Nokogiri 鋸

Public Class Methods

new(...) Show Source

Create a new document

static VALUE new(int argc, VALUE *argv, VALUE klass) { VALUE uri, external_id, rest, rb_doc; rb_scan_args(argc, argv, "0*", &rest); uri = rb_ary_entry(rest, (long)0); external_id = rb_ary_entry(rest, (long)1); htmlDocPtr doc = htmlNewDoc( RTEST(uri) ? (const xmlChar *)StringValuePtr(uri) : NULL, RTEST(external_id) ? (const xmlChar *)StringValuePtr(external_id) : NULL ); rb_doc = Nokogiri_wrap_xml_document(klass, doc); rb_obj_call_init(rb_doc, argc, argv); return rb_doc ; }

parse(string_or_io, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML, &block) Show Source

Parse HTML. thing may be a String, or any object that responds to read and close such as an IO, or StringIO. url is resource where this document is located. encoding is the encoding that should be used when processing the document. options is a number that sets options in the parser, such as Nokogiri::XML::ParseOptions::RECOVER. See the constants in Nokogiri::XML::ParseOptions.

# File lib/nokogiri/html/document.rb, line 64 def parse string_or_io, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML, &block 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) encoding ||= string_or_io.encoding.name end if string_or_io.respond_to?(:read) url ||= string_or_io.respond_to?(:path) ? string_or_io.path : nil 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? read_memory(string_or_io, url, encoding, options.to_i) end

read_io(p1, p2, p3, p4) Show Source

Read the HTML document from io with given url, encoding, and options. See Nokogiri::HTML.parse

static VALUE read_io( VALUE klass, VALUE io, VALUE url, VALUE encoding, VALUE options ) { const char * c_url = NIL_P(url) ? NULL : StringValuePtr(url); const char * c_enc = NIL_P(encoding) ? NULL : StringValuePtr(encoding); VALUE error_list = rb_ary_new(); xmlResetLastError(); xmlSetStructuredErrorFunc((void *)error_list, Nokogiri_error_array_pusher); htmlDocPtr doc = htmlReadIO( io_read_callback, io_close_callback, (void *)io, c_url, c_enc, (int)NUM2INT(options) ); xmlSetStructuredErrorFunc(NULL, NULL); if(doc == NULL) { xmlFreeDoc(doc); xmlErrorPtr error = xmlGetLastError(); if(error) rb_exc_raise(Nokogiri_wrap_xml_syntax_error((VALUE)NULL, error)); else rb_raise(rb_eRuntimeError, "Could not parse document"); return Qnil; } VALUE document = Nokogiri_wrap_xml_document(klass, doc); rb_iv_set(document, "@errors", error_list); return document; }

read_memory(p1, p2, p3, p4) Show Source

Read the HTML document contained in string with given url, encoding, and options. See Nokogiri::HTML.parse

static VALUE read_memory( VALUE klass, VALUE string, VALUE url, VALUE encoding, VALUE options ) { const char * c_buffer = StringValuePtr(string); const char * c_url = NIL_P(url) ? NULL : StringValuePtr(url); const char * c_enc = NIL_P(encoding) ? NULL : StringValuePtr(encoding); int len = RSTRING_LEN(string); VALUE error_list = rb_ary_new(); xmlResetLastError(); xmlSetStructuredErrorFunc((void *)error_list, Nokogiri_error_array_pusher); htmlDocPtr doc = htmlReadMemory(c_buffer, len, c_url, c_enc, (int)NUM2INT(options)); xmlSetStructuredErrorFunc(NULL, NULL); if(doc == NULL) { xmlFreeDoc(doc); xmlErrorPtr error = xmlGetLastError(); if(error) rb_exc_raise(Nokogiri_wrap_xml_syntax_error((VALUE)NULL, error)); else rb_raise(rb_eRuntimeError, "Could not parse document"); return Qnil; } VALUE document = Nokogiri_wrap_xml_document(klass, doc); rb_iv_set(document, "@errors", error_list); return document; }

Public Instance Methods

fragment(tags = nil) Show Source

Create a Nokogiri::XML::DocumentFragment from tags

# File lib/nokogiri/html/document.rb, line 51 def fragment tags = nil DocumentFragment.new(self, tags) end

meta_encoding() Show Source

Get the meta tag encoding for this document. If there is no meta tag, then nil is returned

# File lib/nokogiri/html/document.rb, line 7 def meta_encoding return nil unless meta = css('meta').find { |node| node['http-equiv'] =~ /Content-Type/i } /charset\s*=\s*([\w\d-]+)/i.match(meta['content'])[1] end

meta_encoding=(encoding) Show Source

Set the meta tag encoding for this document. If there is no meta content tag, nil is returned and the encoding is not set.

# File lib/nokogiri/html/document.rb, line 18 def meta_encoding= encoding return nil unless meta = css('meta').find { |node| node['http-equiv'] =~ /Content-Type/i } meta['content'] = "text/html; charset=%s" % encoding encoding end

serialize(options = {}) Show Source

Serialize Node using options. Save options can also be set using a block. See SaveOptions.

These two statements are equivalent:

 node.serialize(:encoding => 'UTF-8', :save_with => FORMAT | AS_XML)

or

  node.serialize(:encoding => 'UTF-8') do |config|
    config.format.as_xml
  end

# File lib/nokogiri/html/document.rb, line 41 def serialize options = {}, &block options[:save_with] ||= XML::Node::SaveOptions::FORMAT | XML::Node::SaveOptions::AS_HTML | XML::Node::SaveOptions::NO_DECLARATION | XML::Node::SaveOptions::NO_EMPTY_TAGS super end

type() Show Source

The type for this document

static VALUE type(VALUE self) { htmlDocPtr doc; Data_Get_Struct(self, xmlDoc, doc); return INT2NUM((long)doc->type); }