【python】SAX和DOM处理XML文件

def make_parser(parser_list=()):
    """Creates and returns a SAX parser.解析器
    Creates the first parser it is able to instantiate of the ones
    given in the iterable created by chaining parser_list and
    default_parser_list.  The iterables must contain the names of Python modules containing both a SAX parser and a create_parser function."""

def parse(source, handler, errorHandler=ErrorHandler()):
    parser = make_parser()
    parser.setContentHandler(handler)
    parser.setErrorHandler(errorHandler)
    parser.parse(source)

def parseString(string, handler, errorHandler=ErrorHandler()):

class SAXException(Exception):
    """Encapsulate an XML error or warning. This class can contain
    basic error or warning information from either the XML parser or
    the application: you can subclass子类 it to provide additional
    functionality, or to add localization. Note that although you will
    receive a SAXException as the argument to the handlers in the
    ErrorHandler interface, you are not actually required to raise
    the exception; instead, you can simply read the information in
    it."""

# ===== CONTENTHANDLER =====
class ContentHandler:
    """Interface for receiving logical document content events.
    This is the main callback interface in SAX, and the one most
    important to applications. The order of events in this interface
    mirrors the order of the information in the document."""

class ContentHandler:
    """Interface for receiving logical document content events.
    This is the main callback interface in SAX, and the one most
    important to applications. The order of events in this interface
    mirrors the order of the information in the document."""
    def __init__(self):
        self._locator = None定位器
    def setDocumentLocator(self, locator):
        """Called by the parser to give the application a locator for
        locating the origin of document events.由解析器调用，为应用程序提供一个定位文档事件的起源。
        SAX parsers are strongly encouraged 鼓励(though not absolutely
        required虽然不是绝对必需的) to supply提供 a locator: if it does so, it must supply
        the locator to the application by invoking this method before
        invoking调用 any of the other methods in the DocumentHandler
        interface.
        The locator allows the application to determine the end
        position of any document-related event, even if the parser is
        not reporting an error. Typically, the application will use
        this information for reporting its own errors (such as
        character content that does not match an application's
        business rules). The information returned by the locator is
        probably not sufficient for use with a search engine.
        Note that the locator will return correct information only
        during the invocation 调用of the events in this interface. The
        application should not attempt to use it at any other time."""
        self._locator = locator
    def startDocument(self):
        """Receive notification of the beginning of a document.
        The SAX parser will invoke this method only once, before any
        other methods in this interface or in DTDHandler (except for
        setDocumentLocator)."""
    def endDocument(self):
        """Receive notification of the end of a document.
        The SAX parser will invoke this method only once, and it will
        be the last method invoked during the parse. The parser shall
        not invoke this method until it has either abandoned parsing
        (because of an unrecoverable error) or reached the end of
        input."""
    def startPrefixMapping(self, prefix, uri):
        """Begin the scope of a prefix-URI Namespace mapping.
开始了prefix-URI名称空间映射的范围。
        The information from this event is not necessary for normal
        Namespace processing: the SAX XML reader will automatically
        replace prefixes for element and attribute names when the
        http://xml.org/sax/features/namespaces feature is true (the
        default).
        There are cases, however, when applications need to use
        prefixes in character data or in attribute values, where they
        cannot safely be expanded automatically; the
        start/endPrefixMapping event supplies the information to the
        application to expand prefixes in those contexts itself, if
        necessary.
        Note that start/endPrefixMapping events are not guaranteed to
        be properly nested relative to each-other: all
        startPrefixMapping events will occur before the corresponding
        startElement event, and all endPrefixMapping events will occur
        after the corresponding endElement event, but their order is
        not guaranteed."""
    def endPrefixMapping(self, prefix):
        """End the scope of a prefix-URI mapping映射.
        See startPrefixMapping for details. This event will always
        occur after the corresponding endElement event, but the order
        of endPrefixMapping events is not otherwise guaranteed.不以其他方式保证"""
    def startElement(self, name, attrs):
        """Signals the start of an element in non-namespace mode.
        The name parameter contains the raw XML 1.0 name of the
        element type as a string and the attrs parameter holds an
        instance of the Attributes class containing the attributes of
        the element."""
    def endElement(self, name):
        """Signals the end of an element in non-namespace mode.
        The name parameter contains the name of the element type, just
        as with the startElement event."""
    def startElementNS(self, name, qname, attrs):
        """Signals the start of an element in namespace mode.
        The name parameter contains the name of the element type as a
        (uri, localname) tuple, the qname parameter the raw XML 1.0
        name used in the source document, and the attrs parameter
        holds an instance of the Attributes class containing the
        attributes of the element.
        The uri part of the name tuple is None for elements which have
        no namespace."""
    def endElementNS(self, name, qname):
        """Signals the end of an element in namespace mode.
        The name parameter contains the name of the element type, just
        as with the startElementNS event."""
    def characters(self, content):
        """Receive notification of character data.
        The Parser will call this method to report each chunk of
        character data. SAX parsers may return all contiguous
        character data in a single chunk, or they may split it into
        several chunks; however, all of the characters in any single
        event must come from the same external entity so that the
        Locator provides useful information."""
    def ignorableWhitespace(self, whitespace):
        """Receive notification of ignorable whitespace in element content.
        Validating Parsers must use this method to report each chunk
        of ignorable whitespace (see the W3C XML 1.0 recommendation,
        section 2.10): non-validating parsers may also use this method
        if they are capable of parsing and using content models.
        SAX parsers may return all contiguous whitespace in a single
        chunk, or they may split it into several chunks; however, all
        of the characters in any single event must come from the same
        external entity, so that the Locator provides useful
        information."""
    def processingInstruction(self, target, data):
        """Receive notification of a processing instruction.
        The Parser will invoke this method once for each processing
        instruction found: note that processing instructions may occur
        before or after the main document element.
        A SAX parser should never report an XML declaration (XML 1.0,
        section 2.8) or a text declaration (XML 1.0, section 4.3.1)
        using this method."""
    def skippedEntity(self, name):
        """Receive notification of a skipped entity.实体
        The Parser will invoke this method once for each entity
        skipped. Non-validating processors may skip entities if they
        have not seen the declarations (because, for example, the
        entity was declared in an external DTD subset). All processors
        may skip external entities, depending on the values of the
        http://xml.org/sax/features/external-general-entities and the
        http://xml.org/sax/features/external-parameter-entities
        properties."""
# ===== DTDHandler =====

