module Nokogiri::HTML5
def self.get(uri, options={})
* :follow_limit => number of redirects which are followed
special option is considered a header. Special options include:
http headers and special options. Everything which is not a
rules. +uri+ may be a +String+ or a +URI+. +options+ contains
handling https, and determining the character encoding using HTML5
Fetch and parse a HTML document from the web, following redirects,
def self.get(uri, options={}) headers = options.clone headers = {:follow_limit => headers} if Numeric === headers # deprecated limit=headers[:follow_limit] ? headers.delete(:follow_limit).to_i : 10 require 'net/http' uri = URI(uri) unless URI === uri http = Net::HTTP.new(uri.host, uri.port) # TLS / SSL support http.use_ssl = true if uri.scheme == 'https' # Pass through Net::HTTP override values, which currently include: # :ca_file, :ca_path, :cert, :cert_store, :ciphers, # :close_on_empty_response, :continue_timeout, :key, :open_timeout, # :read_timeout, :ssl_timeout, :ssl_version, :use_ssl, # :verify_callback, :verify_depth, :verify_mode options.each do |key, value| http.send "#{key}=", headers.delete(key) if http.respond_to? "#{key}=" end request = Net::HTTP::Get.new(uri.request_uri) # basic authentication auth = headers.delete(:basic_auth) auth ||= [uri.user, uri.password] if uri.user && uri.password request.basic_auth auth.first, auth.last if auth # remaining options are treated as headers headers.each {|key, value| request[key.to_s] = value.to_s} response = http.request(request) case response when Net::HTTPSuccess doc = parse(reencode(response.body, response['content-type']), options) doc.instance_variable_set('@response', response) doc.class.send(:attr_reader, :response) doc when Net::HTTPRedirection response.value if limit <= 1 location = URI.join(uri, response['location']) get(location, options.merge(:follow_limit => limit-1)) else response.value end end