gscraper 0.1.5 → 0.1.6
Sign up to get free protection for your applications and to get access to all the features.
- data/History.txt +33 -21
- data/Manifest.txt +3 -0
- data/README.txt +107 -4
- data/lib/gscraper/gscraper.rb +92 -21
- data/lib/gscraper/licenses.rb +27 -4
- data/lib/gscraper/search/page.rb +9 -11
- data/lib/gscraper/search/query.rb +142 -104
- data/lib/gscraper/search/result.rb +13 -12
- data/lib/gscraper/search/search.rb +3 -3
- data/lib/gscraper/sponsored_ad.rb +35 -0
- data/lib/gscraper/sponsored_links.rb +151 -0
- data/lib/gscraper/version.rb +1 -1
- data/lib/gscraper/web_agent.rb +38 -0
- data/test/search/query_result.rb +1 -1
- data/test/test_gscraper.rb +1 -4
- metadata +73 -63
@@ -1,7 +1,12 @@
|
|
1
|
+
require 'gscraper/search/query'
|
2
|
+
require 'gscraper/web_agent'
|
3
|
+
|
1
4
|
module GScraper
|
2
5
|
module Search
|
3
6
|
class Result
|
4
7
|
|
8
|
+
include WebAgent
|
9
|
+
|
5
10
|
# Rank of the result page
|
6
11
|
attr_reader :rank
|
7
12
|
|
@@ -33,18 +38,6 @@ module GScraper
|
|
33
38
|
@similar_url = similar_url
|
34
39
|
end
|
35
40
|
|
36
|
-
#
|
37
|
-
# Opens the URL of the cached page for the Result. If _opts_ are
|
38
|
-
# given, they will be used in accessing the cached page URL.
|
39
|
-
#
|
40
|
-
# result.cached_page # => File
|
41
|
-
#
|
42
|
-
def cached_page(opts={})
|
43
|
-
if @cached_url
|
44
|
-
return GScraper.open(@cached_url,opts)
|
45
|
-
end
|
46
|
-
end
|
47
|
-
|
48
41
|
#
|
49
42
|
# Create a new Query for results that are similar to the Result. If
|
50
43
|
# a _block_ is given, it will be passed the newly created Query
|
@@ -64,6 +57,14 @@ module GScraper
|
|
64
57
|
end
|
65
58
|
end
|
66
59
|
|
60
|
+
#
|
61
|
+
# Fetches the cached page of the result. If a _block_ is given it will
|
62
|
+
# be passed the cached page.
|
63
|
+
#
|
64
|
+
def cached_page(&block)
|
65
|
+
get_page(@cached_url,&block)
|
66
|
+
end
|
67
|
+
|
67
68
|
#
|
68
69
|
# Returns a string containing the result's title.
|
69
70
|
#
|
@@ -3,7 +3,7 @@ require 'gscraper/search/query'
|
|
3
3
|
module GScraper
|
4
4
|
module Search
|
5
5
|
#
|
6
|
-
# Returns a new Query object with the given
|
6
|
+
# Returns a new Query object with the given _options_. See Query.new.
|
7
7
|
#
|
8
8
|
# Search.query(:query => 'ruby', :with_words => 'sow rspec')
|
9
9
|
#
|
@@ -11,8 +11,8 @@ module GScraper
|
|
11
11
|
# q.within_past_week = true
|
12
12
|
# end
|
13
13
|
#
|
14
|
-
def Search.query(
|
15
|
-
Query.new(
|
14
|
+
def Search.query(options={},&block)
|
15
|
+
Query.new(options,&block)
|
16
16
|
end
|
17
17
|
|
18
18
|
#
|
@@ -0,0 +1,35 @@
|
|
1
|
+
require 'gscraper/extensions/uri'
