opts.except(:city, :state, :country, :max_pages)
|
33
|
+
query = city_query + "?" + search_params.to_query
|
34
|
+
|
35
|
+
# build intelligent options hashes/params in URLparams
|
36
|
+
|
37
|
+
base_url = "https://www.airbnb.com"
|
38
|
+
search_url = "#{base_url}/s/#{query}"
|
39
|
+
|
40
|
+
pages = opts.fetch(:max_pages, self.max_page_number(search_url))
|
41
|
+
results = []
|
42
|
+
|
43
|
+
pages.times do |pg|
|
44
|
+
url = "#{search_url}?room_types%5B%5D=Entire+home%2Fapt&page=#{pg}"
|
45
|
+
Nokogiri::HTML(open(url)).css(".target-details.block-link").each do |box|
|
46
|
+
details_url = "#{base_url}#{box["href"]}"
|
47
|
+
inner_pg_data = Nokogiri::HTML(open(details_url))
|
48
|
+
name = inner_pg_data.css('#listing_name').text.strip
|
49
|
+
price = inner_pg_data.css('#price_amount').text[/\d+/]
|
50
|
+
beds = inner_pg_data.css('#summary > div > div > div.col-8 > div > div:nth-child(2) > div.col-9 > div > div:nth-child(4)').text[/\d+/]
|
51
|
+
bedrooms = inner_pg_data.css('#summary > div > div > div.col-8 > div > div:nth-child(2) > div.col-9 > div > div:nth-child(3)').text[/\d+/]
|
52
|
+
capacity = inner_pg_data.css('#summary > div > div > div.col-8 > div > div:nth-child(2) > div.col-9 > div > div:nth-child(2)').text[/\d+/]
|
53
|
+
output = {
|
54
|
+
city: city,
|
55
|
+
name: name,
|
56
|
+
price: price.to_i,
|
57
|
+
bedrooms: bedrooms.to_i,
|
58
|
+
beds: beds.to_i,
|
59
|
+
capacity: capacity.to_i
|
60
|
+
}.to_json
|
61
|
+
|
62
|
+
results << output
|
63
|
+
end
|
64
|
+
end
|
65
|
+
results
|
66
|
+
end
|
67
|
+
|
68
|
+
end
|
69
|
+
|
70
|
+
end
|
metadata
ADDED
@@ -0,0 +1,108 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: ensnare_bnb
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Rob Cole
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-10-26 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: nokogiri
|
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: activesupport
|
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: bundler
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.7'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.7'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rake
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '10.0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '10.0'
|
69
|
+
description: Scrape AirBNB data and convert to JSON format.
|
70
|
+
email:
|
71
|
+
- robcole@gmail.com
|
72
|
+
executables: []
|
73
|
+
extensions: []
|
74
|
+
extra_rdoc_files: []
|
75
|
+
files:
|
76
|
+
- ".gitignore"
|
77
|
+
- Gemfile
|
78
|
+
- LICENSE.txt
|
79
|
+
- README.md
|
80
|
+
- Rakefile
|
81
|
+
- ensnare_bnb.gemspec
|
82
|
+
- lib/ensnare_bnb.rb
|
83
|
+
- lib/ensnare_bnb/version.rb
|
84
|
+
homepage: ''
|
85
|
+
licenses:
|
86
|
+
- MIT
|
87
|
+
metadata: {}
|
88
|
+
post_install_message:
|
89
|
+
rdoc_options: []
|
90
|
+
require_paths:
|
91
|
+
- lib
|
92
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
98
|
+
requirements:
|
99
|
+
- - ">="
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: '0'
|
102
|
+
requirements: []
|
103
|
+
rubyforge_project:
|
104
|
+
rubygems_version: 2.2.2
|
105
|
+
signing_key:
|
106
|
+
specification_version: 4
|
107
|
+
summary: Scrape AirBNB data and convert to JSON format.
|
108
|
+
test_files: []
|