Python爬虫 / python记录 / py实例收藏 · 2019年6月25日

Python爬虫验证码识别、模拟登陆

# Author: Sooele

##云打码
import http.client, mimetypes, urllib, json, time, requests


######################################################################

class YDMHttp:
    apiurl = 'http://api.yundama.com/api.php'
    username = ''
    password = ''
    appid = ''
    appkey = ''

    def __init__(self, username, password, appid, appkey):
        self.username = username
        self.password = password
        self.appid = str(appid)
        self.appkey = appkey

    def request(self, fields, files=[]):
        response = self.post_url(self.apiurl, fields, files)
        response = json.loads(response)
        return response

    def balance(self):
        data = {'method': 'balance', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey}
        response = self.request(data)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['balance']
        else:
            return -9001

    def login(self):
        data = {'method': 'login', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey}
        response = self.request(data)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['uid']
        else:
            return -9001

    def upload(self, filename, codetype, timeout):
        data = {'method': 'upload', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey, 'codetype': str(codetype), 'timeout': str(timeout)}
        file = {'file': filename}
        response = self.request(data, file)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['cid']
        else:
            return -9001

    def result(self, cid):
        data = {'method': 'result', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey, 'cid': str(cid)}
        response = self.request(data)
        return response and response['text'] or ''

    def decode(self, filename, codetype, timeout):
        cid = self.upload(filename, codetype, timeout)
        if (cid > 0):
            for i in range(0, timeout):
                result = self.result(cid)
                if (result != ''):
                    return cid, result
                else:
                    time.sleep(1)
            return -3003, ''
        else:
            return cid, ''

    def report(self, cid):
        data = {'method': 'report', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey, 'cid': str(cid), 'flag': '0'}
        response = self.request(data)
        if (response):
            return response['ret']
        else:
            return -9001

    def post_url(self, url, fields, files=[]):
        for key in files:
            files[key] = open(files[key], 'rb');
        res = requests.post(url, files=files, data=fields)
        return res.text






def getCodeDate(userName,pwd,codePath,codeType):
    # 用户名(普通用户)
    username    = userName

    # 密码
    password    = pwd

    # 软件ID,开发者分成必要参数。登录开发者后台【我的软件】获得!
    appid       = 8102

    # 软件密钥,开发者分成必要参数。登录开发者后台【我的软件】获得!
    appkey      = '3ce611f69d71d1734fa3bb190c791f4a'

    # 图片文件
    filename    = codePath

    # 验证码类型,# 例:1004表示4位字母数字,不同类型收费不同。请准确填写,否则影响识别率。在此查询所有类型 http://www.yundama.com/price.html
    codetype    = codeType

    # 超时时间,秒
    timeout     = 60
    result = None
    # 检查
    if (username == 'username'):
        print('请设置好相关参数再测试')
    else:
        # 初始化
        yundama = YDMHttp(username, password, appid, appkey)

        # 登陆云打码
        uid = yundama.login();
        #print('uid: %s' % uid)

        # 查询余额
        balance = yundama.balance();
        #print('balance: %s' % balance)

        # 开始识别,图片路径,验证码类型ID,超时时间(秒),识别结果
        cid, result = yundama.decode(filename, codetype, timeout);
        #print('cid: %s, result: %s' % (cid, result))
    return result

验证码识别

#人人网的模拟登录
from day137爬虫 import YdmCode
import requests
import urllib
from lxml import etree
#获取session对象
session = requests.Session()
#将验证码图片进行下载
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
url = 'http://www.renren.com/'
page_text = requests.get(url=url,headers=headers).text

tree = etree.HTML(page_text)
code_img_url = tree.xpath('//*[@id="verifyPic_login"]/@src')[0]
urllib.request.urlretrieve(url=code_img_url,filename='code.jpg')
#识别验证码图片中的数据
code_data = YdmCode.getCodeDate('账号','密码','./code.jpg',1000)
print(code_data)

验证码识别+模拟登陆

#人人网的模拟登录
from day137爬虫 import YdmCode
import requests
import urllib
from lxml import etree
#获取session对象
session = requests.Session()
#将验证码图片进行下载
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
url = 'http://www.renren.com/'
page_text = requests.get(url=url,headers=headers).text

tree = etree.HTML(page_text)
code_img_url = tree.xpath('//*[@id="verifyPic_login"]/@src')[0]
urllib.request.urlretrieve(url=code_img_url,filename='code.jpg')
#识别验证码图片中的数据
code_data = YdmCode.getCodeDate('sooele','Sooele0000','./code.jpg',1000)
print(code_data)

#模拟登陆
login_url = ' http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=2019521653580'
data = {
    "email":"账号",
    "icode":code_data,
    "origURL":"http://www.renren.com/home",
    "domain":"renren.com",
    "key_id":"1",
    "captcha_type":"web_login",
    "password":"加密过的密码",
    "rkey":"fa647ac3744264c8eece684183c36fe5",
    "f":"http%3A%2F%2Fwww.renren.com%2F971290517"
}



#该次请求产生的cookie会被自动存储到session对象中

session.post(url=login_url,data=data,headers=headers)

url = 'http://www.renren.com/971290517/profile'
session.get(url=url,headers=headers).text
with open('renren.html','w',encoding='utf-8')as fp:
    fp.write(page_text)
from day137爬虫 import YdmCode
import requests
import urllib
from lxml import etree
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
#%%
#模拟登录古诗文网
s = requests.Session()
login_url = 'https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx'
page_text = requests.get(url=login_url,headers=headers).text
tree = etree.HTML(page_text)
img_src = 'https://so.gushiwen.org'+tree.xpath('//*[@id="imgCode"]/@src')[0]
img_data = s.get(url=img_src,headers=headers).content
with open('./img.jpg','wb') as fp:
    fp.write(img_data)
img_text = getCodeDate('账号','密码','./img.jpg',1004)

#模拟登录
url = 'https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx'
data = {
    "__VIEWSTATE":"",
    "__VIEWSTATEGENERATOR":"",
    "from":"http://so.gushiwen.org/user/collect.aspx",
    "email":"",
    "pwd":"",
    "code":img_text,
    "denglu":"登录",
}
page_text = s.post(url=url,headers=headers,data=data).text
with open('./gushiwen.html','w',encoding='utf-8') as fp:
    fp.write(page_text)
#%%