微博热搜榜单采集，微博热搜榜单爬虫，微博热搜榜单解析，完整代码（话题榜+热搜榜+文娱榜和要闻榜）

Bigcrab__

已于 2024-03-11 14:08:25 修改

阅读量710

点赞数 14

分类专栏：数据采集 Python爬虫文章标签：爬虫新浪微博

于 2024-03-11 14:07:36 首次发布

本文链接：https://blog.csdn.net/m0_72947390/article/details/136621533

版权

数据采集 Python爬虫专栏收录该内容

7 篇文章 8 订阅

订阅专栏

文章目录

代码

1. 话题榜

import requests  
import pandas as pd  
import urllib  
from urllib import parse  
  
headers = {  
    'authority': 'weibo.com',  
    'accept': 'application/json, text/plain, */*',  
    'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',  
    'client-version': 'v2.44.64',  
    'referer': 'https://weibo.com/newlogin?tabtype=topic&gid=&openLoginLayer=0&url=',  
    'sec-ch-ua': '"Chromium";v="116", "Not)A;Brand";v="24", "Microsoft Edge";v="116"',  
    'sec-ch-ua-mobile': '?0',  
    'sec-ch-ua-platform': '"Windows"',  
    'sec-fetch-dest': 'empty',  
    'sec-fetch-mode': 'cors',  
    'sec-fetch-site': 'same-origin',  
    'server-version': 'v2024.02.19.1',  
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36 Edg/116.0.1938.69',  
    'x-requested-with': 'XMLHttpRequest',  
    'x-xsrf-token': 'HOU1s1Hak41bvvQjYsR86Oar',  
}  
  
  
def get_page_resp(num):  
    params = {  
        'sid': 'v_weibopro',  
        'category': 'all',  
        'page': f'{num}',  
        'count': '10',  
    }  
    response = requests.get('https://weibo.com/ajax/statuses/topic_band', params=params, headers=headers)  
    return response  
  
  
def process_resp(response):  
    statuses = response.json()['data']['statuses']  
    if statuses:  
        _df = pd.DataFrame([[statuse['topic'], statuse['summary'], statuse['read'], statuse['mention'], f"https://s.weibo.com/weibo?q=%23{urllib.parse.quote(statuse['topic'])}%23"] for statuse in statuses], columns=['topic', 'summary', 'read', 'mention', 'href'])  
        return _df  
    else:  
        return  
  
  
if __name__ == '__main__':  
    df_list = []  
    num = 1  
    while num:  
        resp = get_page_resp(num)  
        _df = process_resp(resp)  
        if isinstance(_df, pd.DataFrame):  
            df_list.append(_df)  
            num += 1  
        else:  
            num = 0  
    df = pd.concat(df_list).reset_index(drop=True)  
    print(df)  
    df.to_csv('话题榜.csv')

2. 热搜榜

import requests  
import urllib  
import pandas as pd  
import numpy as np  
  
  
def get_hot():  
    headers = {  
        'authority': 'weibo.com',  
        'accept': 'application/json, text/plain, */*',  
        'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',  
        'client-version': 'v2.44.64',  
        'referer': 'https://weibo.com/newlogin?tabtype=search&gid=&openLoginLayer=0&url=',  
        'sec-ch-ua': '"Chromium";v="116", "Not)A;Brand";v="24", "Microsoft Edge";v="116"',  
        'sec-ch-ua-mobile': '?0',  
        'sec-ch-ua-platform': '"Windows"',  
        'sec-fetch-dest': 'empty',  
        'sec-fetch-mode': 'cors',  
        'sec-fetch-site': 'same-origin',  
        'server-version': 'v2024.02.19.1',  
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36 Edg/116.0.1938.69',  
        'x-requested-with': 'XMLHttpRequest',  
        'x-xsrf-token': 'HOU1s1Hak41bvvQjYsR86Oar',  
    }  
  
    response = requests.get('https://weibo.com/ajax/side/hotSearch', headers=headers)  
  
