selenium 正则表达式不知哪里有问题，运行无反应

Question

from selenium import webdriver
import re

def juchao(keyword):

browser = webdriver.Chrome()

url = "http://www.cninfo.com.cn/new/fulltextSearch?notautosubmit=&keyWord=" + keyword

browser.get(url)

data = browser.page_source

# print(data)

browser.quit()



p_title = '<span title class="r-title">(.*?)</span>'

p_href = '<div class="cell"><a target="_blank" href="(.*?)" data-id=.*?</div>'

p_date = '<span class="time">(.*?)</span>'

title = re.findall(p_title, data, re.S)

href = re.findall(p_href, data)

date = re.findall(p_date, data, re.S)



for i in range(len(title)):

    title[i] = re.sub(r'<.*?>', '', title[i])

    href[i] = re.sub('amp;', '', href[i])

    date[i] = date[i].split(' ')[0]

    print(str(i + 1) + '.' + title[i] + '-' + date[i])

    print(href[i])

keywords = ['理财', '现金管理', '纾困']

for i in keywords:

juchao(i)

Answer 1

1. 用chrome浏览器仔细审核一下页面元素，看看就知道为什么匹配不到了
2. 你这里是用re去找元素，干嘛不用selenium的fine_element_byxpath函数去找？比正则不靠谱些吗？