|
2
|
+
|
3
|
+
module GScraper
|
4
|
+
class SponsoredAd
|
5
|
+
|
6
|
+
# Title of the ad
|
7
|
+
attr_reader :title
|
8
|
+
|
9
|
+
# URL of the ad
|
10
|
+
attr_reader :url
|
11
|
+
|
12
|
+
#
|
13
|
+
# Creates a new SponsoredAd with the specified _title_ and _url_.
|
14
|
+
#
|
15
|
+
def initialize(title,url)
|
16
|
+
@title = title
|
17
|
+
@url = URI.parse(url)
|
18
|
+
end
|
19
|
+
|
20
|
+
#
|
21
|
+
# Returns the direct URL of the ad.
|
22
|
+
#
|
23
|
+
def direct_url
|
24
|
+
@url.query_params['adurl'] || @url.query_params['q']
|
25
|
+
end
|
26
|
+
|
27
|
+
#
|
28
|
+
# Returns the title of the ad.
|
29
|
+
#
|
30
|
+
def to_s
|
31
|
+
@title.to_s
|
32
|
+
end
|
33
|
+
|
34
|
+
end
|
35
|
+
end
|
@@ -0,0 +1,151 @@
|
|
1
|
+
require 'gscraper/sponsored_ad'
|
2
|
+
|
3
|
+
module GScraper
|
4
|
+
class SponsoredLinks < Array
|
5
|
+
#
|
6
|
+
# Creates a new SponsoredLinks object with the given _ads_.
|
7
|
+
#
|
8
|
+
def initialize(ads=[])
|
9
|
+
super(ads)
|
10
|
+
end
|
11
|
+
|
12
|
+
#
|
13
|
+
# Returns a mapped Array of the ads within the SponsoredLinks
|
14
|
+
# using the given _block_. If the _block_ is not given, the
|
15
|
+
# SponsoredLinks will be returned.
|
16
|
+
#
|
17
|
+
# sponsored.map # => SponsoredLinks
|
18
|
+
#
|
19
|
+
# sponsored.map { |ad| ad.url } # => [...]
|
20
|
+
#
|
21
|
+
def map(&block)
|
22
|
+
return self unless block
|
23
|
+
|
24
|
+
mapped = []
|
25
|
+
|
26
|
+
each { |ad| mapped << block.call(ad) }
|
27
|
+
return mapped
|
28
|
+
end
|
29
|
+
|
30
|
+
#
|
31
|
+
# Selects the ads within the SponsoredLinks which match the given _block_.
|
32
|
+
#
|
33
|
+
# sponsored.select { |ad| ad.title =~ /consume/i }
|
34
|
+
#
|
35
|
+
def select(&block)
|
36
|
+
SponsoredLinks.new(super(&block))
|
37
|
+
end
|
38
|
+
|
39
|
+
#
|
40
|
+
# Selects the ads using the specified _block_.
|
41
|
+
#
|
42
|
+
# sponsored.ads_with { |ad| ad.title =~ /status symbol/ }
|
43
|
+
#
|
44
|
+
def ads_with(&block)
|
45
|
+
select(&block)
|
46
|
+
end
|
47
|
+
|
48
|
+
#
|
49
|
+
# Selects the ads with the matching _title_. The _title_ may be
|
50
|
+
# either a String or a Regexp. If _block_ is given, each matching
|
51
|
+
# ad will be passed to the _block_.
|
52
|
+
#
|
53
|
+
# sponsored.ads_with_title('be attractive') #=> SponsoredLinks
|
54
|
+
#
|
55
|
+
# sponsored.ads_with_title(/buy me/) do |ad|
|
56
|
+
# puts ad.url
|
57
|
+
# end
|
58
|
+
#
|
59
|
+
def ads_with_title(title,&block)
|
60
|
+
if title.kind_of?(Regexp)
