tautologistics/node-htmlparser

Streaming To Parser in Node - Example Request

joshvito opened this issue · 1 comments

Can you share an example of a working script using Streaming To Parser in Node?
Using your README text generates an error.

fs.createReadStream('./path_to_file.html').pipe(parser);

I get this error in console:

_stream_readable.js:476
  dest.on('unpipe', onunpipe);
       ^
TypeError: Object #<Parser> has no method 'on'
    at ReadStream.Readable.pipe (_stream_readable.js:476:8)
    at Object.<anonymous> (C:\dev\autorelease\script.js:54:8)
    at Module._compile (module.js:456:26)
    at Object.Module._extensions..js (module.js:474:10)
    at Module.load (module.js:356:32)
    at Function.Module._load (module.js:312:12)
    at Function.Module.runMain (module.js:497:10)
    at startup (node.js:119:16)
    at node.js:902:3

Here is my simple script:

// get a file stream reader 
var reader = fs.createReadStream(process.argv[2]);

// get a file stream writer pointing to the json file to write to
var writer = fs.createWriteStream(input_json);

var htmlparser = require("htmlparser");
//var rawHtml = "Xyz <script language= javascript>var foo = '<<bar>>';< /  script><!--<!-- Waah! -- -->";
//var sys = require("sys");

var handler = new htmlparser.DefaultHandler(function (error, dom) {
    if (error)
        logger.log('error', 'handler error in parser', {error: error});
    else
        logger.log('info', '', {dom: JSON.stringify(dom)});
});
var parser = new htmlparser.Parser(handler);
//parser.parseComplete(reader);
//sys.puts(sys.inspect(handler.dom, false, null));

// pipe everything to do the conversion
reader.pipe(parser).pipe(writer);

I have the same issue.