'''
Created on Mar 11, 2014
@author: Brett Paufler
Copyright Brett Paufler 
'''


import re
import urllib2
import os
import imgur_crawl
import sets
import pickle
import random
import imgur_logic
import webbrowser
import imgur_pageup
import Tkinter as tk
import Image, ImageTk
import imageManagement



''' Interesting REG EX'''
#'''href=["'](.[^"']+)["']'''


print "imageCrawler Started"

'''
TODO  BRING THIS BACK
'''
#



'''
Initial Front Page Crawl When Program Starts
'''
def frontPageCrawl():
    print "frontPageCrawl(): Initiated"
    #Crawl imgur Gallery
    imgur_crawl.initialImgurCrawl() 

    #Pre-Processes Front Page
    imgur_crawl.imageFrontPageToDataTextFile()

    #Adds Front page to Rolling Gallery File
    imgur_crawl.frontPageReadtoRollingGalleryFile()
    print "frontPageCrawl(): Finished"
frontPageCrawl()



'''
This processes the existing galleryDatabase
And returns a galleryObject
'''
def testerPageUpAfterInitialCrawl():
    print "testerPageUpAfterInitialCrawl(): Initiated"

    nextImgurGalleryObject = imgur_logic.runLogic()
    print repr(nextImgurGalleryObject)
    
    imgur_pageup.viewNextGallery(nextImgurGalleryObject)
    return nextImgurGalleryObject
    print "testerPageUpAfterInitialCrawl(): Finished"
    return nextImgurGalleryObject()
testerPageUpAfterInitialCrawl()


'''
Save Imgur Page based on Next gallery
Show Gallery
Update database
Wash Repeat
'''

#This is redundant
nIGO = imgur_logic.runLogic()
print repr(nIGO)

'''
This Pulls the Updated Page, saves at imgurGalleryPage
Commented out while work out rest of code

imgGalleryURL = "http://imgur.com/gallery/" + nIGO["gallery"]
imgur_crawl.downloadWebpage(imgGalleryURL, "imgurGalleryPage.html", "imgur")
'''






'''
Extracting Info from Saved Webpage -- IMGUR GALLERY


AND THIS PROBABLY ISN'T GOING TO WORK WITHOUT A PLUG-IN OR LIBRARY EXTENSION

'''
def imgurGalleryPageDataTextFile(savedWebpageLocation = ".//imgur//imgurGalleryPage.html", outputFile = ".//imgur//thisImgurPageDatumFile.txt"):

    print "imgurGalleryPageDataTextFile(): starting"
    currentGalleryData = []  

    with open (savedWebpageLocation, 'r') as rawFile:
        fileString = rawFile.read()
        fileString = fileString.replace("\n"," ")
        fileString = fileString.replace("\t"," ")
        fileString = fileString.replace("\r"," ")
        for r in range(0,10):
            fileString = fileString.replace("  "," ")
       
    print fileString
    '''
    fileBits = fileString.split("<a ")
    print fileBits

    for piece in fileBits:
        
        temp = imgur_crawl.createEmptyGalleryObject()   
        #print piece
        piece = piece[:piece.find("</a>")]
        print piece
    
        if piece.startswith("href="):        
            start = 'href="'
            end = '">'
            urlString = re.search(re.escape(start)+"(.*?)"+re.escape(end),piece).group(1) 
   
   '''
   
         

    textOut = open(outputFile, "w")
    pickle.dump(currentGalleryData, textOut)
    textOut.close()
    
    cbuName = outputFile[:-4] + "TEXTCBU.txt"
    CBUtextOut = open(cbuName, "w")
    for datum in currentGalleryData:
        CBUtextOut.write(repr(datum) + "\n")
    CBUtextOut.close()
    

    print repr(currentGalleryData)
    
    print "imgurGalleryPageDataTextFile(): FINISHING"
    return currentGalleryData
# end imageGalleryPageDataTextFile




imgurGalleryPageDataTextFile()





    



'''

DON"T NEED THESE FOR NOW
TODO BRING BACK OR REDUCE TO FUNCTION (probably not

'''
imageManagement.resizePicture()
#imgur_pageup.runSavePictureButtonTKinputBox()









print "imageCrawler Finished"

#http://imgur.com/gallery/------