guitsaru-scraper 0.2.0 → 0.2.1
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/VERSION +1 -1
- data/lib/scraper/link.rb +5 -1
- data/scraper.gemspec +1 -1
- data/test/test_helper.rb +1 -0
- data/test/test_scraper.rb +24 -0
- metadata +1 -1
data/VERSION
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
0.2.
|
|
1
|
+
0.2.1
|
data/lib/scraper/link.rb
CHANGED
|
@@ -54,7 +54,11 @@ module Scrape
|
|
|
54
54
|
elsif url =~ /^#/
|
|
55
55
|
url = @url.gsub(/#.*/, '').gsub(/\/$/, '') + url
|
|
56
56
|
else
|
|
57
|
-
|
|
57
|
+
if @url =~ /\/$/
|
|
58
|
+
url = @url + (url || '')
|
|
59
|
+
else
|
|
60
|
+
url = (File.dirname(@url) + '/' + (url || ''))
|
|
61
|
+
end
|
|
58
62
|
end
|
|
59
63
|
|
|
60
64
|
# Don't add this link if it matches a pattern in ignore
|
data/scraper.gemspec
CHANGED
data/test/test_helper.rb
CHANGED
|
@@ -9,6 +9,7 @@ require 'scraper'
|
|
|
9
9
|
|
|
10
10
|
class Test::Unit::TestCase
|
|
11
11
|
FakeWeb.register_uri(:get, "http://example.com/main.html", :body => File.join(File.dirname(__FILE__), 'fake_pages/main.html'))
|
|
12
|
+
FakeWeb.register_uri(:get, "http://example.com/folder/", :body => File.join(File.dirname(__FILE__), 'fake_pages/main.html'))
|
|
12
13
|
FakeWeb.register_uri(:get, "http://example.com/first_page.html", :body => File.join(File.dirname(__FILE__), 'fake_pages/first_page.html'))
|
|
13
14
|
FakeWeb.register_uri(:get, "http://example.com/first_child_page.html", :body => File.join(File.dirname(__FILE__), 'fake_pages/first_child_page.html'))
|
|
14
15
|
FakeWeb.register_uri(:get, "http://example.com/not_added.html", :body => File.join(File.dirname(__FILE__), 'fake_pages/not_added.html'))
|
data/test/test_scraper.rb
CHANGED
|
@@ -14,6 +14,30 @@ class TestScraper < Test::Unit::TestCase
|
|
|
14
14
|
end
|
|
15
15
|
|
|
16
16
|
context "scraping" do
|
|
17
|
+
setup do
|
|
18
|
+
@scraper = Scraper.new('http://example.com/main.html', :recursive => false)
|
|
19
|
+
@results = @scraper.scrape
|
|
20
|
+
end
|
|
21
|
+
|
|
22
|
+
should "Include a list of links on the pages." do
|
|
23
|
+
assert(@results.include?(Link.new('http://example.com/first_page.html')))
|
|
24
|
+
assert(@results.include?(Link.new('http://example.com/not_added.html')))
|
|
25
|
+
end
|
|
26
|
+
end
|
|
27
|
+
|
|
28
|
+
context "scraping from folder" do
|
|
29
|
+
setup do
|
|
30
|
+
@scraper = Scraper.new('http://example.com/folder/', :recursive => false)
|
|
31
|
+
@results = @scraper.scrape
|
|
32
|
+
end
|
|
33
|
+
|
|
34
|
+
should "Include a list of links on the pages." do
|
|
35
|
+
assert(@results.include?(Link.new('http://example.com/folder/first_page.html')))
|
|
36
|
+
assert(@results.include?(Link.new('http://example.com/folder/not_added.html')))
|
|
37
|
+
end
|
|
38
|
+
end
|
|
39
|
+
|
|
40
|
+
context "scraping with div" do
|
|
17
41
|
setup do
|
|
18
42
|
@scraper = Scraper.new('http://example.com/main.html')
|
|
19
43
|
@results = @scraper.scrape(:div => '#content')
|