This brief documentation doesn't include full API methods and parameters. Full library API documentation could be found in doc folder.
Library can be installed from npm
npm install diffbot-coffee
Obtaining CoffeeScript Diffbot client is simple as that:
{Client} = require 'diffbot-coffee'
client = new Client '<your_key>'Assume that we have our client configured. In order to use Automatic Article API we need to instantiate Article API instance first:
article = client.article 'http://someurl.com', ['title']After instantiation we can use our client object to retrieve information
article.load (error, result) ->
if error?
console.error error
else
console.log resultIf your content is not publicly available (e.g., behind a firewall), you can use send method or article object
article = client.article 'http://diffbot.com', ['title']
content = '<html><head><title>Test title</title></head><body>Test body</body></html>'
article.send content, (error, result) ->
if error?
console.error error
else
console.log resultThere is also alternative syntax for creating article objects
article = client.article
url: 'http://someurl.com'
fields: ['title']
console.log article.url
console.log article.relative_url
article.load (error, result) ->
if error?
console.error error
else
console.log result.typeSimilar syntax is available for all objects.
Calling Page Classifier API is also pretty simple:
pageclassifier = client.pageclassifier 'http://someurl.com'
pageclassifier.load (error, result) ->
if error?
console.error error
else
console.log result.typeCalling Crawlbot API is similar to calling Article API. One thing worth to notice is that Crawlbot API Version 2 requires apiUrl which will be used to perform crawling. Library implementation makes possible to avoid using urls here. Instead we will use Article API:
crawler = client.crawlbot 'my-bot', ['http://someurl.com', 'http://foo.com'], client.article('', ['title']).url
crawler.create (error, result) ->
if !error?
console.log resultor alternatively we can set optional parameters as object
crawler = client.crawlbot 'my-bot',
seeds: ['http://someurl.com', 'http://foo.com']
apiUrl: client.article('', ['title']).url
crawler.create (error, result) ->
if !error?
console.log resultCrawler object supports next methods
crawler.pause
crawler.restart
crawler.delete
crawler.data
crawler.statusUsage is pretty simple
or alternatively we can set optional parameters as object
crawler = client.crawlbot 'my-bot',
seeds: ['http://someurl.com', 'http://foo.com']
apiUrl: client.article('', ['title']).url
crawler.create (error, result) =>
if !error?
crawler.delete (error, result) =>
if !error? and result
console.log 'Crawler successfully deleted'