Selenium爬虫案例——大学排名

要爬的网站：

 代码：

import time
import pandas as pd
from selenium import webdriver
def save_csv(arr, csv_filename=None):
    """Save the data in csv format"""
    if csv_filename == None:
        csv_filename="paiming.csv"
    arr_df = pd.DataFrame({'name': arr})
    arr_df.to_csv(csv_filename, float_format='%.3f', index=True, header=True)

driver=webdriver.Chrome()
url='https://gkcx.eol.cn/colleges/rank?type=ruanke_rank&fromcoop=360'
driver.maximize_window()
driver.get(url)
li_list=[]
arr=[]
for j in range(58):
      time.sleep(2)
      li_list=driver.find_elements_by_xpath('//*[@id="root"]/div/div[1]/div/div/div/div[1]/div[2]/div/div[3]/ul/li/div[3]/p[1]/span[1]')
      for i in li_list:
            arr.append(i.text)
            print(i.text)
      driver.find_element_by_css_selector("#root > div > div.container > div > div > div > div:nth-child(1) > div.rank_wrap > div > ul > li.ant-pagination-next").click()

print(arr)
save_csv(arr)

运行结果：