PYTHON The XMLReader class

is this article helpful? |

Python replacement for PHP's The XMLReader class [ edit | history ]

Module libxml2

http://dev.laptop.org/~cscott/joyride-api/libxml2-module.html

Below is just a sample for those guys who like PHP style. The code is untested code, you must take your own risk.

import libxml2

class XMLReader(object):
    def __init__(self):
        self.attributeCount = self.depth = 0
        self.baseURI = self.localName = self.name = self.namespaceURI = self.nodeType = self.prefix = self.value = self.xmlLang = ''
        self.hasAttributes = self.hasValue = self.isDefault = self.isEmptyElement = False
        self.xmlDoc = None
        
    def __createFunctions(self):
        dic_func_map = {'close' : 'Close',
                        'expand': 'Expand',
                        'getAttribute' : 'GetAttribute',
                        'getAttributeNo' : 'GetAttributeNo',
                        'getAttributeNs' : 'GetAttributeNs',
                        'getParserProperty' : 'GetParserProp',
                        'isValid' : 'IsValid',
                        'lookupNamespace' : 'LookupNamespace',
                        'moveToAttribute' : 'MoveToAttribute',
                        'moveToAttributeNo' : 'MoveToAttributeNo',
                        'moveToAttributeNs' : 'MoveToAttributeNs',
                        'moveToElement' : 'MoveToElement',
                        'moveToFirstAttribute' : 'MoveToFirstAttribute',
                        'moveToNextAttribute' : 'MoveToNextAttribute',
                        'next' : 'Next',
                        'readInnerXML' : 'ReadInnerXml',
                        'readOuterXML' : 'ReadOuterXml',
                        'readString' : 'ReadString',
                        'setParserProperty' : 'SetParserProp',
                        'setRelaxNGSchema' : 'RelaxNGSetSchema',
                        'setRelaxNGSchemaSource' : 'RelaxNGSetSchema',
                        'setSchema' : 'SetSchema',
                        }
        for k, v in dic_func_map.items():
            setattr(self, k, getattr(self.xmlDoc, v))
        
    def open(self, str_URI, str_encoding='', int_options=0):
        try:
            self.xmlDoc = libxml2.readerForFile(str_URI, str_encoding, int_options)
            self.__createFunctions()
            return True
        except libxml2.treeError, e:
            print e
            return False
    
    def read(self):
        if self.xmlDoc:
            dic_attr_map = {'attributeCount' : 'AttributeCount',
                            'baseURI' : 'BaseUri',
                            'depth' : 'Depth',
                            'localName' : 'LocalName',
                            'name' : 'Name',
                            'nodeType' : 'NodeType',
                            'prefix' : 'Prefix',
                            'value' : 'Value',
                            'namespaceURI' : 'NamespaceUri',
                            'xmlLang' : 'XmlLang',
                            'hasAttributes' : 'HasAttributes',
                            'hasValue' : 'HasValue',
                            'isDefault' : 'IsDefault',
                            'isEmptyElement' : 'IsEmptyElement',
                            }
            for k, v in dic_attr_map.items():
                setattr(self, k, getattr(self.xmlDoc, v)())
            return self.xmlDoc.Read()
        else:
            print 'Please use function open() to open a XML file'
    
    def xml(self, str_source, str_encoding='', int_options=0):
        try:
            self.xmlDoc = libxml2.readerForDoc(str_source, None, str_encoding, int_options)
            return True
        except libxml2.treeError, e:
            print e
            return False
    
if __name__ == '__main__':
    f = '[url]http://php.net/manual/en/book.xmlreader.php[/url]'
    f1 = '[url]http://soap.amazon.com/schemas2/AmazonWebServices.wsdl[/url]'
    f2 = '[url]http://www.google.com/sitemap.xml[/url]'
    f3 = '[url]http://news.google.com/?output=rss[/url]'

    x = XMLReader()           #php > $o = new XMLReader();
    if x.open(f3):          #php > if($o->open($f3)){
        while x.read():         #php > while($o->read()){
            print x.name            #php > echo $o->name;
            print x.getAttribute('isPermaLink') #php > echo $o->getAttribute('isPermaLink');
            print '========='       #php > echo '=========' }}
    else:                   #php > else{
        print 'Can not open file %s' %f3 # echo 'balah balah'}

PHP The XMLReader class

PHP original manual for The XMLReader class [ show | php.net ]

The XMLReader class

Introduction

The XMLReader extension is an XML Pull parser. The reader acts as a cursor going forward on the document stream and stopping at each node on the way.

Class synopsis

XMLReader

XMLReader {

/* Constants */

const int XMLReader::NONE = 0 ;

const int XMLReader::ELEMENT = 1 ;

const int XMLReader::ATTRIBUTE = 2 ;

const int XMLReader::TEXT = 3 ;

const int XMLReader::CDATA = 4 ;

const int XMLReader::ENTITY_REF = 5 ;

const int XMLReader::ENTITY = 6 ;

const int XMLReader::PI = 7 ;

const int XMLReader::COMMENT = 8 ;

const int XMLReader::DOC = 9 ;

const int XMLReader::DOC_TYPE = 10 ;

const int XMLReader::DOC_FRAGMENT = 11 ;

const int XMLReader::NOTATION = 12 ;

const int XMLReader::WHITESPACE = 13 ;

const int XMLReader::SIGNIFICANT_WHITESPACE = 14 ;

const int XMLReader::END_ELEMENT = 15 ;

const int XMLReader::END_ENTITY = 16 ;

const int XMLReader::XML_DECLARATION = 17 ;

const int XMLReader::LOADDTD = 1 ;

const int XMLReader::DEFAULTATTRS = 2 ;

const int XMLReader::VALIDATE = 3 ;

const int XMLReader::SUBST_ENTITIES = 4 ;

