python 爬虫 计算博客园浏览量，刷浏览量

import time

import requests
import json
import re
from selenium import webdriver

url = ‘https://i.cnblogs.com/categories‘
base_url = ‘https://i.cnblogs.com/posts?‘
views = 0
url_list = []
headers = {
    #在headers中添加上自己的cookie
    ‘cookie‘: ‘你自己的cookie‘,‘user-agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36‘,
    ‘upgrade-insecure-requests‘: ‘1‘
}
pattern1 = re.compile(‘<td>发布</td>.*?\d.*?(\d{1,})‘, re.S)        #正则表达式 #这边尤其要注意到浏览量有可能不只是一个位数，还可能是二位数三位数，所以写正则的时候应该是(\d{1,})
pattern2 = re.compile(‘<td class="post-title"><a href="(.*?)"‘, re.S)    #正则表达式
response = requests.get(url=url, headers=headers)
html = response.text
data = json.loads(html)            #通过json.loads把数据转化成字典格式
categories = (i[‘CategoryId‘] for i in data)
for category in categories:
    cate_url = base_url + ‘categoryid=‘ + str(category)  #build每个category的地址
    headers[‘referer‘] = cate_url
    response = requests.get(cate_url, headers=headers)
    html = response.text
    results1 = re.findall(pattern1, html)    #浏览量的findall结果
    results2 = re.findall(pattern2, html)    #网页地址的findall结果
    if results1:
        for result1 in results1:
            views = views + int(result1)    #通过int()内置函数，把string格式的数字转化为int格式的数值，计算浏览量 
        for result2 in results2:
            url_list.append(‘https://‘ + result2)    #build地址

print(‘总浏览量为：‘, views)
print(url_list)
options = webdriver.ChromeOptions()    #通过selenium 模块中的webdriver 模拟一个chrome浏览器
#设置中文
options.add_argument(‘lang=zh_CN.UTF-8‘)
#更换头部
options.add_argument(‘user-agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36"‘)
#https://www.cnblogs.com/francischeng/p/9437809.html
#www.cnblogs.com/francischeng/p/9437809.com‘
driver = webdriver.Chrome(chrome_options=options)
while True:
    for url in url_list:
        driver.delete_all_cookies()
        driver.get(url)
        time.sleep(2)    #睡眠两秒