爬虫3 request3高级 代理操作、模拟登录、单线程+多任务异步协程

- HttpConnectinPool:
- 原因:
- 1.短时间内发起了高频的请求导致ip被禁
- 2.http连接池中的连接资源被耗尽
- 解决:
- 1.代理
- 2.headers中加入Conection:“close”

- 代理:代理服务器,可以接受请求然后将其转发。
- 匿名度
- 高匿:啥也不知道
- 匿名:知道你使用了代理,但是不知道你的真实ip
- 透明:知道你使用了代理并且知道你的真实ip
- 类型:
- http
- https
- 免费代理:
- www.goubanjia.com
- 快代理
- 西祠代理
- http://http.zhiliandaili.cn/  智联HTTP的代理精灵

- cookie的处理

代理的写法示例:

import requests
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'
}
url = 'https://www.baidu.com/s?wd=ip'
page_text1 = requests.get(url,headers=headers,proxies={'https':'183.166.171.51:8888'}).text
with open('ip.html','w',encoding='utf-8') as fp:
    fp.write(page_text1)

一个代理很容易被封,这时候我们要构造一个代理池

#代理池:列表
import random
proxy_list = [
    {'https':'121.231.94.44:8888'},
    {'https':'131.231.94.44:8888'},
    {'https':'141.231.94.44:8888'}
]
url = 'https://www.baidu.com/s?wd=ip'
page_text = requests.get(url,headers=headers,proxies=random.choice(proxy_list)).text
with open('ip.html','w',encoding='utf-8') as fp:
    fp.write(page_text)

如何构造代理池呢?其中一个方法如下

from lxml import etree
ip_url = 'http://t.11jsq.com/index.php/api/entry?method=proxyServer.generate_api_url&packid=1&fa=0&fetch_key=&groupid=0&qty=4&time=1&pro=&city=&port=1&format=html&ss=5&css=&dt=1&specialTxt=3&specialJson=&usertype=2'
page_text = requests.get(ip_url,headers=headers).text
tree = etree.HTML(page_text)
ip_list = tree.xpath('//body//text()')
print(ip_list)
#从代理精灵中提取代理ip

然后

import random
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36',
    'Connection':"close"
}
url = 'https://www.xicidaili.com/nn/%d'
proxy_list_http = []
proxy_list_https = []
for page in range(1,20):
    new_url = format(url%page)
    ip_port = random.choice(ip_list)
    page_text = requests.get(new_url,headers=headers,proxies={'https':ip_port}).text
    tree = etree.HTML(page_text)
    #tbody不可以出现在xpath表达式中
    tr_list = tree.xpath('//*[@id="ip_list"]//tr')[1:]
    for tr in tr_list:
        ip = tr.xpath('./td[2]/text()')[0]
        port = tr.xpath('./td[3]/text()')[0]
        t_type = tr.xpath('./td[6]/text()')[0]
        ips = ip+':'+port
        if t_type == 'HTTP':
            dic = {
                t_type: ips
            }
            proxy_list_http.append(dic)
        else:
            dic = {
                t_type:ips
            }
            proxy_list_https.append(dic)
print(len(proxy_list_http),len(proxy_list_https))
#爬取西祠代理
#检测
for ip in proxy_list_http:
    response = requests.get('https://www/sogou.com',headers=headers,proxies={'https':ip})
    if response.status_code == '200':
        print('检测到了可用ip')

模拟登录!!!

cookie的处理

  • 手动处理:将cookie封装到headers中
  • 自动处理:session对象。可以创建一个session对象,改对象可以像requests一样进行请求发送。不同之处在于如果在使用session进行请求发送的过程中产生了cookie,则cookie会被自动存储在session对象中。

手动加上cookie:

#对雪球网中的新闻数据进行爬取https://xueqiu.com/
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36',
#     'Cookie':'aliyungf_tc=AQAAAAl2aA+kKgkAtxdwe3JmsY226Y+n; acw_tc=2760822915681668126047128e605abf3a5518432dc7f074b2c9cb26d0aa94; xq_a_token=75661393f1556aa7f900df4dc91059df49b83145; xq_r_token=29fe5e93ec0b24974bdd382ffb61d026d8350d7d; u=121568166816578; device_id=24700f9f1986800ab4fcc880530dd0ed'
}
url = 'https://xueqiu.com/v4/statuses/public_timeline_by_category.json?since_id=-1&max_id=20349203&count=15&category=-1'
page_text = requests.get(url=url,headers=headers).json()
page_text

