lib/regexp_crawler/crawler.rb in flyerhzm-regexp_crawler-0.8.1 vs lib/regexp_crawler/crawler.rb in flyerhzm-regexp_crawler-0.8.2

@@ -35,11 +35,11 @@
         response = Net::HTTP.get_response_with_headers(uri, @headers)
         parse_response(response, uri)
       end
 
       def continue_uri(uri, page)
-        if page.start_with?(uri.scheme)
+        if page =~ /^#{uri.scheme}/
           URI.parse(page)
         elsif page.start_with?('/')
           URI.join(uri.scheme + '://' + uri.host, page)
         else
           URI.parse(uri.to_s.split('/')[0..-2].join('/') + '/' + page)
@@ -54,10 +54,10 @@
               page = page.compact.first if page.is_a? Array
               continue_uri = continue_uri(uri, page)
               @pages << continue_uri unless @captured_pages.include?(continue_uri) or @pages.include?(continue_uri)
             end 
           end
-          if @need_parse.nil? or @need_parse.call(uri.to_i, response_body)
+          if @need_parse.nil? or @need_parse.call(uri.to_s, response_body)
             md = @capture_regexp.match(response_body)
             if md
               captures = md.captures
               result = {}
               captures.each_index do |i|