feedalizer 0.1.1 → 0.1.2
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG.txt +5 -9
- data/bin/feedalizer +0 -0
- data/examples/pjvault.rb +0 -1
- data/examples/sydsvenskan-nemi.rb +4 -5
- data/lib/feedalizer.rb +17 -13
- data/tests/test_feedalizer.rb +10 -4
- metadata +13 -6
data/CHANGELOG.txt
CHANGED
@@ -1,11 +1,7 @@
|
|
1
1
|
Noteworthy changes:
|
2
2
|
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
-- 2006-08-23
|
10
|
-
Added optional limit parameter to scrape_items.
|
11
|
-
Thanks to Thanh Vinh Tang for the hint that it is needed.
|
3
|
+
2006-08-23: Added optional limit parameter to scrape_items. (Thanks to Thanh Vinh Tang for the hint that it is needed.)
|
4
|
+
2006-10-11: Release of version 0.1.0.
|
5
|
+
2007-07-09: Feedalizer now uses RSS 2.0 instead of RSS 1.0.
|
6
|
+
2008-03-27: Improved examples/sydsvenskan-nemi.rb.
|
7
|
+
2008-03-27: Release of version 0.1.1.
|
data/bin/feedalizer
CHANGED
File without changes
|
data/examples/pjvault.rb
CHANGED
@@ -5,11 +5,8 @@ $LOAD_PATH.unshift File.join(File.dirname(__FILE__), "..", "lib")
|
|
5
5
|
require "feedalizer"
|
6
6
|
require "time"
|
7
7
|
|
8
|
-
|
9
|
-
|
10
|
-
feedalize(url) do
|
8
|
+
feedalize("http://sydsvenskan.se/serier/nemi/index.jsp?context=serie") do
|
11
9
|
feed.title = "Nemi"
|
12
|
-
feed.about = "..."
|
13
10
|
feed.description = "Daily Nemi strip scraped from Sydsvenskan"
|
14
11
|
|
15
12
|
scrape_items("option") do |rss_item, html_element|
|
@@ -25,5 +22,7 @@ feedalize(url) do
|
|
25
22
|
rss_item.guid.content = link
|
26
23
|
end
|
27
24
|
|
28
|
-
|
25
|
+
if __FILE__ == $0
|
26
|
+
output!(ARGV[0] ? File.open(ARGV[0], "w") : STDOUT)
|
27
|
+
end
|
29
28
|
end
|
data/lib/feedalizer.rb
CHANGED
@@ -3,20 +3,20 @@ require "open-uri"
|
|
3
3
|
require "hpricot"
|
4
4
|
|
5
5
|
class Feedalizer
|
6
|
-
VERSION = "0.1.
|
6
|
+
VERSION = "0.1.2"
|
7
|
+
IDENTIFIER = "Feedalizer/#{VERSION} (http://termos.vemod.net/feedalizer)"
|
7
8
|
|
8
|
-
attr_reader :
|
9
|
+
attr_reader :page
|
9
10
|
|
10
11
|
def initialize(url, &block)
|
11
|
-
@
|
12
|
+
@page = grab_page(url)
|
12
13
|
@rss = RSS::Maker::RSS20.new
|
13
14
|
|
14
|
-
feed.generator =
|
15
|
+
feed.generator = IDENTIFIER
|
15
16
|
feed.link = url
|
17
|
+
feed.description = "Scraped from #{url}"
|
16
18
|
|
17
19
|
instance_eval(&block) if block
|
18
|
-
|
19
|
-
debug! if $DEBUG
|
20
20
|
end
|
21
21
|
|
22
22
|
def feed
|
@@ -24,7 +24,7 @@ class Feedalizer
|
|
24
24
|
end
|
25
25
|
|
26
26
|
def scrape_items(hpricot_query, limit = 15)
|
27
|
-
elements = @
|
27
|
+
elements = @page.search(hpricot_query)
|
28
28
|
|
29
29
|
elements.first(limit).each do |html_element|
|
30
30
|
rss_item = @rss.items.new_item
|
@@ -36,11 +36,12 @@ class Feedalizer
|
|
36
36
|
open(url) { |io| Hpricot(io) }
|
37
37
|
end
|
38
38
|
|
39
|
-
# For backwards-compatibility
|
40
|
-
alias_method :parse_source, :grab_page
|
41
|
-
|
42
39
|
def output
|
43
|
-
@rss.
|
40
|
+
if @rss.respond_to?(:to_feed) # Ruby >= 1.8.7
|
41
|
+
@rss.to_feed.to_s
|
42
|
+
else
|
43
|
+
@rss.to_rss.to_s
|
44
|
+
end
|
44
45
|
end
|
45
46
|
|
46
47
|
def output!(target = STDOUT)
|
@@ -49,10 +50,13 @@ class Feedalizer
|
|
49
50
|
|
50
51
|
def debug!