自动添加cookie:

#创建session对象
session = requests.Session()
session.get('https://xueqiu.com',headers=headers)

url = 'https://xueqiu.com/v4/statuses/public_timeline_by_category.json?since_id=-1&max_id=20349203&count=15&category=-1'
page_text = session.get(url=url,headers=headers).json()
page_text

- 验证码的识别
- 超级鹰:  
- 注册:(用户中心身份)
- 登陆:
- 创建一个软件:899370
- 下载示例代码
- 打码兔
- 云打码

超级鹰示例

import requests
from hashlib import md5

class Chaojiying_Client(object):

    def __init__(self, username, password, soft_id):
        self.username = username
        password =  password.encode('utf8')
        self.password = md5(password).hexdigest()
        self.soft_id = soft_id
        self.base_params = {
            'user': self.username,
            'pass2': self.password,
            'softid': self.soft_id,
        }
        self.headers = {
            'Connection': 'Keep-Alive',
            'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
        }

    def PostPic(self, im, codetype):
        """
        im: 图片字节
        codetype: 题目类型 参考 http://www.chaojiying.com/price.html
        """
        params = {
            'codetype': codetype,
        }
        params.update(self.base_params)
        files = {'userfile': ('ccc.jpg', im)}
        r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files, headers=self.headers)
        return r.json()

    def ReportError(self, im_id):
        """
        im_id:报错题目的图片ID
        """
        params = {
            'id': im_id,
        }
        params.update(self.base_params)
        r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)
        return r.json()

#识别古诗文网中的验证码
def tranformImgData(imgPath,t_type):
    chaojiying = Chaojiying_Client('bobo328410948', 'bobo328410948', '899370')
    im = open(imgPath, 'rb').read()
    return chaojiying.PostPic(im, t_type)['pic_str']

url = 'https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx'
page_text = requests.get(url,headers=headers).text
tree = etree.HTML(page_text)
img_src = 'https://so.gushiwen.org'+tree.xpath('//*[@id="imgCode"]/@src')[0]
img_data = requests.get(img_src,headers=headers).content
with open('./code.jpg','wb') as fp:
    fp.write(img_data)
    
tranformImgData('./code.jpg',1004)
超级鹰

然后就可以轻松登录古诗文 网站啦!(注意验证码的刷新的机制和动态变化的请求参数)

    - 动态变化的请求参数
        - 通常情况下动态变化的请求参数都会被隐藏在前台页面源码中

        (这里直接在页面搜__VIEWSTATE值,然后抓下来用它)

      (用session 发送请求,保持验证码的一致性!)

s = requests.Session()
url = 'https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx'
page_text = s.get(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(img_src,headers=headers).content
with open('./code.jpg','wb') as fp:
    fp.write(img_data)
    
#动态获取变化的请求参数
__VIEWSTATE = tree.xpath('//*[@id="__VIEWSTATE"]/@value')[0]
__VIEWSTATEGENERATOR = tree.xpath('//*[@id="__VIEWSTATEGENERATOR"]/@value')[0]
    
code_text = tranformImgData('./code.jpg',1004)
print(code_text)
login_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': code_text,
    'denglu': '登录',
}
page_text = s.post(url=login_url,headers=headers,data=data).text
with open('login.html','w',encoding='utf-8') as fp:
    fp.write(page_text)

 

 

# 普通单线程 和线程池的速度对比

from time import sleep
import time
from multiprocessing.dummy import Pool
start = time.time()
urls = [
'http://www.baidu.com',
'http://www.sougou.com',
'http://www.qq.com',
'https://www.iqiyi.com/'



]
def get_request(url):
print('正在下载',url)

time.sleep(2)
print('OK了',url)


# pool = Pool(3)
# pool.map(get_request,urls)
for url in urls:
get_request(url)

print('总耗时:',time.time()-start)

 

