class Nokogiri::HTML::Document
Public Class Methods
Create a new document
static VALUE rb_html_document_s_new(int argc, VALUE *argv, VALUE klass) { VALUE uri, external_id, rest, rb_doc; htmlDocPtr doc; rb_scan_args(argc, argv, "0*", &rest); uri = rb_ary_entry(rest, (long)0); external_id = rb_ary_entry(rest, (long)1); doc = htmlNewDoc( RTEST(uri) ? (const xmlChar *)StringValueCStr(uri) : NULL, RTEST(external_id) ? (const xmlChar *)StringValueCStr(external_id) : NULL ); rb_doc = Nokogiri_wrap_xml_document(klass, doc); rb_obj_call_init(rb_doc, argc, argv); return rb_doc ; }
Parse HTML
. string_or_io
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 166 def parse string_or_io, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML options = Nokogiri::XML::ParseOptions.new(options) if Integer === options yield options if block_given? url ||= string_or_io.respond_to?(:path) ? string_or_io.path : nil 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) if string_or_io.is_a?(Pathname) # resolve the Pathname to the file and open it as an IO object, see #2110 string_or_io = string_or_io.expand_path.open url ||= string_or_io.path end unless 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 if string_or_io.nil? or string_or_io.empty? return encoding ? new.tap { |i| i.encoding = encoding } : new end encoding ||= EncodingReader.detect_encoding(string_or_io) read_memory(string_or_io, url, encoding, options.to_i) end
Read the HTML
document from io
with given url
, encoding
, and options
. See Nokogiri::HTML.parse
static VALUE rb_html_document_s_read_io(VALUE klass, VALUE rb_io, VALUE rb_url, VALUE rb_encoding, VALUE rb_options) { VALUE rb_doc; VALUE rb_error_list = rb_ary_new(); htmlDocPtr c_doc; const char *c_url = NIL_P(rb_url) ? NULL : StringValueCStr(rb_url); const char *c_encoding = NIL_P(rb_encoding) ? NULL : StringValueCStr(rb_encoding); int options = NUM2INT(rb_options); xmlSetStructuredErrorFunc((void *)rb_error_list, Nokogiri_error_array_pusher); c_doc = htmlReadIO(io_read_callback, io_close_callback, (void *)rb_io, c_url, c_encoding, options); xmlSetStructuredErrorFunc(NULL, NULL); /* * If EncodingFound has occurred in EncodingReader, make sure to do * a cleanup and propagate the error. */ if (rb_respond_to(rb_io, id_encoding_found)) { VALUE encoding_found = rb_funcall(rb_io, id_encoding_found, 0); if (!NIL_P(encoding_found)) { xmlFreeDoc(c_doc); rb_exc_raise(encoding_found); } } if ((c_doc == NULL) || (!(options & XML_PARSE_RECOVER) && (RARRAY_LEN(rb_error_list) > 0))) { VALUE rb_error ; xmlFreeDoc(c_doc); rb_error = rb_ary_entry(rb_error_list, 0); if (rb_error == Qnil) { rb_raise(rb_eRuntimeError, "Could not parse document"); } else { VALUE exception_message = rb_funcall(rb_error, id_to_s, 0); exception_message = rb_str_concat(rb_str_new2("Parser without recover option encountered error or warning: "), exception_message); rb_exc_raise(rb_class_new_instance(1, &exception_message, cNokogiriXmlSyntaxError)); } return Qnil; } rb_doc = Nokogiri_wrap_xml_document(klass, c_doc); rb_iv_set(rb_doc, "@errors", rb_error_list); return rb_doc; }
Read the HTML
document contained in string
with given url
, encoding
, and options
. See Nokogiri::HTML.parse
static VALUE rb_html_document_s_read_memory(VALUE klass, VALUE rb_html, VALUE rb_url, VALUE rb_encoding, VALUE rb_options) { VALUE rb_doc; VALUE rb_error_list = rb_ary_new(); htmlDocPtr c_doc; const char *c_buffer = StringValuePtr(rb_html); const char *c_url = NIL_P(rb_url) ? NULL : StringValueCStr(rb_url); const char *c_encoding = NIL_P(rb_encoding) ? NULL : StringValueCStr(rb_encoding); int html_len = (int)RSTRING_LEN(rb_html); int options = NUM2INT(rb_options); xmlSetStructuredErrorFunc((void *)rb_error_list, Nokogiri_error_array_pusher); c_doc = htmlReadMemory(c_buffer, html_len, c_url, c_encoding, options); xmlSetStructuredErrorFunc(NULL, NULL); if ((c_doc == NULL) || (!(options & XML_PARSE_RECOVER) && (RARRAY_LEN(rb_error_list) > 0))) { VALUE rb_error ; xmlFreeDoc(c_doc); rb_error = rb_ary_entry(rb_error_list, 0); if (rb_error == Qnil) { rb_raise(rb_eRuntimeError, "Could not parse document"); } else { VALUE exception_message = rb_funcall(rb_error, id_to_s, 0); exception_message = rb_str_concat(rb_str_new2("Parser without recover option encountered error or warning: "), exception_message); rb_exc_raise(rb_class_new_instance(1, &exception_message, cNokogiriXmlSyntaxError)); } return Qnil; } rb_doc = Nokogiri_wrap_xml_document(klass, c_doc); rb_iv_set(rb_doc, "@errors", rb_error_list); return rb_doc; }
