微博评论采集工具，微博采集博主粉丝ID软件，python源码分享

下载地址：www.pan38.com/share.php?c… 提取密码：7789

这个微博数据采集工具包含三个主要文件：主程序、配置文件和工具函数。主程序实现了微博评论采集和粉丝ID采集功能，使用requests库发送请求并处理返回的JSON数据。使用时需要替换为有效的微博cookie和目标微博/用户ID。代码包含了错误处理和随机延迟，以避免被反爬机制检测到。

import requests
import json
import time
import random
import csv
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):
    comments = []
    base_url = 'https://weibo.com/ajax/statuses/buildComments'

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

        try:
            response = self.session.get(base_url, params=params)
            if response.status_code == 200:
                data = response.json()
                for comment in data['data']:
                    comments.append({
                        'id': comment['id'],
                        'text': comment['text'],
                        'user_id': comment['user']['id'],
                        'user_name': comment['user']['screen_name'],
                        'created_at': comment['created_at'],
                        'like_count': comment['like_counts']
                    })
                print(f'已获取第{page}页评论，共{len(comments)}条')
            else:
                print(f'获取评论失败，状态码：{response.status_code}')
                break

            time.sleep(random.uniform(1, 3))

        except Exception as e:
            print(f'获取评论出错：{str(e)}')
            break

    return comments

def get_user_followers(self, user_id, max_pages=20):
    followers = []
    base_url = 'https://weibo.com/ajax/friendships/friends'

    for page in range(1, max_pages + 1):
        params = {
            'page': page,
            'uid': user_id,
            'relate': 'fans',
            'count': 20,
            'type': 'fans',
            'fansSortType': 'time'
        }

        try:
            response = self.session.get(base_url, params=params)
            if response.status_code == 200:
                data = response.json()
                for user in data['users']:
                    followers.append({
                        'id': user['id'],
                        'name': user['screen_name'],
                        'gender': user['gender'],
                        'location': user['location'],
                        'description': user['description'],
                        'followers_count': user['followers_count'],
                        'friends_count': user['friends_count'],
                        'statuses_count': user['statuses_count'],
                        'verified': user['verified'],
                        'verified_reason': user.get('verified_reason', '')
                    })
                print(f'已获取第{page}页粉丝，共{len(followers)}个')
            else:
                print(f'获取粉丝失败，状态码：{response.status_code}')
                break

            time.sleep(random.uniform(2, 5))

        except Exception as e:
            print(f'获取粉丝出错：{str(e)}')
            break

    return followers

def save_to_csv(self, data, filename):
    if not data:
        print('没有数据可保存')
        return

    keys = data[0].keys()
    with open(filename, 'w', newline='', encoding='utf-8-sig') as f:
        writer = csv.DictWriter(f, fieldnames=keys)
        writer.writeheader()
        writer.writerows(data)
    print(f'数据已保存到{filename}')

if name == 'main':

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

crawler = WeiboCrawler(cookie)

# 示例：采集微博评论
weibo_id = '1234567890'  # 替换为目标微博ID
comments = crawler.get_weibo_comments(weibo_id, max_pages=5)
crawler.save_to_csv(comments, f'weibo_{weibo_id}_comments.csv')

# 示例：采集用户粉丝
user_id = '9876543210'  # 替换为目标用户ID
followers = crawler.get_user_followers(user_id, max_pages=10)
crawler.save_to_csv(followers, f'user_{user_id}_followers.csv')