单线程+多任务异步协程

  • 协程   
    • 在函数(特殊的函数)定义的时候,如果使用了async修饰的话,则改函数调用后会返回一个协程对象,并且函数内部的实现语句不会被立即执行
  • 任务对象
    • 任务对象就是对协程对象的进一步封装。任务对象==高级的协程对象==特殊的函数
    • 任务对象时必须要注册到事件循环对象中
    • 给任务对象绑定回调:爬虫的数据解析中
  • 事件循环
    • 当做是一个容器,容器中必须存放任务对象。
    • 当启动事件循环对象后,则事件循环对象会对其内部存储任务对象进行异步的执行。
  • aiohttp:支持异步网络请求的模块
模板如下

import asyncio
def callback(task): #作为任务对象的回调函数
    print('i am callback and ',task.result())   # task.result()就是异步函数的返回值

async def test():
    print('i am test()')
    return 'bobo'

c = test()
#封装了一个任务对象
task = asyncio.ensure_future(c)
task.add_done_callback(callback)  # 绑定回调
#创建一个事件循环的对象
loop = asyncio.get_event_loop()
loop.run_until_complete(task)

异步 I/O

asyncio 是用来编写 并发 代码的库,使用 async/await 语法。

asyncio 被用作多个提供高性能 Python 异步框架的基础,包括网络和网站服务,数据库连接库,分布式任务队列等等。

asyncio 往往是构建 IO 密集型和高层级 结构化 网络代码的最佳选择。

import asyncio
import time
start = time.time()
#在特殊函数内部的实现中不可以出现不支持异步的模块代码
async def get_request(url):
    await asyncio.sleep(2)
    print('下载成功:',url)

urls = [
    'www.1.com',
    'www.2.com'
]
tasks = []
for url in urls:
    c = get_request(url)
    task = asyncio.ensure_future(c)
    tasks.append(task)

loop = asyncio.get_event_loop()
#注意:挂起操作需要手动处理
loop.run_until_complete(asyncio.wait(tasks))
print(time.time()-start)

爬虫应用:

import requests
import aiohttp
import time
import asyncio
s = time.time()
urls = [
    'http://127.0.0.1:5000/bobo',
    'http://127.0.0.1:5000/jay'
]

# async def get_request(url):
#     page_text = requests.get(url).text
#     return page_text
async def get_request(url):
   async with aiohttp.ClientSession() as s:    #这边不能用不支持异步的requests
       async with await s.get(url=url) as response:
           page_text = await response.text()
           print(page_text)
   return page_text
tasks = []
for url in urls:
    c = get_request(url)
    task = asyncio.ensure_future(c)
    tasks.append(task)

loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.wait(tasks))

print(time.time()-s)

multiprocessing包是Python中的多进程管理包。

1、示例:

爬虫脚本:

import aiohttp
import asyncio
import time
from lxml import etree
start = time.time()
urls = [
'http://127.0.0.1:5000/bobo',
'http://127.0.0.1:5000/jay',
'http://127.0.0.1:5000/tom',
'http://127.0.0.1:5000/bobo',
'http://127.0.0.1:5000/jay',
'http://127.0.0.1:5000/tom',
'http://127.0.0.1:5000/bobo',
'http://127.0.0.1:5000/jay',
'http://127.0.0.1:5000/tom',
'http://127.0.0.1:5000/bobo',
'http://127.0.0.1:5000/jay',
'http://127.0.0.1:5000/tom'
]
#特殊的函数:请求发送和响应数据的捕获
#细节:在每一个with前加上async,在每一个阻塞操作的前边加上await
async def get_request(url):
async with aiohttp.ClientSession() as s:
#s.get(url,headers,proxy="http://ip:port",params)
async with await s.get(url) as response:
page_text = await response.text()#read()返回的是byte类型的数据
return page_text
#回调函数
def parse(task):
page_text = task.result()
tree = etree.HTML(page_text)
parse_data = tree.xpath('//li/text()')
print(parse_data)

tasks = []
for url in urls:
c = get_request(url)
task = asyncio.ensure_future(c)
task.add_done_callback(parse)
tasks.append(task)

loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.wait(tasks))

print(time.time()-start)

示例服务器:

from flask import Flask
from time import sleep
app = Flask(__name__)
@app.route('/index')
def index():
    sleep(2)
    return 'hello'
@app.route('/index1')
def index1():
    sleep(2)
    return 'hello1'
if __name__ == '__main__':
    app.run()
原文地址:https://www.cnblogs.com/zhuangdd/p/13696515.html