wombat 0.5.0 → 1.0.0
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.
- data/README.md +5 -1
- data/VERSION +1 -1
- data/lib/wombat/metadata.rb +3 -3
- data/lib/wombat/parser.rb +1 -1
- data/spec/crawler_spec.rb +4 -5
- data/spec/integration/integration_spec.rb +1 -1
- data/spec/parser_spec.rb +1 -1
- data/wombat.gemspec +1 -1
- metadata +1 -1
data/README.md
CHANGED
@@ -62,7 +62,7 @@ end
|
|
62
62
|
```
|
63
63
|
|
64
64
|
### This is just a sneak peek of what Wombat can do. For the complete documentation, please check the [project Wiki](http://github.com/felipecsl/wombat/wiki).
|
65
|
-
### [API Documentation](http://rubydoc.info/gems/wombat/0.
|
65
|
+
### [API Documentation](http://rubydoc.info/gems/wombat/0.5.0/frames).
|
66
66
|
|
67
67
|
|
68
68
|
## Contributing to Wombat
|
@@ -85,6 +85,10 @@ end
|
|
85
85
|
|
86
86
|
### version 1.0.0
|
87
87
|
|
88
|
+
* Breaking change: Metadata#format renamed to Metadata#document_format due to method name clash with [Kernel#format](http://www.ruby-doc.org/core-1.9.3/Kernel.html#method-i-format)
|
89
|
+
|
90
|
+
### version 0.5.0
|
91
|
+
|
88
92
|
* [Fixed a bug on malformed selectors](https://github.com/felipecsl/wombat/commit/e0f4eec20e1e2bb07a1813a1edd019933edeceaa)
|
89
93
|
* [Fixed a bug where multiple calls to #crawl would not clean up previously iterated array results and yield repeated results](https://github.com/felipecsl/wombat/commit/40b09a5bf8b9ba08aa51b6f41f706b7c3c4e4252)
|
90
94
|
|
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.
|
1
|
+
1.0.0
|
data/lib/wombat/metadata.rb
CHANGED
@@ -5,7 +5,7 @@ require 'wombat/iterator'
|
|
5
5
|
module Wombat
|
6
6
|
class Metadata < PropertyContainer
|
7
7
|
def initialize
|
8
|
-
self[:
|
8
|
+
self[:document_format] = :html
|
9
9
|
super
|
10
10
|
end
|
11
11
|
|
@@ -17,8 +17,8 @@ module Wombat
|
|
17
17
|
self[:list_page] = url
|
18
18
|
end
|
19
19
|
|
20
|
-
def
|
21
|
-
self[:
|
20
|
+
def document_format(format)
|
21
|
+
self[:document_format] = format
|
22
22
|
end
|
23
23
|
end
|
24
24
|
end
|
data/lib/wombat/parser.rb
CHANGED
data/spec/crawler_spec.rb
CHANGED
@@ -115,9 +115,9 @@ describe Wombat::Crawler do
|
|
115
115
|
|
116
116
|
it 'should assign metadata format' do
|
117
117
|
@crawler_instance.should_receive(:parse) do |arg|
|
118
|
-
arg[:
|
118
|
+
arg[:document_format].should == :xml
|
119
119
|
end
|
120
|
-
@crawler.
|
120
|
+
@crawler.document_format :xml
|
121
121
|
@crawler_instance.crawl
|
122
122
|
end
|
123
123
|
|
@@ -197,7 +197,7 @@ describe Wombat::Crawler do
|
|
197
197
|
@crawler.list_page '/portal'
|
198
198
|
|
199
199
|
@crawler.search "css=.btn-search"
|
200
|
-
@crawler.
|
200
|
+
@crawler.document_format :xml
|
201
201
|
|
202
202
|
@crawler_instance.crawl
|
203
203
|
@crawler_instance.response_code.should be(200)
|
@@ -224,12 +224,11 @@ describe Wombat::Crawler do
|
|
224
224
|
@crawler.list_page '/portal'
|
225
225
|
|
226
226
|
@crawler.search "css=.btn-search"
|
227
|
-
@crawler.
|
227
|
+
@crawler.document_format :xml
|
228
228
|
lambda { @crawler_instance.crawl }.should raise_error(RestClient::ResourceNotFound)
|
229
229
|
@crawler_instance.response_code.should be(404)
|
230
230
|
end
|
231
231
|
end
|
232
|
-
|
233
232
|
end
|
234
233
|
end
|
235
234
|
end
|
@@ -154,7 +154,7 @@ describe 'basic crawler setup' do
|
|
154
154
|
crawler = Class.new
|
155
155
|
crawler.send(:include, Wombat::Crawler)
|
156
156
|
|
157
|
-
crawler.
|
157
|
+
crawler.document_format :xml
|
158
158
|
crawler.base_url "http://ws.audioscrobbler.com"
|
159
159
|
crawler.list_page "/2.0/?method=geo.getevents&location=#{URI.escape('San Francisco')}&api_key=060decb474b73437d5bbec37f527ae7b"
|
160
160
|
|
data/spec/parser_spec.rb
CHANGED
@@ -113,7 +113,7 @@ describe Wombat::Parser do
|
|
113
113
|
it 'should correctly parse xml documents' do
|
114
114
|
fake_document = double :xml
|
115
115
|
fake_parser = double :parser
|
116
|
-
@metadata.
|
116
|
+
@metadata.document_format :xml
|
117
117
|
@parser.mechanize.should_not_receive(:get)
|
118
118
|
RestClient.should_receive(:get).and_return fake_document
|
119
119
|
Nokogiri.should_receive(:XML).with(fake_document).and_return fake_parser
|
data/wombat.gemspec
CHANGED