Python爬取微博热搜以及链接

基本操作，不再详述

直接贴源码（根据当前时间创建文件）：

import requests
from bs4 import BeautifulSoup
import time

def input_to_file(number,time,str1):
    with open('D:\python\python_code\'+time+'.txt',"a+",encoding="utf-8") as f:
        f.write(str(number)+"	"+str1+"
")
        f.close()


def get_topic():
    headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.81 Safari/537.36',
    'Host': 's.weibo.com'
    }
    topic_list = []
    #for i in range(0,10):
    link = 'https://s.weibo.com/top/summary'
    request = requests.get(link,headers = headers,timeout = 10)
    #print(str(i+1),"页响应状态码：",request.status_code)
    #print(request.text)
    soup = BeautifulSoup(request.text,"lxml")
    td_list = soup.find_all('td',class_ = 'td-02')
    for each in td_list:
        print("开始获取链接")
        a_object = each.a
        print("开始获取热点内容")
        topic = a_object.text.strip()
        topic_list.append(topic+"
"+"https://s.weibo.com"+a_object.get('href'))
    return topic_list

print("开始获取网址内容")
topics = get_topic()
i = 0
print("开始写入文件")
time_now = time.strftime('%Y_%m_%d_%H_%M_%S',time.localtime(time.time()))
print("the time now is:",time_now)
for each in topics:
    i+=1
    input_to_file(i,str(time_now),each)
print("所有的热点信息以及链接已经写入文件")

希望对大家有所帮助

以上