'''
Created on Mar 27, 2014

@author: Brett Paufler

Copyright Brett Paufler
'''


import os
import urllib2


'''
STEP TWO
Gets the Scratches webpages, based on info in Step One

    lotto_pickle is the next step
'''




def extractScratchersURL():
    '''Depends upon files downloaded with lotto_download_html
    
        cycles through scratchers.html (1-20)
        and outputs list of html addresses
    
    '''
    
    sourceDir = ".\\lottery"
    dirListing = os.listdir(sourceDir)
    #print dirListing

    sourceFiles = []
    
    #finds current Scratcher page names
    #VERY BRITTLE
    for webPage in dirListing:
        if webPage.startswith("scratch"):
            #print webPage
            pathString = ".\\lottery\\" + webPage
            page = open(pathString, 'r')
            for line in page:
                #print line
                if 'href="/Play/Scratchers' in line:
                    sB = line.split('href="')
                    for bit in sB:
                        print bit
                        if "/Play/Scratchers-games/" in bit:
                            bitLess = bit.split('">')
                            for bM in bitLess:
                                if "/Play/Scratchers-games/" in bM:
                                    sourceFiles.append(bM)
    
    unique = []
    baseURL = "http://www.calottery.com"
    for item in sourceFiles:
        uniURL = baseURL + item + '.html'
        unique.append(uniURL)
    
    unique = set(unique)
    
    print unique
    return unique





def downloadWebpage(thisURL="http://www.calottery.com", name="caLottery.html", dirThis="lottery"):
    print "downlaodWebpage called"
    if dirThis == "":
        localName = name
    else:
        localName = ".//" + dirThis + ".//" + name
    imgurHomeURL = thisURL
    imgurPage = urllib2.urlopen(imgurHomeURL)  
    LocalWegPage = open(localName, 'wb')
    LocalWegPage.write(imgurPage.read())
    LocalWegPage.close()
    if os.path.exists(localName):
        print thisURL + " webpage saved as " + localName


def downloadALLScratchers():
    '''runs the Wad downloading all the scratchers pages
    
    '''
    print "downloadAllScratchers started"
    
    #list of pages to download, complete URL
    pages = extractScratchersURL()

    for url in pages:
        nameList = url.split("-Scratchers/")
        for word in nameList:
            if "Scratchers" not in word:
                sN = "SGAME-" + word + ".html"
                print "DOWNLOADING URL: %s \t sN: %s" % (url, sN)

                downloadWebpage(url, sN)


if __name__ == '__main__':
    print "downloading all scratchers"            
    downloadALLScratchers()