爬虫入门（三）

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    = ‘lianda0707‘

# 密码
password    = ‘ld18513185949.07‘                            

# 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       = 6998                                     

# 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      = ‘cf4dda0913c13bb707a251a847bce5a1‘    

# 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))

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

 1 url = ‘https://movie.douban.com/typerank?type_name=%E6%83%8A%E6%82%9A&type=19&interval_id=100:90&action=‘
 2 
 3 bro = webdriver.Chrome(executable_path=r‘F:\爬虫+数据\day03\chromedriver_win32\chromedriver.exe‘)
 4 bro.get(url)
 5 sleep(3)
 6 
 7 bro.execute_script(‘window.scrollTo(0,document.body.scrollHeight)‘)
 8 sleep(3)
 9 bro.execute_script(‘window.scrollTo(0,document.body.scrollHeight)‘)
10 sleep(3)
11 bro.execute_script(‘window.scrollTo(0,document.body.scrollHeight)‘)
12 
13 sleep(2)
14 page_text = bro.page_source
15 
16 with open(‘./douban.html‘,‘w‘,encoding=‘utf8‘) as fp:
17     fp.write(page_text)
18 
19 sleep(1)
20 bro.quit()

# 谷歌无头浏览器
from selenium.webdriver.chrome.options import Options
chrome_options = Options()
chrome_options.add_argument(‘--headless‘)
chrome_options.add_argument(‘--disable-gpu‘)

#获取豆瓣电影中更多电影详情数据
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‘F:\爬虫+数据\day03\chromedriver_win32\chromedriver.exe‘,chrome_options=chrome_options) #多加一个参数
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)
print(page_text)
sleep(1)

# qq空间
bro = webdriver.Chrome(executable_path=r‘F:\爬虫+数据\day03\chromedriver_win32\chromedriver.exe‘)
url = ‘https://qzone.qq.com/‘

bro.get(url=url)
sleep(2)
# NoSuchElementException  这个错 
# 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(‘460086804‘)
bro.find_element_by_id(‘p‘).end_keys(‘shuo0127‘)

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

page_text = bro.page_source