#coding=utf-8
import os
import re
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time
from selenium.webdriver.common.action_chains import ActionChains
import collections
import mongoDbBase
import numpy
import imagehash
from PIL import Image,ImageFile
import datetime
class finalNews_IE:
def __init__(self,strdate,logonUrl,firstUrl,keyword_list,exportPath,codepath,codedir):
self.iniDriver()
self.db = mongoDbBase.mongoDbBase()
self.date = strdate
self.firstUrl = firstUrl
self.logonUrl = logonUrl
self.keyword_list = keyword_list
self.exportPath = exportPath
self.codedir = codedir
self.hash_code_dict ={}
for f in range(0,10):
for l in range(1,5):
file = os.path.join(codedir, "codeLibrary\code" + str(f) + '_'+str(l) + ".png")
# print(file)
hash = self.get_ImageHash(file)
self.hash_code_dict[hash]= str(f)
def iniDriver(self):
# 通过配置文件获取IEDriverServer.exe路径
IEDriverServer = "C:\Program Files\Internet Explorer\IEDriverServer.exe"
os.environ["webdriver.ie.driver"] = IEDriverServer
self.driver = webdriver.Ie(IEDriverServer)
def WriteData(self, message, fileName):
fileName = os.path.join(os.getcwd(), self.exportPath + '/' + fileName)
with open(fileName, 'a') as f:
f.write(message)
# 获取图片文件的hash值
def get_ImageHash(self,imagefile):
hash = None
if os.path.exists(imagefile):
with open(imagefile, 'rb') as fp:
hash = imagehash.average_hash(Image.open(fp))
return hash
# 点降噪
def clearNoise(self, imageFile, x=0, y=0):
if os.path.exists(imageFile):
image = Image.open(imageFile)
image = image.convert('L')
image = numpy.asarray(image)
image = (image > 135) * 255
image = Image.fromarray(image).convert('RGB')
# save_name = "D:\work\python36_crawl\Veriycode\mode_5590.png"
# image.save(save_name)
image.save(imageFile)
return image
#切割验证码
# rownum:切割行数;colnum:切割列数;dstpath:图片文件路径;img_name:要切割的图片文件
def splitimage(self, imagePath,imageFile,rownum=1, colnum=4):
img = Image.open(imageFile)
w, h = img.size
if rownum <= h and colnum <= w:
print('Original image info: %sx%s, %s, %s' % (w, h, img.format, img.mode))
print('开始处理图片切割, 请稍候...')
s = os.path.split(imageFile)
if imagePath == '':
dstpath = s[0]
fn = s[1].split('.')
basename = fn[0]
ext = fn[-1]
num = 1
rowheight = h // rownum
colwidth = w // colnum
file_list =[]
for r in range(rownum):
index = 0
for c in range(colnum):
# (left, upper, right, lower)
# box = (c * colwidth, r * rowheight, (c + 1) * colwidth, (r + 1) * rowheight)
if index < 1:
colwid = colwidth + 6
elif index < 2:
colwid = colwidth + 1
elif index < 3:
colwid = colwidth
box = (c * colwid, r * rowheight, (c + 1) * colwid, (r + 1) * rowheight)
newfile = os.path.join(imagePath, basename + '_' + str(num) + '.' + ext)
file_list.append(newfile)
img.crop(box).save(newfile, ext)
num = num + 1
index += 1
return file_list
def compare_image_with_hash(self, image_hash1,image_hash2, max_dif=0):
"""
max_dif: 允许最大hash差值, 越小越精确,最小为0
推荐使用
"""
dif = image_hash1 - image_hash2
# print(dif)
if dif < 0:
dif = -dif
if dif <= max_dif:
return True
else:
return False
# 截取验证码图片
def savePicture(self):
self.driver.get(self.logonUrl)
self.driver.maximize_window()
time.sleep(1)
self.driver.save_screenshot(self.codedir +"\Temp.png")
checkcode = self.driver.find_element_by_id("checkcode")
location = checkcode.location # 获取验证码x,y轴坐标
size = checkcode.size # 获取验证码的长宽
rangle = (int(location['x']), int(location['y']), int(location['x'] + size['width']),
int(location['y'] + size['height'])) # 写成我们需要截取的位置坐标
i = Image.open(self.codedir +"\Temp.png") # 打开截图
result = i.crop(rangle) # 使用Image的crop函数,从截图中再次截取我们需要的区域
filename = datetime.datetime.now().strftime("%M%S")
filename =self.codedir +"\Temp_code.png"
result.save(filename)
self.clearNoise(filename)
file_list = self.splitimage(self.codedir,filename)
verycode =''
for f in file_list:
imageHash = self.get_ImageHash(f)
for h,code in self.hash_code_dict.items():
flag = self.compare_image_with_hash(imageHash,h,0)
if flag:
# print(code)
verycode+=code
break
print(verycode)
self.driver.close()
def longon(self):
self.driver.get(self.logonUrl)
self.driver.maximize_window()
time.sleep(1)
self.savePicture()
accname = self.driver.find_element_by_id("username")
# accname = self.driver.find_element_by_id("//input[@id='username']")
accname.send_keys('ctrchina')
accpwd = self.driver.find_element_by_id("password")
# accpwd.send_keys('123456')
code = self.getVerycode()
checkcode = self.driver.find_element_by_name("checkcode")
checkcode.send_keys(code)
submit = self.driver.find_element_by_name("button")
submit.click()