基于Python开发的学生管理系统的设计与实现+详细文档+全部资料（高分毕业设计）.zip

from __future__ import absolute_import, division, unicode_literals from pip._vendor.six import with_metaclass import types from . import inputstream from . import tokenizer from . import treebuilders from .treebuilders._base import Marker from . import utils from . import constants from .constants import spaceCharacters, asciiUpper2Lower from .constants import specialElements from .constants import headingElements from .constants import cdataElements, rcdataElements from .constants import tokenTypes, ReparseException, namespaces from .constants import htmlIntegrationPointElements, mathmlTextIntegrationPointElements def parse(doc, treebuilder="etree", encoding=None, namespaceHTMLElements=True): """Parse a string or file-like object into a tree""" tb = treebuilders.getTreeBuilder(treebuilder) p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements) return p.parse(doc, encoding=encoding) def parseFragment(doc, container="div", treebuilder="etree", encoding=None, namespaceHTMLElements=True): tb = treebuilders.getTreeBuilder(treebuilder) p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements) return p.parseFragment(doc, container=container, encoding=encoding) def method_decorator_metaclass(function): class Decorated(type): def __new__(meta, classname, bases, classDict): for attributeName, attribute in classDict.items(): if isinstance(attribute, types.FunctionType): attribute = function(attribute) classDict[attributeName] = attribute return type.__new__(meta, classname, bases, classDict) return Decorated class HTMLParser(object): """HTML parser. Generates a tree structure from a stream of (possibly malformed) HTML""" def __init__(self, tree=None, tokenizer=tokenizer.HTMLTokenizer, strict=False, namespaceHTMLElements=True, debug=False): """ strict - raise an exception when a parse error is encountered tree - a treebuilder class controlling the type of tree that will be returned. Built in treebuilders can be accessed through html5lib.treebuilders.getTreeBuilder(treeType) tokenizer - a class that provides a stream of tokens to the treebuilder. This may be replaced for e.g. a sanitizer which converts some tags to text """ # Raise an exception on the first error encountered self.strict = strict if tree is None: tree = treebuilders.getTreeBuilder("etree") self.tree = tree(namespaceHTMLElements) self.tokenizer_class = tokenizer self.errors = [] self.phases = dict([(name, cls(self, self.tree)) for name, cls in getPhases(debug).items()]) def _parse(self, stream, innerHTML=False, container="div", encoding=None, parseMeta=True, useChardet=True, **kwargs): self.innerHTMLMode = innerHTML self.container = container self.tokenizer = self.tokenizer_class(stream, encoding=encoding, parseMeta=parseMeta, useChardet=useChardet, parser=self, **kwargs) self.reset() while True: try: self.mainLoop() break except ReparseException: self.reset() def reset(self): self.tree.reset() self.firstStartTag = False self.errors = [] self.log = [] # only used with debug mode # "quirks" / "limited quirks" / "no quirks" self.compatMode = "no quirks" if self.innerHTMLMode: self.innerHTML = self.container.lower() if self.innerHTML in cdataElements: self.tokenizer.state = self.tokenizer.rcdataState elif self.innerHTML in rcdataElements: self.tokenizer.state = self.tokenizer.rawtextState elif self.innerHTML == 'plaintext': self.tokenizer.state = self.tokenizer.plaintextState else: # state already is data state # self.tokenizer.state = self.tokenizer.dataState pass self.phase = self.phases["beforeHtml"] self.phase.insertHtmlElement() self.resetInsertionMode() else: self.innerHTML = False self.phase = self.phases["initial"] self.lastPhase = None self.beforeRCDataPhase = None self.framesetOK = True def isHTMLIntegrationPoint(self, element): if (element.name == "annotation-xml" and element.namespace == namespaces["mathml"]): return ("encoding" in element.attributes and element.attributes["encoding"].translate( asciiUpper2Lower) in ("text/html", "application/xhtml+xml")) else: return (element.namespace, element.name) in htmlIntegrationPointElements def isMathMLTextIntegrationPoint(self, element): return (element.namespace, element.name) in mathmlTextIntegrationPointElements def mainLoop(self): CharactersToken = tokenTypes["Characters"] SpaceCharactersToken = tokenTypes["SpaceCharacters"] StartTagToken = tokenTypes["StartTag"] EndTagToken = tokenTypes["EndTag"] CommentToken = tokenTypes["Comment"] DoctypeToken = tokenTypes["Doctype"] ParseErrorToken = tokenTypes["ParseError"] for token in self.normalizedTokens(): new_token = token while new_token is not None: currentNode = self.tree.openElements[-1] if self.tree.openElements else None currentNodeNamespace = currentNode.namespace if currentNode else None currentNodeName = currentNode.name if currentNode else None type = new_token["type"] if type == ParseErrorToken: self.parseError(new_token["data"], new_token.get("datavars", {})) new_token = None else: if (len(self.tree.openElements) == 0 or currentNodeNamespace == self.tree.defaultNamespace or (self.isMathMLTextIntegrationPoint(currentNode) and ((type == StartTagToken and token["name"] not in frozenset(["mglyph", "malignmark"])) or type in (CharactersToken, SpaceCharactersToken))) or (currentNodeNamespace == namespaces["mathml"] and currentNodeName == "annotation-xml" and token["name"] == "svg") or (self.isHTMLIntegrationPoint(currentNode) and type in (StartTagToken, CharactersToken, SpaceCharactersToken))): phase = self.phase else: phase = self.phases["inForeignContent"] if type == CharactersToken: new_token = phase.processCharacters(new_token) elif type == SpaceCharactersToken: new_token = phase.processSpaceCharacters(new_token) elif type == StartTagToken: new_token = phase.processStartTag(new_token) elif type == EndTagToken: new_token = phase.processEndTag(new_token) elif type == CommentToken: new_token = phase.processComment(new_token) elif type == DoctypeToken: new_token = phase.processDoctype(new_token) if (type == StartTagToken and token["selfClosing"] and not t