模拟登录之图片验证码处理

登录图片验证码处理

　　超级鹰、云打码等API接口获取。

案例：古诗文网登录https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx

import requests
from lxml.html.clean import etree
from fake_useragent import UserAgent
UA = UserAgent()
headers = {'User-Agent': UA.random, }
session=requests.Session()#为避免cookie影响，一般直接采用session请求

#验证码处理(机器识别,参考官方文档操作说明http://www.chaojiying.com/api-14.html---ABC123456,ABC123456)
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()
def getCodeImgText(imgPath,imgType):#imgType 验证码类型  官方网站>>价格体系
    chaojiying = Chaojiying_Client('bobo328410948', 'bobo328410948', '899370')#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']


#二维码识别
url='https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx'
response=session.get(url,headers=headers)
tree=etree.HTML(response.text)
img_src='https://so.gushiwen.org/'+tree.xpath('//img[@id="imgCode"]/@src')[0]
print(img_src)
response_img=session.get(url=img_src,headers=headers)
with open('Code.jpg','wb')as f :
    f.write(response_img.content)
code=getCodeImgText('Code.jpg',1004)
print(code)
#一般额外的参数隐藏在页面中
__VIEWSTATE=tree.xpath('//input[@id="__VIEWSTATE"]/@value')[0]
__VIEWSTATEGENERATOR=tree.xpath('//input[@id="__VIEWSTATEGENERATOR"]/@value')[0]
print(__VIEWSTATE)
print(__VIEWSTATEGENERATOR)
#请求参数
data = {
    '__VIEWSTATE': __VIEWSTATE,
    '__VIEWSTATEGENERATOR': __VIEWSTATEGENERATOR,
    'from': 'http://so.gushiwen.org/user/collect.aspx',
    'email':'934321247@qq.com',
    'pwd': 'ABC123456',
    'code': code,
    'denglu': '登录',
}
#登录提交数据data
url = 'https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx'
response = session.post(url=url,data=data,headers=headers)
with open('index.html','w',encoding='utf-8')as f:
    f.write(response.text)
# print(response.text)
text=etree.HTML(response.text).xpath('//div[@class="mainreg2"]')
for i in text:
    print(i.xpath('./span[2]/text()'))