    df = pd.DataFrame(response.json()['data']['realtime'])  
    df['url'] = df['word'].map(lambda x: 'https://s.weibo.com/weibo?q=' + urllib.parse.quote(x))  
    df['onboard_time'] = pd.to_datetime(df['onboard_time'], unit='s')  
    gov_name = response.json()['data']['hotgov']['name']  
    gov_url = response.json()['data']['hotgov']['url']  
    df = df[['word_scheme', 'word', 'star_name', 'realpos', 'label_name', 'onboard_time', 'url', 'raw_hot']]  
    gov_info = [gov_name, gov_name[1:-1], {}, 0, '顶', np.nan, gov_url, np.nan]  
    df = pd.DataFrame(np.insert(df.values, 0, gov_info, axis=0), columns=df.columns)  
    return df  
  
  
if __name__ == '__main__':  
    df = get_hot()  
    df.to_csv('热搜榜.csv')

3. 文娱榜和要闻榜

这里需要更换cookies

import requests  
import pandas as pd  
import urllib  
  
# 跟换为自己的cookies  
def get_entertainment_and_news():  
    headers = {  
        'authority': 'weibo.com',  
        'accept': 'application/json, text/plain, */*',  
        'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',  
        'client-version': 'v2.44.75',  
        # 跟换为自己的cookies  
        'cookie': 'SINAGLOBAL=1278126679099.0298.1694199077980; UOR=,,localhost:8888; _s_tentry=localhost:8888; Apache=6414703468275.693.1710132397752; XSRF-TOKEN=4A9SIIBq9XqCDDTlkpxBLz76; ULV=1710132397782:20:1:1:6414703468275.693.1710132397752:1708482016120; login_sid_t=b637e1846742b4dd85dfe4d86c2c9413; cross_origin_proto=SSL; wb_view_log=1920*10801; SUBP=0033WrSXqPxfM725Ws9jqgMF55529P9D9WFARU4r6-VQ2BMDorVsYLdC5JpX5o275NHD95Qce0eX1KefehMXWs4DqcjMi--NiK.Xi-2Ri--ciKnRi-zNSoe0Sh.0SK5NS5tt; ALF=1712724726; SSOLoginState=1710132727; SCF=ApDYB6ZQHU_wHU8ItPHSso29Xu0ZRSkOOiFTBeXETNm74LTwE3TL5gaw4A4raSthpN-_7ynDOKXDUkiKc1jk720.; SUB=_2A25I6v2nDeRhGeBN6FYY8yvMzDiIHXVrhn9vrDV8PUNbktAGLXb1kW9NRGsSAV5UnWQYNJKU-WfqLNcAf0YTSxtn; WBPSESS=LZz_sqga1OZFrPjFnk-WNlnL5lU4G2v_-YZmcP-p0RFdJenqKjvGkmGWkRfJEjOjxH0yfYfrC4xwEi4ExzfXLO84Lg-HDSQgWx5p8cnO_TnE_Gna1RnTgtIpZu7xWJpq8fJ35LrwI2KAkj4nnVzB_A==',  
        'referer': 'https://weibo.com/hot/entertainment',  
        'sec-ch-ua': '"Chromium";v="116", "Not)A;Brand";v="24", "Microsoft Edge";v="116"',  
        'sec-ch-ua-mobile': '?0',  
        'sec-ch-ua-platform': '"Windows"',  
        'sec-fetch-dest': 'empty',  
        'sec-fetch-mode': 'cors',  
        'sec-fetch-site': 'same-origin',  
        'server-version': 'v2024.03.06.1',  
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36 Edg/116.0.1938.69',  
        'x-requested-with': 'XMLHttpRequest',  
        'x-xsrf-token': '4A9SIIBq9XqCDDTlkpxBLz76',  
    }  
  
    response_entertainment = requests.get('https://weibo.com/ajax/statuses/entertainment', headers=headers)  
    response_news = requests.get('https://weibo.com/ajax/statuses/news', headers=headers)  
  
    df_entertainment = pd.DataFrame(response_entertainment.json()['data']['band_list'])  
    df_entertainment['url'] = df_entertainment['word'].map(  
        lambda x: 'https://s.weibo.com/weibo?q=' + '%23' + urllib.parse.quote(x) + '%23')  
    df_news = pd.DataFrame(response_news.json()['data']['band_list'])  
    df_news['url'] = df_news['topic'].map(  
        lambda x: 'https://s.weibo.com/weibo?q=' + '%23' + urllib.parse.quote(x) + '%23')  
    return df_entertainment, df_news  
  
  
if __name__ == '__main__':  
    df_entertainment, df_news = get_entertainment_and_news()  
    df_entertainment.to_csv('文娱榜.csv')  
    df_news.to_csv('要闻榜.csv')

