Last active
January 19, 2016 13:33
-
-
Save chirag64/199bf529a32ff387f21f to your computer and use it in GitHub Desktop.
A quick and hacky script to fetch key sentences from a blog or news article. Basically fetches the sentences with most words in them.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// Get all sentences | |
var sentences = document.body.innerText.split("."); | |
// Remove all sentences with newline characters in them since they're likely tags or sidebar data | |
for (i=sentences.length - 1; i>-1; i--) | |
{ | |
if (sentences[i].trim().indexOf("\n") !== -1) | |
{ | |
sentences.splice(i,1); | |
} | |
} | |
// Sort all sentences by character length | |
var slength = {}; | |
for (i=0; i<sentences.length;i++) | |
{ | |
slength[i] = sentences[i].length; | |
} | |
var NUM = 5; | |
var sorted = Object.keys(slength).sort(function(a,b){return slength[b]-slength[a]}); | |
sorted = sorted.slice(0,NUM); | |
sorted.sort(function(a,b){return parseInt(a)-parseInt(b)}); | |
// Put all sentences with highest count of characters in a string and then print it | |
var str = ""; | |
for (i=0; i<sorted.length; i++) | |
{ | |
//console.log(sorted[i]); | |
str += (sentences[parseInt(sorted[i])].trim() + ".\n\n"); | |
} | |
console.log(str); | |
//alert(str); | |
document.write(str.replace(/\n\n/g,"<br /><br />")) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment