Python 批量刷博客园访问量脚本过程解析
程序员文章站
2024-02-07 09:27:28
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。
提取http代理ip...
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。
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
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",
]
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()
结果
以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。