Using the FileSystem/File API to dump page contents

dumpToDiskViaFileSystemAPI.js

// Customized version of the FileSystem API examples described at http://www.html5rocks.com/en/tutorials/file/filesystem/
//   - Primarily used to dump the microdata example content protrayed in http://www.w3.org/html/wg/drafts/microdata/master/
//   - Runs on any page containing one or more pre elements, but assumes that jQuery has been loaded as either part of the 
//     page or after the fact via jQuerify. 
//   - On Windows 8, the resulting files appear to be created in "%LOCALAPPDATA%\Google\Chrome\User Data\Default\File System" 
//     Example: C:\Users\<userName>\AppData\Local\Google\Chrome\User Data\Default\File System\001\p\00

// Define the success callback for webkitRequestFileSystem()
function onInitFs(fs) {

    // Generate unique file names
    var i = 0;

    // Grab each pre element and write its contents to disk
    $('pre').each(function () {
        var content = $(this).text(),
            fileName = 'preContent' + i++ + '.txt';

        fs.root.getFile(fileName, { create: true }, function (fileEntry) {

            // Create a FileWriter object for our FileEntry
            fileEntry.createWriter(function (fileWriter) {

                fileWriter.onwriteend = function (e) {
                    console.log('Write completed.');
                };

                fileWriter.onerror = function (e) {
                    console.log('Write failed: ' + e.toString());
                };

                // Create a new Blob and write to the output stream/FileWriter
                fileWriter.write(new Blob([content], { type: "text/plain" }));

            }, errorHandler);

        }, errorHandler);
    });
}

// Request persistent storage and when allowed, call into webkitRequestFileSystem and thus onInitFS
window.webkitStorageInfo.requestQuota(PERSISTENT, 1024 * 1024, function (grantedBytes) {
    window.webkitRequestFileSystem(PERSISTENT, grantedBytes, onInitFs, errorHandler);
}, errorHandler);

function errorHandler(e) {
    var msg = '';

    switch (e.code) {
        case FileError.QUOTA_EXCEEDED_ERR:
            msg = 'QUOTA_EXCEEDED_ERR';
            break;
        case FileError.NOT_FOUND_ERR:
            msg = 'NOT_FOUND_ERR';
            break;
        case FileError.SECURITY_ERR:
            msg = 'SECURITY_ERR';
            break;
        case FileError.INVALID_MODIFICATION_ERR:
            msg = 'INVALID_MODIFICATION_ERR';
            break;
        case FileError.INVALID_STATE_ERR:
            msg = 'INVALID_STATE_ERR';
            break;
        default:
            msg = 'Unknown Error';
            break;
    };

    console.log('Error: ' + msg);
}

Unexpectedly, the content written to disk is HtmlEncoded. Haven't figured out where in the specs this behavior is documented and switching to text/html doesn't have an impact on the writer

Whoops. It looks like the reason the content was HtmlEncoded is due to the fact that I was calling .html() on pre elements rather than .text(). It's not entirely obvious that .text() on pre is what is needed to extract the unadulterated html but at least I've finally made sense of the confusing behavior and resolved the mix-up.