image_downloader 0.2.2 → 0.2.3

data/README.rdoc

@@ -32,15 +32,15 @@ After installation, you can use the following code as an example:
   # download all images on page in any place (by regexp, all that look like url with image)
   downloader.parse(:any_looks_like_image => true)
 
-  #####
+  ##### or
   # download images from all elements where usually images placed (<img...>, <a...>, ...)
   downloader.parse()
 
-  #####
+  ##### or
   # download image from exect places in page
   downloader.parse(:collect => {:link_icon => true})
 
-  #####
+  ##### or
   # download images by regexp
   downloader.parse(:regexp => /[^'"]+\.jpg/i)
 
@@ -58,7 +58,7 @@ For "parse" method available following options
   }
 
   # find by regexp
-  :regexp => /['"]([^'"]+\.jpg)[^'"]*['"]/i)
+  :regexp => /['"]([^'"]+\.jpg)[^'"]*['"]/i) # for ruby 1.8 (in 1.9 not allowed () for scan method)
   :regexp => /[^'"]+\.jpg/i # the same, but shorter
   :regexp => /[^'"]+\.css/  # other files can also be downloaded
 

data/lib/image_downloader/parser.rb

@@ -30,23 +30,33 @@ module ImageDownloader
     end
 
     def get_content_raw
-      @content = open(self.argument_url, 'User-Agent' => self.user_agent).read
+      @content = self.open_url.read
       @content.gsub!(/[\n\r\t]+/,' ')
     end
 
     def get_images_raw(path,h={})
-      self.content.scan(/['"]+[^'"]+\.(?:#{Images::IMAGE_EXTENSIONS.join('|')})['"]+/).map{|src|
-        src.gsub!(/['"]/,'')
-        self.push_to_images(path,src)
+      self.content.scan(/['"]+([^'"]+\.(?:#{Images::IMAGE_EXTENSIONS.join('|')}))[^'"]*['"]+/i) {|src|
+        self.push_to_images(path,Parser.clear(src[0]))
+      }
+      self.content.scan(/(?:href|src)=([^\s'">]+\.(?:#{Images::IMAGE_EXTENSIONS.join('|')}))[^\s'">]*[>\s]+/i) {|src|
+        self.push_to_images(path,Parser.clear(src[0]))
       }
     end
 
+    def self.clear(str)
+      if str =~ /url/i
+        str.gsub!(/^.*?url\(/,'')
+        str.gsub!(/\)/,'')
+      end
+      str
+    end
+
     def get_images_regexp(path,regexp)
       self.content.scan(regexp) {|src| self.push_to_images(path,src.to_s)}
     end
 
     def get_content
-      @content = Nokogiri::HTML(open(self.argument_url, 'User-Agent' => self.user_agent))
+      @content = Nokogiri::HTML(self.open_url)
     end
 
     def get_images(path,h={})
@@ -112,5 +122,9 @@ module ImageDownloader
       alias all_image_places all_collect_from_methods
     end
 
+    def open_url
+      open(self.argument_url, 'User-Agent' => self.user_agent)
+    end
+
   end
 end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: image_downloader
 version: !ruby/object:Gem::Version 
-  hash: 19
+  hash: 17
   prerelease: false
   segments: 
   - 0
   - 2
-  - 2
-  version: 0.2.2
+  - 3
+  version: 0.2.3
 platform: ruby
 authors: 
 - Malykh Oleg
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-07-21 00:00:00 +04:00
+date: 2011-07-25 00:00:00 +04:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency