Python-批量刷博客园访问量脚本

其他 2019-06-28 11:01:34 阅读次数: 0

今早无聊。。。7点起来突然想写个刷访问量的。。那就动手吧

仅供测试，不建议刷访问量哦~~

很简单的思路，第一步提取代理ip，第二步模拟访问。

0x01 提取HTTP代理IP

网上很多收费的代理和免费的代理IP

如:

无论哪个网站，我们需要的就是爬取上面的ip和端口号，整理到一起。

具体的网站根据具体的结构爬取 比如上面那个网站，ip和端口在td标签

这里利用bs4爬取即可。贴上脚本

##获取代理ip
def Get_proxy_ip():
    print("==========批量提取ip刷博客园访问量 By 卿=========")
    print("          Blogs:https://www.cnblogs.com/-qing-/")
    print("          Started!      ")
    global proxy_list
    proxy_list = []
    url = "https://www.kuaidaili.com/free/inha/"
    headers = {
            "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
            "Accept-Encoding":"gzip, deflate, sdch, br",
            "Accept-Language":"zh-CN,zh;q=0.8",
            "Cache-Control":"max-age=0",
            "Connection":"keep-alive",
            "Cookie":"channelid=0; sid=1561681200472193; _ga=GA1.2.762166746.1561681203; _gid=GA1.2.971407760.1561681203; _gat=1; Hm_lvt_7ed65b1cc4b810e9fd37959c9bb51b31=1561681203; Hm_lpvt_7ed65b1cc4b810e9fd37959c9bb51b31=1561681203",
            "Host":"www.kuaidaili.com",
            "Upgrade-Insecure-Requests":"1",
            "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0",
            "Referrer Policy":"no-referrer-when-downgrade",
            }
    for i in range(1,100):
        url = url = "https://www.kuaidaili.com/free/inha/"+str(i)
        html = requests.get(url = url,headers = headers).content
        soup = BeautifulSoup(html,'html.parser')
        ip_list = '';
        port_list = '';
        protocol_list = '';
        for ip in soup.find_all('td'):
            if "IP" in ip.get('data-title') :
                ip_list = ip.get_text()##获取ip             
            if "PORT" in ip.get('data-title'):
                port_list = ip.get_text()##获取port
            if ip_list != '' and port_list != '':
                proxy = ip_list+":"+port_list
                ip_list = '';
                port_list = '';
                proxy_list.append(proxy)
        iv_main()
        time.sleep(2)
        proxy_list = []

这样就把 提取的ip和端口放到列表里

0x02 模拟访问刷博客园文章

这里就很简单了 ，遍历上面那个代理ip的列表，使用requests模块取访问就是了

def iv_main():
    proxies = {}
    requests.packages.urllib3.disable_warnings()
    #proxy_ip = random.choice(proxy_list)
    url = 'https://www.cnblogs.com/-qing-/p/11080845.html'
    for proxy_ip in proxy_list:
        headers2 = {
            'accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
            'accept-encoding':'gzip, deflate, sdch, br',
            'accept-language':'zh-CN,zh;q=0.8',
            'cache-control':'max-age=0',
            'cookie':'__gads=ID=8c6fd85d91262bb1:T=1561554219:S=ALNI_MZwz0CMKQJK-L19DrX5DPDtYvp63Q; _gat=1; _ga=GA1.2.359634670.1561535095; _gid=GA1.2.1087331661.1561535095',
            'if-modified-since':'Fri, 28 Jun 2019 02:10:23 GMT',
            'referer':'https://www.cnblogs.com/',
            'upgrade-insecure-requests':'1',
            'user-agent':random.choice(user_agent_list),
            }
        proxies['HTTP'] = proxy_ip
        #user_agent = random.choice(user_agent_list)
        try:
            r = requests.get(url,headers=headers2,proxies=proxies,verify=False) #verify是否验证服务器的SSL证书
            print("[*]"+proxy_ip+"访问成功！")
        except:
            print("[-]"+proxy_ip+"访问失败！")

最好带上随机的ua请求头

user_agent_list = [
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) "
                      "Chrome/45.0.2454.85 Safari/537.36 115Browser/6.0.3",
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
    "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0",
    "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
]

0x03 优化整合

这里可以稍微优化下，加入队列线程优化(虽然python这个没啥用)

最终代码整合:

