微博评论爬取

import requests
    from fake_useragent import UserAgent
    import csv
    from datetime import datetime
    
    def convert_created_at(created_at):
        dt = datetime.strptime(created_at, '%a %b %d %H:%M:%S +0800 %Y')
        formatted_created_at = dt.strftime('%Y-%m-%d %H:%M:%S')
        return formatted_created_at
    
    def get_weibo_mid(weibo_id):
        url = f'https://weibo.com/ajax/statuses/show?id={weibo_id}'
        header = {
            'user-agent': UserAgent().random
        }
        response = requests.get(url=url, headers=header)
    
        if response.status_code == 200:
            try:
                json_data = response.json()
                weibo_mid = json_data.get('mid')
                if weibo_mid:
                    return weibo_mid
                else:
                    print("未找到微博 MID。")
            except Exception as e:
                print(f"解析微博 MID 时发生异常：{e}")
        else:
            print(f"无法获取微博 MID。状态码：{response.status_code}")
        return None
    
    def get_weibo_comments(weibo_id, csv_filename):
        header = {
            'user-agent': UserAgent().random
        }
        with open(csv_filename, mode='w', encoding='utf-8-sig', newline='') as file:
            csv_writer = csv.writer(file)
            csv_writer.writerow(['User', 'Comment', 'Created_at'])
    
            max_id = ''
            while max_id != 0:
                pl_url = f'https://weibo.com/ajax/statuses/buildComments?flow=1&is_reload=1&id={weibo_id}&is_show_bulletin=2&is_mix=0&max_id={max_id}&count=10'
                resp = requests.get(url=pl_url, headers=header)
                json_data = resp.json()
                max_id = json_data['max_id']
                lis = json_data['data']
                for li in lis:
                    user = li['user']['screen_name']
                    text_raw = li['text_raw']
                    created_at = li['created_at']
                    formatted_created_at = convert_created_at(created_at)
                    print(user, ':', text_raw, formatted_created_at)
                    csv_writer.writerow([user, text_raw, formatted_created_at])
    
    if __name__ == "__main__":
        weibo_id = input('请输入微博的id:')
        weibo_mid = get_weibo_mid(weibo_id)
        if weibo_mid:
            csv_filename = f'weibo_{weibo_mid}.csv'
            get_weibo_comments(weibo_mid, csv_filename)

LiuYuan's Blog

Navigation

Recent Posts