872 views
python爬虫

4.requests高级知识

文章目录

requests高级知识

- 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/

使用代理

#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)

获取代理IP

#爬取西祠代理
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'
}

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))

检查代理ip是否能用

# 使用代理ip随意请求一个网址
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')

cookies处理

- 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。

模拟登陆-验证码识别

- 验证码的识别
    - 超级鹰:http://www.chaojiying.com/about.html
        - 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
- 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    

- 超级鹰SDk
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()

模拟登陆-古诗文网

# 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']

#模拟登陆
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)
影子专属博客 赣ICP备17013143号