Python ParserCreate.returns_unicode方法代码示例

# 需要导入模块: from xml.parsers.expat import ParserCreate [as 别名]
# 或者: from xml.parsers.expat.ParserCreate import returns_unicode [as 别名]
def _fetchUnicodes(glyphPath):
	# Given a path to an existing .glif file, get a list of all
	# unicode values from the XML data.
	# NOTE: this assumes .glif files written by glifLib, since
	# we simply stop parsing as soon as we see anything else than
	# <glyph>, <advance> or <unicode>. glifLib always writes those
	# elements in that order, before anything else.
	from xml.parsers.expat import ParserCreate

	unicodes = []
	def _startElementHandler(tagName, attrs, _unicodes=unicodes):
		if tagName == "unicode":
			_unicodes.append(int(attrs["hex"], 16))
		elif tagName not in ("glyph", "advance"):
			raise _DoneParsing()

	p = ParserCreate()
	p.StartElementHandler = _startElementHandler
	p.returns_unicode = True
	f = open(glyphPath)
	try:
		p.ParseFile(f)
	except _DoneParsing:
		pass
	return unicodes

# 需要导入模块: from xml.parsers.expat import ParserCreate [as 别名]
# 或者: from xml.parsers.expat.ParserCreate import returns_unicode [as 别名]
 def parse(self, text):
     from xml.parsers.expat import ParserCreate
     parser = ParserCreate()
     parser.returns_unicode = 0
     parser.StartElementHandler = self.startElementHandler
     parser.EndElementHandler = self.endElementHandler
     parser.Parse(text)

# 需要导入模块: from xml.parsers.expat import ParserCreate [as 别名]
# 或者: from xml.parsers.expat.ParserCreate import returns_unicode [as 别名]
 def parse(self, file, baseURI):
     from xml.parsers.expat import ParserCreate        
     parser = ParserCreate(namespace_separator="")
     parser.returns_unicode = 0
     dh = DocumentHandler(parser, self.add)
     dh.set_base(baseURI)        
     parser.ParseFile(file)
     file.close()

# 需要导入模块: from xml.parsers.expat import ParserCreate [as 别名]
# 或者: from xml.parsers.expat.ParserCreate import returns_unicode [as 别名]
	def __init__(self, text):
		from xml.parsers.expat import ParserCreate
		self.unicodes = []
		self._elementStack = []
		parser = ParserCreate()
		parser.returns_unicode = 0  # XXX, Don't remember why. It sucks, though.
		parser.StartElementHandler = self.startElementHandler
		parser.EndElementHandler = self.endElementHandler
		parser.Parse(text)

# 需要导入模块: from xml.parsers.expat import ParserCreate [as 别名]
# 或者: from xml.parsers.expat.ParserCreate import returns_unicode [as 别名]
 def parse(self, text):
     from xml.parsers.expat import ParserCreate
     parser = ParserCreate()
     # no attribute returns_unicode in Python3
     if hasattr(parser, "returns_unicode"):
         parser.returns_unicode = 0
     parser.StartElementHandler = self.startElementHandler
     parser.EndElementHandler = self.endElementHandler
     parser.Parse(text)

# 需要导入模块: from xml.parsers.expat import ParserCreate [as 别名]
# 或者: from xml.parsers.expat.ParserCreate import returns_unicode [as 别名]
def _parse(file, name, handler_class):
    parser = ParserCreate(namespace_separator="^")
    parser.returns_unicode = 0
    
    documentHandler = handler_class(parser, name)

    parser.ParseFile(file)
        
    file.close()
    return documentHandler.module

# 需要导入模块: from xml.parsers.expat import ParserCreate [as 别名]
# 或者: from xml.parsers.expat.ParserCreate import returns_unicode [as 别名]
    def __parse_xml(self):
        parser = ParserCreate()
        parser.returns_unicode = True
        parser.StartElementHandler = self.__start_element
        parser.EndElementHandler = self.__end_element
        parser.CharacterDataHandler = self.__char_data
        try:
            xml = urllib.urlopen(self.url).read()
        except:
            print 'new work unreadable'

        parser.Parse(xml)

# 需要导入模块: from xml.parsers.expat import ParserCreate [as 别名]
# 或者: from xml.parsers.expat.ParserCreate import returns_unicode [as 别名]
def read_xml():
    try:
        handler=DefaultSaxHandler()
        parser=ParserCreate()
        parser.returns_unicode = True
        parser.StartElementHandler = handler.start_element
        parser.EndElementHandler = handler.end_element
        parser.CharacterDataHandler = handler.char_data

        parser.Parse(xmldata)
    except:
        print 'read error!'

