本文共 1335 字，大约阅读时间需要 4 分钟。

import requests
import pandas as pd
import json
import re
import urllib.parse
def get_one_page():
    params = {
        'containerid': '100103type=60&q=新冠肺炎&t=0',
        'page_type': 'searchall',
        'page': 1
    }
    url = 'https://m.weibo.cn/api/container/getIndex'
    
    # 发送请求
    response = requests.get(url, params=params)
    response.encoding = 'utf-8'  # 设置编码
    response_text = response.text
    
    # 解析响应
    try:
        data = json.loads(response_text)
        cards = data.get('data', {}).get('cards', [])
    except:
        cards = []
    
    # 提取微博信息
    one_page_data = []
    for card in cards:
        if 'mblog' not in card:
            continue
        blog = card['mblog']
        text = re.sub(r'<.*?>', '', blog['text'])  # 去除HTML标签
        mid = blog['mid']
        reposts = blog['reposts_count']
        comments = blog['comments_count']
        likes = blog['attitudes_count']
        
        # 创建数据元组
        entry = (text, mid, reposts, comments, likes)
        one_page_data.append(entry)
    
    return one_page_data
# 主函数
if __name__ == '__main__':
    data = get_one_page()
    print(data)

主要优化点：

请注意：由于直接使用了微博的API，建议在实际使用前查看微博的使用政策，确保符合法律法规。

转载地址：http://cwrf.baihongyu.com/