clawer for kasi-time.com

kasi.js

// Usage: node kasi.js <id>
// Example:
//   Get lyric from http://www.kasi-time.com/item-55961.html
//   node kasi.js 55961

var http = require('http');
var vm = require('vm');

var no = process.argv[2];

// To Render HTML to Plain Text
var render = (function () {

  // Focus on horizontial (tab) and vertical (line break) and escaped characters
  var br0 = ['br', 'hr'];
  var br1 = ['li', 'p', 'tr', 'table'];
  var tab = ['td'];

  // Escape map from entity name to code
  var esc = {
    'euro': 8364, 'nbsp': 32, 'quot': 34, 'amp': 38, 'lt': 60, 'gt': 62,
    'iexcl': 161, 'cent': 162, 'pound': 163, 'curren': 164, 'yen': 165, 'brvbar': 166, 'sect': 167, 'uml': 168, 'copy': 169, 'ordf': 170, '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
  };

  var unescape = function (str) {
    return str.replace(/&([^#;]+);/gi, function (match, entity) {
      return '&#' + (esc[entity] || entity) + ';';
    }).replace(/&#([0-9]+);/gi, function (match, code) {
      return String.fromCharCode(+code);
    });
  };

  return function (html) {

    var text = '';
    var re = /[<]([^<>]+)[>]/gi, match, lastIndex = 0;
    var nest = [];

    while ((match = re.exec(html))) {

      var name = match[1], close = name[0] == '\/', open = !close;

      name = name.slice(+close).trim();

      if (name.slice(-1) == '\/') {
        open = close = true;
        name = name.slice(0, name.length - 1).trim();
      }

      text += unescape(html.slice(lastIndex, re.lastIndex - match[0].length));

      var last = nest[nest.length - 1];

      if (~br0.indexOf(name)) text += '\n';
      else if (open) {
        if (name == last) close = true;
        nest.push(name);
      }

      if (close) {
        while ((last = nest.pop()) != name) {
          if (~br1.indexOf(last)) text += '\n';
          if (~tab.indexOf(last)) text += '\t';
        }
        if (~br1.indexOf(name)) text += '\n';
        if (~tab.indexOf(name)) text += '\t';
      }

      lastIndex = re.lastIndex;

    }

    text += unescape(html.slice(lastIndex));

    while (nest.length > 0) {
      var unclosed = nest.pop();
      if (~br1.indexOf(unclosed)) text += '\n';
      if (~tab.indexOf(unclosed)) text += '\t';
    }

    return text;

  };

})();

http.get('http://www.kasi-time.com/item_js.php?no=' + no, function (res) {

  if (res.statusCode != 200) {
    return console.log('ERROR - HTTP Status ' + res.statusCode);
  }

  // Initialize a Buffer to receive message body
  // MAXIMUM body data size is bound to 1MB
  var buffer = new Buffer(1024 * 1024), bufptr = 0;

  res
  .on('data', function (chunk) {

    // Use buffer copy concating data chunks
    bufptr += chunk.copy(buffer, bufptr);

  })
  .on('end', function () {

    // Get JavaScript code
    var code = buffer.slice(0, bufptr).toString();

    // Compile code to Script object
    var script = vm.createScript(code, 'item.js');

    // Create a Sandbox (Execution Context Object)
    var sandbox = {
      document: {
        write: function (html) {
          var text = render(html);

          return console.log(text);
        }
      }
    };

    // Execute Script in Sandbox
    script.runInNewContext(sandbox);

  });

}).on('error', function (err) {

  console.log(err);

});