# 需要导入模块: from xml.parsers.expat import ParserCreate [as 别名]
# 或者: from xml.parsers.expat.ParserCreate import returns_unicode [as 别名]
def _fetchGlyphName(glyphPath):
	# Given a path to an existing .glif file, get the glyph name
	# from the XML data.
	from xml.parsers.expat import ParserCreate

	p = ParserCreate()
	p.StartElementHandler = _startElementHandler
	p.returns_unicode = True
	f = open(glyphPath)
	try:
		p.ParseFile(f)
	except _DoneParsing, why:
		glyphName = why.args[0]
		if glyphName is None:
			raise ValueError, (".glif file doen't have a <glyph> top-level "
					"element: %r" % glyphPath)

# 需要导入模块: from xml.parsers.expat import ParserCreate [as 别名]
# 或者: from xml.parsers.expat.ParserCreate import returns_unicode [as 别名]
def parse(data, facet_uri, globals, locals):
    parser = ParserCreate(namespace_separator="^")
    parser.returns_unicode = 0
    
    htmlHandler = HTMLHandler(parser)
    parser.Parse(data)

    codestr = htmlHandler.get_codestr()
    try:
        exec codestr+"\n" in globals, locals
        globals[facet_uri] = locals['_tmp']
        del locals['_tmp']
    except Exception, e:
        from traceback import print_exc
        print_exc()                
        print e, codestr

# 需要导入模块: from xml.parsers.expat import ParserCreate [as 别名]
# 或者: from xml.parsers.expat.ParserCreate import returns_unicode [as 别名]
	def _expatParseFile(self, pathOrFile):
		parser = ParserCreate()
		parser.returns_unicode = 0  # XXX, Don't remember why. It sucks, though.
		parser.StartElementHandler = self.startElementHandler
		parser.EndElementHandler = self.endElementHandler
		parser.CharacterDataHandler = self.characterDataHandler
		if isinstance(pathOrFile, (str, unicode)):
			f = open(pathOrFile)
			didOpen = 1
		else:
			didOpen = 0
			f = pathOrFile
		parser.ParseFile(f)
		if didOpen:
			f.close()
		return self.getRoot()

# 需要导入模块: from xml.parsers.expat import ParserCreate [as 别名]
# 或者: from xml.parsers.expat.ParserCreate import returns_unicode [as 别名]
	def parseFile(self, file):
		from xml.parsers.expat import ParserCreate
		parser = ParserCreate("latin1")
		parser.returns_unicode = 0
		parser.StartElementHandler = self.startElementHandler
		parser.EndElementHandler = self.endElementHandler
		parser.CharacterDataHandler = self.characterDataHandler
		
		pos = 0
		while 1:
			chunk = file.read(BUFSIZE)
			if not chunk:
				parser.Parse(chunk, 1)
				break
			pos = pos + len(chunk)
			if self.progress:
				self.progress.set(pos / 100)
			parser.Parse(chunk, 0)

# 需要导入模块: from xml.parsers.expat import ParserCreate [as 别名]
# 或者: from xml.parsers.expat.ParserCreate import returns_unicode [as 别名]
from xml.parsers.expat import ParserCreate

class DefaultSaxHandler(object):
    def start_element(self, name, attrs):
        print('sax:start_element: %s, attrs: %s' % (name, str(attrs)))

    def end_element(self, name):
        print('sax:end_element: %s' % name)

    def char_data(self, text):
        print('sax:char_data: %s' % text)

xml = r'''<?xml version="1.0"?>
<ol>
    <li><a href="/python">Python</a></li>
    <li><a href="/ruby">Ruby</a></li>
</ol>
'''
handler = DefaultSaxHandler()
parser = ParserCreate()
parser.returns_unicode = True
parser.StartElementHandler = handler.start_element
parser.EndElementHandler = handler.end_element
parser.CharacterDataHandler = handler.char_data
parser.Parse(xml)

# 需要导入模块: from xml.parsers.expat import ParserCreate [as 别名]
# 或者: from xml.parsers.expat.ParserCreate import returns_unicode [as 别名]
from xml.parsers.expat import ParserCreate
# 把处理的函数赋给paser解析器对应的handler

def start_element(name,attr):
    print name, attr
def end_element(name):
    print name
def char_data(text):
    print text     
    
parser = ParserCreate()
parser.StartElementHandler = start_element  #注册
parser.EndElementHandler = end_element
parser.CharacterDataHandler = char_data

parser.returns_unicode = True #当设置returns_unicode为True时，返回的所有element名称和char_data都是unicode，处理国际化更方便。

xml = r'''<?xml version="1.0"?>
<ol>
    <li><a href="/python">Python</a></li>
    <li><a href="/ruby">Ruby</a></li>
</ol>
'''
parser.Parse(xml)

################################
# 五、HTML Parser

# 如果我们要编写一个搜索引擎:第一步是用爬虫把目标网站的页面抓下来，第二步就是解析该HTML页面，看看里面的内容到底是新闻、图片还是视频内存。
# HTML本质上是XML的子集,但是HTML的语法没有XML那么严格，所以不能用标准的DOM或SAX来解析HTML。
################################