# 超级鹰的示范代码

#!/usr/bin/env python

# coding:utf-8

import requests

from hashlib import md5

class Chaojiying_Client(object):

def __init__(self, username, password, soft_id):

self.username = username

password = password.encode('utf8')

self.password = md5(password).hexdigest()

self.soft_id = soft_id

self.base_params = {

'user': self.username,

'pass2': self.password,

'softid': self.soft_id,

}

self.headers = {

'Connection': 'Keep-Alive',

'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',

}

def PostPic(self, im, codetype):

"""im: 图片字节codetype: 题目类型 参考 http://www.chaojiying.com/price.html"""

params = {

'codetype': codetype,

}

params.update(self.base_params)

files = {'userfile': ('ccc.jpg', im)}

r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files, headers=self.headers)

return r.json()

def ReportError(self, im_id):

"""im_id:报错题目的图片ID"""

params = {

'id': im_id,

}

params.update(self.base_params)

r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)

return r.json()

#自己封装的一个识别验证码图片的函数

def transform_code_img(imgPath,imgType):

chaojiying = Chaojiying_Client('username', 'password', 'soft_id') #用户中心>>软件ID 生成一个替换 96001

im = open(imgPath, 'rb').read()#本地图片文件路径 来替换 a.jpg 有时WIN系统须要//

return chaojiying.PostPic(im, imgType)['pic_str']#1902 验证码类型 官方网站>>价格体系 3.4+版 print 后要加()

#调用识别验证码的函数对验证码进行识别

transform_code_img('./a.jpg',4004)

### 将古诗文网中的验证码图片进行识别

### 以下代码并未进过验证，只是为了展示实现原理 ###

sess = requests.Session() #创建好session对象,保存cookies

#处理动态变化的请求参数

#1.解析出本次登录页面对应的验证码图片地址

login_url = 'https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx'

page_text = sess.get(url=login_url,headers=headers).text

tree = etree.HTML(page_text)

#解析出了验证码图片的地址

img_path = 'https://so.gushiwen.org'+tree.xpath('//*[@id="imgCode"]/@src')[0]

img_data = sess.get(url=img_path,headers=headers).content #请求到了图片数据

#将图片保存到本地存储

with open('./code.jpg','wb') as fp:

fp.write(img_data)

#将动态变化的请求参数从页面源码中解析出来

__VIEWSTATE = tree.xpath('//*[@id="__VIEWSTATE"]/@value')[0]

__VIEWSTATEGENERATOR = tree.xpath('//*[@id="__VIEWSTATEGENERATOR"]/@value')[0]

#识别验证码

code_result = transform_code_img('./code.jpg',1004)

print(code_result)

post_url = 'https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx'

data = {

"__VIEWSTATE":__VIEWSTATE,

"__VIEWSTATEGENERATOR":__VIEWSTATEGENERATOR,

"from": "http://so.gushiwen.org/user/collect.aspx",

"email": "email_address",

"pwd": "password",

"code": code_result,

"denglu": "登录",

}

#模拟登录的请求

response = sess.post(url=post_url,headers=headers,data=data)

page_text = response.text #登录成功后页面的源码数据

with open('gushiwen.html','w',encoding='utf-8') as fp:

fp.write(page_text)