# -*- coding:utf-8 -*-
#By 卿 
#Blog:https://www.cnblogs.com/-qing-/

import requests
from bs4 import BeautifulSoup
import re
import time
import random
import threading

print("==========批量提取ip刷博客园访问量 By 卿=========")
print("          Blogs:https://www.cnblogs.com/-qing-/")
print("          Started!      ")
user_agent_list = [
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) "
                      "Chrome/45.0.2454.85 Safari/537.36 115Browser/6.0.3",
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
    "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0",
    "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
]
def iv_main():
    proxies = {}
    requests.packages.urllib3.disable_warnings()
    #proxy_ip = random.choice(proxy_list)
    url = 'https://www.cnblogs.com/-qing-/p/11080845.html'
    for proxy_ip in proxy_list:
        headers2 = {
            'accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
            'accept-encoding':'gzip, deflate, sdch, br',
            'accept-language':'zh-CN,zh;q=0.8',
            'cache-control':'max-age=0',
            'cookie':'__gads=ID=8c6fd85d91262bb1:T=1561554219:S=ALNI_MZwz0CMKQJK-L19DrX5DPDtYvp63Q; _gat=1; _ga=GA1.2.359634670.1561535095; _gid=GA1.2.1087331661.1561535095',
            'if-modified-since':'Fri, 28 Jun 2019 02:10:23 GMT',
            'referer':'https://www.cnblogs.com/',
            'upgrade-insecure-requests':'1',
            'user-agent':random.choice(user_agent_list),
            }
        proxies['HTTP'] = proxy_ip
        #user_agent = random.choice(user_agent_list)
        try:
            r = requests.get(url,headers=headers2,proxies=proxies,verify=False) #verify是否验证服务器的SSL证书
            print("[*]"+proxy_ip+"访问成功！")
        except:
            print("[-]"+proxy_ip+"访问失败！")

##获取代理ip
def Get_proxy_ip():
    global proxy_list
    proxy_list = []
    url = "https://www.kuaidaili.com/free/inha/"
    headers = {
            "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
            "Accept-Encoding":"gzip, deflate, sdch, br",
            "Accept-Language":"zh-CN,zh;q=0.8",
            "Cache-Control":"max-age=0",
            "Connection":"keep-alive",
            "Cookie":"channelid=0; sid=1561681200472193; _ga=GA1.2.762166746.1561681203; _gid=GA1.2.971407760.1561681203; _gat=1; Hm_lvt_7ed65b1cc4b810e9fd37959c9bb51b31=1561681203; Hm_lpvt_7ed65b1cc4b810e9fd37959c9bb51b31=1561681203",
            "Host":"www.kuaidaili.com",
            "Upgrade-Insecure-Requests":"1",
            "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0",
            "Referrer Policy":"no-referrer-when-downgrade",
            }
    for i in range(1,100):
        url = url = "https://www.kuaidaili.com/free/inha/"+str(i)
        html = requests.get(url = url,headers = headers).content
        soup = BeautifulSoup(html,'html.parser')
        ip_list = '';
        port_list = '';
        protocol_list = '';
        for ip in soup.find_all('td'):
            if "IP" in ip.get('data-title') :
                ip_list = ip.get_text()##获取ip             
            if "PORT" in ip.get('data-title'):
                port_list = ip.get_text()##获取port
            if ip_list != '' and port_list != '':
                proxy = ip_list+":"+port_list
                ip_list = '';
                port_list = '';
                proxy_list.append(proxy)
        iv_main()
        time.sleep(2)
        proxy_list = []
        

th=[]
th_num=10
for x in range(th_num):
        t=threading.Thread(target=Get_proxy_ip)
        th.append(t)
for x in range(th_num):
        th[x].start()
for x in range(th_num):
        th[x].join()

猜你喜欢

转载自www.cnblogs.com/-qing-/p/11101414.html
今日推荐
火速冲上 GitHub 热榜 —— 开源编程语言、框架哪有这么可爱？
北京人形机器人创新中心发布全球首个纯电驱拟人奔跑的全尺寸人形机器人“天工”
LFOSSA 源来如此公开课 | 掌握云原生未来：CNCF 认证全面攻略与备考秘籍
国产云输入法——仅华为无云端数据上传安全问题
开源日报 | 工业开源项目OGG 1.0；姐姐，你要和我一起配置火狐吗；苹果AI遥遥落后？Fedora 40
开放签电子签章：停止新增，优化体验，前进更进（五一假期前工作）
开源日报 | 中学生开源前端动画引擎；全球首个Llama3 8B中文版开源模型；联想电脑恐出局；Linus讽刺AI炒作
周排行
浏览器对同一域名进行请求的最大并发连接数
React Hook之自定义Hook
【转】MyBatis缓存机制
-Java-泛型
自动化测试常用脚本-发送邮件
LeetCode#859: Buddy Strings
java、Python处理字符串
第二篇の博客
Hadoop伪分布式环境安装
SQL Server进阶（十一）临时表、表变量
每日归档
更多
2024-04-27(56)
2024-04-26(39)
2024-04-25(22)
2024-04-24(36)
2024-04-23(26)
2024-04-22(39)
2024-04-21(0)
2024-04-20(6)
2024-04-19(5)
2024-04-18(0)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022