|
61
|
+
ads = ads_with { |ad| ad.title =~ title }
|
62
|
+
else
|
63
|
+
ads = ads_with { |ad| ad.title == title }
|
64
|
+
end
|
65
|
+
|
66
|
+
ads.each(&block) if block
|
67
|
+
return ads
|
68
|
+
end
|
69
|
+
|
70
|
+
#
|
71
|
+
# Selects the ads with the matching _url_. The _url_ may be
|
72
|
+
# either a String or a Regexp. If _block_ is given, each matching
|
73
|
+
# ad will be passed to the _block_.
|
74
|
+
#
|
75
|
+
# sponsored.ads_with_url(/\.com/) # => SponsoredLinks
|
76
|
+
#
|
77
|
+
# sponsored.ads_with_url(/^https:\/\//) do |ad|
|
78
|
+
# puts ad.title
|
79
|
+
# end
|
80
|
+
#
|
81
|
+
def ads_with_url(url,&block)
|
82
|
+
if url.kind_of?(Regexp)
|
83
|
+
ads = ads_with { |ad| ad.url =~ url }
|
84
|
+
else
|
85
|
+
ads = ads_with { |ad| ad.url == url }
|
86
|
+
end
|
87
|
+
|
88
|
+
ads.each(&block) if block
|
89
|
+
return ads
|
90
|
+
end
|
91
|
+
|
92
|
+
#
|
93
|
+
# Returns an Array containing the titles of the ads within the
|
94
|
+
# SponsoredLinks.
|
95
|
+
#
|
96
|
+
# sponsored.titles # => [...]
|
97
|
+
#
|
98
|
+
def titles
|
99
|
+
map { |ad| ad.title }
|
100
|
+
end
|
101
|
+
|
102
|
+
#
|
103
|
+
# Returns an Array containing the URLs of the ads within the
|
104
|
+
# SponsoredLinks.
|
105
|
+
#
|
106
|
+
# sponsored.urls # => [...]
|
107
|
+
#
|
108
|
+
def urls
|
109
|
+
map { |ad| ad.url }
|
110
|
+
end
|
111
|
+
|
112
|
+
#
|
113
|
+
# Iterates over each ad's title within the SponsoredLinks, passing each to
|
114
|
+
# the given _block_.
|
115
|
+
#
|
116
|
+
# each_title { |title| puts title }
|
117
|
+
#
|
118
|
+
def each_title(&block)
|
119
|
+
titles.each(&block)
|
120
|
+
end
|
121
|
+
|
122
|
+
#
|
123
|
+
# Iterates over each ad's url within the SponsoredLinks, passing each to
|
124
|
+
# the given _block_.
|
125
|
+
#
|
126
|
+
# each_url { |url| puts url }
|
127
|
+
#
|
128
|
+
def each_url(&block)
|
129
|
+
urls.each(&block)
|
130
|
+
end
|
131
|
+
|
132
|
+
#
|
133
|
+
# Returns the titles of the ads that match the specified _block_.
|
134
|
+
#
|
135
|
+
# sponsored.titles_of { |ad| ad.url.include?('www') }
|
136
|
+
#
|
137
|
+
def titles_of(&block)
|
138
|
+
ads_with(&block).titles
|
139
|
+
end
|
140
|
+
|
141
|
+
#
|
142
|
+
# Returns the urls of the ads that match the specified _block_.
|
143
|
+
#
|
144
|
+
# sponsored.urls_of { |ad| ad.title =~ /buy these pants/ }
|
145
|
+
#
|
146
|
+
def urls_of(&block)
|
147
|
+
ads_with(&block).urls
|
148
|
+
end
|
149
|
+
|
150
|
+
end
|
151
|
+
end
|
data/lib/gscraper/version.rb
CHANGED
@@ -0,0 +1,38 @@
|
|
1
|
+
require 'gscraper/gscraper'
|
2
|
+
|
3
|
+
module GScraper
|
4
|
+
module WebAgent
|
5
|
+
protected
|
6
|
+
|
7
|
+
#
|
8
|
+
# Returns the WWW::Mechanize agent.
|
9
|
+
#
|
10
|
+
def web_agent(&block)
