Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 14 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ var nextCounter = 0;

google('node.js best practices', function(err, next, links){
if (err) console.error(err);
for (var i = 0; i < links.length; ++i) {
console.log(links[i].title + ' - ' + links[i].link); //link.href is an alias for link.link
console.log(links[i].description + "\n");
Expand All @@ -56,6 +56,18 @@ google('node.js best practices', function(err, next, links){
});
```

Specifying a proxy to be used when searching

```javascript
var google = require('google');

google.proxy = 'http://user:password@192.168.5.4:80';

google('node.js best practices', function(err, next, links){
});
```

CLI
---

Expand Down Expand Up @@ -114,6 +126,7 @@ Contributors
* [ithil](https://github.com/ithil)
* [Jaimie Pillora](https://github.com/jpillora)
* [Jan Ehrhardt](https://github.com/jehrhardt)
* [Griffith T. Pickett](https://github.com/tpickett)


License
Expand Down
71 changes: 43 additions & 28 deletions lib/google.js
Original file line number Diff line number Diff line change
@@ -1,14 +1,14 @@
var request = require('request')
, cheerio = require('cheerio')
, fs = require('fs')
, querystring = require('querystring')
, util = require('util');
var request = require('request'),
cheerio = require('cheerio'),
fs = require('fs'),
querystring = require('querystring'),
util = require('util');


var linkSel = 'h3.r a'
, descSel = 'div.s'
, itemSel = 'li.g'
, nextSel = 'td.b a span';
var linkSel = 'h3.r a',
descSel = 'div.s',
itemSel = 'li.g',
nextSel = 'td.b a span';

var URL = 'http://www.google.%s/search?hl=%s&q=%s&start=%s&sa=N&num=%s&ie=UTF-8&oe=UTF-8';

Expand All @@ -19,48 +19,63 @@ function google(query, callback) {
google.resultsPerPage = 10;
google.tld = 'com';
google.lang = 'en';
google.proxy = null;

var igoogle = function(query, start, callback) {
if (google.resultsPerPage > 100) google.resultsPerPage = 100; //Google won't allow greater than 100 anyway

var newUrl = util.format(URL, google.tld, google.lang, querystring.escape(query), start, google.resultsPerPage);
request(newUrl, function(err, resp, body) {
var newUrl = util.format(URL, google.tld, google.lang, querystring.escape(query), start, google.resultsPerPage),
requestOptions = {
url: newUrl,
method: 'GET'
};

//make sure we have a set proxy for the scrape
if (google.proxy != null) {
//set request.proxy to the provided google.proxy
requestOptions.proxy = google.proxy;
}

request(requestOptions, function(err, resp, body) {
if ((err == null) && resp.statusCode === 200) {
var $ = cheerio.load(body)
, links = []
, text = [];
var $ = cheerio.load(body),
links = [],
text = [];

$(itemSel).each(function(i, elem) {
var linkElem = $(elem).find(linkSel)
, descElem = $(elem).find(descSel)
, item = {title: $(linkElem).first().text(), link: null, description: null, href: null}
, qsObj = querystring.parse($(linkElem).attr('href'));

var linkElem = $(elem).find(linkSel),
descElem = $(elem).find(descSel),
item = {
title: $(linkElem).first().text(),
link: null,
description: null,
href: null
},
qsObj = querystring.parse($(linkElem).attr('href'));

if (qsObj['/url?q']) {
item.link = qsObj['/url?q']
item.href = item.link
}

$(descElem).find('div').remove();
item.description = $(descElem).text();

links.push(item);
});

var nextFunc = null;
if ($(nextSel).last().text() === 'Next'){
if ($(nextSel).last().text() === 'Next') {
nextFunc = function() {
igoogle(query, start + google.resultsPerPage, callback);
igoogle(query, start + google.resultsPerPage, callback);
}
}

callback(null, nextFunc, links);
} else {
callback(new Error('Error on response' + (resp ? ' ('+resp.statusCode+')' : '') + ':' + err +" : " + body), null, null);
callback(new Error('Error on response' + (resp ? ' (' + resp.statusCode + ')' : '') + ':' + err + " : " + body), null, null);
}
});
}

module.exports = google;