# coding=gbk
import xml.sax
import sys
get_record=[] # 接受获取xml文档数据
class GetStorehouse(xml.sax.ContentHandler):# 事件处理器
    def __init__(self):
        self.CurrentDate=""# 自定义当前元素标签名属性
        self.title=""# 自定义商品二级分类属性
        self.name=""
        self.amount=""
        self.price=""
    def startElement(self,label,atrributes):# 遇到元素开始标签出发该函数
        self.CurrentDate=label # label为实例对象在解析的时候传递的标签名
        if label=="goods":
            category=atrributes["category"]
            return category
    def endElement(self,label):
        global get_record
        if self.CurrentDate=="title":
            get_record.append(self.title)
        elif self.CurrentDate=="name":
            get_record.append(self.name)
        elif self.CurrentDate=="amount":
            get_record.append(self.amount)
        elif self.CurrentDate=="price":
            get_record.append(self.price)
    def characters(self,content):
        if self.CurrentDate=="title":
            self.title=content
        elif self.CurrentDate=="name":
            self.name=content
        elif self.CurrentDate=="amount":
            self.amount=content
        elif self.CurrentDate=="price":
            self.price=content
#=======
parser=xml.sax.make_parser()#创建一个解析器的XMLreader对象
parser.setFeature(xml.sax.handler.feature_namespaces,0)# 从xml文件解析数据，关闭从命名空间解析数据
Handler=GetStorehouse()
parser.setContentHandler(Handler)
parser.parse("storehouse.xml")
print(get_record)

['淡水鱼', '鲫鱼', '18', '8', '    ', '温带水果', '猕猴桃', '10', '10', '    ', '\n']

<storehouse>
    <goods category="fish">
        <title>淡水鱼</title>
        <name>鲫鱼</name>
        <amount>18</amount>
        <price>8</price>
    </goods>
    <goods category="fruit">
        <title>温带水果</title>
        <name>猕猴桃</name>
        <amount>10</amount>
        <price>10</price>
    </goods>
</storehouse>