Created
April 28, 2016 23:32
-
-
Save karlding/a09050233c8e6d56f9ea1e342487ba35 to your computer and use it in GitHub Desktop.
Screenshot each page of the CECA employment statistics website using CasperJS, for "safekeeping". Follow the on-screen prompts for instructions.
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 system = require('system'); | |
var casper = require('casper').create({ | |
pageSettings: { | |
loadImages: true, | |
loadPlugins: false, | |
userAgent: 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36' | |
} | |
}); | |
// read from cin to prevent login credentials being stored in bash history | |
system.stdout.writeLine('WatIAm login:'); | |
var username = system.stdin.readLine(); | |
system.stdout.writeLine('WatIAm password:'); | |
var password = system.stdin.readLine(); | |
system.stdout.writeLine('Term: (ex. 1161)'); | |
var term = system.stdin.readLine(); | |
system.stdout.writeLine('Date: (ex. 20160114)'); | |
var date = system.stdin.readLine(); | |
casper.start('https://info.uwaterloo.ca/infocecs/students/statistics/index.php'); | |
casper.setHttpAuth(username, password); | |
casper.on( 'page.error', function (msg, trace) { | |
this.echo( 'Error: ' + msg, 'ERROR' ); | |
}); | |
var faculty; | |
// first scrape all the valid faculties | |
casper.then(function() { | |
faculty = this.evaluate(function() { | |
var faculties = document.querySelectorAll('select[name="Faculty"] option'); | |
var temp = []; | |
for (i = 0; i < faculties.length; ++i) { | |
temp.push(faculties[i].text); | |
} | |
return temp; | |
}); | |
}); | |
// iterate through all the faculties we scraped | |
var current = 0; | |
casper.then(function() { | |
for (; current < faculty.length; ) { | |
(function(cntr) { | |
var id = current; | |
casper.then(function() { | |
iterateFaculty(id); | |
}); | |
})(current); | |
current++; | |
} | |
}); | |
function iterateFaculty(id) { | |
var baseurl = "https://info.uwaterloo.ca/infocecs/students/statistics/graph.php"; | |
var screenshoturl = baseurl + "?Term=" + term + "&Faculty=" + id + "&Level=-1&Date=" + date; | |
casper.thenOpen(screenshoturl, function() { | |
}); | |
casper.then(function() { | |
var location = term + "/" + date + "/" + faculty[id].replace(/\s+/g, '-').toLowerCase() + ".png"; | |
this.capture(location); | |
console.log("Saving to: " + location); | |
}) | |
} | |
casper.run(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment