_lxml.py 文件源码

def prepare_markup(self, markup, user_specified_encoding=None,
                       exclude_encodings=None,
                       document_declared_encoding=None):
        """
        :yield: A series of 4-tuples.
         (markup, encoding, declared encoding,
          has undergone character replacement)

        Each 4-tuple represents a strategy for parsing the document.
        """
        if isinstance(markup, unicode):
            # We were given Unicode. Maybe lxml can parse Unicode on
            # this system?
            yield markup, None, document_declared_encoding, False

        if isinstance(markup, unicode):
            # No, apparently not. Convert the Unicode to UTF-8 and
            # tell lxml to parse it as UTF-8.
            yield (markup.encode("utf8"), "utf8",
                   document_declared_encoding, False)

        # Instead of using UnicodeDammit to convert the bytestring to
        # Unicode using different encodings, use EncodingDetector to
        # iterate over the encodings, and tell lxml to try to parse
        # the document as each one in turn.
        is_html = not self.is_xml
        if is_html:
            self.processing_instruction_class = ProcessingInstruction
        else:
            self.processing_instruction_class = XMLProcessingInstruction
        try_encodings = [user_specified_encoding, document_declared_encoding]
        detector = EncodingDetector(
            markup, try_encodings, is_html, exclude_encodings)
        for encoding in detector.encodings:
            yield (detector.markup, encoding, document_declared_encoding, False)