python模拟登陆 验证码el_python 实现（附带验证码识别）的模拟登陆

python的requests模块是个神器，这里用request模块实现模拟登登陆：

#coding:utf-8

import sys

import requests

from bs4 import BeautifulSoup

import re

from pylsy import pylsytable

#验证码识别#

import os

os.chdir("C:\Python27\Lib\site-packages")

from pytesser import *

#验证码识别的库

login_url = 'http://mis.teach.ustc.edu.cn/userinit.do'

a_url = 'http://mis.teach.ustc.edu.cn/login.do'

pre_url = 'http://mis.teach.ustc.edu.cn/'

grades_url = 'http://mis.teach.ustc.edu.cn/querycjxx.do'

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.72 Safari/537.36',

'Referer': 'http://mis.teach.ustc.edu.cn/userinit.do',

'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',

'Accept-Encoding': 'gzip, deflate',

'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6',

'Connection': 'keep-alive',

}

pre_data = {'userbz': 's'}

login_data = {

'userbz': 's',

'hidjym': '',

}

grades_data = {

'xuenian': '',

'chaxun': '+%B2%E9++%D1%AF+',

'px': '1',

'zd': '0',

}

#提交post指令

def judging(name):

divide = 125#阙值根据具体调试

list1 = []

for i in range(256):

if i < divide:

list1.append(0)

else:

list1.append(1)

image = Image.open(name)

image2 = image.convert('L')

#根据阙值二值化分割

image_text = image2.point(table,'1')

return image_to_string(image_text)

#识别率有待改进

def getGrades(filename):

userid=raw_input("name:")

password=raw_input("password:")

s = requests.Session()

login_r = s.post(login_url, headers=headers, data=pre_data)

soup = BeautifulSoup(login_r.text,"html.parser")

img_src = pre_url + soup.find('img', id='random')['src']

f = open('c.png', 'wb')

img = s.get(img_src)

f.write(img.content)

f.close()

code = judging('c.png')

login_data['userCode']=userid

login_data['passWord']=password

login_data['check'] = code

li_r = s.post(a_url, headers=headers, data=login_data)

grades = s.post(grades_url, headers=headers, data=grades_data)

f = open(filename, 'w')

reload(sys)

sys.setdefaultencoding('utf8')

f.writelines(grades.text)

f.close()

def sousa(filename):

f = open(filename)

text = f.read()

#html.parser

soup=BeautifulSoup(text,"html.parser")

trs=soup.find_all('tr',class_='bg')

courseName=[]

courseGrades=[]

courseGPA=[]

del trs[0]

for course in trs:

tds=course.find_all('td',class_='bg')

courseName.append(tds[2].string)

courseGrades.append(tds[4].string)

courseGPA.append(tds[6].string)

return (courseName,courseGrades,courseGPA)

def writeGrades(filename):

courseName,courseGrades,courseGPA=sousa()

f=open(filename,'w')

for i in range(len(courseGPA)):

f.write('%s %s %s \n' % (courseName[i],courseGrades[i],courseGPA[i]))

f.close()

if __name__ == '__main__':

getGrades('test.txt')

courseName,courseGrades,courseGPA=sousa('test.txt')

attributes=['courseName','courseGrades','coursePoints']

table=pylsytable(attributes)

table.add_data('courseName',courseName)

table.add_data('courseGrades',courseGrades)

table.add_data('coursePoints',courseGPA)

print table

利用requests.Session()并构造post指令，具体情况具体分析。

图像处理用到了PIL，pytesser库 ，pytesser调用的tesseract是谷歌的一个用于识别的开源框架，可用于数字、字母、汉字识别(需要优化)。

相关主要代码：

image = Image.open(name)

image_text = image2.point(table,'1')

return image_to_string(image_text)