Google SEO|外贸营销推广

from Queue import Queue

import threading
import random
import time

class ProduceToQueue( threading.Thread ):
   def __init__( self, threadName, queue ):
      threading.Thread.__init__( self, name = threadName )
      self.sharedObject = queue
      
   def run( self ):
      for i in range( 11, 21 ):
         time.sleep( random.randrange( 4 ) )
         print "%s adding %s to queue" % ( self.getName(), i )
         self.sharedObject.put( i )

      print self.getName(), "finished producing values"
      print "Terminating", self.getName()

class ConsumeFromQueue( threading.Thread ):
   def __init__( self, threadName, queue ):
      threading.Thread.__init__( self, name = threadName )
      self.sharedObject = queue

   def run( self ):
      sum = 0
      current = 10

      for i in range( 10 ):
         time.sleep( random.randrange( 4 ) )
         print "%s attempting to read %s..." % ( self.getName(), current + 1 )
         current = self.sharedObject.get()
         print "%s read %s" % ( self.getName(), current )
         sum += current

      print "%s retrieved values totaling: %d" % ( self.getName(), sum )
      print "Terminating", self.getName()

queue = Queue()
producer = ProduceToQueue( "Producer", queue )
consumer = ConsumeFromQueue( "Consumer", queue )

producer.start()
consumer.start()

producer.join()
consumer.join()

from PIL import Image

im = Image.open("captcha.gif")
im = im.convert("P")

print im.histogram()

from PIL import Image
from operator import itemgetter

im = Image.open("captcha.gif")
im = im.convert("P")
his = im.histogram()

values = {}

for i in range(256):
  values[i] = his[i]

for j,k in sorted(values.items(), key=itemgetter(1), reverse=True)[:10]:
  print j,k

from PIL import Image

im = Image.open("captcha.gif")
im = im.convert("P")
im2 = Image.new("P",im.size,255)

im = im.convert("P")

temp = {}

for x in range(im.size[1]):
  for y in range(im.size[0]):
    pix = im.getpixel((y,x))
    temp[pix] = pix
    if pix == 220 or pix == 227: # these are the numbers to get
      im2.putpixel((y,x),0)

im2.save("output.gif")

for each binary image:
  for each pixel in the binary image:
    if the pixel is on:
      if any pixel we have seen before is next to it:
        add to the same set
      else:
        add to a new set

#!/usr/bin/env python
# -*- coding: UTF-8 -*-
#图像二值处理
import os
from PIL import Image
j=1
dir="./pic/"
path = "./font/"
for f in os.listdir(dir):
   if f.endswith(".gif"):
       img = Image.open(dir+f) # 读入图片
       img = img.convert("RGBA")
       pixdata = img.load()
       #二值化
       for y in xrange(img.size[1]):
           for x in xrange(img.size[0]):
               if pixdata[x, y][0] < 90:
                   pixdata[x, y] = (0, 0, 0, 255)
       for y in xrange(img.size[1]):
           for x in xrange(img.size[0]):
               if pixdata[x, y][1] < 136:
                   pixdata[x, y] = (0, 0, 0, 255)
       for y in xrange(img.size[1]):
           for x in xrange(img.size[0]):
               if pixdata[x, y][2] > 0:
                   pixdata[x, y] = (255, 255, 255, 255)
       img.save(path+f, "GIF")

from PIL import Image

im = Image.open("captcha.gif")
im = im.convert("P")
im2 = Image.new("P",im.size,255)

im = im.convert("P")

temp = {}

for x in range(im.size[1]):
  for y in range(im.size[0]):
    pix = im.getpixel((y,x))
    temp[pix] = pix
    if pix == 220 or pix == 227: # these are the numbers to get
      im2.putpixel((y,x),0)

# new code starts here

inletter = False
foundletter=False
start = 0
end = 0

letters = []

for y in range(im2.size[0]): # slice across
  for x in range(im2.size[1]): # slice down
    pix = im2.getpixel((y,x))
    if pix != 255:
      inletter = True
  if foundletter == False and inletter == True:
    foundletter = True
    start = y

  if foundletter == True and inletter == False:
    foundletter = False
    end = y
    letters.append((start,end))

  inletter=False
print letters

#!/usr/bin/env python
# -*- coding: UTF-8 -*-
#图像分割
import os ,Image
j = 1
dir="./font/"
for f in os.listdir(dir):
   if f.endswith(".gif"):
       img = Image.open(dir+f)
       for i in range(4):
           x = 16 + i*15   #这里的数字参数需要自己
           y = 2           #根据验证码图片的像素进行
           img.crop((x, y, x+7, y+10)).save("fonts/%d.gif" % j)   #适当的修改
           print "j=",j
           j += 1

