您当前的位置：首页 > 计算机 > 编程开发 > Python

一个非常简单的网页刷量脚本（Python）

时间：08-06来源：作者：点击数：30

一、脚本功能

增加网页浏览量，简称刷量

二、脚本文件结构

ipporxy.txt # 存放代理ip
main.py # 主程序
proxiesIp.py # 代理ip检测
user_set.py # 刷量调整区域

三、具体代码

ipporxy.txt

116.253.208.239:33080

123.56.175.31:3128

139.9.64.238:443

123.56.175.31:3128

139.9.64.238:443

main.py

#!/usr/bin/env python
'''
1. 手动输入某个新闻链接，然后模拟人工访问网页
2. 可定义：N 个网页、刷新数量、刷新速度、访问浏览器
3. 数量要求：[700 ~ 100000]
'''
from ast import Try
import requests
import warnings
import urllib3
from bs4 import BeautifulSoup 
import os,time,random,datetime
import _thread,queue
import user_set as user
from selenium import webdriver
from selenium.webdriver.chrome.options import Options 
from requests.packages.urllib3.exceptions import InsecureRequestWarning


warnings.filterwarnings('ignore')
requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
urllib3.disable_warnings()
available_ip = ''
test_url = 'https://www.baidu.com'

# 读取有效 ip 文件
def ip_file ():
    available_ips=[]
    try:
        with open('./ipporxy.txt','r',encoding='UTF-8') as f:
            for l in f.readlines():
                available_ips.append(l.rstrip('\n'))
        return available_ips
    except Exception:
        print("Error 没有ipporxy.txt文件")
        exit()

def ip_random ():
    ips = ip_file ()
    if ips:
        proxie = random.choice(ips)
        requests.DEFAULT_RETRIES = 5
        s = requests.session()
        s.keep_alive = False
        proxies = { "http": proxie, "https": proxie}
        try:
            res = requests.get(test_url,proxies=proxies,verify=False,timeout=2)
        except Exception:
            print('代理 ip 连接出错，更换ip中...')
            ip_random ()
        else:
            if res.status_code == 200:
                print('ip 通道正常：[%s]，可以使用....'%proxie)
                available_ip = proxies
    else:
        print('Error 没有可用的代理 ip')
    

# 设置主功能，传入线程
def pv_pool(name,url,count):
    for i in range(count):
        headers = random.choice(user.UserAgent1)
        chrome_options = Options() 
        webdriver.DesiredCapabilities.CHROME['acceptSslCerts']=True
        chrome_options.add_argument('headless')
        chrome_options.add_argument('--disable-gpu')
        chrome_options.add_argument('--no-sandbox')
        chrome_options.add_argument('--user-agent=%s'%headers)
        try:
            chrome_options.add_argument('--proxy-server=%s'%available_ip) 
            driver = webdriver.Chrome(options = chrome_options) 
            driver.get(url) # 访问页面
        except Exception:
            print('Error 访问出现错误，更换 ip')
            ip_random ()
            continue
        else:
            time.sleep(random.uniform(user.speed_low,user.speed_high))
            driver.close()
            print("第 %d 次访问网页【%s】"%(i+1,datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')))
    print('~~~~{}线程结束时间：{}~~~~~\n'.format(name,datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')))


if __name__ == "__main__":
    # 获取有效 ip 地址
    ip_random ()

    # 开始刷点击量
    for site in user.webSites:
        url = site['url']
        times = int(site['times'])//3
        print(times)
        try:
            # print(url,times)
            # 启动多线程
            print('※※※※※线程启动时间：{}※※※※\n'.format(datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')))
            _thread.start_new_thread(pv_pool, (1,url,times))
            _thread.start_new_thread(pv_pool, (2,url,times))
            _thread.start_new_thread(pv_pool, (3,url,times))
        except:
            print ("Error: 无法启动线程")
    while 1:
        pass

proxiesIp.py

import telnetlib
import requests

test_url = 'https://www.baidu.com'

