python爬虫之热搜爬取

首先安装必要的库

pip install requests
pip install json
pip install re

代码如下

import datetime
import json
import requests
from requests.exceptions import RequestException
import re
import time
def get_one_page(url):
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None

def parse_one_page(html):
    pattern = re.compile('<tr class="">.*?<a href="(.*?)" target="_blank">(.*?)</a>.*?</tr>', re.S)

    items = re.findall(pattern, html)

    for item in items:
        yield {
            'url': 'https://s.weibo.com'+item[0],
            'topic': item[1].replace('#','',2),
        }

def write_to_file(content):
    with open('热搜榜单.txt', 'a', encoding='utf-8') as f:
        f.write('检索时间' + str(datetime.datetime.now())[0:17])
        f.write(json.dumps(content, ensure_ascii=False) + '\n')




def main():
    name = int(input(' 热搜榜;0;时代榜:1'))
    table = ['realtimehot','socialevent']
    url = 'https://s.weibo.com/top/summary?cate=' + table[name]
    html = get_one_page(url)
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)


if __name__ == '__main__':
    main()

通过这个可以与之前的根据关键词检索嵌套，多层循环进行微博爬虫.