나영갤에서 그림 받아오기.

#!/usr/bin/python
 
import re
import urllib
import random
import os
import glob
 
gallUrlPost = 'http://gall.dcinside.com/list.php?id=nayoung&no='     <span> ### 다른갤 선택시 적당히 찾아보시고 바꿔주세요.</span>
gallUrl = gallUrlPost[0:-4]
gallSrcNo = 11000          <span> ### 최근 게시물로부터의 몇개 아래까지의 DB검색을 의미합니다. 나영갤에 포스트된 글이 원래 많아서 11000 이니깐 다른갤로 수정시 적당히 변경하세요. </span>  
saveDir = "/Users/purewater/Documents/Pictures/myimages/"           <span> ### 받아올 이미지 저장되는 디렉토리입니다. "myimages"는 없으면 자동으로 생성하는데 상위 디랙토리는 생성되어 있어야 합니다.</span>
print ""
print '[[[ Stats for Getting the Pics from Gallery ]]]'
print 'Gallery Url : ',gallUrl
print 'Checking saveDir...'
tmpDir = os.path.split(saveDir)
rlsavDir = tmpDir[0]
if os.path.isdir(saveDir):
       print rlsavDir, "aleady exist."
else:
       print rlsavDir, "does not exist."
       print "Creating saveDir"
       om = os.mkdir(saveDir)
       if os.path.isdir(saveDir):
	  print "SaveDir was created successfully."
       else:
          print "Fail to create saveDir"
 
def readRange():
    print 'Connect to Server...'
    #f = urllib.urlopen(gallUrl)
    try:
       f = urllib.urlopen(gallUrl)
    except:
       print "Can not connect Server. Check Network..."
       return 0
       #break
    print "Connected. ranging..."
    html = f.read()
    parserToFind1 = '>\d+\d</span>'
    parserToFind2 = '<a href="/list.php\?id=nayoung&no=\d+\d&page'
    #parserToFind3 = '/> <a href="/list.php?id=nayoung&no='
    parserFound = re.findall(parserToFind1, html)
    parserFound2 = re.findall(parserToFind2, html)
    realDBnum = parserFound2[6][33:38]
    #print html
    maxNum = parserFound[0][1:6]    
    #print parserFound[0]
    subNum1 = int(maxNum)
    print 'Most recent thread No.', subNum1
    print "Real DB No:",realDBnum
    #print 'maxNumber :', subNum1,',max realDBnum :', realDBnum
    print 'max realDBnum :', realDBnum
    realDBnum2 = int(realDBnum) - gallSrcNo
    subNum2 = subNum1 - gallSrcNo
    #print 'minNumber :', subNum2,',min realDBnum :', realDBnum2
    print 'min realDBnum :', realDBnum2
    print "Drawing in range..."
    extNo = random.randint(realDBnum2,int(realDBnum))
    print 'Adopted random posting number :: ', extNo
    return extNo
 
def bigOne(bigOne,tmpBigone):
    if tmpBigone > bigOne:
       bigOne = tmpBigOne
    else:
       bigOne = bigOne
       return bigOne
 
def calcDirSize(arg, dir, files):
    for file in files:
        stats = os.stat(os.path.join(dir, file))
        size = stats[6]
	#print arg
        arg.append(size)
 
def getDirSize(dir):
    sizes = []
    os.path.walk(dir, calcDirSize, sizes)
    total = 0								
    for size in sizes:					
	total = total + size
    #print total
    return float(total)
 
def backupPics(inputBackfile):
	backupDir = saveDir+"backupPics/"
	#print "backupDir is", backupDir
	if os.path.isdir(backupDir):
	   null = 0	
	   #print backupDir,"aleady exist."
	else:
	   print backupDir, "does not exist."
	   print "Creating saveDir"
	   try:
              om = os.mkdir(backupDir)
           except:
              print "mkdir IOError."
           if os.path.isdir(saveDir):
              print "backupDir was created successfully."
	   else:
	      print "Fail to create backupDir"
 
        fileList = glob.glob(backupDir+'[0-9]*.jpg')
        flSize = len(fileList)
	#print "flSize :",flSize
	bigOne = 0
        for name in fileList:	
	    srcName = os.path.split(name)
	    dirName = srcName[0]
	    fileName = srcName[1]
	    fullFileName = os.path.splitext(fileName)
	    onlyFileName = fullFileName[0]
	    extName = fullFileName[1]
	    #print "filename :",fileName,"onlyFileName :",onlyFileName
	    #print str(onlyFileName)
	    pF = re.search('\D*\d*\D', onlyFileName)
	    #print "PF is",str(pF)
	    if pF:
	       #print "pF is Exist"
	       null = 0
	    else:
	       #print "pF is not Exist"
	       tmpBigone = int(onlyFileName)
 
               if tmpBigone > bigOne:
	          bigOne = tmpBigone
               else:
	          bigOne = bigOne
 
