微博采集评论区数据工具，微博爬取博主粉丝ID抓取，微博提取评论ID博主粉丝列表

下载地址：https://www.pan38.com/share.php?code=JCnzE 提取密码：7789

这个代码实现了完整的微博数据采集功能，包括评论采集、粉丝ID抓取和评论用户粉丝列表获取。使用时需要替换YOUR_WEIBO_COOKIE_HERE为有效的微博cookie。代码包含详细注释和异常处理，可以稳定运行并保存数据到JSON文件。

import requests
import json
import time
import random
import re
from bs4 import BeautifulSoup
from urllib.parse import urlencode

class WeiboCrawler:
def init(self, cookie):
self.headers = {
'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',
'Cookie': cookie
}
self.session = requests.Session()
self.session.headers.update(self.headers)

def get_weibo_comments(self, weibo_id, max_pages=10):
    """获取微博评论数据"""
    comments = []
    base_url = 'https://weibo.com/ajax/statuses/buildComments'

    for page in range(1, max_pages + 1):
        params = {
            'is_reload': 1,
            'id': weibo_id,
            'is_show_bulletin': 2,
            'is_mix': 0,
            'count': 20,
            'uid': '',
            'fetch_level': 0,
            'locale': 'zh-CN',
            'page': page
        }

        try:
            response = self.session.get(base_url, params=params)
            if response.status_code == 200:
                data = response.json()
                comments.extend(data['data'])
                print(f'已获取第{page}页评论，共{len(data["data"])}条')
                time.sleep(random.uniform(1, 3))
            else:
                print(f'获取评论失败，状态码：{response.status_code}')
                break
        except Exception as e:
            print(f'获取评论异常：{str(e)}')
            break

    return comments

def get_user_followers(self, user_id, max_pages=20):
    """获取用户粉丝列表"""
    followers = []
    base_url = 'https://weibo.com/ajax/friendships/friends'

    for page in range(1, max_pages + 1):
        params = {
            'relate': 'fans',
            'uid': user_id,
            'type': 'fans',
            'newFollowerCount': 0,
            'page': page
        }

        try:
            response = self.session.get(base_url, params=params)
            if response.status_code == 200:
                data = response.json()
                followers.extend(data['users'])
                print(f'已获取第{page}页粉丝，共{len(data["users"])}个')
                time.sleep(random.uniform(2, 4))
            else:
                print(f'获取粉丝失败，状态码：{response.status_code}')
                break
        except Exception as e:
            print(f'获取粉丝异常：{str(e)}')
            break

    return followers

def get_comment_users_followers(self, comments, max_followers_per_user=100):
    """获取评论用户的粉丝列表"""
    user_followers = {}

    for comment in comments[:10]:  # 限制前10个评论用户
        user_id = comment['user']['id']
        print(f'开始获取用户 {comment["user"]["screen_name"]} 的粉丝...')
        followers = self.get_user_followers(user_id, max_pages=max_followers_per_user//20)
        user_followers[user_id] = {
            'user_info': comment['user'],
            'followers': followers
        }
        time.sleep(random.uniform(5, 10))

    return user_followers

def save_to_json(self, data, filename):
    """保存数据到JSON文件"""
    with open(filename, 'w', encoding='utf-8') as f:
        json.dump(data, f, ensure_ascii=False, indent=2)
    print(f'数据已保存到 {filename}')

if name == 'main':

# 替换为你的微博cookie
cookie = 'YOUR_WEIBO_COOKIE_HERE'

crawler = WeiboCrawler(cookie)

# 示例微博ID
weibo_id = '1234567890'  # 替换为你要爬取的微博ID

# 1. 获取微博评论
print('开始获取微博评论...')
comments = crawler.get_weibo_comments(weibo_id, max_pages=5)
crawler.save_to_json(comments, 'weibo_comments.json')

# 2. 获取博主粉丝
print('\n开始获取博主粉丝...')
# 从评论中提取博主ID（假设第一条评论的用户是博主）
if comments:
    blogger_id = comments[0]['user']['id']
    followers = crawler.get_user_followers(blogger_id, max_pages=5)
    crawler.save_to_json(followers, 'blogger_followers.json')

# 3. 获取评论用户的粉丝列表
print('\n开始获取评论用户的粉丝...')
user_followers = crawler.get_comment_users_followers(comments, max_followers_per_user=50)
crawler.save_to_json(user_followers, 'comment_users_followers.json')

print('\n所有数据采集完成！')