WWDC2014 video download

download_wwdc_2014

#!/usr/bin/python

import urllib2
from xml.dom import minidom
from bs4 import BeautifulSoup
import json
import os
import subprocess

#read download session
videoList = []
if os.path.exists("/tmp/wwdc_download"):
    print "Find list!"
    f = open("/tmp/wwdc_download", "rw")
    videoList = json.load(f)
    f.close()
else:
    page =  urllib2.urlopen("https://developer.apple.com/videos/wwdc/2014/")
    print "Downloading list..."
    print "Get the page!"
    soup = BeautifulSoup(page)
    videos = soup.body.find_all("li", attrs={"class": "session"})
    for video in videos:
        sessionID = video.attrs['id']
        name = video.find("li", attrs={"class" : "title"}).string
        pDownload = video.find("p", attrs={"class" : "download"})
        links = pDownload.find_all("a")
        urls = {}
        for link in links:
            urls[link.string] = link.attrs["href"]
        print "%s: %s" %(sessionID, name)
        #print urls["HD"]

        obj = {}
        obj["ID"] = sessionID
        obj["name"] = name
        obj["urls"] = urls
        obj["isdone"] = 0

        videoList.append(obj)

    f = open("/tmp/wwdc_download", "w")
    json.dump(videoList, f)
    f.close()

for obj in videoList:
    if obj["isdone"] == 0:
        url = obj["urls"]["HD"]
        print "Downloading %s: %s" %(obj["ID"], obj["name"])
        output = ""+obj["ID"]+": "+obj["name"]+".mov"
        subprocess.call(['wget', '-c', '-P', '~/wwdc2014/', url, "-O", output])
        obj["isdone"] = 1
        #save new data to disk
        f = open("/tmp/wwdc_download", "w")
        json.dump(videoList, f)
        f.close()