|
11
|
+
@web_agent ||= GScraper.web_agent
|
12
|
+
|
13
|
+
block.call(@web_agent) if block
|
14
|
+
return @web_agent
|
15
|
+
end
|
16
|
+
|
17
|
+
#
|
18
|
+
# Fetches the specified _url_, with the given _referer_ using the
|
19
|
+
# web_agent.
|
20
|
+
#
|
21
|
+
# get_page('http://www.hackety.org/')
|
22
|
+
#
|
23
|
+
def get_page(url,referer=nil,&block)
|
24
|
+
web_agent.get(url,referer,&block)
|
25
|
+
end
|
26
|
+
|
27
|
+
#
|
28
|
+
# Posts the specified _url_ and the given _query_ parameters using the
|
29
|
+
# web_agent.
|
30
|
+
#
|
31
|
+
# post_page('http://www.wired.com/', :q => 'the future')
|
32
|
+
#
|
33
|
+
def post_page(url,query={})
|
34
|
+
web_agent.post(url,query)
|
35
|
+
end
|
36
|
+
|
37
|
+
end
|
38
|
+
end
|
data/test/search/query_result.rb
CHANGED
@@ -10,7 +10,7 @@ class QueryResult < Test::Unit::TestCase
|
|
10
10
|
end
|
11
11
|
|
12
12
|
def test_first_result
|
13
|
-
result = @query.
|
13
|
+
result = @query.top_result
|
14
14
|
|
15
15
|
assert_not_nil result, "The Query for 'ruby' has no first-result"
|
16
16
|
assert_equal result.rank, 1, "The first result for the Query 'ruby' does not have the rank of 1"
|
data/test/test_gscraper.rb
CHANGED
metadata
CHANGED
@@ -1,33 +1,55 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
|
-
rubygems_version: 0.9.4
|
3
|
-
specification_version: 1
|
4
2
|
name: gscraper
|
5
3
|
version: !ruby/object:Gem::Version
|
6
|
-
version: 0.1.
|
7
|
-
date: 2007-12-29 00:00:00 -08:00
|
8
|
-
summary: A ruby web-scraping interface to various Google Services
|
9
|
-
require_paths:
|
10
|
-
- lib
|
11
|
-
email: postmodern.mod3@gmail.com
|
12
|
-
homepage: " by Postmodern Modulus III"
|
13
|
-
rubyforge_project: gscraper
|
14
|
-
description: "== FEATURES/PROBLEMS: * Supports the Google Search service. * Provides HTTP access with custom User-Agent strings. == REQUIREMENTS: * Hpricot * Mechanize == INSTALL:"
|
15
|
-
autorequire:
|
16
|
-
default_executable:
|
17
|
-
bindir: bin
|
18
|
-
has_rdoc: true
|
19
|
-
required_ruby_version: !ruby/object:Gem::Version::Requirement
|
20
|
-
requirements:
|
21
|
-
- - ">"
|
22
|
-
- !ruby/object:Gem::Version
|
23
|
-
version: 0.0.0
|
24
|
-
version:
|
4
|
+
version: 0.1.6
|
25
5
|
platform: ruby
|
26
|
-
signing_key:
|
27
|
-
cert_chain:
|
28
|
-
post_install_message:
|
29
6
|
authors:
|
30
7
|
- Postmodern Modulus III
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2008-03-15 00:00:00 -07:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: hpricot
|
17
|
+
version_requirement:
|
18
|
+
version_requirements: !ruby/object:Gem::Requirement
|
19
|
+
requirements:
|
20
|
+
- - ">="
|
21
|
+
- !ruby/object:Gem::Version
|
22
|
+
version: "0"
|
23
|
+
version:
|
24
|
+
- !ruby/object:Gem::Dependency
|
25
|
+
name: mechanize
|
26
|
+
version_requirement:
|
27
|
+
version_requirements: !ruby/object:Gem::Requirement
|
28
|
+
requirements:
|
29
|
+
- - ">="
|
30
|
+
- !ruby/object:Gem::Version
|
31
|
+
version: "0"
|
32
|
+
version:
|
33
|
+
- !ruby/object:Gem::Dependency
|
34
|
+
name: hoe
|
35
|
+
