Python爬虫案例-头条热搜

爬虫代码

import requests
import time
def get_toutiao_hot():
    while True:
        url = "https://www.toutiao.com/hot-event/hot-board/?origin=toutiao_pc"
        resp = requests.get(url)
        resp.encoding = 'utf-8'
        resp = resp.json()
        news_ls = []
        i = 0
        news = resp.get('data')
        news.reverse()
        for new in news:
            i += 1
            print(('\033[1;37m'+str(i)+'\033[0m').center(50,'*'))
            news_ls.append({'title':new.get('Title'),'url':new.get('Url')})
            print('\033[1;36m'+new.get('Title')+'\033[0m')
        fixed_top_data = resp.get('fixed_top_data')
        fixed_top_data = fixed_top_data[0]
        news_ls.append({'title':fixed_top_data.get('Title'),'url':fixed_top_data.get('Url')})
        print(('\033[1;37m'+str(i+1)+'\033[0m').center(50,'*'))
        print('\033[1;36m'+news_ls[-1].get('title')+'\033[0m')
        user_input = input("输入新闻编号获取进一步访问的超链接,输入q/Q退出,输入r/R刷新热榜：")
        if user_input == 'q' or user_input == 'Q':
            break
        elif user_input == 'r' or user_input == 'R':
            continue
        elif user_input in [str(i) for i in range(1,len(news_ls)+1)]:
            news_index = eval(user_input) - 1
            print(news_ls[news_index].get('url'))
            print("\033[1;33m" + "按住Ctrl键，点击超链接进行访问" + "\033[0m")
            print('\033[5;31m'+'10s后自动刷新热榜'+'\033[0m')
            time.sleep(10)
            continue
        else:
            print("Invalid User Input.")
            print('\033[5;31m'+"3s后自动刷新热榜"+'\033[0m')
            time.sleep(3)
            continue
    print("Over,退出头条热搜!")
if __name__ == '__main__':
    get_toutiao_hot()

爬虫结果