爬虫实战1--使用selenium访问豆瓣网验证码处理

一，去云打码注册登录管理自己的服务；调用里面的官网函数获取我们想要的验证码，具体操作看文档。

def discern(filepath,codetype):
    # 用户名
    username = '1130402601'
    # 密码
    password = '2716532cxw'
    # 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 = 6124
    # 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 = '2e20bec419802d64b56a89f8e42fe985'
    # 超时时间，秒
    timeout = 60
    # 初始化
    yundama = YDMHttp(username, password, appid, appkey)
    # 登陆云打码
    yundama.login();

    # 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(filepath, codetype, timeout);
    return result

二，使用selenium和PhantomJS
安装教程

wget https://bitbucket.org/ariya/phantomjs/downloads/phantomjs-2.1.1-linux-x86_64.tar.bz2
tar -xvjf phantomjs-2.1.1-linux-x86_64.tar.bz2 
sudo cp -R phantomjs-2.1.1-linux-x86_64 /usr/local/share/ 
sudo ln -sf /usr/local/share/phantomjs-2.1.1-linux-x86_64/bin/phantomjs /usr/local/bin/

三，全部代码
1，text_使用selenium访问豆瓣网验证码处理.py（核心逻辑）

import time
import requests
from selenium import webdriver
from yundama import discern

# driver = webdriver.PhantomJS()

driver = webdriver.Chrome("/home/cuixin/chromedriver")

driver.get("http://www.douban.com")

# 输入账号密码
driver.find_element_by_name("form_email").send_keys("[email protected]")
driver.find_element_by_name("form_password").send_keys("hello123")

#获取图片
valicode_url = driver.find_element_by_id("captcha_image").get_attribute("src")
resp = requests.get(valicode_url)
file_path = "./files/captcha_image.jpeg"
with open(file_path, "wb") as file:
    file.write(resp.content)

#调用云打码
valicode = discern(filepath=file_path,codetype=3000)

print(valicode)
#输入验证码
driver.find_element_by_name("captcha-solution").send_keys(valicode)

# 等待
time.sleep(2)

# 模拟点击登录
driver.find_element_by_xpath("//input[@class='bn-submit']").click()

# 等待
print("登录中......")
time.sleep(10)

print(driver.title)


# 生成登陆后快照
# driver.save_screenshot("./files/douban.png")

# 保存源码
with open("./files/douban_new.html", "w") as file:
    file.write(driver.page_source)
#
# #退出
driver.quit()

2，yundama.py（代码来自云API文档，只需要改下discern函数里面的参数，要求规范填写）

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 discern(filepath,codetype):
    # 用户名
    username = '1130402601'
    # 密码
    password = '2716532cxw'
    # 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 = 6124
    # 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 = '2e20bec419802d64b56a89f8e42fe985'
    # 超时时间，秒
    timeout = 60
    # 初始化
    yundama = YDMHttp(username, password, appid, appkey)
    # 登陆云打码
    yundama.login();

    # 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(filepath, codetype, timeout);
    return result

if __name__ == '__main__':
    discern("./11.jpg",5000)