version_requirement:
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 1.5.1
|
41
|
+
version:
|
42
|
+
description: "== FEATURES/PROBLEMS: * Supports the Google Search service. * Provides access to search results and ranks. * Provides access to the Sponsored Links. * Provides HTTP access with custom User-Agent strings. * Provides proxy settings for HTTP access. == REQUIREMENTS: * Hpricot * WWW::Mechanize == INSTALL:"
|
43
|
+
email: postmodern.mod3@gmail.com
|
44
|
+
executables: []
|
45
|
+
|
46
|
+
extensions: []
|
47
|
+
|
48
|
+
extra_rdoc_files:
|
49
|
+
- History.txt
|
50
|
+
- LICENSE.txt
|
51
|
+
- Manifest.txt
|
52
|
+
- README.txt
|
31
53
|
files:
|
32
54
|
- History.txt
|
33
55
|
- LICENSE.txt
|
@@ -37,10 +59,13 @@ files:
|
|
37
59
|
- lib/gscraper.rb
|
38
60
|
- lib/gscraper/version.rb
|
39
61
|
- lib/gscraper/gscraper.rb
|
62
|
+
- lib/gscraper/web_agent.rb
|
40
63
|
- lib/gscraper/extensions/uri/http.rb
|
41
64
|
- lib/gscraper/extensions/uri.rb
|
42
65
|
- lib/gscraper/extensions.rb
|
43
66
|
- lib/gscraper/licenses.rb
|
67
|
+
- lib/gscraper/sponsored_ad.rb
|
68
|
+
- lib/gscraper/sponsored_links.rb
|
44
69
|
- lib/gscraper/search/result.rb
|
45
70
|
- lib/gscraper/search/page.rb
|
46
71
|
- lib/gscraper/search/query.rb
|
@@ -51,47 +76,32 @@ files:
|
|
51
76
|
- test/search/query_result.rb
|
52
77
|
- test/search/query_pages.rb
|
53
78
|
- test/search/page_results.rb
|
54
|
-
|
55
|
-
|
79
|
+
has_rdoc: true
|
80
|
+
homepage: " by Postmodern Modulus III"
|
81
|
+
post_install_message:
|
56
82
|
rdoc_options:
|
57
83
|
- --main
|
58
84
|
- README.txt
|
59
|
-
|
60
|
-
-
|
61
|
-
|
62
|
-
|
63
|
-
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
85
|
+
require_paths:
|
86
|
+
- lib
|
87
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
88
|
+
requirements:
|
89
|
+
- - ">="
|
90
|
+
- !ruby/object:Gem::Version
|
91
|
+
version: "0"
|
92
|
+
version:
|
93
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
94
|
+
requirements:
|
95
|
+
- - ">="
|
96
|
+
- !ruby/object:Gem::Version
|
97
|
+
version: "0"
|
98
|
+
version:
|
68
99
|
requirements: []
|
69
100
|
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
- !ruby/object:Gem::Version
|
78
|
-
version: 0.0.0
|
79
|
-
version:
|
80
|
-
- !ruby/object:Gem::Dependency
|
81
|
-
name: mechanize
|
82
|
-
version_requirement:
|
83
|
-
version_requirements: !ruby/object:Gem::Version::Requirement
|
84
|
-
requirements:
|
85
|
-
- - ">"
|
86
|
-
- !ruby/object:Gem::Version
|
87
|
-
version: 0.0.0
|
88
|
-
version:
|
89
|
-
- !ruby/object:Gem::Dependency
|
90
|
-
name: hoe
|
91
|
-
version_requirement:
|
92
|
-
version_requirements: !ruby/object:Gem::Version::Requirement
|
93
|
-
requirements:
|
94
|
-
- - ">="
|
95
|
-
- !ruby/object:Gem::Version
|
96
|
-
version: 1.4.0
|
97
|
-
version:
|
101
|
+
rubyforge_project: gscraper
|
102
|
+
rubygems_version: 1.0.1
|
103
|
+
signing_key:
|
104
|
+
specification_version: 2
|
105
|
+
summary: A ruby web-scraping interface to various Google Services
|
106
|
+
test_files:
|
107
|
+
- test/test_gscraper.rb
|