/* Properties */

public readonly int $attributeCount ;

public readonly string $baseURI ;

public readonly int $depth ;

public readonly bool $hasAttributes ;

public readonly bool $hasValue ;

public readonly bool $isDefault ;

public readonly bool $isEmptyElement ;

public readonly string $localName ;

public readonly string $name ;

public readonly string $namespaceURI ;

public readonly int $nodeType ;

public readonly string $prefix ;

public readonly string $value ;

public readonly string $xmlLang ;

/* Methods */

bool close ( void )

DOMNode expand ( void )

string getAttribute ( string $name )

string getAttributeNo ( int $index )

string getAttributeNs ( string $localName , string $namespaceURI )

bool getParserProperty ( int $property )

bool isValid ( void )

bool lookupNamespace ( string $prefix )

bool moveToAttribute ( string $name )

bool moveToAttributeNo ( int $index )

bool moveToAttributeNs ( string $localName , string $namespaceURI )

bool moveToElement ( void )

bool moveToFirstAttribute ( void )

bool moveToNextAttribute ( void )

bool next ([ string $localname ] )

bool open ( string $URI [, string $encoding [, int $options= 0 ]] )

bool read ( void )

string readInnerXML ( void )

string readOuterXML ( void )

string readString ( void )

bool setParserProperty ( int $property , bool $value )

bool setRelaxNGSchema ( string $filename )

bool setRelaxNGSchemaSource ( string $source )

bool setSchema ( string $filename )

bool xml ( string $source [, string $encoding [, int $options= 0 ]] )

}

Properties

attributeCount: The number of attributes on the node
baseURI: The base URI of the node
depth: Depth of the node in the tree, starting at 0
hasAttributes: Indicates if node has attributes
hasValue: Indicates if node has a text value
isDefault: Indicates if attribute is defaulted from DTD
isEmptyElement: Indicates if node is an empty element tag
localName: The local name of the node
name: The qualified name of the node
namespaceURI: The URI of the namespace associated with the node
nodeType: The node type for the node
prefix: The prefix of the namespace associated with the node
value: The text value of the node
xmlLang: The xml:lang scope which the node resides

Predefined Constants

XMLReader Node Types

XMLReader::NONE: No node type
XMLReader::ELEMENT: Start element
XMLReader::ATTRIBUTE: Attribute node
XMLReader::TEXT: Text node
XMLReader::CDATA: CDATA node
XMLReader::ENTITY_REF: Entity Reference node
XMLReader::ENTITY: Entity Declaration node
XMLReader::PI: Processing Instruction node
XMLReader::COMMENT: Comment node
XMLReader::DOC: Document node
XMLReader::DOC_TYPE: Document Type node
XMLReader::DOC_FRAGMENT: Document Fragment node
XMLReader::NOTATION: Notation node
XMLReader::WHITESPACE: Whitespace node
XMLReader::SIGNIFICANT_WHITESPACE: Significant Whitespace node
XMLReader::END_ELEMENT: End Element
XMLReader::END_ENTITY: End Entity
XMLReader::XML_DECLARATION: XML Declaration node

XMLReader Parser Options

XMLReader::LOADDTD: Load DTD but do not validate
XMLReader::DEFAULTATTRS: Load DTD and default attributes but do not validate
XMLReader::VALIDATE: Load DTD and validate while parsing
XMLReader::SUBST_ENTITIES: Substitute entities and expand references

XMLReader::close — Close the XMLReader input
XMLReader::expand — Returns a copy of the current node as a DOM object
XMLReader::getAttribute — Get the value of a named attribute
XMLReader::getAttributeNo — Get the value of an attribute by index
XMLReader::getAttributeNs — Get the value of an attribute by localname and URI
XMLReader::getParserProperty — Indicates if specified property has been set
XMLReader::isValid — Indicates if the parsed document is valid
XMLReader::lookupNamespace — Lookup namespace for a prefix
XMLReader::moveToAttribute — Move cursor to a named attribute
XMLReader::moveToAttributeNo — Move cursor to an attribute by index
XMLReader::moveToAttributeNs — Move cursor to a named attribute
XMLReader::moveToElement — Position cursor on the parent Element of current Attribute
XMLReader::moveToFirstAttribute — Position cursor on the first Attribute
XMLReader::moveToNextAttribute — Position cursor on the next Attribute
XMLReader::next — Move cursor to next node skipping all subtrees
XMLReader::open — Set the URI containing the XML to parse
XMLReader::read — Move to next node in document
XMLReader::readInnerXML — Retrieve XML from current node
XMLReader::readOuterXML — Retrieve XML from current node, including it self
XMLReader::readString — The methodName purpose
XMLReader::setParserProperty — Set or Unset parser options
XMLReader::setRelaxNGSchema — Set the filename or URI for a RelaxNG Schema
XMLReader::setRelaxNGSchemaSource — Set the data containing a RelaxNG Schema
XMLReader::setSchema — Validate document against XSD
XMLReader::XML — Set the data containing the XML to parse