2.2.8. 将字符实体替换为Unicode数字实体:replaceStrEntToNumEnt -

2.2.8. 将字符实体替换为Unicode数字实体:replaceStrEntToNumEnt


#------------------------------------------------------------------------------
# convert the string entity to unicode unmber entity
# refer: http://www.htmlhelp.com/reference/html40/entities/latin1.html
# TODO: need later use this htmlentitydefs instead following
def replaceStrEntToNumEnt(text) :
    strToNumEntDict = {
        # Latin-1 Entities
        "&nbsp;"	:   "&#160;",
        "&iexcl;"	:   "&#161;",
        "&cent;"    :   "&#162;",
        "&pound;"	:   "&#163;",
        "&curren;"	:   "&#164;",
        "&yen;"	    :   "&#165;",
        "&brvbar;"	:   "&#166;",
        "&sect;"	:   "&#167;",
        "&uml;"	    :   "&#168;",
        "&copy;"	:   "&#169;",
        "&ordf;"	:   "&#170;",
        "&laquo;"	:   "&#171;",
        "&not;"	    :   "&#172;",
        "&shy;"	    :   "&#173;",
        "&reg;"	    :   "&#174;",
        "&macr;"	:   "&#175;",
        "&deg;"	    :   "&#176;",
        "&plusmn;"	:   "&#177;",
        "&sup2;"	:   "&#178;",
        "&sup3;"	:   "&#179;",
        "&acute;"	:   "&#180;",
        "&micro;"	:   "&#181;",
        "&para;"	:   "&#182;",
        "&middot;"	:   "&#183;",
        "&cedil;"	:   "&#184;",
        "&sup1;"    :   "&#185;",
        "&ordm;"    :   "&#186;",
        "&raquo;"	:   "&#187;",
        "&frac14;"	:   "&#188;",
        "&frac12;"	:   "&#189;",
        "&frac34;"	:   "&#190;",
        "&iquest;"	:   "&#191;",
        "&Agrave;"	:   "&#192;",
        "&Aacute;"	:   "&#193;",
        "&Acirc;"	:   "&#194;",
        "&Atilde;"	:   "&#195;",
        "&Auml;"	:   "&#196;",
        "&Aring;"	:   "&#197;",
        "&AElig;"	:   "&#198;",
        "&Ccedil;"	:   "&#199;",
        "&Egrave;"	:   "&#200;",
        "&Eacute;"	:   "&#201;",
        "&Ecirc;"	:   "&#202;",
        "&Euml;"    :   "&#203;",
        "&Igrave;"	:   "&#204;",
        "&Iacute;"	:   "&#205;",
        "&Icirc;"	:   "&#206;",
        "&Iuml;"    :   "&#207;",
        "&ETH;"	    :   "&#208;",
        "&Ntilde;"	:   "&#209;",
        "&Ograve;"	:   "&#210;",
        "&Oacute;"	:   "&#211;",
        "&Ocirc;"	:   "&#212;",
        "&Otilde;"	:   "&#213;",
        "&Ouml;"	:   "&#214;",
        "&times;"	:   "&#215;",
        "&Oslash;"	:   "&#216;",
        "&Ugrave;"	:   "&#217;",
        "&Uacute;"	:   "&#218;",
        "&Ucirc;"	:   "&#219;",
        "&Uuml;"	:   "&#220;",
        "&Yacute;"	:   "&#221;",
        "&THORN;"	:   "&#222;",
        "&szlig;"	:   "&#223;",
        "&agrave;"	:   "&#224;",
        "&aacute;"	:   "&#225;",
        "&acirc;"	:   "&#226;",
        "&atilde;"	:   "&#227;",
        "&auml;"	:   "&#228;",
        "&aring;"	:   "&#229;",
        "&aelig;"	:   "&#230;",
        "&ccedil;"	:   "&#231;",
        "&egrave;"	:   "&#232;",
        "&eacute;"	:   "&#233;",
        "&ecirc;"	:   "&#234;",
        "&euml;"	:   "&#235;",
        "&igrave;"	:   "&#236;",
        "&iacute;"	:   "&#237;",
        "&icirc;"	:   "&#238;",
        "&iuml;"	:   "&#239;",
        "&eth;"	    :   "&#240;",
        "&ntilde;"	:   "&#241;",
        "&ograve;"	:   "&#242;",
        "&oacute;"	:   "&#243;",
        "&ocirc;"	:   "&#244;",
        "&otilde;"	:   "&#245;",
        "&ouml;" 	:   "&#246;",
        "&divide;"	:   "&#247;",
        "&oslash;"	:   "&#248;",
        "&ugrave;"	:   "&#249;",
        "&uacute;"	:   "&#250;",
        "&ucirc;"	:   "&#251;",
        "&uuml;"	:   "&#252;",
        "&yacute;"	:   "&#253;",
        "&thorn;"	:   "&#254;",
        "&yuml;"	:   "&#255;",
        # http://www.htmlhelp.com/reference/html40/entities/special.html
        # Special Entities
        "&quot;"    : "&#34;",
        "&amp;"     : "&#38;",
        "&lt;"      : "&#60;",
        "&gt;"      : "&#62;",
        "&OElig;"   : "&#338;",
        "&oelig;"   : "&#339;",
        "&Scaron;"  : "&#352;",
        "&scaron;"  : "&#353;",
        "&Yuml;"    : "&#376;",
        "&circ;"    : "&#710;",
        "&tilde;"   : "&#732;",
        "&ensp;"    : "&#8194;",
        "&emsp;"    : "&#8195;",
        "&thinsp;"  : "&#8201;",
        "&zwnj;"    : "&#8204;",
        "&zwj;"     : "&#8205;",
        "&lrm;"     : "&#8206;",
        "&rlm;"     : "&#8207;",
        "&ndash;"   : "&#8211;",
        "&mdash;"   : "&#8212;",
        "&lsquo;"   : "&#8216;",
        "&rsquo;"   : "&#8217;",
        "&sbquo;"   : "&#8218;",
        "&ldquo;"   : "&#8220;",
        "&rdquo;"   : "&#8221;",
        "&bdquo;"   : "&#8222;",
        "&dagger;"  : "&#8224;",
        "&Dagger;"  : "&#8225;",
        "&permil;"  : "&#8240;",
        "&lsaquo;"  : "&#8249;",
        "&rsaquo;"  : "&#8250;",
        "&euro;"    : "&#8364;",
        }

    replacedText = text;
    for key in strToNumEntDict.keys() :
        replacedText = re.compile(key).sub(strToNumEntDict[key], replacedText);
    return replacedText;

例 2.12. replaceStrEntToNumEnt的使用范例

line = replaceStrEntToNumEnt(line);


2.2.7. 去除控制字符:removeCtlChr		2.2.9. 将xxx=yyy转换为元祖（tuple）变量:convertToTupleVal

详解crifan的Python库：crifanLib.py2.2. 和字符串(str,unicode等)处理有关的函数

2.2.8. 将字符实体替换为Unicode数字实体:replaceStrEntToNumEnt

详解crifan的Python库：crifanLib.py

2.2. 和字符串(str,unicode等)处理有关的函数