过程

1. 话题榜

从F12中可以得到所有数据在右侧请求中，解析可以得到参数如下：

sid: 这个值为 v_weibopro 是固定的
category: 这个值为 all 是固定的
page: 这个值为页码，每一页10个，从第一页开始计算
count: 这个值为 10 是固定的，修改无效

所有的数据存储在['data']['statuses']下，进行解析，代码如下：

statuses = response.json()['data']['statuses']
    if statuses:
        _df = pd.DataFrame([[statuse['topic'], statuse['summary'], statuse['read'], statuse['mention'], f"https://s.weibo.com/weibo?q=%23{urllib.parse.quote(statuse['topic'])}%23"] for statuse in statuses], columns=['topic', 'summary', 'read', 'mention', 'href'])
        return _df
    else:
        return 0

可以获得所有结果：

2. 热搜榜

从F12中发现，这个请求是Get型的请求，什么参数都不需要，估计微博是直接放弃了

直接将得到的数据进行处理，

df = pd.DataFrame(response.json()['data']['realtime'])  
df['url'] = df['word'].map(lambda x: 'https://s.weibo.com/weibo?q=' + urllib.parse.quote(x))  
df['onboard_time'] = pd.to_datetime(df['onboard_time'], unit='s')  
gov_name = response.json()['data']['hotgov']['name']  
gov_url = response.json()['data']['hotgov']['url']  
df = df[['word_scheme', 'word', 'star_name', 'realpos', 'label_name', 'onboard_time', 'url', 'raw_hot']]  
gov_info = [gov_name, gov_name[1:-1], {}, 0, '顶', np.nan, gov_url, np.nan]  
df = pd.DataFrame(np.insert(df.values, 0, gov_info, axis=0), columns=df.columns)

得到：

3. 文娱榜和要闻榜

这里从F12中可以发现，文娱榜和要闻榜直接一个请求就可以获取，但是在解析的过程中，发现还是需要cookie的，所以这里需要自己获取cookies；

在response中发现数据无需要清理，直接在表格中获取一下自己需要的参数即可，在这里还是把url添加一下，有的人根本不看前文怎么获取的；

	response_entertainment = requests.get('https://weibo.com/ajax/statuses/entertainment',  headers=headers)
    response_news = requests.get('https://weibo.com/ajax/statuses/news',  headers=headers)
    
    df_entertainment = pd.DataFrame(response_entertainment.json()['data']['band_list'])
    df_entertainment['url'] = df_entertainment['word'].map(lambda x: 'https://s.weibo.com/weibo?q=' + '%23' + urllib.parse.quote(x) + '%23')
    
    df_news = pd.DataFrame(response_news.json()['data']['band_list'])
    df_news['url'] = df_news['topic'].map(lambda x: 'https://s.weibo.com/weibo?q=' + '%23' + urllib.parse.quote(x) + '%23')

得到文娱榜如下：

得到要闻榜如下：

Bigcrab__

关注

14
点赞
踩
9

收藏

觉得还不错? 一键收藏
0
评论
微博热搜榜单采集，微博热搜榜单爬虫，微博热搜榜单解析，完整代码（话题榜+热搜榜+文娱榜和要闻榜）

这里从F12中可以发现，文娱榜和要闻榜直接一个请求就可以获取，但是在解析的过程中，发现还是需要cookie的，所以这里需要自己获取cookies；在response中发现数据无需要清理，直接在表格中获取一下自己需要的参数即可，在这里还是把url添加一下，有的人根本不看前文怎么获取的；从F12中发现，这个请求是Get型的请求，什么参数都不需要，估计微博是直接放弃了。这里需要更换cookies。直接将得到的数据进行处理，
复制链接

扫一扫