gulp-tika-extractor 
Document extractor using Tika for Gulp
Usage
First, install gulp-tika-extractor as a development dependency:
npm install --save-dev gulp-tika-extractorThen, add it to your gulpfile.js:
var extract = require('gulp-tika-extractor');
gulp.task('extract pdf document to txt', function(){
gulp.src(['file.pdf'])
.pipe(extract())
.pipe(gulp.dest('extracted/'));
});