adwords_scraper 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +35 -0
- data/Rakefile +2 -0
- data/adwords_scraper.gemspec +19 -0
- data/lib/adwords_scraper.rb +92 -0
- data/lib/adwords_scraper/version.rb +3 -0
- metadata +69 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 asahi
|
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 +1,35 @@
|
|
1
|
+
# AdwordsScraper
|
2
|
+
|
3
|
+
This gem scrapes the Adwords ads from a Google search engine results page, maps
|
4
|
+
it by position and then parses the title, description, display url, redirect,
|
5
|
+
sitelinks (if any), boxed warning (for pharma ads and if applicable) as well as
|
6
|
+
reviews text (if any).
|
7
|
+
|
8
|
+
## Installation
|
9
|
+
|
10
|
+
Add this line to your application's Gemfile:
|
11
|
+
|
12
|
+
gem 'adwords_scraper'
|
13
|
+
|
14
|
+
And then execute:
|
15
|
+
|
16
|
+
$ bundle
|
17
|
+
|
18
|
+
Or install it yourself as:
|
19
|
+
|
20
|
+
$ gem install adwords_scraper
|
21
|
+
|
22
|
+
## Usage
|
23
|
+
|
24
|
+
Once installed, simply run the following (replace "green ipod" with your own
|
25
|
+
keyword text:
|
26
|
+
|
27
|
+
AdwordsScraper.start("green ipod")
|
28
|
+
|
29
|
+
## Contributing
|
30
|
+
|
31
|
+
1. Fork it
|
32
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
33
|
+
3. Commit your changes (`git commit -am 'Added some feature'`)
|
34
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
35
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/adwords_scraper/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["asahi"]
|
6
|
+
gem.email = ["sodani@gmail.com"]
|
7
|
+
gem.description = %q{Scrapes Google Adwords ads using Mechanize}
|
8
|
+
gem.summary = %q{run AdwordsScraper.start and pass a keyword string.}
|
9
|
+
gem.homepage = ""
|
10
|
+
|
11
|
+
gem.add_development_dependency "mechanize"
|
12
|
+
|
13
|
+
gem.files = `git ls-files`.split($\)
|
14
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
15
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
16
|
+
gem.name = "adwords_scraper"
|
17
|
+
gem.require_paths = ["lib"]
|
18
|
+
gem.version = AdwordsScraper::VERSION
|
19
|
+
end
|
@@ -0,0 +1,92 @@
|
|
1
|
+
require "adwords_scraper/version"
|
2
|
+
require "mechanize"
|
3
|
+
|
4
|
+
module AdwordsScraper
|
5
|
+
def self.test
|
6
|
+
"inside test"
|
7
|
+
end
|
8
|
+
|
9
|
+
def self.start(keyword)
|
10
|
+
doc = fetch_serp(keyword)
|
11
|
+
scrape_serp(doc)
|
12
|
+
|
13
|
+
end
|
14
|
+
|
15
|
+
def self.fetch_serp(keyword)
|
16
|
+
url = query_url(keyword)
|
17
|
+
|
18
|
+
agent = Mechanize.new
|
19
|
+
|
20
|
+
# It's best to mimic a common browser or else Google may not display all ad
|
21
|
+
# formats
|
22
|
+
agent.user_agent = 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.121 Safari/535.2'
|
23
|
+
agent.get url
|
24
|
+
end
|
25
|
+
|
26
|
+
def self.query_url(keyword)
|
27
|
+
'http://www.google.com/search?gcx=w&sourceid=chrome&ie=UTF-8&q='+ keyword.gsub(" ", "+")
|
28
|
+
end
|
29
|
+
|
30
|
+
def self.scrape_serp(doc)
|
31
|
+
container = {}
|
32
|
+
selectors = {}
|
33
|
+
selectors['top'] = "#tads .vsta"
|
34
|
+
selectors['right'] = "#mbEnd li" # .vsra (old)
|
35
|
+
selectors['bottom'] = "#tadsb li"
|
36
|
+
|
37
|
+
selectors.each do |location, selector|
|
38
|
+