# ip 检测，存储有效 ip地址
def ip_is_alive(ip_port):
    ip,port=ip_port[0],ip_port[1]
    try:
        tn = telnetlib.Telnet(ip, port=port,timeout=1)
    except:
        print('[-]无效ip:{}:{}'.format(ip,port))
    else:
        proxies = ip+':'+port
        try:
            res = requests.get(test_url, proxies={"http": proxies, "https": proxies},timeout=1)
        except:
            print('[-]无效ip:{}:{}'.format(ip,port))
        else:   
            if res.status_code == 200:
                print('[+]有效ip:{}:{}'.format(ip,port))
                # 将有效 ip 写入文件中
                with open('ipporxy.txt','a+') as f:
                    f.write(ip+':'+port+'\n')

user_set.py

#!/usr/bin/env python
import proxiesIp
import requests
from lxml import etree

# 设置多个需要刷量网址，及其次数，默认值为num
num = 30
webSites = [{'url':'www.baidu.com','times':num}]

# 多个网页
# webSites = [{'url':'xxx','times':num},{'url':'xxx','times':num}]

# 设置随机的刷新速度
speed_low = 2
speed_high = 3

# 设置微信浏览器：安卓，ios
UserAgent1 =[
    {'User-Agent':'mozilla/5.0 (linux; u; android 4.1.2; zh-cn; mi-one plus build/jzo54k) applewebkit/534.30 (khtml, like gecko) version/4.0 mobile safari/534.30 MicroMessenger/5.0.1.352'},
    {'User-Agent':'mozilla/5.0 (iphone; cpu iphone os 5\_1\_1 like mac os x) applewebkit/534.46 (khtml, like gecko) mobile/9b206 MicroMessenger/5.0'},
    {'User-Agent':'Mozilla/5.0 (Linux; Android 5.0; SM-N9100 Build/LRX21V) > AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 > Chrome/37.0.0.0 Mobile Safari/537.36 > MicroMessenger/6.0.2.56\_r958800.520 NetType/WIFI'},
    {'User-Agent':'Mozilla/5.0 (iPhone; CPU iPhone OS 7\_1\_2 like Mac OS X) > AppleWebKit/537.51.2 (KHTML, like Gecko) Mobile/11D257 > MicroMessenger/6.0.1 NetType/WIFI'},
    {'User-Agent':'Mozilla/5.0 (Linux; U; Android 2.3.6; zh-cn; GT-S5660 Build/GINGERBREAD) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1 MicroMessenger/4.5.255'},
    {'User-Agent':'Mozilla/5.0 (iPhone; CPU iPhone OS 7_1_2 like Mac OS X) AppleWebKit/537.51.2 (KHTML, like Gecko) Mobile/11D257 MicroMessenger/6.1 NetType/WIFI'}]

# 设置pc浏览器：chrome、safari、火狐 等
UserAgent2 = [
    {'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36'},
    {'User-Agent':'Mozilla/5.0 (Windows NT6.1; WOW64) Apple\WebKit/537.36 (KHTML, likeGecko) Chrome/69.0.3497.92 Safari/537.36'},
    {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'},
    {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:40.0) Gecko/20100101 Firefox/40.1'},
    {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'},
    {'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'},
    {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.18362'},
    {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36'}]

# 测试伪装 ip 地址，后期设置 ip 接口获取
def turn_symbol(c1):
    new_c1 = c1.replace('\n','').replace('\t','')
    return  new_c1

#获取免费代理网站ip(ip+空格+port形式)
def getfreeIps():
    f=open('ipporxy.txt', "r+")
    f.truncate()
    for i in range(1,100):
        url = 'http://www.89ip.cn/index_{}.html'.format(i)
        res = requests.get(url)
        res.encoding = 'utf-8'
        html=etree.HTML(res.text)
        ipdress=html.xpath('//table[@class="layui-table"]/tbody/tr/td[1]/text()')
        port=html.xpath('//table[@class="layui-table"]/tbody/tr/td[2]/text()')
        ipdress=list(map(turn_symbol,ipdress))
        port=list(map(turn_symbol,port))
        data=list(zip(ipdress,port))
        
        for j in range(len(data)):
            # 测试并存储有效 ip 
            proxiesIp.ip_is_alive([data[j][0],data[j][1]])

if __name__ == "__main__":
    # 测试可用的 ip 地址，并进行本地存储
    getfreeIps()