爬虫（3）

一、模拟登录案例（识别验证码）

1、打码平台 - 云打码：www.yundama.com

　　使用步骤：

　　　　- 注册两个账户，普通用户和开发者用户；

　　　　- 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 -> 下载最新云打码DLL -> PythonHTTP示例下载

　　　　- 下载后解压缩，如下：

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
username    = 'username'

# 密码
password    = 'password'                            

# 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       = 1                                     

# 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      = '22cc5376925e9387a23cf797cb9ba745'    

# 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     = 60                                    

# 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))

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

2、案例一：模拟登录人人网，爬取个人中心页面数据

def getCodeData(username, pwd, codePath, codeType):
    username = username     # 用户名（云打码普通用户用户名）
    password = pwd              # 普通用户对应的密码
    appid = 6003          # 软件代码，开发者分成必要参数。登录开发者后台【我的软件】获得！
    appkey = '1f4b564483ae5c907a1d34f8e2f2776c'    # 通讯密钥，开发者分成必要参数。登录开发者后台【我的软件】获得！
    filename = codePath          # 识别的图片的路径
    codetype = codeType           # 识别的类型，在帮助文档可查看对应验证码类型
    timeout = 20 
    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

# 人人网的模拟登陆
import requests
import urllib
from lxml import etree
# 获取session对象
session = requests.Session()

# 下载验证码图片
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 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值,2004表示4位纯汉字，其他类型代码参考云打码帮助文档
code_data = getCodeData(云打码用户名', '云打码密码', './code.jpg', 2004)
# print(code_data)    # code_data为识别结果

login_url = 'http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=2019141727367'
data = {
    "email":"1547360919@qq.com",
    "icode":code_data,
    "origURL":"http://www.renren.com/home",
    "domain":"renren.com",
    "key_id":"1",
    "captcha_type":"web_login",
    "password":"38ce96b6b81595f845e55c1dd4e712ad6f1efe50fe31dbd5bf517b273d7c3b6e",
    "rkey":"07a9f1810ecf9b507634a45447a628e7",
    "f":""
}

# 如果请求成功，产生的cookie会自动保存在session对象中
session.post(url=login_url, data=data, headers=headers)

url = 'http://www.renren.com/448850039/profile'
page_text = session.get(url=url, headers=headers).text

with open('renren.html', 'w', encoding='utf8') as f:
    f.write(page_text)

3、案例二：模拟登录古诗文网

# 模拟登陆古诗文网
from lxml import etree
import requests

s = requests.Session()

headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36'
}

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, verify=False).text          # verify=False是解决请求https协议问题，SSL错误

tree = etree.HTML(page_text)
img_code_url = 'https://so.gushiwen.org' + tree.xpath('//*[@id="imgCode"]/@src')[0]

# 验证码图片请求也会有session产生，因此不能使用urllib的urlretrieve方法
img_data = s.get(url=img_code_url, headers=headers, verify=False).content
with open('./gs_code_img.jpg','wb') as f:
    f.write(img_data)

# 识别验证码
code_data = getCodeData('bobo328410948', 'bobo328410948', './gs_code_img.jpg', 1004)

relogin_url = 'https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx'
# 当有些参数是动态变化的时，我们可以去网页源代码中找找
data = {
    "__VIEWSTATE":"u+DzAnizDr8zKG7K/Q/OHyl4Kae1i0R5uxnuMk+EONOCJb5GTyGoJgnx1n/wlOx4XePU+CN5dRcmV/ptirBjyW6SyzcQqdOMuyeIbuFfEWNcUm7K00I9RH7g5gA=",
    "__VIEWSTATEGENERATOR":"C93BE1AE",
    "from":"http://so.gushiwen.org/user/collect.aspx",
    "email":"1547360919@qq.com",
    "pwd":"512abc...",
    "code":code_data,
    "denglu":"登录"
} 
page_data = s.post(url=relogin_url, data=data, headers=headers, verify=False).text
with open('./gushici.html', 'w', encoding='utf8') as f:
    f.write(page_data)

4、随机获取User-Agent

# 但是因其服务器不稳定，有时候获取不到，因此我们很少用
from fake_useragent import UserAgent
ua = UserAgent(verify_ssl=False,use_cache_server=False).random
headers = {
    'User-Agent':ua
}

# fake_useragent的安装方式为 pip install fake-useragent

二、selenium

　　参考博客：https://www.cnblogs.com/bobo-zhang/p/9685362.html

　　selenium是一个第三方库，对外提供的接口可以操作浏览器，然后让浏览器完成自动化操作。可用于获取动态加载的数据。

1、环境搭建

　　- 安装

　　　　pip install selenium

　　- 获取某一款浏览器的驱动程序（以谷歌浏览器为例）

　　　　谷歌浏览器驱动下载地址：http://chromedriver.storage.googleapis.com/index.html

　　　　注意：下载的驱动程序必须和浏览器版本统一，大家可以根据 http://blog.csdn.net/huilan_same/article/details/51896672 中提供的版本映射表进行对应