Public Instance Methods
Create a Nokogiri::XML::DocumentFragment
from tags
# File lib/nokogiri/html/document.rb, line 153 def fragment tags = nil DocumentFragment.new(self, tags, self.root) end
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 11 def meta_encoding case when meta = at('//meta[@charset]') meta[:charset] when meta = meta_content_type meta['content'][/charset\s*=\s*([\w-]+)/i, 1] end end
Set the meta tag encoding for this document.
If an meta encoding tag is already present, its content is replaced with the given text.
Otherwise, this method tries to create one at an appropriate place supplying head and/or html elements as necessary, which is inside a head element if any, and before any text node or content element (typically <body>) if any.
The result when trying to set an encoding that is different from the document encoding is undefined.
Beware in CRuby, that libxml2 automatically inserts a meta tag into a head element.
# File lib/nokogiri/html/document.rb, line 36 def meta_encoding= encoding case when meta = meta_content_type meta['content'] = 'text/html; charset=%s' % encoding encoding when meta = at('//meta[@charset]') meta['charset'] = encoding else meta = XML::Node.new('meta', self) if dtd = internal_subset and dtd.html5_dtd? meta['charset'] = encoding else meta['http-equiv'] = 'Content-Type' meta['content'] = 'text/html; charset=%s' % encoding end case when head = at('//head') head.prepend_child(meta) else set_metadata_element(meta) end encoding end end
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
Nokogiri::XML::Node#serialize
# File lib/nokogiri/html/document.rb, line 146 def serialize options = {} options[:save_with] ||= XML::Node::SaveOptions::DEFAULT_HTML super end
Get the title string of this document. Return nil if there is no title tag.
# File lib/nokogiri/html/document.rb, line 72 def title title = at('//title') and title.inner_text end
Set the title string of this document.
If a title element is already present, its content is replaced with the given text.
Otherwise, this method tries to create one at an appropriate place supplying head and/or html elements as necessary, which is inside a head element if any, right after a meta encoding/charset tag if any, and before any text node or content element (typically <body>) if any.
# File lib/nokogiri/html/document.rb, line 87 def title=(text) tnode = XML::Text.new(text, self) if title = at('//title') title.children = tnode return text end title = XML::Node.new('title', self) << tnode case when head = at('//head') head << title when meta = at('//meta[@charset]') || meta_content_type # better put after charset declaration meta.add_next_sibling(title) else set_metadata_element(title) end text end
The type for this document
static VALUE rb_html_document_type(VALUE self) { htmlDocPtr doc; Data_Get_Struct(self, xmlDoc, doc); return INT2NUM((long)doc->type); }
Private Instance Methods
# File lib/nokogiri/html/document.rb, line 62 def meta_content_type xpath('//meta[@http-equiv and boolean(@content)]').find { |node| node['http-equiv'] =~ /\AContent-Type\z/i } end
# File lib/nokogiri/html/document.rb, line 107 def set_metadata_element(element) case when head = at('//head') head << element when html = at('//html') head = html.prepend_child(XML::Node.new('head', self)) head.prepend_child(element) when first = children.find { |node| case node when XML::Element, XML::Text true end } # We reach here only if the underlying document model # allows <html>/<head> elements to be omitted and does not # automatically supply them. first.add_previous_sibling(element) else html = add_child(XML::Node.new('html', self)) head = html.add_child(XML::Node.new('head', self)) head.prepend_child(element) end end