Created
April 22, 2014 23:10
-
-
Save avermeulen/11197548 to your computer and use it in GitHub Desktop.
Html Scraping using PhantomJS and JQuery
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 page = require('webpage').create(); | |
page.onAlert = function (msg) { | |
console.log('alert!!> ' + msg); | |
}; | |
page.onConsoleMessage = function (msg, line, source) { | |
console.log('console> ' + msg); | |
}; | |
//http://www.f1calendar.com | |
page.open('http://www.f1calendar.com', function(status) { | |
console.log("status : " + status); | |
page.injectJs('./jquery-1.11.0.js'); | |
if (!phantom.state){ | |
page.evaluate(function(){ | |
var getRaces = function(){ | |
var races = $("table#formula_one_events tbody"); | |
var raceList = {}; | |
$.each(races, function(idx, race){ | |
var events = $(race).find(".vevent"); | |
$.each(events, function(id, evt){ | |
var raceName = $(evt).find(".event-column .extra:first").text() | |
.replace(",", "") | |
.replace("Formula 1 ", ""); | |
var theRace = raceList[raceName] = raceList[raceName] || {events : []}; | |
var eventType = $(evt).find(".event-column .category").text(); | |
var eventTime = $(evt).find(".date-column .dtstart").attr("title"); | |
theRace.events.push( {eventType : eventType, eventTime : eventTime} ); | |
}); | |
}); | |
return raceList; | |
}; | |
var formatRaceEventDetails = function(raceList){ | |
var raceDetailsList = []; | |
for(var race in raceList){ | |
//console.log("race : " + race); | |
var events = raceList[race].events; | |
var e = {}; | |
events.forEach(function(ev){ | |
switch(ev.eventType){ | |
case "First Practice Session": | |
e.practice1 = ev.eventTime; | |
break; | |
case "Second Practice Session": | |
e.practice2 = ev.eventTime; | |
break; | |
case "Third Practice Session": | |
e.practice3 = ev.eventTime; | |
break; | |
case "Qualifying Session": | |
e.qualifying = ev.eventTime; | |
break; | |
case "Grand Prix": | |
e.race = ev.eventTime; | |
break; | |
}; | |
}); | |
if (race.trim() !== ""){ | |
raceDetailsList.push({ | |
raceName : race.trim(), | |
events : e | |
}); | |
} | |
} | |
return raceDetailsList; | |
}; | |
var raceDetailsList = formatRaceEventDetails(getRaces()); | |
console.log(JSON.stringify(raceDetailsList)); | |
}); | |
} | |
else{ | |
console.log('state'); | |
} | |
phantom.exit(); | |
}); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment