selenium爬虫丁香医生实时播报

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
import pandas as pd
import re

browser = webdriver.Chrome()
wait = WebDriverWait(browser,10)
browser.get('http://3g.dxy.cn/newh5/view/pneumonia_timeline?whichFrom=dxy')

date = []
title = []
try:
    for i in range(1,800):
        d = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'#root > div > div.tab2___PhOZ6 > div:nth-child({}) > div.tabLeft2___SbuNE > span.leftTime___2zf53'.format(i))))
        date.append(d.text)
        t = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'#root > div > div.tab2___PhOZ6 > div:nth-child({}) > div.tabRight___3Z0eJ > p.topicTitle___2ovVO'.format(i))))
        title.append(t.text)
except:
    pass

date2 = []
for j in range(len(date)):
    if '\n' in date[j]:
        date2.append(date[j].split('\n')[1])
    else:
        date2.append(date[j])
        
    


data = {'时间':date2,'标题':title}
df = pd.DataFrame(data)


df.to_excel('实时播报--.xlsx')