一.验证码处理
1.云打码平台处理验证码的实现流程:
1.对携带验证码的页面数据进行抓取 2.可以将页面数据中验证码进行解析,验证码图片下载到本地 3.可以将验证码图片提交给三方平台进行识别,返回验证码图片上的数据值 - 云打码平台: - 1.在官网中进行注册(普通用户和开发者用户) - 2.登录开发者用户: - 1.实例代码的下载(开发文档-》调用实例及最新的DLL-》PythonHTTP实例下载) - 2.创建一个软件:我的软件-》添加新的软件 -3.使用示例代码中的源码文件中的代码进行修改,让其识别验证码图片中的数据值
示例:
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 = 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 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/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 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' } 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)
二.图片懒加载,selenium,PhantomJS
1.图片懒加载的概念:
图片懒加载是一种网页优化技术。图片作为一种网络资源,在被请求时也与普通静态资源一样,将占用网络资源,而一次性将整个页面的所有图片加载完,将大大增加页面的首屏加载时间。为了解决这种问题,通过前后端配合,使图片仅在浏览器当前视窗内出现时才加载该图片,达到减少首屏图片请求数的技术就被称为“图片懒加载”。
2.如何实现图片懒加载技术:
在网页源码中,在img标签中首先会使用一个“伪属性”(通常使用src2,original......)去存放真正的图片链接而并非是直接存放在src属性中。当图片出现到页面的可视化区域中,会动态将伪属性替换成src属性,完成图片的加载。
#!/usr/bin/env python # -*- coding:utf-8 -*- import requests from lxml import etree if __name__ == "__main__": url = 'http://sc.chinaz.com/tupian/gudianmeinvtupian.html' headers = { 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36', } #获取页面文本数据 response = requests.get(url=url,headers=headers) response.encoding = 'utf-8' page_text = response.text #解析页面数据(获取页面中的图片链接) #创建etree对象 tree = etree.HTML(page_text) div_list = tree.xpath('//div[@id="container"]/div') #解析获取图片地址和图片的名称 for div in div_list: image_url = div.xpath('.//img/@src'2) #src2伪属性 image_name = div.xpath('.//img/@alt') print(image_url) #打印图片链接 print(image_name)#打印图片名称
3.selenium
是Python的一个第三方库,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的操作。
环境的建立
安装selenum: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 下载的驱动程序必须和浏览器的版本统一,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
示例:
from selenium import webdriver from time import sleep bro = webdriver.Chrome(executable_path=r"E:python学习数据+爬虫第三天chromedriver_win32chromedriver.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) print(bro.page_source) bro.quit()
代码介绍:
#导包 from selenium import webdriver #创建浏览器对象,通过该对象可以操作浏览器 browser = webdriver.Chrome('驱动路径') #使用浏览器发起指定请求 browser.get(url) #使用下面的方法,查找指定的元素进行操作即可 find_element_by_id 根据id找节点 find_elements_by_name 根据name找 find_elements_by_xpath 根据xpath查找 find_elements_by_tag_name 根据标签名找 find_elements_by_class_name 根据class名字查找
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'C:UsersAdministratorDesktop爬虫+数据day_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()
4.phantomJs
PhantomJS是一款无界面的浏览器,其自动化操作流程和上述操作谷歌浏览器是一致的。由于是无界面的,为了能够展示自动化操作流程,PhantomJS为用户提供了一个截屏的功能,使用save_screenshot函数实现。
#phantomJs #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'C:UsersAdministratorDesktop爬虫+数据day_03_爬虫phantomjs-2.1.1-windowsinphantomjs.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()
5.谷歌无头浏览器
#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'C:UsersAdministratorDesktop爬虫+数据day_03_爬虫chromedriver.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.requests模块的cookie和线程池
1.cookie的概念:
当用户通过浏览器首次访问一个域名时,访问的web服务器会给客户端发送数据,以保持web服务器与客户端之间的状态保持,这些数据就是cookie。
2.cookie的作用:
我们在浏览器中,经常涉及到数据的交换,比如你登录邮箱,登录一个页面。我们经常会在此时设置30天内记住我,或者自动登录选项,Cookie是由HTTP服务器设置的,保存在浏览器中,但HTTP协议是一种无状态协议,在数据交换完毕后,服务器端和客户端的链接就会关闭,每次交换数据都需要建立新的链接。
3.思路:
我们需要使用爬虫程序对人人网的登录时的请求进行一次抓取,获取请求中的cookie数据
在使用个人信息页的url进行请求时,该请求需要携带 1 中的cookie,只有携带了cookie后,服务器才可识别这次请求的用户信息,方可响应回指定的用户信息页数据。
示例:
#!/usr/bin/env python # -*- coding:utf-8 -*- import requests if __name__ == "__main__": #登录请求的url(通过抓包工具获取) post_url = 'http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=201873958471' #创建一个session对象,该对象会自动将请求中的cookie进行存储和携带 session = requests.session() #伪装UA headers={ 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36', } formdata = { 'email': '17701256561', 'icode': '', 'origURL': 'http://www.renren.com/home', 'domain': 'renren.com', 'key_id': '1', 'captcha_type': 'web_login', 'password': '7b456e6c3eb6615b2e122a2942ef3845da1f91e3de075179079a3b84952508e4', 'rkey': '44fd96c219c593f3c9612360c80310a3', 'f': 'https%3A%2F%2Fwww.baidu.com%2Flink%3Furl%3Dm7m_NSUp5Ri_ZrK5eNIpn_dMs48UAcvT-N_kmysWgYW%26wd%3D%26eqid%3Dba95daf5000065ce000000035b120219', } #使用session发送请求,目的是为了将session保存该次请求中的cookie session.post(url=post_url,data=formdata,headers=headers) get_url = 'http://www.renren.com/960481378/profile' #再次使用session进行请求的发送,该次请求中已经携带了cookie response = session.get(url=get_url,headers=headers) #设置响应内容的编码格式 response.encoding = 'utf-8' #将响应内容写入文件 with open('./renren.html','w') as fp: fp.write(response.text)
2.基于multiprocessing.dummy线程池的数据爬取
实例:
爬取梨视频数据
普通爬取:
import requests import random from lxml import etree import re from fake_useragent import UserAgent #安装fake-useragent库:pip install fake-useragent url = 'http://www.pearvideo.com/category_1' #随机产生UA,如果报错则可以添加如下参数: #ua = UserAgent(verify_ssl=False,use_cache_server=False).random #禁用服务器缓存: #ua = UserAgent(use_cache_server=False) #不缓存数据: #ua = UserAgent(cache=False) #忽略ssl验证: #ua = UserAgent(verify_ssl=False) ua = UserAgent().random headers = { 'User-Agent':ua } #获取首页页面数据 page_text = requests.get(url=url,headers=headers).text #对获取的首页页面数据中的相关视频详情链接进行解析 tree = etree.HTML(page_text) li_list = tree.xpath('//div[@id="listvideoList"]/ul/li') detail_urls = [] for li in li_list: detail_url = 'http://www.pearvideo.com/'+li.xpath('./div/a/@href')[0] title = li.xpath('.//div[@class="vervideo-title"]/text()')[0] detail_urls.append(detail_url) for url in detail_urls: page_text = requests.get(url=url,headers=headers).text vedio_url = re.findall('srcUrl="(.*?)"',page_text,re.S)[0] data = requests.get(url=vedio_url,headers=headers).content fileName = str(random.randint(1,10000))+'.mp4' #随机生成视频文件名称 with open(fileName,'wb') as fp: fp.write(data) print(fileName+' is over')
基于线程池的爬取
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)