Python爬取微博评论代码

import requests
import csv
import time
import json
from urllib.parse import quote

class WeiboCommentSpider:
    def __init__(self):
        self.headers = {
            'Cookie': 'SCF=AvNaC-yoAZgGhIJXnWWnzLZULdN-SvZo--eSuhRzMO_PIwasCHQEJft-Oixnam7I9JsN7fPfHauIZu0S2bFpsm4.; SINAGLOBAL=6789592846111.761.1746428994697; SUBP=0033WrSXqPxfM725Ws9jqgMF55529P9D9W5_RVZP51uTS_INkIiodohZ5JpX5KMhUgL.FoqpS0e4Shq7Soq2dJLoIp7LxKqL1KnLB-BLxKqL1KnLB-xki--fiK.fiKyW; ALF=1750776292; SUB=_2A25FN1y0DeRhGeBP7FEY9CjMzTqIHXVmTdB8rDV8PUJbkNAbLVjfkW1NRS_rOYlA-AlgWKNAESqKp5vr3L8Yb0oF; _s_tentry=www.weibo.com; Apache=3376029741618.9136.1748313163542; ULV=1748313163615:8:3:1:3376029741618.9136.1748313163542:1747578705000',  # 替换为实际有效的Cookie
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
            'Referer': 'https://weibo.com/'
        }
        self.session = requests.Session()
        
    def clean_text(self, text):
        """清洗文本数据"""
        text = text.replace('\n', ' ').replace('\r', ' ')
        text = ' '.join(text.split())  # 去除多余空格
        return text.strip()
    
    def get_comments(self, weibo_id, max_pages=10):
        """获取微博评论"""
        base_url = 'https://weibo.com/ajax/statuses/buildComments'
        max_id = ''
        page = 1
        all_comments = []
        
        with open(f'weibo_{weibo_id}_comments.csv', 'w', encoding='utf-8-sig', newline='') as f:
            writer = csv.DictWriter(f, fieldnames=[
                '用户ID', '昵称', '性别', '地区', 
                '点赞数', '回复数', '评论内容', '发布时间'
            ])
            writer.writeheader()
            
            while page <= max_pages:
                params = {
                    'flow': 0,
                    'is_reload': 1,
                    'id': weibo_id,
                    'is_show_bulletin': 2,
                    'is_mix': 0,
                    'count': 20,  # 每页数量
                    'max_id': max_id if max_id else 0,
                    'uid': '',  # 可填写用户ID
                    'fetch_level': 0
                }
                
                try:
                    print(f'正在获取第 {page} 页评论...')
                    response = self.session.get(base_url, params=params, headers=self.headers)
                    response.raise_for_status()
                    data = response.json()
                    
                    if not data.get('data'):
                        print('没有更多评论了')
                        break
                    
                    for comment in data['data']:
                        user = comment.get('user', {})
                        cleaned_text = self.clean_text(comment.get('text_raw', ''))
                        
                        row = {
                            '用户ID': user.get('id', ''),
                            '昵称': user.get('screen_name', ''),
                            '性别': '女' if user.get('gender') == 'f' else '男' if user.get('gender') == 'm' else '未知',
                            '地区': user.get('location', '未知'),
                            '点赞数': comment.get('like_counts', 0),
                            '回复数': comment.get('total_number', 0),
                            '评论内容': cleaned_text,
                            '发布时间': comment.get('created_at', '')
                        }
                        all_comments.append(row)
                        writer.writerow(row)
                    
                    max_id = data.get('max_id')
                    if not max_id or max_id == 0:
                        print('已获取所有评论')
                        break
                    
                    page += 1
                    time.sleep(2)  # 礼貌性延迟
                    
                except Exception as e:
                    print(f'获取第 {page} 页评论失败: {str(e)}')
                    break
        
        print(f'共获取 {len(all_comments)} 条评论')
        return all_comments

if __name__ == '__main__':
    spider = WeiboCommentSpider()
    # 替换为你要爬取的微博ID，如：https://weibo.com/123456789/ABCDEFGHIJ
    weibo_id = 'PoqAaAhNv'  
    comments = spider.get_comments(weibo_id, max_pages=10)
    
    # 可选：保存为JSON
    with open(f'weibo_{weibo_id}_comments.json', 'w', encoding='utf-8') as f:
        json.dump(comments, f, ensure_ascii=False, indent=2)