2、编码流程

　　- 导包：from selenium import webdriver

　　- 实例化某一款浏览器对象

　　- 自制定自动化操作代码

　　PS：本人在导包的时候遇到了如下错误：

　　查了半天，尝试了各种都不管用，原来是我开着fiddler抓包软件了，将其关掉就可以了，[尴尬]！

3、简单示例代码

from selenium import webdriver
from time import sleep

bro = webdriver.Chrome(executable_path=r'D:@Lilymyprojectpachongchromedriver.exe')
bro.get(url='https://www.baidu.com/')
sleep(2)

text_input = bro.find_element_by_id('kw')    # 获取到输入框
text_input.send_keys('人民币')
sleep(2)

search_btn = bro.find_element_by_id('su').click()    # 获取到搜索按钮，并点击
sleep(2)

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

bro.quit()  # 关闭浏览器

4、示例：获取豆瓣电影更多详情数据

from selenium import webdriver
from time import sleep

url = 'https://movie.douban.com/typerank?type_name=%E5%96%9C%E5%89%A7&type=24&interval_id=100:90&action='
bro = webdriver.Chrome(executable_path=r'D:@Lilymyprojectpachongchromedriver.exe')

bro.get(url=url)
sleep(2)

bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')       # 浏览器向下滚动一屏的距离
sleep(2)

bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')   # 浏览器向下滚动一屏的距离
sleep(2)

bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')   # 浏览器向下滚动一屏的距离
sleep(2)

page_text = bro.page_source
with open('./douban.html','w',encoding='utf8') as f:
    f.write(page_text)
    
bro.quit()

5、示例：模拟登陆爬取QQ空间示例（嵌套iframe框架）

#qq空间
bro = webdriver.Chrome(executable_path=r'D:@Lilymyprojectpachongchromedriver.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('QQ空间用户名')
bro.find_element_by_id('p').send_keys('QQ空间密码')

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()

6、PhantomJs（无界面浏览器）

# 以获取豆瓣电影为例，仅仅在实例化浏览器对象时有区别，其他并无区别
from selenium import webdriver
from time import sleep

url = 'https://movie.douban.com/typerank?type_name=%E5%96%9C%E5%89%A7&type=24&interval_id=100:90&action='
bro = webdriver.Chrome(executable_path=r'D:@Lilymyprojectpachongphantomjs.exe')

bro.get(url=url)
sleep(2)

bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')       # 浏览器向下滚动一屏的距离
sleep(2)

bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')   # 浏览器向下滚动一屏的距离
sleep(2)

bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')   # 浏览器向下滚动一屏的距离
sleep(2)

page_text = bro.page_source
with open('./douban.html','w',encoding='utf8') as f:
    f.write(page_text)
    
bro.quit()

7、谷歌无头浏览器

　　由于PhantomJs最近已经停止了更新和维护，所以推荐使用谷歌的无头浏览器，是一款无界面的谷歌浏览器。

　　示例代码如下：

#谷歌无头浏览器
from selenium.webdriver.chrome.options import Options

# 创建一个参数对象，用来控制chrome以无界面方式打开
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'D:@Lilymyprojectpachongchromedriver.exe',chrome_options=chrome_options)
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)
bro.quit()

三、线程池

1、示例：爬取梨视频热门视频

# 爬取梨视频数据
import requests
import re
from lxml import etree
from multiprocessing.dummy import Pool
import random

# 实例化一个线程池对象
pool = Pool(5)
url = 'https://www.pearvideo.com/category_1'
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'
}
page_text = requests.get(url=url,headers=headers).text
tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@id="listvideoList"]/ul/li')

video_url_list = []
for li in li_list:
    detail_url = 'https://www.pearvideo.com/'+li.xpath('./div/a/@href')[0]
    detail_page = requests.get(url=detail_url,headers=headers).text
    video_url = re.findall('srcUrl="(.*?)",vdoUrl',detail_page,re.S)[0]
    video_url_list.append(video_url)
    

video_data_list = pool.map(getVideoData, video_url_list)
pool.map(saveVideo, video_data_list)


def getVideoData(url):
    return requests.get(url=url,headers=headers).content


def saveVideo(data):
    fileName = str(random.randint(0,5000))+'.mp4'
    with open(fileName,'wb') as fp:
        fp.write(data)

四、总结

　　本篇涉及到的反爬机制：

　　- 验证码

　　- 动态加载