基于爬虫+词云图+Kmeans聚类+LDA主题分析+社会网络语义分析对大唐不夜城用户评论进行分析

from time import sleep
from selenium.webdriver.chrome.service import Service
from selenium.webdriver import Chrome,ChromeOptions
from selenium.webdriver.***mon.by import By
import warnings
import csv
import random
#忽略警告
warnings.filterwarnings("ignore")

# 创建一个驱动
service = Service('./chromedriver.exe')
options = ChromeOptions()
options.add_experimental_option('excludeSwitches', ['enable-automation','enable-logging'])
options.add_experimental_option('useAutomationExtension', False)
# 创建一个浏览器
driver = Chrome(service=service,options=options)
driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
    "source": """
        Object.defineProperty(navigator, 'webdriver', {
        get: () => false
        })
    """
    })
with open('***ments.csv','a',encoding='utf-8',newline='')as f:
    csvwriter = csv.writer(f)
    csvwriter.writerow(('景点','用户评论'))
    main()

def main():
    driver.get('https://you.ctrip.***/sight/xian7/130441.html')
    sleep(2)
    for i in range(109):
        ***ment_list = driver.find_elements(By.XPATH,'//*[@id="***mentModule"]/div[5]/div/div[2]/div[2]')
        for item in ***ment_list:
            try:
                ***ment = item.find_element(By.XPATH,'.').text
                ***ment = ***ment.strip()
                ***ment = ***ment.replace('\n','')
                csvwriter.writerow(('大唐不夜城',***ment))
                f.flush()
                print(***ment)
            except:
                pass
        driver.find_element(By.CSS_SELECTOR,'li.ant-pagination-next>span').click()
        print(f'=====================第{i+1}页爬取完毕！=========================')
        sleep(random.random()*5)