Python爬虫案例-微博热搜

数智侠

于 2024-07-27 23:06:51 发布

阅读量62

点赞数 1

分类专栏： Python 文章标签： python 爬虫开发语言

本文链接：https://blog.csdn.net/taogumo/article/details/140743002

版权

Python 专栏收录该内容

15 篇文章 0 订阅

订阅专栏

爬虫代码

import requests
import time
from bs4 import BeautifulSoup
def get_weibo_hot():
    while True:
        url = "https://s.weibo.com/top/summary?cate=realtimehot"
        headers = {"Cookie":"SUB=_2AkMT0zixf8NxqwJRmP4RzG3iaIxxyQnEilj8lqJRMxHRl-yT9kqm0dtRB6OFMWXlM5SjftExkMQK6NASTHqZWXWFEB;"}
        resp = requests.get(url=url,headers=headers)
        resp.encoding = 'utf-8'
        html = resp.text
        soup = BeautifulSoup(html,'html.parser')
        news = soup.findAll(class_='td-02')
        news.reverse()
        base_url = "https://s.weibo.com"
        news_ls = []
        i = 0
        for new in news:
            i = i + 1
            url = base_url + new.find('a').attrs['href']
            # print(url)
            title = new.find('a').text
            print(('\033[1;37m' + str(i) + '\033[0m').center(50,'*'))
            print('\033[1;36m' + title + '\033[0m')
            news_ls.append({"title":title,"url":url})

        news_length = len(news_ls)
        # news_ls.reverse()
        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,news_length+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,退出微博热搜!")
if __name__ == '__main__':
    get_weibo_hot()