crawler-find-word - npm Package Compare versions

Comparing version 0.1.0 to 0.1.1

package.json

		{
		"name": "crawler-find-word",
		"version": "0.1.0",
		"version": "0.1.1",
		"description": "crawler service",
		@@ -28,3 +28,4 @@ "main": "crawler-find-word.js",
		"keywords": [
		"crawler"
		"crawler","crawling","scraper","spider","search","find",
		"word","phrase","javascript","node","nodejs","url"
		],
		@@ -31,0 +32,0 @@ "bugs": {

README.md

		@@ -1,2 +0,2 @@
		## crawler-find-phrase
		## Simple but powerful crawler - find phrase deep in the web

		@@ -8,19 +8,40 @@ [![Build Status](https://travis-ci.org/idangvili/crawler-find-word.svg?branch=master)](https://travis-ci.org/idangvili/crawler-find-word)
		Deep crawl to find word in the body of web pages by base url
		Simple but powerful, popular and production crawling/scraping package for Node.

		## Features:

		Configurable level of maximum pages to visit
		Configurable root URL and Word to search
		Use event driven API, Raise 'Done' event when process ends.
		Return usefull statistical data.
		Use Cheerio to find word or phrase in the DOM.
		Tested with Mocha and Chai

		## Future features

		Add 'Error' event handling.
		Priority queue of requests.
		Control rate limit.
		Charset detection and conversion.

		## Demo

		### 'use strict';
		### var srv = require('crawler-find-word');
		### var print = function(){
		### var count = srv.pages.length;
		### for(var i=0; i < count; ){
		### var u = srv.pages.pop();
		### console.log(JSON.stringify(u));
		### i++;
		### };
		### }
		###
		### srv.eventHandler.on('done', print);
		### srv.crawl('https://cnn.com/', 'trump', 2);
		```node

		'use strict';
		var srv = require('crawler-find-word');
		var print = function(){
		var count = srv.pages.length;
		for(var i=0; i < count; ){
		var u = srv.pages.pop();
		console.log(JSON.stringify(u));
		i++;
		};
		}

		srv.eventHandler.on('done', print);
		srv.crawl('https://cnn.com/', 'trump', 2);

		```

		## Run
		@@ -27,0 +48,0 @@

New alerts