Convert an Image to text of colored HTML using Python

pypic2x.py

# -*- coding: utf-8 -*-
import os
import urllib2
from PIL import Image
from os.path import basename
from urlparse import urlsplit

cfill = r"█"

Chars = [
    [ r"█" , r"▓" , r"▒" , r"░" , r" " ]
]


def url2name(url):
    return basename(urlsplit(url)[2])

def download(url, destDir = "./", localFileName = None):
    localName = url2name(url)
    req = urllib2.Request(url)
    r = urllib2.urlopen(req)
    if r.info().has_key('Content-Disposition'):
        # If the response has Content-Disposition, we take file name from it
        localName = r.info()['Content-Disposition'].split('filename=')[1]
        if localName[0] == '"' or localName[0] == "'":
            localName = localName[1:-1].split("'")[0].split('"')[0]
    elif r.url != url: 
        # if we were redirected, the real file name we take from the final URL
        localName = url2name(r.url)
    if localFileName: 
        # we can force to save the file as specified name
        localName = localFileName
    localName = os.path.abspath(os.path.join( destDir, localName))
    f = open(localName, 'wb')
    f.write(r.read())
    f.close()
    return localName

def getChar(pix ,charset):
    chars = Chars[charset]
    charindex = sum(pix) * len(chars) / ( 255 + 255 + 255) - 1
    charindex = charindex if charindex >= 0 else 0
    return chars[charindex]

def getColorTag(pix):
    return "".join(['0'*(2-len(x)) + x for x in [hex(y)[2:] for y in pix]])   


    
    
class ImgFile:
    def __init__(self,  path):
        self.tempFile = False
        if path.lower().startswith("http://"):
            self.tempFile = True
            import tempfile
            self.imgPath = download(path, tempfile.gettempdir())
        else:
            self.tempFile = False
            self.imgPath = path
        
        self.image = Image.open(self.imgPath)
        self.image = self.image.convert('RGB')
        self.width, self.height = self.image.size
    
    def __del__(self):
        if self.tempFile:
            import os
            os.unlink(self.imgPath)
        
    def resize(self, w = -1, h = -1):
        w = w if w > 0 else self.width
        h = h if h > 0 else self.height
        self.image.thumbnail((w, h), Image.ANTIALIAS)
        self.width, self.height = self.image.size
            
    def getPixels(self):
        return (self.width,  self.height,  self.image.load())
            
    def toTEXT(self):
        w, h, pixels = self.getPixels()         
        
        txtout = ""

        for y in range(h):
            for x in range(w):
                txtout += getChar(pixels[x,y], 0)
            txtout += "\n"
            
        return txtout
    
    def toHTML(self):
        w, h, pixels = self.getPixels()        
        
        txtout = '''<meta http-equiv="content-type" content="text/html; charset=UTF-8"/>
                <div class="fontbox" style="font-family:monospace; font-size:8px; line-height: 100%">
                '''

        for y in range(h):
            currenttag = ""
            for x in range(w):
                tag = getColorTag(pixels[x,y])
                if tag != currenttag:
                    if currenttag != "":
                        txtout += "</font>"
                    txtout += '<font color="#' + tag + '">'
                    currenttag = tag
                txtout += cfill
            txtout += "</font><br/>\n"
        
        return txtout

         


if __name__ == '__main__':
    import argparse
    import sys
    
    parser = argparse.ArgumentParser(description='Process images to Text or HTML.')
    parser.add_argument("-i", type=str, help="Image file path or URL")
    parser.add_argument("-x", type=int, default=-1, help="Width of Image")
    parser.add_argument("-y", type=int, default=-1, help="Height of Image")
    parser.add_argument("-t", type=str, default="text", help="output Type [text|html]")
    parser.add_argument("-d", type=bool, default=False, help="Debug [True|False]")
    
    argv = sys.argv
    
    argvres = parser.parse_args(sys.argv[1:])
    if argvres.d:
        print "-i : %s\n-x : %i\n-y : %i\n-t : %s"%(argvres.i, argvres.x, argvres.y, argvres.t)
    
    
    img = ImgFile(argvres.i)
    resizeParams = dict()
    
    if argvres.x > 0:
        resizeParams["w"] = argvres.x
    if argvres.y > 0:
        resizeParams["h"] = argvres.y
    if len(resizeParams) > 0:
        img.resize(**resizeParams)
    
    if argvres.t == "text":
        print img.toTEXT()
    elif argvres.t == "html":
        print img.toHTML()
    else:
        print "Unknown Type: " +argvres.t