rubyful_soup 1.0.2 → 1.0.3
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/CHANGELOG +5 -0
- data/lib/rubyful_soup.rb +7 -7
- metadata +1 -1
data/CHANGELOG
CHANGED
data/lib/rubyful_soup.rb
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
#Rubyful Soup
|
2
2
|
#Elixir and Tonic
|
3
3
|
#"The Screen-Scraper's Friend"
|
4
|
-
#v1.0.
|
4
|
+
#v1.0.3
|
5
5
|
#http://www.crummy.com/software/RubyfulSoup/
|
6
6
|
#
|
7
7
|
#Rubyful Soup is a port to the Ruby language and idiom of the Python
|
@@ -18,7 +18,7 @@ $KCODE = 'u'
|
|
18
18
|
require 'jcode'
|
19
19
|
|
20
20
|
#This code makes SGMLParser able to parse XML with namespaces.
|
21
|
-
class SGMLParser
|
21
|
+
class HTML::SGMLParser
|
22
22
|
if const_defined? :Tagfind
|
23
23
|
remove_const(:Tagfind)
|
24
24
|
Tagfind = /[a-zA-Z][-_.:a-zA-Z0-9]*/
|
@@ -223,9 +223,9 @@ module TagModule
|
|
223
223
|
setup(parent, previous)
|
224
224
|
end
|
225
225
|
|
226
|
-
#soup.title_tag or soup.title is the same as soup.find('title')
|
226
|
+
#soup.title_tag, or soup.title, is the same as soup.find('title')
|
227
227
|
def method_missing(name, *args)
|
228
|
-
#puts "Missing method #{name}"
|
228
|
+
#puts "Missing method #{name} for #{self.class.name}"
|
229
229
|
name = name.to_s
|
230
230
|
if name[-4...name.length] == '_tag'
|
231
231
|
name = name[0...name.length-4]
|
@@ -433,7 +433,7 @@ end
|
|
433
433
|
#This class is useful for parsing XML or made-up markup languages,
|
434
434
|
#or when BeautifulSoup makes an assumption counter to what you were
|
435
435
|
#expecting."""
|
436
|
-
class BeautifulStoneSoup < SGMLParser
|
436
|
+
class BeautifulStoneSoup < HTML::SGMLParser
|
437
437
|
include TagModule
|
438
438
|
|
439
439
|
#As a public service we will by default silently replace MS smart quotes
|
@@ -619,7 +619,7 @@ class BeautifulStoneSoup < SGMLParser
|
|
619
619
|
|
620
620
|
#Propagate comments right through.
|
621
621
|
def handle_comment(data)
|
622
|
-
handle_data("<!--#{
|
622
|
+
handle_data("<!--#{data}-->")
|
623
623
|
end
|
624
624
|
|
625
625
|
def handle_special(data)
|
@@ -631,7 +631,7 @@ class BeautifulStoneSoup < SGMLParser
|
|
631
631
|
end
|
632
632
|
|
633
633
|
def unknown_entityref(ref)
|
634
|
-
handle_data("%#{
|
634
|
+
handle_data("%#{ref}")
|
635
635
|
end
|
636
636
|
|
637
637
|
def attlistdecl(element_name, attributes, raw_content)
|
metadata
CHANGED
@@ -3,7 +3,7 @@ rubygems_version: 0.8.4
|
|
3
3
|
specification_version: 1
|
4
4
|
name: rubyful_soup
|
5
5
|
version: !ruby/object:Gem::Version
|
6
|
-
version: 1.0.
|
6
|
+
version: 1.0.3
|
7
7
|
date: 2005-11-04
|
8
8
|
summary: An HTML/XML parser that handles bad markup and provides tree traversal methods.
|
9
9
|
require_paths:
|