candidate = doc.search(selector)
|
39
|
+
if !candidate.search('h3').empty? && candidate.size < 10 # two validations
|
40
|
+
container[location] = candidate
|
41
|
+
end
|
42
|
+
end
|
43
|
+
ad_container = []
|
44
|
+
|
45
|
+
container.each do |location, ad_docs|
|
46
|
+
ad_docs.each do |ad_doc|
|
47
|
+
next unless ad_doc.search('img').empty? # skipping ads that have an image attribute
|
48
|
+
begin
|
49
|
+
p = ad_doc.search('a').first['id'].match(/\d/)[0]
|
50
|
+
rescue => e
|
51
|
+
binding.pry
|
52
|
+
end
|
53
|
+
position = "#{location}:#{p}"
|
54
|
+
ad_container << [ position, parse_ad(ad_doc) ]
|
55
|
+
end
|
56
|
+
end
|
57
|
+
ad_container
|
58
|
+
end
|
59
|
+
|
60
|
+
def self.parse_ad(doc)
|
61
|
+
container = {}
|
62
|
+
|
63
|
+
desc = ''
|
64
|
+
d = doc.search('.ac').first.children
|
65
|
+
d.each do |i|
|
66
|
+
if i.name == 'br'
|
67
|
+
desc = desc + ' '
|
68
|
+
else
|
69
|
+
desc = desc + i.text
|
70
|
+
end
|
71
|
+
end
|
72
|
+
container['description'] = desc.gsub(' ', ' ')
|
73
|
+
|
74
|
+
container['title'] = doc.search('h3').text # doc title text
|
75
|
+
container['displayurl'] = doc.search('cite').text # display URL
|
76
|
+
container['boxed_warning'] = doc.search('.pwl').text # boxed warning
|
77
|
+
container['review'] = doc.search('.f div').text # supplemental text in gray
|
78
|
+
|
79
|
+
redirect = doc.at_css('a')['href'].match(/.*(https?:\/\/\S+)/)[1]
|
80
|
+
container['redirect'] = CGI.unescape(redirect) #unescape URL encoding
|
81
|
+
|
82
|
+
sitelinks = doc.search('table a')
|
83
|
+
unless sitelinks.empty?
|
84
|
+
sitelinks_array = []
|
85
|
+
sitelinks.each {|i| sitelinks_array << i.text }
|
86
|
+
container['sitelinks'] = sitelinks_array
|
87
|
+
end
|
88
|
+
|
89
|
+
container
|
90
|
+
end
|
91
|
+
|
92
|
+
end
|
metadata
ADDED
@@ -0,0 +1,69 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: adwords_scraper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- asahi
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-07-28 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: mechanize
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0'
|
30
|
+
description: Scrapes Google Adwords ads using Mechanize
|
31
|
+
email:
|
32
|
+
- sodani@gmail.com
|
33
|
+
executables: []
|
34
|
+
extensions: []
|
35
|
+
extra_rdoc_files: []
|
36
|
+
files:
|
37
|
+
- .gitignore
|
38
|
+
- Gemfile
|
39
|
+
- LICENSE
|
40
|
+
- README.md
|
41
|
+
- Rakefile
|
42
|
+
- adwords_scraper.gemspec
|
43
|
+
- lib/adwords_scraper.rb
|
44
|
+
- lib/adwords_scraper/version.rb
|
45
|
+
homepage: ''
|
46
|
+
licenses: []
|
47
|
+
post_install_message:
|
48
|
+
rdoc_options: []
|
49
|
+
require_paths:
|
50
|
+
- lib
|
51
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
52
|
+
none: false
|
53
|
+
requirements:
|
54
|
+
- - ! '>='
|
55
|
+
- !ruby/object:Gem::Version
|
56
|
+
version: '0'
|
57
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
58
|
+
none: false
|
59
|
+
requirements:
|
60
|
+
- - ! '>='
|
61
|
+
- !ruby/object:Gem::Version
|
62
|
+
version: '0'
|
63
|
+
requirements: []
|
64
|
+
rubyforge_project:
|
65
|
+
rubygems_version: 1.8.24
|
66
|
+
signing_key:
|
67
|
+
specification_version: 3
|
68
|
+
summary: run AdwordsScraper.start and pass a keyword string.
|
69
|
+
test_files: []
|