爬虫 --- 04. 代理服务器, 验证码识别, 处理cookie,线程池
一.代理服务器
1.基本概念
- 代理的网站： - 快代理 - 西祠代理 - goubanjia (概率较高) - 代理知识：https://help.kuaidaili.com/wiki/ - 匿名度： - 透明：对方服务器可以知道你使用了代理，并且也知道你的真实IP - 匿名：对方服务器可以知道你使用了代理，但不知道你的真实IP - 高匿：对方服务器不知道你使用了代理，更不知道你的真实IP。 - 类型： - http：该类型的代理ip只可以发起http协议头对应的请求 - https：该类型的代理ip只可以发起https协议头对应的请求
2.示例
#简单版
import requests headers = { 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36' } url = 'https://www.baidu.com/s?wd=ip' page_text = requests.get(url=url,headers=headers,proxies={"https":"101.80.87.77:9000"}).text with open('./ip.html','w',encoding='utf-8') as fp: fp.write(page_text)
#升级版(减少被封的几率)
import requests import random https = [ {'https':'223.19.212.30:8380'}, {'https':'221.19.212.30:8380'} ] http = [ {'http':'223.19.212.30:8380'}, {'http':'221.19.212.30:8380'} ] headers = { 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36' } url = 'https://www.baidu.com/s?wd=ip' if url.split(':')[0] == 'https': page_text = requests.get(url=url,headers=headers,proxies=random.choice(https)).text else: page_text = requests.get(url=url,headers=headers,proxies=random.choice(http)).text with open('./ip.html','w',encoding='utf-8') as fp: fp.write(page_text)
二.验证码识别
常用的接口网站
1.云打码，
2.打码兔，
3.超级鹰
云打码使用流程 http://www.yundama.com/demo.html 注册： 普通用户 开发者用户 登录： 登录普通用户： 查询剩余题分 登录开发者用户： 创建一个软件：我的软件-》创建一个新软件（软件名称，秘钥不可以修改），使用软件的id和秘钥 下载示例代码：开发文档-》点此下载：云打码接口DLL-》PythonHTTP示例下载
以下代码是下载的文件中的内容
用的时候需加载
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
#将示例代码中的可执行程序封装成函数 def transformCodeImg(imgPath,imgType): # 普通用户名 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 = imgPath # 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 = imgType # 超时时间，秒 timeout = 30 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); return result
三.处理cookie
- cookie：可是使得服务器端记录客户端的相关状态
- 处理cookie的方法:
-手动处理: 在hears中加入cookie,但cookie是有有效时长的
-自动处理: 使用会话对象Session
- Session的用法:
- 实例化一个会话对象: requests.Session()
- session的作用:
- 会话对象可以进行请求发送(post,get)
- 如果在进行请求发送过程中产生的cookie,会被自动存在session中
#需求：爬取雪球网中的新闻标题和对应的内容简介
import requests
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36'
}
#实例化对象
sesion = requests.Session()
#这一步如果产生cookie,则cookie会被自动存储到session中
session.get(url="https://xueqiu.com/",headers=headers)
url = 'https://xueqiu.com/v4/statuses/public_timeline_by_category.json?since_id=-1&max_id=-1&count=10&category=-1'#session对象中就携带了cookie,发送请求 json_obj = session.get(url=url,headers=headers).json() print(json_obj)
四.综合示例(验证码,模拟登陆,cookie)
#对古诗文网进行模拟登陆 #1.获取验证码图片,并且让打码平台进行识别 import requests from lxml import etree s = requests.Session() url = "https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx" headers = { 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36' } page_text = s.get(url= 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("./gushiwen.jpg","wb") as fp: fp.write(img_data) result= transformCodeImg("./gushiwen.jpg",1004) print(result) __VIEWSTATE = tree.xpath('//*[@id="__VIEWSTATE"]/@value')[0] __VIEWSTATEGENERATOR = tree.xpath('//*[@id="__VIEWSTATEGENERATOR"]/@value')[0] #模拟登陆 post_url = "https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx" data = { "__VIEWSTATE": __VIEWSTATE, "__VIEWSTATEGENERATOR": __VIEWSTATEGENERATOR, "from": "http://so.gushiwen.org/user/collect.aspx", "email": "www.zhangbowudi@qq.com", "pwd": "bobo328410948", "code": result, "denglu": "登录", } response = s.post(url= post_url,data= data, headers=headers) print(response.status_code) page_text = response.text with open("./gushi.html","w",encoding="utf-8") as fp: fp.write(page_text)
五.线程池的使用
线程池需要用到爬虫较为耗时的操作中
耗时的操作:
视频的下载,
视频的保存
import re from multiprocessing.dummy import Pool pool = Pool(4) #创建线程池 url = "https://www.pearvideo.com/category_1" page_text = requests.get(url=url, headers= headers).text tree = etree.HTML(page_text) li_list = tree.xpath('//ul[@id="listvideoListUl"]/li') video_urls = [] #存放所有的视频url for li in li_list: deta_url ='https://www.pearvideo.com/'+ li.xpath('./div/a/@href')[0] detail_page = requests.get(url= deta_url,headers= headers).text ex = 'srcUrl="(.*?)",vdoUrl=' videl_src = re.findall(ex,detail_page,re.S)[0] video_urls.append(videl_src) #使用异步(线程池)下载视频 all_video = pool.map(getVidelData,video_urls) #前参数为函数,后参数为列表 print("下载完成")
使用异步保存视频 pool.map(saveVideo,all_video)
print("保存完成")
#下载视频的函数
def getVidelData(url): return requests.get(url=url,headers=headers).content
#保存视频的函数
import random def saveVideo(data): name = str(random.randint(0,9999))+".mp4" with open(name,"wb") as fp: fp.write(data)
