class Nokogiri::HTML::Document
def fragment tags = nil
###
def fragment tags = nil DocumentFragment.new(self, tags, self.root) end
def meta_content_type
def meta_content_type css('meta[@http-equiv]').find { |node| node['http-equiv'] =~ /\AContent-Type\z/i and !node['content'].nil? and !node['content'].empty? } end
def meta_encoding
Get the meta tag encoding for this document. If there is no meta tag,
##
def meta_encoding meta = meta_content_type and match = /charset\s*=\s*([\w-]+)/i.match(meta['content']) and match[1] end
def meta_encoding= encoding
Set the meta tag encoding for this document. If there is no meta
##
def meta_encoding= encoding meta = meta_content_type and meta['content'] = "text/html; charset=%s" % encoding end
def parse string_or_io, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML
Nokogiri::XML::ParseOptions::RECOVER. See the constants in
is a number that sets options in the parser, such as
encoding that should be used when processing the document. +options+
+url+ is resource where this document is located. +encoding+ is the
responds to _read_ and _close_ such as an IO, or StringIO.
Parse HTML. +string_or_io+ may be a String, or any object that
##
def parse string_or_io, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML options = Nokogiri::XML::ParseOptions.new(options) if Fixnum === options # Give the options to the user yield options if block_given? if string_or_io.respond_to?(:encoding) unless string_or_io.encoding.name == "ASCII-8BIT" encoding ||= string_or_io.encoding.name end end if string_or_io.respond_to?(:read) url ||= string_or_io.respond_to?(:path) ? string_or_io.path : nil if !encoding # Libxml2's parser has poor support for encoding # detection. First, it does not recognize the HTML5 # style meta charset declaration. Secondly, even if it # successfully detects an encoding hint, it does not # re-decode or re-parse the preceding part which may be # garbled. # # EncodingReader aims to perform advanced encoding # detection beyond what Libxml2 does, and to emulate # rewinding of a stream and make Libxml2 redo parsing # from the start when an encoding hint is found. string_or_io = EncodingReader.new(string_or_io) begin return read_io(string_or_io, url, encoding, options.to_i) rescue EncodingFound => e encoding = e.found_encoding end end return read_io(string_or_io, url, encoding, options.to_i) end # read_memory pukes on empty docs return new if string_or_io.nil? or string_or_io.empty? encoding ||= EncodingReader.detect_encoding(string_or_io) read_memory(string_or_io, url, encoding, options.to_i) end
def serialize options = {}
end
config.format.as_xml
node.serialize(:encoding => 'UTF-8') do |config|
or
node.serialize(:encoding => 'UTF-8', :save_with => FORMAT | AS_XML)
These two statements are equivalent:
block. See SaveOptions.
Serialize Node using +options+. Save options can also be set using a
###
def serialize options = {} options[:save_with] ||= XML::Node::SaveOptions::DEFAULT_HTML super end
def title
Get the title string of this document. Return nil if there is
##
def title title = at('title') and title.inner_text end
def title=(text)
Set the title string of this document. If there is no head
##
def title=(text) unless title = at('title') head = at('head') or return nil title = Nokogiri::XML::Node.new('title', self) head << title end title.children = XML::Text.new(text, self) end