feedium 0.1.6 → 0.1.7
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.
- checksums.yaml +4 -4
- data/examples/parse.rb +1 -1
- data/lib/feedium/request.rb +3 -1
- data/lib/feedium/version.rb +1 -1
- data/lib/feedium.rb +11 -6
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 87bb2ca448ee83469233e386786cd2eb0ca79769
|
4
|
+
data.tar.gz: 8cf645f6f608dae97d64d09d484316d831a2bbb7
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6a3db6240adb8c5dfc7e0df4bebc0f6a3c1845b6981aee11be381ad7471bdd2a943f5dec61e7eea00cf5ff1e8ef1422edb5bfbbf7e2ae2c173c4afeb3f55f5e7
|
7
|
+
data.tar.gz: b5a2b8fefe268e6be2d6104c6abdf0e654125879ec27d15210a839fccb0b628f10e704b204f46b345e7a46a3bec620bdbc903daf494cdc3c12da370becb93cbd
|
data/examples/parse.rb
CHANGED
@@ -2,4 +2,4 @@ dir = File.expand_path(File.join(File.dirname(__FILE__), '..', 'lib'))
|
|
2
2
|
require File.join(dir, 'feedium')
|
3
3
|
|
4
4
|
# puts Feedium.parse('http://mangastream.com/rss')
|
5
|
-
puts Feedium.
|
5
|
+
puts Feedium.find('http://www.gazzettadelsud.it/feed.jsp')
|
data/lib/feedium/request.rb
CHANGED
@@ -4,7 +4,9 @@ class Feedium::Request
|
|
4
4
|
URI_REQEX = /^(http|https):\/\/[a-z0-9]+([\-\.]{1}[a-z0-9]+)*\.[a-z]{2,5}(:[0-9]{1,5})?(\/.*)?$/ix
|
5
5
|
MAX_CONTENT_SIZE = 5 * 1048576 # bytes in 1MB
|
6
6
|
|
7
|
-
def initialize(url)
|
7
|
+
def initialize(url, base_uri = nil)
|
8
|
+
url = URI.parse(base_uri).merge(url).to_s if base_uri
|
9
|
+
|
8
10
|
begin
|
9
11
|
@uri = URI.parse(url)
|
10
12
|
rescue URI::InvalidURIError => e
|
data/lib/feedium/version.rb
CHANGED
data/lib/feedium.rb
CHANGED
@@ -25,20 +25,25 @@ module Feedium
|
|
25
25
|
doc = Nokogiri::HTML(@request.io.read)
|
26
26
|
|
27
27
|
if doc.at('base') && doc.at('base')['href']
|
28
|
-
base_uri = doc.at('base')['href']
|
28
|
+
@base_uri = doc.at('base')['href']
|
29
29
|
else
|
30
|
-
base_uri = "#{@request.uri.scheme}://#{@request.uri.host}"
|
30
|
+
@base_uri = "#{@request.uri.scheme}://#{@request.uri.host}"
|
31
31
|
end
|
32
32
|
|
33
33
|
doc.xpath("//link[@rel='alternate'][@href][@type]").each do |l|
|
34
34
|
if CONTENT_TYPES.include?(l['type'].downcase.strip)
|
35
|
-
return @request.url if self.feed?(
|
35
|
+
return @request.url if self.feed?(l['href'])
|
36
36
|
end
|
37
37
|
end
|
38
38
|
|
39
39
|
doc.xpath("//a[@href]").each do |a|
|
40
|
-
|
41
|
-
|
40
|
+
found = %w(feed rss atom).detect {|k| !a['href'].index(k).nil? }
|
41
|
+
|
42
|
+
begin
|
43
|
+
return @request.url if found && self.feed?(a['href'])
|
44
|
+
rescue Feedium::RequestError
|
45
|
+
next
|
46
|
+
end
|
42
47
|
end
|
43
48
|
|
44
49
|
nil
|
@@ -53,7 +58,7 @@ module Feedium
|
|
53
58
|
end
|
54
59
|
|
55
60
|
def self.feed?(url)
|
56
|
-
@request = Request.new(url)
|
61
|
+
@request = Request.new(url, @base_uri)
|
57
62
|
@request.send
|
58
63
|
|
59
64
|
content_type = @request.io.content_type.downcase
|