爬虫第三弹 selenium

reptile_third

云打码平台

• 注册: 普通用户和开发者用户
• 登录:
  • 登录普通用户(查看余额)
  • 登录开发者用户:
    • 创建一个软件: 我的软件-> 创建软件
    • 下载示例代码: 开发者中心->下载最新的dll->pythonHttp示例代码下载

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

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

# 用户名(普通用户)
username    = 'bobo328410948'

# 密码
password    = 'bobo328410948'                            

# 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       = 6003                                    

# 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      = '1f4b564483ae5c907a1d34f8e2f2776c'    

# 图片文件
filename    = 'getimage.jpg'                        

# 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    = 1004

# 超时时间，秒
timeout     = 10                                    

# 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))

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

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       = 6003                                    

    # 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      = '1f4b564483ae5c907a1d34f8e2f2776c'    

    # 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     = 2                                   
    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

人人网的模拟登录

import urllib
import requests
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')

#识别验证码中的数据值
code_data = getCodeDate('bobo328410948','bobo328410948','./code.jpg',2004)

# 模拟登录
login_url = 'http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=201914927558'
data = {
    "email":"www.zhangbowudi@qq.com",
    "icode":code_data,
    "origURL":"http://www.renren.com/home",
    "domain":"renren.com",
    "key_id":"1",
    "captcha_type":"web_login",
    "password":"4f0350f09aeffeef86307747218b214b0960bdf35e30811c0d611fe39db96ec1",
    "rkey":"9e75e8dc3457b14c55a74627fa64fb43",
    "f":"http%3A%2F%2Fwww.renren.com%2F289676607",
}

#该次请求产生的coolie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/289676607/profile'
page_text = session.get(url=url,headers=headers).text

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

模拟登录古诗文网

import urllib
import requests
from lxml import etree
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('bobo328410948','bobo328410948','./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":"9AsGvh3Je/0pfxId7DYRUi258ayuEG4rrQ1Z3abBgLoDSOeAUatOZOrAIxudqiOauXpR9Zq+dmKJ28+AGjXYHaCZJTTtGgrEemBWI1ed7oS7kpB7Rm/4yma/+9Q=",
    "__VIEWSTATEGENERATOR":"C93BE1AE",
    "from":"http://so.gushiwen.org/user/collect.aspx",
    "email":"www.zhangbowudi@qq.com",
    "pwd":"bobo328410948",
    "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)

• 环境安装: pip install selenium
• 编码流程:
  • 导包 : from selenium import webdriver
  • 实例化某一款浏览器对象
  • 自指定自动化操作代码

百度人民币

from selenium import webdriver
from time import sleep


bro = webdriver.Chrome(executable_path=r'C:UsersAdminDocumentsTencent Files1973727272FileRecvday_03_爬虫chromedriver.exe')
bro.get(url='https://www.baidu.com/')
sleep(2)
text_input = bro.find_element_by_id('kw')

text_input.send_keys('人民币')
sleep(2)
bro.find_element_by_id('su').click()

sleep(3)

#获取当前的页面源码数据
print(bro.page_source)
bro.quit()

获取豆瓣电影中更多电影详情数据

from selenium import webdriver
from time import sleep
url = 'https://movie.douban.com/typerank?type_name=%E6%83%8A%E6%82%9A&type=19&interval_id=100:90&action='
bro = webdriver.Chrome(executable_path=r'C:UsersAdminDocumentsTencent Files1973727272FileRecvday_03_爬虫chromedriver.exe')
bro.get(url)
sleep(3)
bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(3)
bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(3)
bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(2)
page_text = bro.page_source

with open('./douban.html','w',encoding='utf-8') as fp:
    fp.write(page_text)

sleep(1)
bro.quit()

qq空间

bro = webdriver.Chrome(executable_path=r'C:UsersAdminDocumentsTencent Files1973727272FileRecvday_03_爬虫chromedriver.exe')
url = 'https://qzone.qq.com/'
bro.get(url=url)
sleep(2)
# 定位到一个具体的iframe
bro.switch_to.frame('login_frame')
bro.find_element_by_id('switcher_plogin').click()
sleep(2)

bro.find_element_by_id('u').send_keys('1973727272')
bro.find_element_by_id('p').send_keys('')

bro.find_element_by_id('login_button').click()
sleep(5)

page_text = bro.page_source
with open('qq.html', 'w', encoding='utf-8') as fp:
    fp.write(page_text)
bro.quit()