            #print "The BIG one is",bigOne
 
	lNumdet = bigOne + 1
	#print "LNumdet",lNumdet
	#inputFile = backupDir + str(lNumdet)+".jpg"
        srcfile = open(inputBackfile, 'r')
	readLines = srcfile.readlines()
	#print inputFile
	srcName = os.path.split(inputBackfile)
	dirName = srcName[0]
	fileName = srcName[1]
        onlyFileName = os.path.splitext(inputBackfile)
        extName = onlyFileName[1]
	#print dirName
	#print extName
	outputBackfile = backupDir + str(lNumdet)+".jpg"
        #print outputBackfile
	trgfile = open(outputBackfile, 'w')
	for eachLine in readLines:
           trgfile.write(eachLine)
 
	return (flSize,backupDir)
 
 
while 1:
	fileNo = 0
	no = readRange()
	if no == 0:
		print "Quit..."
		break
	else:
		print 'Get post DB No :',no
	#print html
	#no = 39302
	url = gallUrlPost + str(no)
	print "Connecting..."
	try:
	   f = urllib.urlopen(url)
	except:
	   print "Can not connect Server. Check Network..."
	print "Connected. Analyzing thread..."
	html = f.read()
	if 'download.php' not in html:
		print 'Thread', no, 'does not contain any downloadable picture..'
		print "Re-drawing..."
		continue
	else:
		imageUrlList = re.findall("http://image.dcinside.com/download.php[^']+", html)
		print "Reading complete."
		print 'The number of downloaded pics :', len(imageUrlList)
        #print '_______________________________________________'
        #print imageUrlList
        #print '-----------------------------------------------'
        for url in imageUrlList:
	        #print fileNo
	        contents = urllib.urlopen(url).read()
	        file(saveDir+str(fileNo)+'.jpg', 'w').write(contents)
	        iBfile = saveDir+str(fileNo)+'.jpg'
		retValue = backupPics(iBfile)
		ret = bigOne(retValue[0],0)
		#print "retValue :",retValue[0]
		fileNo = fileNo + 1
	totalDirsize = getDirSize(retValue[1])
	#print retValue[1]
	print fileNo,'files backuped. The total number of backup files is',ret+1,'(',round(totalDirsize/1048567,2),'MB)'
	print 'Done...'
	break
 

#!/usr/bin/python
 
import glob
import os
import random
 
saveDir = "/Users/purewater/Documents/Pictures/myimages/"    <span>### recvg.py 가 받아온 파일들이 저장된 디렉토리입니다. recvg.py의 경로와 일치해야 합니다.</span>
fileList = glob.glob(saveDir+"*.jpg")
flSize = len(fileList)
 
print '[[[ Current repository stats ]]]'
print 'The number of files in REPOS. :', flSize - 1
for name in fileList:
	#print name
	pfname = os.path.split(name)
	#print pfname[0]
	#print pfname[1]
 
 
def copyFile(inputFile):
    srcfile = open(inputFile, 'r')
    readLines = srcfile.readlines()
    #print inputFile
 
    srcName = os.path.split(inputFile)
    dirName = srcName[0]
    fileName = srcName[1]
    onlyFileName = os.path.splitext(inputFile)
    extName = onlyFileName[1]
    #print dirName
    #print extName
    print fileName,'is copyied to cbg.jpg'
    print 
 
    outputFile = dirName+'/cbg'+extName    
    print 'cbg.jpg path ::'
    print outputFile
    trgfile = open(outputFile, 'w')
    for eachLine in readLines:
	  trgfile.write(eachLine)
 
    srcfile.close()
    trgfile.close()
 
 
if os.path.isfile(saveDir+"cbg.jpg"):
   print "cbg.jpg exists."
   lastNum = flSize -2
else:
   print "cbg.jpg does not exist. "
   lastNum = flSize - 1
 
#print "last::", lastNum
rn = random.randint(0,lastNum)
#print rn
s = saveDir+str(rn)+".jpg"
copyFile(s)