python查询MongoDB数据库中重复数据的标题和数量

from urllib.parse import quote_plus
import pymongo

# 创建MongoClient实例，连接到MongoDB
connection_string = f''
client = pymongo.MongoClient(connection_string)
db = client['spider']
collection = db['inner_books']

# 定义聚合管道
pipeline = [
    {
        '$group': {
            '_id': '$title',  # 按照title字段分组
            'count': {'$sum': 1}  # 计算每个title出现的次数
        }
    },
    {
        '$match': {
            'count': {'$gt': 1}  # 筛选出出现次数大于1的title
        }
    }
]

# 执行聚合查询
results = collection.aggregate(pipeline)

# 输出重复数据的标题和数量
for result in results:
    print(f"标题: {result['_id']}, 数量: {result['count']}")

# 如果需要统计总的重复数据数量
total_duplicates = sum(result['count'] for result in results)
print(f"总的重复数据数量: {total_duplicates}")