python_爬蟲_爬取7*24小時財經新聞

import requests
import timefrom bs4 import BeautifulSoup

def sina():
    is_first = True
    task_q = [] # 本地存儲新聞
    task_time = []
    while True:
        data_list = getNews()

        if is_first:
            task_q = data_list
            for data in data_list:
                print(data['n_time'],data['n_info'])
                time.sleep(0.5)
                task_time.append(data['n_time'])
            is_first = False
        else:
            for data in data_list:
                if data['n_time'] in task_time:
                    pass
                else:
                    task_time.append(data['n_time'])
                    print('-'*30)
                    print('新消息',data['n_time'],data['n_info'])

        time.sleep(5)
def getNews(): # 獲取新聞函數
    news_list =[]
    base_url = 'http://live.sina.com.cn/zt/f/v/finance/globalnews1'
    response = requests.get(base_url)
    response.encoding = response.apparent_encoding
    html = response.text

    html_bs4 = BeautifulSoup(html,'lxml')
    info_list = (html_bs4.find_all('div',{'data-nick':'fin_圖文直播'}))

    for info in info_list:  # 獲取頁面中自動刷新的新聞
        n_time = info.select('p[class="bd_i_time_c"]')[0].get_text()  # 新聞時間及內容
        n_info = info.select('p[class="bd_i_txt_c"]')[0].get_text()
        data = {
            'n_time': n_time,
            'n_info': n_info
        }
        news_list.append(data)
    return news_list[::-1] # 這里倒序，這樣打印時才會先打印舊新聞，后打印新新聞
if __name__ == '__main__':
    sina()


'''
1 先得到頁面的15條新聞
2 15條新聞放到列表並傳遞
3 每隔30秒請求一次頁面，界面中時間與列表中的時間對照，不相同則讀取
'''