Created
April 9, 2011 20:35
-
-
Save dima4p/911742 to your computer and use it in GitHub Desktop.
Monkey patch for Mechanize
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class Mechanize | |
class Page | |
def initialize(uri=nil, response=nil, body=nil, code=nil, mech=nil) | |
@encoding = nil | |
method = response.respond_to?(:each_header) ? :each_header : :each | |
re_test = /charset\s*=/i | |
re_select = /charset\s*=\s*([^; "]+)/i | |
response.send(method) do |header,v| | |
next unless v =~ re_test | |
encoding = v[re_select, 1] | |
@encoding = encoding unless encoding == 'none' | |
end | |
# Force the encoding to be 8BIT so we can perform regular expressions. | |
# We'll set it to the detected encoding later | |
body.force_encoding('ASCII-8BIT') if body && body.respond_to?(:force_encoding) | |
if !@encoding and body =~ /<meta\s+http-equiv\s*=\s*"?Content-Type"?(.*?)>/i | |
encoding = $1[re_select, 1] | |
@encoding = encoding unless encoding == 'none' | |
end | |
@encoding ||= Util.detect_charset(body) | |
super(uri, response, body, code) | |
@mech ||= mech | |
raise Mechanize::ContentTypeError.new(response['content-type']) unless | |
response['content-type'] =~ /^(text\/html)|(application\/xhtml\+xml)/i | |
@parser = @links = @forms = @meta = @bases = @frames = @iframes = nil | |
end | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment