Created
May 12, 2014 17:01
-
-
Save awavering/28838586aceb40e926d4 to your computer and use it in GitHub Desktop.
BSD Team Page Scraper
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
var bsd=[]; | |
$("article.headshot").each(function(){ | |
var name = $("h4:first",this).text() | |
var email = $("a", this).text()+"bluestatedigital.com"; | |
var city = $("h5:last", this).text(); | |
var title = $("h5:first", this).text().replace(/\n/g," "); | |
var image = $("img", this).attr("src"); | |
var team = null; | |
if(title.match(/Team/) || (title.match(/\,/) && !title.match(/(NY|DC|LA|UK|SF)$/) ) ) { | |
var split_title = title.split(", "); | |
var team = split_title.pop(); | |
title = split_title.join(", "); | |
} | |
else{ | |
team = "Management"; | |
} | |
if(!team.match(/Team/)){ | |
console.log(name, title, team); | |
} | |
title = title.replace(/ +/g,"").replace(/\n/g," "); | |
team = team.replace(/ +/g,"").replace(/\n/g," "); | |
var employee = {"name":name , "email": email, "city": city, "title": title, "image": image, "team": team }; | |
bsd.push( employee ); | |
}); | |
var sql="INSERT INTO bsd.employees(name,email,city,title,image,team) VALUES"; | |
for(var i=0;i<bsd.length;i++){var emp=bsd[i]; | |
sql += '("' + emp.name + '","' + emp.email + '","' + emp.city + '","' + emp.title+ '","' + emp.image + '","' + emp.team + '"), '; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment