• requests模块的进阶使用

    代理

    • 代理服务器,可以接受请求后将其转发,从而更换我们请求所对应的ip
    • 匿名度
      • 高匿:啥也不知道
      • 匿名:服务器会知道我使用了代理但是不知道我的真实ip
      • 透明:服务器会知道我使用了代理并且知道我的真实ip
    • 类型
      • http:意味着这个服务器只能转发http协议的请求
      • https:只能转发https协议的请求
    • 免费代理
    • 为了避免ip失效,我们应该构建一个代理池,里面存放可用的代理
    • 代理池的构建也是通过爬虫实现的,我们可以去快代理上去爬取,但是频繁访问快代理也是会被封的,所以我们需要去买一些代理来爬取快代理,有点以小博大的意思(这里的代理选取主要用于举例,主要是方法)
    # 代理池的用法
# ip_pool = [
#     {'https':'https://171.35.149.66:9999'},
#     {'https':'https://171.35.149.66:9999'},
#     ...
# ]

# url = 'https://www.baidu.com/s?wd=ip'
# page_text = requests.get(url=url,headers=headers,proxies=random.choice(ip_pool)).text
# with open('ip.html','w',encoding='utf-8') as fp:
#     fp.write(page_text)

    import requests
from lxml import etree
import random

headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36',
    'Connection':'close'
}

# 去代理精灵购买代理,并通过爬虫快速提取到购买的代理ip
ip_url = '.....'(购买后会生成一个url连接)
page_text = requests.get(url=ip_url,headers=headers).text
tree = etree.HTML(page_text)
ip_pool = tree.xpath('//body//text()')

# 爬取快代理
url = 'https://www.kuaidaili.com/free/inha/%d/'
proxy_http_list = []
proxy_https_list = []
for page in range(1,20):
    new_url = format(url%page)
    page_text = requests.get(new_url,headers=headers,proxies=random.choice(ip_pool)).text
    tree = etree.HTML(page_text)
    tr_list = tree.xpath('//*[@id="list"]/table//tr')[1:]  # 注意!tbody不能出现在xpath表达式中
    
    for tr in tr_list:
        ip = tr.xpath('./td[1]/text()')[0]
        port = tr.xpath('./td[2]/text()')[0]
        t_type = tr.xpath('./td[4]/text()')[0]
        cip = t_type+'://'+ip+':'+port
        dic = {
           t_type: cip
        }
        if t_type == 'HTTP':
            proxy_http_list.append(dic)
        else:
            proxy_https_list.append(dic)

print(len(proxy_http_list),len(proxy_https_list))   #查看个数

    # 检查代理是否可用
# 让其随意访问一个网站(http/https要分开),如果状态码为200,即为可用

for ip in proxy_http_list:
    response = requests.get('http://...',headers=headers,proxies=ip)
    if response.status_code == '200':
        ... #将可用ip存储起来

    • cookie的处理

      • cookie的作用:可以让浏览器记录和保存我们当前客户端的某些状态
      • 手动处理:将cookie封装到headers中
      • 自动处理:创建一个session对象,该对象可以像requests一样进行请求发送.不同之处在于如果使用session进行请求发送的过程中产生了cookie,则cookie会自动保存在session对象中.

    • 模拟登陆

    • 实现验证码识别

    • 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

    • 模拟登陆失败的话检查以下原因

      • 核对用户名和密码有无出错
      • 核对验证码是否正确
      • 检查请求参数是否为动态变化的
      • 最后检查cookie
    # 对雪球网的新闻数据进行爬取  https://xueqiu.com/
# 手动处理cookie
import requests
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36',
    'Cookie':'acw_tc=2760820e15998126544901640efe534c6e7b7ac5b225fee97814d7b22bf4a5; xq_a_token=4db837b914fc72624d814986f5b37e2a3d9e9944; xqat=4db837b914fc72624d814986f5b37e2a3d9e9944; xq_r_token=2d6d6cc8e57501dfe571d2881cabc6a5f2542bf8; xq_id_token=eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJ1aWQiOi0xLCJpc3MiOiJ1YyIsImV4cCI6MTYwMDQ4MzAwNywiY3RtIjoxNTk5ODEyNjE5NDkzLCJjaWQiOiJkOWQwbjRBWnVwIn0.Uf32VSRz3a-_uxv4lrdqq3K8GTOBcz4EIhTbL1pV3eTbFOv5JU89CmD2svrgJ6cBpUys0LGNuoR9l82uemyMjz5d3vtOijWOLui-VEcFGm1_U4gV90OsB9cH7CG7FE8xy0_O300VyaFjHtV6dDOfbrJdUz3ijLMntMoF3X_0454gUxqYZ78cAY5zwKYpt-BEUQFfJ2eAccbO2Gu432-fK3I6YT5kjkxHr-L0dIZIuEkqKNZBkzTG_dyoADaUG7vs-RL7N8gdWNaL3dfyeB2i8WsoLNiML8fyK5r-ujROfrhUKC8AcIof2fXT5a0mRXfG2ZLUzVE3udvqxyPhrc7XZA; u=601599812654691; Hm_lvt_1db88642e346389874251b5a1eded6e3=1599812658; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1599812658; device_id=24700f9f1986800ab4fcc880530dd0ed'
}

url = 'https://xueqiu.com/statuses/hot/listV2.json?since_id=-1&max_id=105684&size=15'
page_text = requests.get(url=url,headers=headers).json()
print(page_text)

    #创建session对象,自动处理cookie
import requests
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36'
}
session = requests.Session()
session.get('https://xueqiu.com/',headers=headers)  #先去访问一次主页,获取cookie

url = 'https://xueqiu.com/statuses/hot/listV2.json?since_id=-1&max_id=105684&size=15'
page_text = session.get(url=url,headers=headers).json()
print(page_text)

    模拟登陆

    # 超级鹰定义的类
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()

    # 识别古诗文网的验证码 https://www.gushiwen.org/
# 模拟登陆

# 获取验证码
def transformImgData(img_path,img_type):
    chaojiying = Chaojiying_Client(UserName, Password, 软件id)  # 此处依次输入超级鹰用户名,密码和生成的软件id
    im = open(img_path, 'rb').read()
    return chaojiying.PostPic(im, img_type)['pic_str']

import requests
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36',
}
url = 'https://so.gushiwen.cn/user/login.aspx'

# session获取cookie
session = requests.Session()

# 获取验证码图片
page_text = session.get(url=url,headers=headers).text
tree = etree.HTML(page_text)
img_url = 'https://so.gushiwen.cn'+tree.xpath('//*[@id="imgCode"]/@src')[0]  #验证码图片
img_data = session.get(url=img_url,headers=headers).content
with open('./code.jpg','wb') as fp:
    fp.write(img_data)

# 获取动态数据
__VIEWSTATEGENERATOR = tree.xpath('//*[@id="__VIEWSTATEGENERATOR"]/@value')  
__VIEWSTATE = tree.xpath('//*[@id="__VIEWSTATE"]/@value')

# 解析出验证码
code = transformImgData('./code.jpg',1004)
print(code)

# 模拟登陆
login_url = 'https://so.gushiwen.cn/user/login.aspx?from='
data = {
    '__VIEWSTATE': __VIEWSTATE,
    '__VIEWSTATEGENERATOR': __VIEWSTATEGENERATOR,
    'from': '',
    'email': '...',      #填写古诗文网账号和密码
    'pwd': '...',
    'code': code,
    'denglu': '登录',
}
login_page = session.post(url=login_url,headers=headers,data=data).text
with open('./login.html','w',encoding='utf-8') as fp:
    fp.write(login_page)
  • 相关阅读:
    【转】Centos yum 换源
    centos7下使用yum安装mysql
    【转】简易smtp调用类
    【转】Beanstalkd 队列简易使用
    【转】mysql 拖库写库用法
    【转】scp 命令格式
    【转】mac os 安装php
    pip 国内源 gem 国内源
    【转】25个必须记住的SSH命令
    NHibernate 有好几种数据库查询方式
  • 原文地址：https://www.cnblogs.com/straightup/p/13664753.html
Copyright © 2020-2023  润新知