# New code is here. We just extract each image and save it to disk with
# what is hopefully a unique name

count = 0
for letter in letters:
  m = hashlib.md5()
  im3 = im2.crop(( letter[0] , 0, letter[1],im2.size[1] ))
  m.update("%s%s"%(time.time(),count))
  im3.save("./%s.gif"%(m.hexdigest()))
  count += 1

import sys, base64
import requests
import time

def get_content():
    url = "http://www.idc0310.com/userself/RndCode.asp?rndtype=LOGIN_RndCode"
    url2 = 'http://www.todaynic.com/user/verpic.net?1192157892&background=d9dadb'
    r = requests.get(url2)
    return r.content

def content_to_file(content, num):
    f = open('%s%d.png'%(file_path, num), 'wb')
    f.write(content)
    f.close()

def main():
    times = 100
    print('%d files needed.'%times)
    for i in range(times):
        num_of_file = i
        c = get_content()
        content_to_file(c, i)
        print('%d files done.'%i)
        time.sleep(2)

import os, Image

# load font modules  (char, image)
fontMods = []
for i in range(10):
    fontMods.append((str(i), Image.open("./good/%02d.bmp" % i)))
for i in range(26):
    c = chr(ord('A') + i)
    fontMods.append((c, Image.open("./good/%s.bmp" % c)))

def recognize(f):
    im = Image.open(f)
    im2 = im.convert('1')
    # check 5 fonts
    result = "./result/"
    for i in range(5):
        x = 10 + i*18
        y = 6
        target = im.crop((x, y, x+8, y+10))
        points = []
        for mod in fontMods:
            diffs = 0
            for yi in range(10):
                for xi in range(8):
                    if mod[1].getpixel((xi, yi)) != target.getpixel((xi, yi)):
                        diffs += 1
            points.append((diffs, mod[0]))
        points.sort()
        result += points[0][1]
    result += ".png"
    print "save to", result
    im.save(result);

for imgfile in os.listdir("."):
    if imgfile.endswith(".png"):
        recognize(imgfile)

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Author: Administrator
# @Date:   2016-01-07 10:11:09
# @Last Modified by:   Administrator
# @Last Modified time: 2016-01-09 12:03:01
import os
from PIL import Image


#图像的二值化处理

def binary(f):
    print(f)
    img = Image.open(f)
    #img = img.convert('1')
    img = img.convert("RGB")  # 参考文章中无该行，无该行，我这里会报错
    pixdata = img.load()
    for y in range(img.size[1]):
        for x in range(img.size[0]):
            if pixdata[x, y][0] < 90:
                pixdata[x, y] = (0, 0, 0, 255)
    for y in range(img.size[1]):
        for x in range(img.size[0]):
            if pixdata[x, y][1] < 136:
                pixdata[x, y] = (0, 0, 0, 255)
    for y in range(img.size[1]):
        for x in range(img.size[0]):
            if pixdata[x, y][2] > 0:
                pixdata[x, y] = (255, 255, 255, 255)
    return img
nume = 0

#图像的分割，就是验证码按字符分割出来

def division(img):
    global nume
    font = []
    for i in range(4):
        x = 2 + i*10  # 该函数中的像素值都需要自己进行微调
        y = 0
        temp = img.crop((x, y, x + 6, y + 10))
        temp.save("./temp/%d.bmp" % nume)
        nume = nume + 1
        font.append(temp)
    return font

#分隔出来的字符与预先定义的字体库中的结果逐个像素进行对比找出差别最小的项

def recognize(img):

    fontMods = []
    for i in range(10):
        fontMods.append((str(i), Image.open("./num/%d.bmp" % i)))
    result = ""
    font = division(img)
    for i in font:
        target = i
        points = []
        print("正在比对数字:{0}".format(i))
        for mod in fontMods:
            print("test fontmods {0}".format(mod))
            diffs = 0
            for yi in range(10):
                for xi in range(6):
                    # print(xi, yi, "mod[1].getpixel((xi, yi)):"+str(mod[1].getpixel((xi, yi))))
                    # print(xi, yi, "target.getpixel((xi, yi)):"+str(target.getpixel((xi, yi))))

                    if 0 in target.getpixel((xi, yi)):
                        compare = 0
                    else:
                        compare = 255

                    if isinstance(mod[1].getpixel((xi, yi)), int):
                        if mod[1].getpixel((xi, yi)) != compare:
                            diffs += 1
                    elif mod[1].getpixel((xi, yi)) != target.getpixel((xi, yi)):
                        diffs += 1

            print("diffs：" + str(diffs))
            points.append((diffs, mod[0]))
        points.sort()
        result += points[0][1]
    return result
if __name__ == '__main__':
    codedir = "./pic/"
    for imgfile in os.listdir(codedir):
        if imgfile.endswith(".bmp"):
            dir = "./result/"
            img = binary(codedir+imgfile)
            num = recognize(img)
            dir += (num + ".gif")
            print("save to", dir)
            img.save(dir)