|
51
52
|
@rss.items.each do |item|
|
52
|
-
STDERR.puts [ item.title, item.date, item.link ].join("
|
53
|
-
STDERR.puts
|
53
|
+
STDERR.puts [ item.title, item.date, item.link ].join("; ")
|
54
54
|
end
|
55
55
|
end
|
56
|
+
|
57
|
+
# Backwards-compatibility
|
58
|
+
alias_method :parse_source, :grab_page
|
59
|
+
alias_method :source, :page
|
56
60
|
end
|
57
61
|
|
58
62
|
# A handy wrapper for Feedalizer.new :-)
|
data/tests/test_feedalizer.rb
CHANGED
@@ -14,7 +14,7 @@ class TestFeedalizer < Test::Unit::TestCase
|
|
14
14
|
|
15
15
|
def test_construction
|
16
16
|
assert_kind_of RSS::Maker::RSS20::Channel, @feedalizer.feed
|
17
|
-
assert_kind_of Hpricot::Doc, @feedalizer.
|
17
|
+
assert_kind_of Hpricot::Doc, @feedalizer.page
|
18
18
|
end
|
19
19
|
|
20
20
|
def test_block
|
@@ -23,12 +23,13 @@ class TestFeedalizer < Test::Unit::TestCase
|
|
23
23
|
assert_kind_of Feedalizer, inside
|
24
24
|
end
|
25
25
|
|
26
|
-
def
|
26
|
+
def test_defaults
|
27
27
|
assert_equal TEST_FILE, @feedalizer.feed.link
|
28
|
+
assert_equal "Scraped from #{TEST_FILE}", @feedalizer.feed.description
|
28
29
|
end
|
29
30
|
|
30
|
-
def
|
31
|
-
assert_equal "Test", @feedalizer.
|
31
|
+
def test_page
|
32
|
+
assert_equal "Test", @feedalizer.page.search("html/head/title").text
|
32
33
|
end
|
33
34
|
|
34
35
|
def test_scrape_items
|
@@ -76,4 +77,9 @@ class TestFeedalizer < Test::Unit::TestCase
|
|
76
77
|
assert output.include?("<rss")
|
77
78
|
assert output.size > 320
|
78
79
|
end
|
80
|
+
|
81
|
+
def test_backwards_compatibility
|
82
|
+
assert @feedalizer.respond_to?(:page)
|
83
|
+
assert @feedalizer.respond_to?(:parse_source)
|
84
|
+
end
|
79
85
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: feedalizer
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Christoffer Sawicki
|
@@ -9,11 +9,12 @@ autorequire:
|
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
11
|
|
12
|
-
date:
|
12
|
+
date: 2009-11-23 00:00:00 +01:00
|
13
13
|
default_executable:
|
14
14
|
dependencies:
|
15
15
|
- !ruby/object:Gem::Dependency
|
16
16
|
name: hpricot
|
17
|
+
type: :runtime
|
17
18
|
version_requirement:
|
18
19
|
version_requirements: !ruby/object:Gem::Requirement
|
19
20
|
requirements:
|
@@ -23,14 +24,18 @@ dependencies:
|
|
23
24
|
version:
|
24
25
|
- !ruby/object:Gem::Dependency
|
25
26
|
name: hoe
|
27
|
+
type: :development
|
26
28
|
version_requirement:
|
27
29
|
version_requirements: !ruby/object:Gem::Requirement
|
28
30
|
requirements:
|
29
31
|
- - ">="
|
30
32
|
- !ruby/object:Gem::Version
|
31
|
-
version: 1.
|
33
|
+
version: 1.8.0
|
32
34
|
version:
|
33
|
-
description:
|
35
|
+
description: |-
|
36
|
+
Feedalizer is a *small* Ruby library that glues together Hpricot with the
|
37
|
+
standard RSS library in a way that makes it easy to transform web pages into
|
38
|
+
RSS feeds. If you ask me, it makes it *too* easy.
|
34
39
|
email:
|
35
40
|
- christoffer.sawicki@gmail.com
|
36
41
|
executables:
|
@@ -59,6 +64,8 @@ files:
|
|
59
64
|
- TODO.txt
|
60
65
|
has_rdoc: true
|
61
66
|
homepage: http://termos.vemod.net/feedalizer
|
67
|
+
licenses: []
|
68
|
+
|
62
69
|
post_install_message:
|
63
70
|
rdoc_options:
|
64
71
|
- --main
|
@@ -80,9 +87,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
80
87
|
requirements: []
|
81
88
|
|
82
89
|
rubyforge_project: feedalizer
|
83
|
-
rubygems_version: 1.
|
90
|
+
rubygems_version: 1.3.5
|
84
91
|
signing_key:
|
85
|
-
specification_version:
|
92
|
+
specification_version: 3
|
86
93
|
summary: Transforms web pages into RSS feeds
|
87
94
|
test_files: []
|
88
95
|
|