generic.py 文件源码

def get_original_bytes(self):
        # We're a text string object, but the library is trying to get our raw
        # bytes.  This can happen if we auto-detected this string as text, but
        # we were wrong.  It's pretty common.  Return the original bytes that
        # would have been used to create this object, based upon the autodetect
        # method.
        if self.autodetect_utf16:
            return codecs.BOM_UTF16_BE + self.encode("utf-16be")
        elif self.autodetect_pdfdocencoding:
            return encode_pdfdocencoding(self)
        else:
            raise Exception("no information about original bytes")