pushsaxhtml.py

来自「xml开源解析代码.版本为libxml2-2.6.29,可支持GB3212.网络」· Python 代码 · 共 66 行

PY
66
字号
#!/usr/bin/python -uimport sysimport libxml2# Memory debug specificlibxml2.debugMemory(1)log = ""class callback:    def startDocument(self):        global log        log = log + "startDocument:"    def endDocument(self):        global log        log = log + "endDocument:"    def startElement(self, tag, attrs):        global log        log = log + "startElement %s %s:" % (tag, attrs)    def endElement(self, tag):        global log        log = log + "endElement %s:" % (tag)    def characters(self, data):        global log        log = log + "characters: %s:" % (data)    def warning(self, msg):        global log        log = log + "warning: %s:" % (msg)    def error(self, msg):        global log        log = log + "error: %s:" % (msg)    def fatalError(self, msg):        global log        log = log + "fatalError: %s:" % (msg)handler = callback()ctxt = libxml2.htmlCreatePushParser(handler, "<foo", 4, "test.xml")chunk = " url='tst'>b"ctxt.htmlParseChunk(chunk, len(chunk), 0)chunk = "ar</foo>"ctxt.htmlParseChunk(chunk, len(chunk), 1)ctxt=Nonereference = """startDocument:startElement html None:startElement body None:startElement foo {'url': 'tst'}:error: Tag foo invalid:characters: bar:endElement foo:endElement body:endElement html:endDocument:"""if log != reference:    print "Error got: %s" % log    print "Exprected: %s" % reference    sys.exit(1)# Memory debug specificlibxml2.cleanupParser()if libxml2.debugMemory(1) == 0:    print "OK"else:    print "Memory leak %d bytes" % (libxml2.debugMemory(1))    libxml2.dumpMemory()

⌨️ 快捷键说明

复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?